text
stringlengths 28
334k
|
|---|
<s>[INST] Amen. And there's I mean there's a lot of people, a lot of historians argue that that battle was because of the Russian winter because of delaying the Russian invasion, but also psychologically delaying the invasion. It was the first time, I think it was the first time the Germans failed not or didn't succeed like they wanted to early in the war, which is a little like psychologically the impact of that I think is immeasurable. And also a lot of people argue from a military strategy perspective that the just like you said it was an aerial attack and that Hitler didn't think that that that kind of attack would then be useful for the rest of the war. So that's that's really part where whereas it might have been very useful. So it's uh it's really interesting how these little battles can steer the directions of war. Of course need growing up in the soviet Union, we didn't hear much about this battle, just like you said, millions of Soviets died. All those people in history that you read about dying. Those are all civilians. But I mean, not all, but a very large number of them civilians and their stories, obviously that's the rooted the literature of the poetry, the music. Just the way people talk the way they drink vodka, the way they love, the way they hate, the way they fear. That's all like rooted in World War Two and World War One. And so, but we never kind of think about europe and we certainly growing up didn't think about their role in the United States all this. There's plenty of stories of heroism in uh in the soviet union enough enough for many lifetimes. So, but it was fascinating to read from a greek perspective. Um because I, you know, I don't have many greek friends, I hope you don't change that. Uh there was this is the beginning of a love affair of your people. [/INST] Uh Yeah, likewise, the americans don't hear about the soviet contribution to the end of World War Two because obviously we became, you know, enemies after that because of the two systems. But yeah, without the Russians with World War Two wouldn't have been one either. </s><s>[INST] Yeah, the stories are written by the victories. That's really interesting. I just looking at the history, you wonder what's missing? [/INST] I'll tell you what's missing that. I know for a fact because my dad told my dad told me combat as hell and he would tell me the reality of what it's really like guys pissing themselves calling for their mother. The fog of war obviously fracture side happens all the time. It's pandemonium. I mean there's skill involved, but I mean there's no like it's a lot of it is just luck. My dad said my dad won three, he got, you know, metals break purple hearts, all that sh it and he said the reason was because he can't, he always said there's another thing you told me you can't pin a medal on a dead guy. So it's like those are the guys who deserve it, but you can't pin a medal, you can't do the pompoms with. And um I'll tell you one thing is that it is written by the victors and all these leaders, they say we're in the front, we're not in the front, we're not. Whenever the history books say he led his troops into battle, it's like did he really did even So then how did he live? Because they put like kids in the front, you know, it's like nobody limps back from the front with like an injury, you know that's that's army pr you know whenever you read, You know, 27 soldiers died, 14 were injured? The word injured? His pr that's like injured was he did he sprained his ankle, did he need, did he get carried off the court or you know, he was maimed. I mean he was like his leg was blown off, you know, it's like so I think that you know Alexander the great was just kind of in the back on his horse and just kind of had his unique bloom a few times and he was like is it bad up there? And then like after that he was like okay my scribe, give me my scribe. Okay when you write this down, can you put me in the front? Yeah. And I was just make me a big hero and I was in there and then he, you know, he just blew his you know, he had sex with his unique and rode off into the sunset because there's just no way you survive in the front especially warfare back then. I mean it's like brutal. </s><s>[INST] Then again you have like uh genghis khan the sense I got that he was a little bit up on the front at least at first or is that also is he a little bit of give [/INST] me my scribe? Yeah, it's all lower. I mean you ever played a game of telephone, you know, it's like, you know, there's no video cameras back then so should just get turns into myth, you know, and there's no way he was in the front, there's no way he would have lived, you know, he was probably good on horseback because those, those dudes were good on horseback that it was like game of Thrones back then. You had all these different people and that kind of yeah, the Mongols were wild dude, they are actually said like um they started like they were more adaptable to the horse because they were so good on horseback. The kids started to be born like kind of bow legged, like to fit the horse. It's wild and they would stretch their heads and ship like that, they wrap them and stretch their heads so they find like Mongol skulls and they, they looked like coneheads and they were brutal and vicious then they would Murad and rape and all the fun stuff that you know, when, you know, when you visit other places back then there's no charge. If he stops and souvenir shops, What you do is you take women and those are the tokens, you know, you burn a few huts. Different tourism was different back then. </s> |
<s>[INST] Beautiful. So that yeah, the machine learning is doing the fusion and then it's a human orchestrated ensemble. That's different approaches. That's great. Uh still impressively you're able to get it done in a few years. That's not obvious to me. That is doable. If I just put myself in that mindset. But when you look back at the jeopardy challenge, again, when you're looking up at the stars, what [/INST] are you most proud of </s><s>[INST] looking back at those days? [/INST] I'm most proud of? Um, my um, yeah, my commitment and my team's commitment to be true to the science, to not be afraid to fail. </s><s>[INST] That's beautiful because there's so much pressure because it is a public event. It is a public show that you were dedicated to the idea, right. Do you think it was a success in the eyes of the world? It was a success by your, I'm sure exceptionally high standards. Is there something you regret you would do differently? [/INST] It was a success. It was a success for our goal? Our goal was to build the most advanced open domain question answering system. We went back to the old problems that we used to try to solve and we did dramatically better on all of them as well as we beat jeopardy. So we want a jeopardy. So it was it was a success. It was. I worry that the world would not understand it as success because it came down to only one game. And I knew statistically speaking this can be a huge technical success and we could still lose that one game. And that's a whole another theme of this, of the journey. But it was a success. It was not a success in natural language understanding, but that was not the goal. </s><s>[INST] Yeah, that was. But I I would argue I understand what you're saying in terms of the science, but I would argue that the inspiration of it right? The they not a success in terms of solving natural language understanding there was a success of being an inspiration to future challenges. Absolutely. The drive future efforts. What's the difference between how human being compete in jeopardy and how Watson does it? That's important in terms of intelligence. [/INST] Yeah. So that that's that actually came up very early on in the project also. In fact I had people who wanted to be on the project, who were early on, who has approached me once I committed to do it, I had wanted to think about how humans do it and they were, you know, from a cognition perspective, like human cognition and how that should play, and I would not take them on the project because another assumption or another state I put in the ground was I don't really care how humans do this, </s><s>[INST] at least in the context [/INST] of this, probably need to build in the context of this project, in nl you and in building an ai that understands how it needs to ultimately communicate with humans, I very </s><s>[INST] much care. So [/INST] it wasn't that I didn't care um in general, in fact, as an AI scientist, I care a lot about that, but I'm also a practical engineer and I committed to getting this thing done and I wasn't going to get distracted, um I had to kind of say, look, if I'm gonna get this done, I'm gonna charge this path, and this path says we're going to engineer a machine that's going to get this thing done and we know what search and NLP can do. We have to build on that foundation if I come in and take a different approach and start wondering about how the human mind might or might not do this, I'm not going to get there from here in the time and, you know, in the time frame, </s><s>[INST] I think that's a great way to lead the team, but now that's done and one when you're back, so analyze what's the difference actually. [/INST] So, so I was a little bit surprised actually to discover over time as this would come up from time to time and we reflect on it that um, and and talking to ken Jennings a little bit and hearing ken Jennings talk about about how he answered questions that it might have been closer to the way humans answer questions than I might have imagined previously </s><s>[INST] because humans are probably in the game of jeopardy at the level of ken Jennings probably also cheating [/INST] their </s><s>[INST] weight to winning right, [/INST] cheating shallow analysis, shallow, they're doing </s><s>[INST] the fastest [/INST] possible, they're doing shallow analysis. So they are very quickly analyzing the question and coming up with some, you know, key, you know, key vectors or cues if you will, and they're taking those cues and they're very quickly going through like their library of stuff, not deeply reasoning about what's going on and then sort of like a lots of different, like what we call these, these scores would kind of score that in a very shallow way and then say, oh boom, you know, that's what it is. And and so it's interesting as we reflected on that. So we may maybe doing something that's not too far off from the way humans do it, but we certain certainly didn't approach it by saying, you know, how would a human do this now in an elemental cognition? Like the project I'm leading now? We asked those questions all the time because ultimately we're trying to do something that is to make the the the intelligence of the machine and intelligence of the human very compatible, well compatible in the sense they can communicate with one another and they can reason with this shared understanding. So how they think about things and how they build answers, how they build, explanations becomes a very important question to consider. </s> |
<s>[INST] Okay, now I can go back and understand it. But that's the brave thing about science is that in the chaos of the irreducible universe, we nevertheless persist to find those pockets. That's kind of the whole point. Because like you say that the limits of science, but that, you know, yes, it's highly limited, but there's a hope there. And like, there's so many questions I want to ask here. So one, you said narrative, which is really interesting. So obviously from at every level of society, you look at Twitter, everybody's constructing narratives about the pandemic, about not just the pandemic, but all the cultural tension that we're going through. So there's narratives, but they're not necessarily connected to the underlying reality of these systems. So our human narratives, I don't even know if they're, I don't like those pockets of reducibility, because we're, it's like constructing things that are not actually representative [/INST] of reality and thereby not giving us like good solutions to how to predict the system. It gets complicated because, you know, people want to say, explain the pandemic to me, explain </s><s>[INST] what's going to happen. [/INST] In the future. Yes. But also, can you explain it? </s><s>[INST] Is there a story to tell? What already happened in the past? [/INST] Yeah. What's going to happen? But I mean, you know, it's similar to sort of explaining things in AI or in any computational system. Like, you know, explain what happened. Well, it could just be this happened because of this detail in this detail in this detail and a million details, and there isn't a big story to tell, there's no kind of big arc of the story that says, oh, it's because, you know, there's a viral field that has these properties and people start showing symptoms, you know, when the, when the seasons change, people will show symptoms and people don't even understand seasonal variation of flu, for example, it's a, it's a, it's something where, where, you know, there could be a big big story, or it could be just a zillion little details that, that mount up. </s><s>[INST] See, but okay. Let's, let's pretend that this pandemic, like the coronavirus resembles something like the one D rule 30 cellular automata. Okay. So, I mean, that's how epidemiologists model virus spread. Indeed. Yes. They sometimes use cellular automata. Yes. And okay. So you can say it's simplistic, but okay. Let's say it is, it's representative of actually what happens. Uh, you know, the, the dynamic of you have a graph, it probably is closer to the hypergraph, uh, it's actually, that's another funny thing. [/INST] Indeed. Yes. There's some graphs use cellular automata. Yes. It's actually, that's, that's another funny thing as we were getting ready to release this physics project, we realized that a bunch of things we'd worked out about about foliations of causal graphs and things were directly relevant to thinking about contact tracing and interactions with cellphones and so on which </s><s>[INST] is really weird and interactions of cell phones and so on, it's really weird. Well like, it just feels like, uh, it feels like we should be able to get some beautiful core insight about the spread of this particular virus on the hypergraph of human civilization, right? [/INST] I tried. I tried. I didn't, I didn't manage to figure it out. Maybe you're one person. Yeah, but I mean, I think actually it's a funny thing because it turns out the main model, you know, the SIR model, I only realized recently was invented by the grandfather of a good friend of mine from high school. So that was just a, you know, it's a weird thing, right? The question is, you know, okay, so you know, you know, on this graph of how humans are connected, you know something about what happens if this happens and that happens. That graph is made in complicated ways. It depends on all sorts of issues that where we don't have the data about how human society works well enough to be able to make that graph. There's actually one of my kids did a study of sort of what happens on different kinds of graphs and how robust are the results? Okay. His basic answer is there are a few general results that you can get that are quite robust, like you know, a small number of big gatherings is worse than a large number of small gatherings. Okay. That's quite robust. But when you ask more detailed questions, it seemed like it just depends. It depends on details. In other words, it's kind of telling you in that case, you know, the irreducibility matters, so to speak. It's not, there's not going to be this kind of one sort of master theorem that says, and </s><s>[INST] therefore this is how things are going to work. Yeah, but there's a certain kind of, from a graph perspective, the certain kind of dynamic to human interaction, so like large groups and small groups, I think it matters who the groups are. For example, you can imagine large, depends how you define large, but you can imagine groups of 30 people as long as they are cliques or whatever, as long as the outgoing degree of that graph is small or something like that, like you can imagine some beautiful underlying rule of human dynamic interaction where I can still be happy, where I can have a conversation with you and a bunch of other people that mean a lot to me in my life and then stay away from the bigger, I don't know, not going to a Miley Cyrus concert or something like [/INST] that and figuring out mathematically some nice removal of behavior. See this is an interesting thing, so I mean, this is the question of what you're describing is kind of the problem of the many situations where you would like to get away from computational irreducibility. A classic one in physics is thermodynamics, the second law of thermodynamics, the law that says entropy tends to increase things that start orderly, tend to get more disordered, or which is also the thing that says given that you have a bunch of heat, the microscopic motion of molecules, it's hard to turn that heat into systematic mechanical work. It's hard to just take something being hot and turn that into, oh, all the atoms are going to line up in the bar of metal and the piece of metal is going to shoot in some direction. That's essentially the same problem as how do you go from this computationally irreducible mess of things happening and get something you want out of it. It's kind of mining, you're kind of, now actually I've understood in recent years that the story of thermodynamics is actually precisely a story of computational irreducibility, but it is already an analogy. You can kind of see that as can you take the, what you're asking to do there is you're asking to go from the kind of the mess of all these complicated human interactions and all this kind of computational processes going on and you say, I want to achieve this particular thing out of it. I want to kind of extract from the heat of what's happening. I want to kind of extract this useful piece of sort of mechanical work that I find helpful. </s> |
<s>[INST] It's possible something like plants is actually a set of living organisms on ecosystem of living organisms. They're just operating a different time scale and a far superior intelligence and human beings and then human beings will die out and plants will still be there and they will be they're yeah, [/INST] they're also there's an evolutionary adaptation playing a role at all of these levels. For instance, if mice don't get enough food and get stressed, the next generation of mice will be more sparse and more scrawny. And the reason for this is because they in natural environment, they might have probably hidden a drought or something else. And if they're over grace, then all the things that sustain them might go extinct and there will be no mice few generations from now. So to make sure that there will be mice and five generations from now basically the might scale back and a similar thing happens with the predators of mice, they should make sure that the mice don't completely go extinct. So in some sense, if the predators are smart enough, they will be tasked with shepherding their food supply. Maybe the reason why alliance have much larger brains and antelopes is not so much because it's so hard to catch the antelope as opposed to run away from the lion. But the lion's need to make complex models of the environment more complex than the antelopes. </s><s>[INST] So first of all, just describing that there's a bunch of complex systems and human beings may not even be the most special or intelligent of those complex systems even on earth. Makes me feel a little better about the extinction of human species that we're talking [/INST] about. Maybe you're just gonna exploit to put the carbon back into the atmosphere. </s><s>[INST] This is just a nice uh [/INST] you know, the big stain on evolution is not as it was trees evolved trees before they could be digested again. Right? There were no insects that could break all of them apart. Uh cellulose is so robust that you cannot get all of it with microorganisms. So many of these trees fell into swamps and all this carbon became inert and could no longer be recycled into organisms and we are the species that is destined to take care of that. So this </s><s>[INST] is kind of [/INST] take it out of the ground, put it back into the atmosphere and the earth is already greening. So within a million years or so when the ecosystems have recovered from the rapid changes that they're not compatible right now, there's going to be awesome again. </s><s>[INST] And there won't be even a memory of us of us. Little apes. [/INST] I think there will be memories of us. I suspect we are the first generally intelligent species in the sense we are the first species with an industrial society because we will leave more phones than bones in the stratosphere. </s><s>[INST] Or ci phones them bones. I like it. But then let me push back. You kind of suggested that we have a very narrow definition of, of intel. I mean, why aren't trees more general uh higher level of general intelligence. [/INST] Trees were intelligent and there would be at different time scales, which means within 100 years the tree is probably not going to make models that are as complex as the ones that we make in 10 years. </s><s>[INST] But maybe the trees are the ones that made the phones right? [/INST] Like </s><s>[INST] you [/INST] could say the entirety of life, did it? You know? Uh The first cell never died. The first cell only split, right? And every divided and every cell in our body is still an instance of the first cell that split off from that very first cell. There was only one cell on this planet as part as we know. And so the cell is not just a building block of life. It's a hyper organism, right? And we are part of this hyper organism. So nevertheless, </s><s>[INST] this hyper organism know the this little particular branch of it, which is as humans because of the industrial revolution. And maybe the exponential growth of technology might somehow destroy ourselves. So what what do you think is the most likely way we might destroy ourselves? So, some people worry about genetic manipulation. Some people, as we've talked about, worry about either dumb artificial intelligence or super intelligent artificial intelligence destroying us. Some people worry all nuclear weapons and weapons of war in general. What do you think if you had to if you're a betting man, What would you better on in terms of self destruction? And it would be higher than 50 would be higher than 50%. [/INST] So it's very likely that nothing that you bet on matters after we've been our bets. So I don't think that bets are literally the right way to go about Once </s><s>[INST] you're dead, it doesn't you won't be there to collect. [/INST] So it's also not clear if the species go extinct, but I think that our present civilization is not sustainable. So the thing that will change is there will be probably fewer people on the planet than are today. And even if not then still most of people that are alive today will not have offspring 100 years from now because of the geographic changes and so on and the changes in the food supply. It's quite likely that many areas of the planet will only be livable with a close cooling chain in 100 years from now. So many of the areas around the equator and in uh uh subtropical climates that are now quite pleasant to live in will stop to be inhabitable without conditions. </s><s>[INST] So, you honestly, wow, cooling chain, close knit cooling chain communities. So, you think you have a strong worry about the the effects of global warming [/INST] itself. It's not the big issue. If you live in Arizona right now, you have basically three months in the summer in which you cannot be outside. And so you have a close cooling chain, you have air conditioning in your car and your home and you're fine. And if they are conditioning would stop for a few days that in many areas you would not be able to survive. Can we just pause for a second, Like you say, so many brilliant poetic things like, what is the clothes that do people use </s> |
<s>[INST] So if you were sad, you're implying the state's not doing something wrong. But by the way, this does remind me, do you know what Jordan Peterson thinks about Bitcoin [/INST] and about the future impact of Bitcoin and the society? No, I don't actually. We're hopefully going to be talking to him soon about that. He did a book club on his book, Maps of Meaning, and he engaged with us about it. So we're hoping to deliver the orange pill to Mr. Peterson. I think his audience is one of the most important audiences in the world to understand Bitcoin. People that are conscientious and responsible. I think they'll quickly understand Bitcoin's value proposition and help elucidate it to </s><s>[INST] the world. I'm trying to remember what he said about it. Basically I think his support of Bitcoin is grounded in the kind of people who are opposing Bitcoin. So without understanding Bitcoin, he starts to like Bitcoin because of the people who are opposing it. That's partially why I am interested in Bitcoin. It's like all the people in power and all the kind of shady, fraudulent, and non-genuine [/INST] people who are dismissing Bitcoin are making me think, hmm. One of Jordan's definitions of God is, he says God is found in the truthful speech that rectifies pathological hierarchies. I think that is a beautiful definition of what Bitcoin is doing in the world and that we have this pathological hierarchy called central banking by which the rich get richer and the poor get poorer. That is used as a mechanism for perpetual theft and funding warfare at a global scale. Like Ron Paul said, it's no coincidence that the 20th century of total war was also the century of central banking. When you have an institution of currency counterfeiting, which the central bank is, you are no longer bounded by your own balance sheet when you go to war. You don't have to just go to war on your own resources. You can now pillage the commonwealth and pull for the savings of society as a whole before you go bankrupt. And indeed, this is what Hitler did, Hitler hyperinflated in the Weimar Republic to fund his war efforts. And frankly, every dictator, every world war, every internment camp in history was made possible by the weaponization of money in fiat currency. So I hope, I know Jordan Peterson is a huge proponent of free speech and I think that's ultimately at its deepest essence, that's what Bitcoin really is. It is just the purest form of monetary speech we've ever had and by purifying that primary operating system of human action, I think we can eliminate this pathological hierarchy that is unfortunately the dominant institution in the world today. </s><s>[INST] Yeah, I'm definitely, especially with these explorations of Bitcoin, this journey I've been on, I'll revisit some of the aspects of human history that I've been looking at like Stalin and Hitler from a perspective of, a monetary perspective, like what are the effects of inflation? How was it used as a tool in gaining power, in maintaining power, in manipulating the populace, in doing, in inflicting suffering and I would say evil onto the world. It's interesting, it's interesting, I'm going to have to sort of go back into the whole. So I tend to focus more on the human nature and less about the tools that human nature leverages to affect change, but you're right that in some sense money is a tool which can be effectively used to perform moral and the moral actions depending on how it's used. [/INST] And there's a feedback between the two, specifically with money itself, here's the way I've been posing it lately is that I actually think, we typically think of people as good or bad or again, trying to label people all the time, but I think people and their characters are emergent properties of the incentive structures they inhabit. So what does Charlie Munger say, don't show me the incentives, I'll show you the outcome kind of thing. This is a flawed incentive structure we've been operating within. Now I'm not speaking to the intention, people want to argue with me all the time, like Jerome Powell's not a bad guy, he's doing his best at the central bank, he's doing what he thinks is right, that's fine. Whether that's true or not, it actually doesn't matter. The intention is divergent from the outcome. The institution that they are running is premised on deception and theft and it is handicapping the productive economy. So even the terms we use printing money, you're not creating any new value, you're not infusing the economy with anything, any new productive factors whatsoever, you're just harvesting the economic surplus created by entrepreneurs in the marketplace. It's impossible to add any value to an economy by increasing the paper claims on its savings. So there's a feedback loop between man and tool, between creator and created and I think we have to honor the relationship above either one, right? </s> |
<s>[INST] Okay, all this is brilliant. But didn't you just say that we are actually in a state of anarchism relative to other countries. So isn't this what emerges this? Is this what aren't we actually living in a state of anarchism where we all have agreed? I haven't agreed to anything. So, like the basic criticism you have is like, you're born on the land, geographical land, your geographical area, and you're forced to have signed a bunch of stuff just by being born in a particular place. So, so really you could if you could just much easier to choose which space of ideas you are associated with, that would be actually a state of anarchism. Yes. And you could have like a military that you sign up with. Sure. [/INST] And you're certainly not putting people in prison to get raped because they're selling drugs. Yeah. Uh and you're certainly not allowing everyone else on the street who wants to be there. </s><s>[INST] Can we say something nice about Ayn rand? [/INST] I can talk about nice things about her all day. I own a copy of the fountainhead. You </s><s>[INST] know what to you is Iran's best idea. One that you find impactful, insightful, useful for us in modern society that you think about. [/INST] That your life has meaning and productive work is your highest value and that you shouldn't apologize. And this is something I despise. You shouldn't apologize for saying I want to be happy and I'm going to work towards that. and that was a few others that you owe nobody else. Some random stranger a second of your time, you see this a lot on twitter and social media, people like demanding a debate or demanding you act a certain way and engage with them. You don't owe them anything. Um so I think those are some of her uh best ideas and she teaches you how to think. Iran does not have all the answers, but she has all the questions. </s><s>[INST] Do you think? What do you think about the whole selfishness thing? I mean, do you are you triggered by the word selfishness? So [/INST] it's really unfortunate what she does because you were just talking about earlier about mold bug being carelessly. She this is indefensible in my opinion. So she talks about the virtue of selfishness and she claims that when people talk about selfishness, they mean concerned primarily with the self. They don't, when people talk about selfishness, they mean in a sociopathic way, concerned exclusively with oneself, right? They mean like, oh if someone is dying on the street, I'm not gonna, you know, even waste the second saving them because I'm selfish. So she sets up this complete caricature of the term. What she when she's attacking selflessness in her best sense is when there are people who have no sense of self, they have no values of their own, they have no goals of their own, everything that's in their mind has gotten secondhand from the culture at large and there's nothing unique or special from their perspective worth fighting for. So when she attacks, um, which she advocates for the self, she basically means self development. Self improvement and achievement. So I think that word choice is really, um, it false and needlessly off putting. </s><s>[INST] Yeah, uh, controversial perhaps for the purpose of being controversial. I [/INST] don't know, but it's just, it's not accurate. That's not what people mean by selfishness. </s><s>[INST] Yeah, I would say it's one of the, one of the reasons probably her philosophy is, uh, not as much adopted or thought about is like, it's funny like the use of words mean something exactly as you said, that's my criticism. That's this mobile, which could be incorrect criticism by the way. So I'm not exactly sure. Can we talk about some modern day chaos and politics? [/INST] Yes, please. Chaos. </s><s>[INST] Speaking of your hatred for chaos, let's talk about the session. [/INST] Oh yeah, I was the first one on this trip. </s><s>[INST] Yeah, you were while the civil war beat you to it. But [/INST] sure, in contemporary times, </s><s>[INST] in contemporary times, you were, you're on this. Can you talk about what is the idea of secession? What are the odds that it might happen? What does it mean for the United States in some way for different States to secede. [/INST] Sure, America has been one country with several cultures since the beginning, um, there's absolutely no reason for someone, this goes back to the anarchist idea. If you despise donald trump, which is your prerogative. If you think joe biden is a clown, which is your prerogative, there's absolutely no reason for you to be governed by someone you disapprove of. This is an incoherent nonsensical concept. The only reason we even take it as a hypothesis is that we're trained to the contrary since kindergarten, a secession. I don't know along what lines, but increasingly it's becoming harder and harder for people to have conversations. I think social media and this is something people despite social media for. I think this is something that social media has done. Well, which I'm advocating for is it tends to kind of run through ideas through like an evolutionary process and drive them to their logical conclusion. Uh, so it's very hard to be a modern online because there's gonna be people, you know, pushing through your ideas through several cycles and then you're gonna end up at some kind of more pure or if you want to dislike it. Extreme perspective having these different pockets, It's not really governable because people fundamentally have different worldviews. So I don't know what's the session would look like. I think the number is really have increasing an exponential rate. Um, I do </s><s>[INST] not a number of supporters, [/INST] supporters. I think the claim that this can only be accomplished through violence is false. It's a lie just like any divorce doesn't have to involve beating your ex husband or ex wife. So and I'm very much looking forward to this becoming a reality far quicker than I ever expected. </s> |
<s>[INST] Well, I think that's one of the profound ideas and deep work that you don't expand on too much is uh boredom. [/INST] Yeah, well, so the deep work had a superficial idea about boredom which was I had this chapter called embrace boredom and very functional list idea was basically you have to have some boredom in your regular schedule or your mind is going to form a Pavlovian connection between as soon as I feel boredom again, stimuli and once it forms that connection is never going to tolerate deep work. So there's this very pragmatic treatment of boredom of your mind better be used to the idea that sometimes you don't get stimulated because otherwise you can't write for three hours, like it's just not going to tolerate it, but more recently. What I'm really interested in boredom, is it as a fundamental human drive, right? Because it's incredibly uncomfortable and think about the other things that are incredibly uncomfortable like hunger or thirst, they serve a really important purpose for a species, right. Like if something is really distressing, there's a reason, pain is really uncomfortable because we need to worry about getting injured, thirst is really uncomfortable because we need water to survive. So what's boredom? Why is that uncomfortable? And and I've been interested in this notion that boredom is about driving us towards productive action like as a species. I mean think about it like what what got us to actually take advantage of these brains? What got us to actually work with fire? What got us to start shaping stones and the hand axes and figuring out if we could actually sharpen a stick sharp enough that we could throw it as a meal, a weapon or a distance weapon for hunting mammoth, right? Boredom drives us towards action. So now I'm fascinated by this fundamental action instinct because I have this theory that I'm working on that were out of sync with it just like we got, we have this drive for hunger but then we introduce junk food and got out of sync with hunger and it makes us really unhealthy. We have this drive towards action but then we overload ourselves and we have all of these distractions and then that causes uh it's like a cognitive action obesity type things because it short circuits this system that wants us to do things but we put more things on our plate and we can possibly do and then we're really frustrated, we can't do them and we're short circuit all of our wires. So it all comes back to this question. Well what would be the ideal, the ideal, the amount of stuff to do in type of things to do? Like if we wanted to look back at our ancestral environment and say if I could just build from scratch, what type, how much work I do and what I work on to be as in touch with that as like paleo people are trying to get their diets in touch with that. And so now I'm just but see this is I'm just it's something I made up but now I'm going deep on it and one of my podcast listeners I was I was talking about on the show and I was like well I am trying to learn about animals and boredom. And she sent me this cool article from an animal behavioralist journal about what we know about human boredom versus animal boredom. So trying to figure out that puzzle is the wave that's high so I can get through the wave that's low of like I don't know about this pandemic book launch and you know and my research and my research is stumbling a little bit because of the pandemic. And so I needed a nice, you know, high so there we go. There's a case study. </s><s>[INST] Well it's both a case study and very interesting set of concepts because I didn't even realize that it's so simple. I'm one of the people that has uh interesting push and pull dynamic with hunger, trying to understand the hunger with myself. Like I probably have an unhealthy relationship with food, I don't know, but there's probably probably a perfect, that's a nice way to think about diet as action. There's probably an optimal diet response to the the experience that our bodies telling us the signal that the body's sending, which is hunger in that same way boredom is sending a signal. And most of our intellectual activities in this world are creative activities are essentially a response uh, to that signal. [/INST] Yeah. And think about this analogy that we have this hunger instinct that junk food short circuits, right? It's like, oh, well we'll satisfy that hyper palatable e and it doesn't end up well now, think about modern attention engineered, digitally mediated entertainment. We have this board of instinct, oh, we can we can take care of that with a hyper palatable alternative. Is that gonna lead to a similar problem? </s> |
<s>[INST] Some way, somehow. Because if it didn't correlate to thoughts, that this process would be way too inefficient. Because there's going to be a bunch of people who are just not, you're not gonna get the, what is it called? The floating needle. [/INST] Like, no matter what. I can't explain to you how you get a floating needle. But it sure as hell isn't hand sweat. And it sure as hell isn't squeezing the cans. </s><s>[INST] Right, so you eventually, most people will get to the floating needle. And somehow- You get floating needles. There's like a feed, but there probably is a feedback mechanism that each person realizes how their mind and body, because you want a resolution, right? It's probably- You want your needle to float. For both people. Yes. And it's probably a great experience when you're like, yes, it's like a gamified feeling, right? [/INST] Well, when you get floating needles, well, when you're training on how to use the e-meter, there are drills where you practice generating with your mind various needle reactions. So, you know, there is a drill where you sit there and you consciously try to create a floating needle by recalling happy thoughts. You go to your happy place. And at the end of every auditing session, you actually have to go to a third party, sit down in front of an e-meter and verify that your needle's floating. Nice. Every single auditing session not only has to end on a floating needle, but then you have to go to someone else and have the floating needle verified. Any Scientologist who's a seasoned recipient of auditing </s><s>[INST] knows how to make their needle float at the examiner. I gotta be honest though, this process, again, sorry to be sort of going there, but it feels like this is a very rigorous talk therapy session. [/INST] Is there good aspects to this? Sure. A lot of people find auditing very helpful. I mean, I've heard some describe it as quite thoroughly addictive. Me personally, I never enjoyed getting auditing. That's probably more a function of having been raised in it. And it was never something I wanted to do. It was something that was forced on me as a child. And also I was never, I don't like talking about private secret stuff. Like you kind of have to want to be an open book to honestly and thoroughly participate in an auditing session. </s><s>[INST] Because there's not necessarily a belief [/INST] that this is going to be private. There's no expectation of privacy, but there's no expectation that your stuff's going to be leaked for blackmail either, I mean. You kind of. </s><s>[INST] You trust the people in the organizationization. Even despite rumors and stuff like that, but the rumors are coming from people [/INST] that are lying to you essentially. If you're a Scientologist and you're participating, in participating in an auditing session, you know that anyone in the organization has the ability to know the stuff that you talk. It's not like, oh my God, I'm only telling my auditor because I think no one's ever going to know. You know that people know, </s><s>[INST] but you also trust the organization. [/INST] How quickly does it go to past memories? For people who are seasoned, like they actually like going past life. Yeah. I hated it. I would make sure, I was really good at making my needle float. I didn't want to have some auditor, because I never believed in the past life memories. So I didn't want to be in that impassable, reach an impass and an auditing session while I was being asked for something I couldn't provide. Cause I knew this auditing session has to end on a good point. But Scientologists enjoy for the most part going, they call it whole track, whole track is past life. Going whole track. Your time track they call it the time track is your whole memory. But whole track refers to anything past life. So going whole track or deep whole track, with high reality. Meaning it's not like, oh I have a fuzzy memory and I'm not sure if it's real. a real seasoned Scientologist that are like, I was on this planet this time circling this time I was eating for breakfast. </s><s>[INST] This time circling this time I was eating for breakfast. Fascinating. Before the origin of life on Earth? Billions of years ago on a distant planet where you were eating for breakfast. I wonder if there's a nice shortcut to sneak up to actual trauma that happened to you as a therapy device. So putting cytology aside, I'm thinking about as a technique for therapy, discussing, basically, you know, some people have trauma and one of the things you do with therapy is like bringing the trauma to the surface. That's the stuff that happened to your childhood. Maybe it's a more convenient thing to do to kind of map that indirectly onto a fictitious telling of what happened to you, something like that trauma on a distant planet elsewhere. [/INST] It could be a nice way to sneak up to it. Yeah, and it goes both flows there, not just things that have happened to you, but things that you've done. So, you know, you could be being asked for, you know, you'd be going back to, I wiped out a civilization. I committed genocide, I don't know, this race on this planet. Oh wow. </s><s>[INST] Oh yeah. But so you can actually take on a whole new guilt. Oh yeah. So, okay, all right, you might actually take on a lot more guilt than I go of. Because if you feel like that self critical aspect of the brain, boy, because my brain is really self critical. So I could see myself manufacturing if I was forced to over time, some kind of story where I didn't genocide a whole population of like Pluto or something at a distance [/INST] in somewhere in Nalfa Centauri. Oh yeah. </s> |
<s>[INST] Right? So our intuition allows us to sort of imagine that we can replace what's been lost, but expansion beyond what we have. I mean, we're already one of the most if not the most intelligent things on this earth, right? So it's hard to imagine um if the brain can hold up with an order of magnitude greater set of information thrown at it, if it can do, if you can reason through that part of me, this is the Russian thing I think is uh I tend to think that the limitations is where the superpower is that, you know, immortality and uh huge increase in bandwidth of information by connecting computers with the brain is not going to produce greater intelligence. It might produce lesser intelligence. So I don't know there's something about the scarcity being essential to uh fitness or performance, but that could be just because we're so uh limited. [/INST] Exactly. You make do with what you have, but you can you don't have to pipe it directly to the brain. I mean, we already have devices like phones where we can look up information at any point and that can make us more productive. You don't have to argue about, I don't know what happened in that baseball game, whatever it is because you can look it up right away. And I think in that sense, uh we can learn to utilize tools and that's what we we have been doing for a long, long time. Um So and we are already the brain is already drinking from the water uh firehose like vision, there's way more information division that we actually process. So brain is already good at identifying what matters. Um and that we can switch that from vision to some other wavelength or some other kind of modality. But I think that the same process supposed probably still apply but but also indeed this ability to have information more accessible and more relevant I think can enhance what we do. I mean kids today at school they learn about D. N. A. I mean things that were discovered just a couple of years ago. Uh It's already common knowledge and we are building on it and we don't see a problem where um where there's too much information that we can absorb and learn. Maybe people become a little bit more narrow in what they know they are in one field but this information that we have accumulated, it is passed on and people are picking up on it and they are building on it. So it's not like we have reached the point of saturation. Um We are still the process that allows us to be selective and decide what's interesting. Um I think still works even even with the more information we have today, </s><s>[INST] it's fascinating to think about like Wikipedia becoming a sensor like uh so the fire hose of information from Wikipedia. So it's like you integrated directly into the brain where you're thinking like you're observing the world with all of Wikipedia directly piping into your brain. So like when I see a light I immediately have like the history of who invented electricity like integrated very quickly into. So just the way you think about the world might be very interesting if you can integrate that kind of information. What are your thoughts if I could ask uh on uh early steps on the on the neuralink side? I don't know if you've got a chance to see but uh there's a monkey playing pong through the brain. Computer interface. And uh the dream there is sort of you're already replacing the thumbs essentially that you would use to play a video game. The dream is to be able to increase further the the interface by which you interact with the computer. Are you impressed by this? Are you worried about this? What are your thoughts as a human? [/INST] I think it's wonderful. I think it's great that we could we could do something like that. I mean you can there are devices that read your E. G. For instance and you humans can learn um to control things using using just their thoughts in that sense. And I I don't think it's that different. I mean those signals would go to limbs. They would go to thumbs. Uh Now the same signals go through a sensor to some computing system. Uh It's still probably has to be built on human terms not to overwhelm them, but utilize what's there and since the right kind of um, patterns that I use it to generate, but oh, that I think it's really quite possible and, and wonderful and could be very much more efficient. </s><s>[INST] Is there, So you mentioned surprising being a characteristic of creativity. Is there something you already mentioned a few examples, but is there something that jumps out at you as was particularly surprising from the various evolutionary computation systems you've worked on the solutions that were ah come up along the way, not necessarily the final solution, but maybe things that even discarded. Is there something that just jumps to mind? [/INST] It happens all the time? I mean, evolution is so creative so good at discovering solutions you don't anticipate a lot of times they are taking advantage of something that you didn't think. Was there like a bug in the software? A lot of, there's a great paper, the community put it together about surprising anecdotes about evolution competition. A lot of them are indeed in some software environment, there was a loophole or bug and the system utilizes that </s> |
<s>[INST] Yeah. Election year pandemic. I wonder if we can do some smooth analysis, lets run the simulation over a few times. A little noise. Yeah. You see, you see if it can dramatically change the behavior of the system, Okay, we talked about your love for proving that something is impossible. So there's quite a few still open problems in complexity of algorithms. Uh So let me ask does P equals np problem? Probably not if P equals np what kind of, you know, and you'll be really surprised somebody proves it. What would that proof look like and why would that even be? What would that mean? What would that proof look like and what possible universe could be equals Np. Is there something inside? So you can say there? [/INST] It could it could be true. I mean, I'm not a complexity theorist, but every complexity theorist I know is convinced they're not equal And are basically not working out anymore. I mean there is $1 million Millennium Prizes. Okay, so here here's how I think the P not equals M. P. Proof is going to eventually happen. I think it's going to fall out and it's going to be not super simple, but not as hard as people think because my my theory about a lot of theoretical computer science based on just some results I've done. So this is a huge extrapolation is that a lot of what we're doing is just a few skating deeper mathematics. So like this happens to me a lot, not a lot of what's happened to me a few times in my work where we obfuscate it because we say, well there's an algorithm and has this much, you know, memory and they're connected on a network and okay, here's our setup and now we're trying to see how fast it can solve a problem and people do bounds about. And then the end, it turns out that like we were just obfuscating some underlying, you know, mathematical thing that already existed, right? So this has happened to me. I had this paper was quite fond of a while ago. It was looking at this problem called contention resolution, where you you you put an unknown set of people on a shared channel and they're trying to break symmetry. So it's like an ethernet, whatever. Only one person can use it at the time. You try to break symmetry. There's all these bounds people have proven over the years about how long it takes to do this. Right? And like I discovered at some point there's this one combinatorial results From the early 1990s, all of these lower bound proofs all come from this. In fact, it improved a lot of them and simplified a lot. You can put it all in one paper, you know, it's like, are we really And then Okay, so this new paper that I submitted a couple weeks ago, I found you could take some of these same lower bound proofs for this contention resolution problem. You could reprove them using Shannon's source code theorem That actually when you're breaking contention, what you're really doing is building a code over, you know, uh if you have a distribution on the network sizes is the code over that source. And if you plug in a high entropy information source and plug in from 1948, the source code theorem that says on a noiseless channel, you can't send things at a faster rate than the entropy allows. The exact same lower bounds fall back out again. Right. So like this type of thing happens. There's a there's some famous lower bounds and distributed algorithms that turned out to all be algebraic topology underneath the covers and they won the girdle prize. We're working on that. So, my sense is what's going to happen is at some point, someone really smart to be very exciting is going to realize there's some sort of other representation of what's going on with these turing machines trying to sort of efficiently </s><s>[INST] usually follow a lot of that [/INST] there will be an existing mathematical result that </s><s>[INST] apply someone or something. I guess it could be a I theo improvers kind of thing. [/INST] It could be Yeah, I mean, well, yeah, there's the're improvers like what that means now, which is not fun. </s><s>[INST] It's just a bunch of very [/INST] carefully formulated postulates that. But I take your point, </s><s>[INST] Yeah. So, okay, uh you know, a small tangent on them then you're kind of implying the mathematics. It almost feels like a kind of weird evolutionary tree that ultimately leads back to some kind of ancestral if you fundamental ideas that all they're just like they're all somehow connected uh in that sense, do you think uh math is fundamental to our universe and we're just like slowly trying to understand these patterns? Or is it is it discovered? Or is it just a little game that we play amongst ourselves to try to fit little patterns to the world? [/INST] Yeah, that's the question. Right? That's the physicist question. I mean, I'm probably I'm in the discovered camp, but I don't do theoretical physics. So I know they have a they feel like they have a stronger claim that the answering that question. So you don't come back to it. Everything comes back to it. I mean, all of physics, the fact that the universe is well, Okay, yeah, it's a complicated question. </s><s>[INST] So, how often do you think, how deeply does this result describe the fundamental reality of nature? [/INST] So, the reason I hesitated because it's something I'm I taught the seminar and did a little work on what are called biological algorithms. So, there's this notion of Yeah, so physicists used mathematics to explain the universe, Right. And it was unreasonable that mathematics works so well, yeah. All these differential equations, why does that explain all we need to know about thermodynamics and gravity and all these, all these types of things? Well, there's this there's this movement within the intersection of computer science and biology? Uh just kind of Wolfram e um I guess really that algorithms can be very explanatory, right? Like if you're trying to if you're trying to explain parsimonious lee something about like an ant colony or something like this, you're not going to ultimately it's not going to be explained as an equation, like a physics equation, it's gonna be explained by an algorithm. This algorithm run distributed lee is going to explain the behavior. So that's mathematical, but not quite mathematical. But it is if you think about an algorithm, like a lambda calculus, which brings you back to the world of mathematics, I'm thinking out loud here, but basically abstract math is unreasonably effective at explaining a lot of things. And that's just what I feel like I glimpse I'm not a uh not like a super well known theoretician, I don't have really famous results. So even as a sort of middling, you know, career theoretician, I keep encountering this where we think we're solving some problem about computers and algorithms and it's some much deeper underlying math. It's Shannon, but Shannon is entropy but entropy was really, you know, goes all the way back to whatever it was boiling all the way back to looking at the early physics. And and it's it was to me, I think it's amazing. </s> |
<s>[INST] to be bold. So both. I mean, there's a there's an interesting duality there. So there's the way you speak to other people about like your plans and what you are like privately, just in your own mind, [/INST] and maybe it's connected with what you're saying about Yeah, sincerity as well. Like if you if you appear to be sincerely optimistic about something that's big or crazy, it's putting yourself up to be kind of like ridiculed or something. And so if you say my mission is to um yeah, go to mars it's just so bonkers that it's hard to say </s><s>[INST] it is, but uh one powerful thing, just like you said is if you say it and you believe it, then actually amazing people uh come and work with you. Exactly. It's not just skill, but the dreams, there's something about optimism that uh like that fire that you have when you're optimistic of actually having the hope of building something totally cool, something totally new that when those people get in a room together, like they can actually do it. Uh Yeah, there's yeah, there's that's uh and also makes life really fun when you're in that room, so all that together, ultimately, I don't know, that's what makes this crazy ride of a startup really look fun and l as in this example, a person who succeeded that, there's not many other inspiring figures, which is said I used to be a google and there's uh there's something that happens that sometimes when the company grows bigger and bigger and bigger, where that kind of ambition kind of quiets down a little bit, you know, google had this ambition still does of making the world's information accessible to everyone. And I remember, I don't know, that's beautiful. I still love that dream of that. You know, they used to scan books, but just every way possible, Make the world's information accessible. Same with Wikipedia. Every time I open up Wikipedia, um I'm just are inspired by how awesome humans are man and creating this together. I don't know what the meetings are over there, but they it's just beautiful, like what they've created is incredible. And I love to be able to be part of something like that and you're right for that. You have to be bold [/INST] and there's and strange to me also, I think you're right that there's how many boring companies they are something I talk about, especially in Fintech, it's like why am I excited about this is so lame, like what is, this isn't even like important, even if you succeed, this is gonna be like terrible, like, this is not good. Um And it's just strange how people can kind of get fake enthusiastic about like boring ideas when there's so many bigger ideas that um, yeah, I mean you read these things like this company raises money, it's just like that's a lot of money for the worst idea I've ever heard. </s><s>[INST] Some ideas are really big. So like I worked on autonomous vehicles quite a bit and there's so many ways in which you can present that idea to yourself to the team you work with, your just yeah, like to yourself when you're quietly looking in the mirror in the morning, uh, that's really boring or really exciting. Like if you're really ambitious with autonomous vehicles there, it changes the nature of like human robot interaction is changing the nature of how we move, forget money, forget all that stuff. It changes like everything about robotics and ai machine learning, it changes everything about manufacturer. I mean the cars, transportation is so fundamentally connected to cars and if that changes it changes the fabric of society, of movies of everything. Uh, and if you go bold and take risks and go be willing to go bankrupt with your company as opposed to cautiously. You could, you could really change the world and it's so sad for me to see all these autonomous companies thomas, vehicle companies there, like really more focused about fundraising and kind of like smoking mirrors are really afraid that the entirety of their marketing is grounded in fear and presenting enough smoke to where they keep raising funds so they can cautiously use technology of previous decade or previous two decades to kind of test vehicles here and there as opposed to do crazy things emboldened, go huge scale to huge data collection. And um, yeah, so that's just an example. Like the idea can be big, but if you don't allow yourself to take that idea and think really big with it, uh, then you're not going to make anything happen. Yeah, you're absolutely right in that. So you, you've been connected in your work, uh, with a bunch of amazing people. How much interaction do you have with the investment with investors? I get that whole process is the entire mystery to me. Is there some people that just have influence on the trajectory of you're thinking completely or is it just this collective energy that they behind the company? [/INST] Yeah. I mean, I, I came here and I, I, I was amazed how yeah, people would, I was only here for a few months and I met some incredible investors. Uh, oh, and I almost run out of money and uh, once they invested, I was like, I am not gonna let you down. And I was like, okay, I understand them like an email update every like three minutes and then they don't care at all. So they kind of want to, I don't know like, so for some, I like it when it's just like they're always available to talk. But, um a lot of building a business, especially a high tech business um there's a little for them to add, right, there's a little for them to add on product, there's a lot for them to add on like business development. And if we are doing product research, which is for us research into the market research into how to make a great hedge fund and we do that for years, there's not much to tell the investors, </s> |
<s>[INST] And so we're creating something. It's like when you have children, you put creatures into this world that will suffer, can suffer and may suffer, depending on how you view life, may likely suffer. And so now you carry this responsibility for doing your best to alleviate any suffering that might go through. And that perhaps that's a romanticizing this notion of life. Perhaps bacteria are not capable of suffering, but perhaps it'll create more complex life forms that would be able to suffer. And that feels like a responsibility as well. Of course, other people would be concerned. The more obvious concern is like, well, you just created a life form. How do you know it's not going to be a super deadly virus that somehow is able to hurt humans? Yeah, my concern is more. I feel like that's a solvable problem. The problem of creating conscious beings that are able to suffer. That's a tricky one. [/INST] Yeah, I can see why, because it goes back to again, would we first of all, do we have a responsibility to propagate more of this chemistry that we have on this planet elsewhere, given that we know ultimately we will be vanished by the entire planet? And if this is, in fact, a very rare chemical event that happens because all the right circumstances came together and we were the lucky one, do we have a responsibility to sponsor it? This is if we were to back up sponsor. </s><s>[INST] I like it. It's a good way to put it. [/INST] Yeah, if we try to back up remnants of our civilization, right? So we want to potentially create conditions on different planets so that humans can survive, given that we know what we want to just for the sake of growing. </s><s>[INST] Yeah, propagating, becoming a multi-planetary species. [/INST] Exactly, but what really is at stake here, I think it's actually or what is really more interesting is what we don't see, which is the again, that chemical behavior that enabled everything at first place. That's different than sending potato crops or engineering bacteria to live on different planet. That's very different. You are really stripping it down to what is what is possible at the chemical level. So even if you are instigating the chemistry on different planets, you are letting that very planet to do its thing. You're not necessarily contaminating those planets with different chemistry, because the idea behind us at least the way I thought about is that you understand that planet, you understand the conditions, you understand the chemistry of the planet really well before choosing the planet as a candidate at first place. And then, it's not about sending a missing ingredient per se, but again, just sending more of what it already has. This – that will be respecting that planet's condition, too, so I'm not suggesting any occupation. I'm not suggesting any colonization. I'm not suggesting any like, let's just strip everything and make everything earth-like. That's not what I'm saying. It's more about empowering that place. What you are saying is likely to be the motivator behind all this. it's not because I see suffering, I see pain. It's very interesting. I think this is a question that really reveals </s><s>[INST] a lot about the person who's answering it. Well, okay, so the pushback on my pushback. If I'm deeply troubled by suffering, then I should be probably paralyzed about the history of life on Earth. [/INST] And, you know, there's- Can you elaborate? </s><s>[INST] What do you mean? Most of life who's ever lived suffered [/INST] in ways that are almost unimaginable to me. </s><s>[INST] You mean like our own species? Our own species than before. And animals living today, and we're not even talking about factory farms, we're just animals living in extreme poverty in the jungle. You don't, people think like in the natural environment, animals live in a happy place. No, it's a brutal place of desperately trying to survive, of desperately trying to look for food. And it's just like all of that life, that's just mammals and we understand mammals, but like throughout like trillions of organisms that lead up to those mammals and the organisms living everywhere like even bacteria, there's death everywhere. So maybe this idea of death, this idea of suffering is actually, this thing that we see as a bug [/INST] is actually a feature food. Yeah, I don't think suffering is a linear property like that with life. And I may be with Nick Lane on this one, that the likeliness of anything similar to what we got here, evolving in another planetary body, </s><s>[INST] I think is quite low. Where would you say is the biggest unlikely thing? Do you mean humans, [/INST] or do you mean even multicellular organisms? Probably multicellularly. But I understand both sides of the equation, right? In one level, I can see that we may not have any other choice but to back up this chemistry somewhere else. So you would be saving. It's the ultimate saving, or our own record. It's not about, yes, let's also save beetles and all the amazing songs, but this would be the ultimate repository of life. </s><s>[INST] But I can also see your point of view, for sure. It's really interesting. So like, don't seed a plant with a missing ingredient. Try to understand what the ingredients it has, is it possible to construct life? For me, from a computer person, it just feels like something [/INST] that could be solved computationally. We can learn from the mistakes that we've done here and aspire not to repeat them. It is possible. We do amazing things as humans. There's a lot of suffering, but there's also a lot of beauty. And we could choose what we want to be or what we want to see, right? So these attempts don't need not to come from, need not to come from a place of fear, but it can be ultimately, </s> |
<s>[INST] to [/INST] find me. So one day I was uh I was like 10:30 AM. on Saturday September 16 was the day 2006. Yeah 2006, September 16. I was used to the builders coming around knocking, making sure everything was all right. So I was asleep, heard this knock at the door and get up, look through the keyhole, nobody's there. You know the people, nobody's there was like, huh? Open the door, step out into the hallway, walking down the hall is bobby Kirby another south Carolina guy. And they um, Orlando Orange County cop and they turn around and they're like, hey Brett, I'm like, hey bobby, how are you? And it's like, we're good, how are you? And I'm like, I'm fine. Would you like to come in? And he was like, let's put you in cuffs first. And I was like, that's probably a good idea. He walks out </s><s>[INST] like, he's [/INST] like, have you got anything in here? And I was like, yeah, there's 100 and $20,000 in the bedroom. And he was like, seriously? I was like, yeah, that an Ak 47. His face goes white and he's like, you've got a rifle. And I was like, no, I'm kidding with you. He was like, he was like, okay. So they throw me in jail in Orange County. And uh, they give me diesel therapy and diesel therapy is, it took like two weeks to transport me from Orange County Orlando to Columbia south Carolina. And what happens is is you stop at every county jail, you possibly can go through the processing, which is about six hours. Once you get to your buck. Hey, time to transport you. </s><s>[INST] They do that on purpose, [/INST] on purpose, on </s><s>[INST] purpose. Where [/INST] is you down mentally and physically and everything? I get to uh Columbia south Carolina while I was at Orange County. What happens is this inmate? Because when we were in federal holding this inmate, he looks at me, his name was Yeti and he's like, hey man, you know, the only time you get off in federal prison is the drug program. I was like, oh man, I don't use drugs. And he's like, you can find drug problem catcher. And I was like, I can find a drug problem. So what happens is every county joy stopped at on the way to Colombia. I tell them I'm alcoholic and cocaine. So by the time I get to Columbia south Carolina, they've got this paper trail of Mr johnson requesting help for drugs. I had hired strom thurman's son as an attorney. They make me drop him because I paid for him with illegal funds. So they give me a public defender. He gets a psychological evaluation ordered for me. So psychologist comes into county jail four hour interview about halfway through. He looks at me, he's like use any type of drugs. I was like, yeah, he's like, what do you use cocaine, smoke or snort snort? How much an eight ball day? That's a lot. Yeah. Do you have any trouble out of that? Yeah, I can't get an erection and he looks at me and I'm looking at him like because I had gotten that shipped from boogie nights. So like finally I'm like is that right? And he was like, it could </s><s>[INST] happen. I was like [/INST] okay, that makes it into my pre sentence report. So all federal inmates probation office and prosecutors, they do this detailed background check to basically tell the judge how much time to give you. All right? So that drug bit with that interview makes it into the PSR. So they have interviewed I mean, they have sentencing. I had pled guilty day of sentencing. There was the prosecutor, he stands up and this this dude is screaming at this point and he's like Mr johnson's manipulated the Secret Service. He's manipulating the prosecutor that he points at the judge and he's manipulating you today, your honor. We insist on the upper limits of the guidelines. Well, I've been telling everybody in the jail that If they give me any more than 60 months, I am not staying. So we're like, okay, sure. So the judge looks at me and she's like, I agree, I'm like And she says 75 months. So I looked at my lawyer and I was like uh can you get the drug program for me? He's like, I don't know, I'll ask. So he stands up your honor where you order the drug program for? Mr johnson, the judge says no, but I'll recommend he gets evaluated. So the secret service had told her he's full of sh it. So she's like, no, but I recommend it gets evaluated. I looked at my lawyer and I was like, what does that mean? He was like, you're probably not gonna get it. And I was like, how soon can you get me to the camp? And he was like, well if you don't appeal, I can get you there pretty quick. My exact words were, fuck the appeal, get me to the camp. I'll take it from there. He looks at me like I'm the biggest idiot in the world I get sent to because you can get a camp recommended I have friends, family members look for camps that don't have a fence around them and we settle on Ashland Kentucky. Six weeks later I'm in Ashland Kentucky and uh pull up their 14 ft fence razor wire on top. And I'm like, I don't climb fences. I go in. First question I ask, is are there any jobs outside of the fence? And he was like uh guards like, well you can work in the national Forest and I'm like, no, I'll die out there. And he was like, well you could do landscaping. I'm like I could run a weed eater. Two days later I walked into the landscaping office and the cop, this is this this genius of some of these people and institutions. The cop behind his desk the entire wall is a blown up photo of the compound and the outlying area So I can literally sit there and plot where I'm going. All right. My dad, I hadn't spoken to that man in years and he shows up at my sentencing and stands up in front of the judge and he's like your honor. I want to make sure Brett gets a good start. He can live with me when he gets out everything else. Looking back the man meant that and I just thought it was bullsh it at the time. So he starts to visit me in prison. I mean in prison he starts to visit and about the third visit in he looks at me he's like I've been reading about you online. I was like yeah he's like yeah he's like that's a lot of money you made. And I was like yeah he's like you think you can teach somebody how to do that. And I'm like, so what I used to say and again that it's just it's this thing of you know, really coming to terms with things. What I used to say was is I thought my dad was back in my life and he was just trying to use me all right. The truth of the matter was is that my dad hadn't really seen me except in that that frame of crime. You know being that criminal with my mom. Everything else. I really think that's how the man was trying to communicate with me, he </s> |
<s>[INST] It [/INST] just doesn't get talked about because it gets overshadowed by you know, all of the other kind of stuff around this and the way that you know, he interacted with people and treated people </s><s>[INST] what was the heart, the key insights to your testimony and that impeachment. [/INST] Look I think there is a straight line between that whole series of episodes and the current war in Ukraine because Vladimir Putin and the people around him in the Kremlin concluded that the U. S. Did not care one little bit about Ukraine and it was just a game For Trump, it was personal game. He was basically trying to get uh Vladimir Zelensky to do him a personal favor related to his desire to stay on in um in power in the 2020 election. And generally they just thought that we were using Ukraine as some kind of proxy or some kind of instrument within our own domestic politics is, that's what it looked like. And I think that he knows the result of that Putin, you know, took the idea aware that he could, you know, do whatever he wanted. We were constantly being asked even prior to this by people around Putin, like Nikolai Patrushev, the head of the National Security Council equivalent in Russia, who we met with frequently, what's Ukraine t we don't get it, you know, why do you even care? So they they thought that we weren't serious that we weren't serious about Ukraine's territorial integrity and its independence or it is a national security player. And Putin also thought that he could just manipulate the political space in the United States. Actually could because what he was doing was seeding all this descent and fueling, you know already uh you know, debates inside of us politics, the kinds of you know, things that we see just kind of coming out now, this kind of idea that Ukraine was a burden, that Ukraine was, You know, basically just trying to extract things from the United States. The Ukraine had somehow played inside of us politics trump was convinced that the Ukrainians had done something against him, that they had intervened in the elections. And that was kind of, you know, a combination of people around him, trying to find excuses to, you know, kind of what had happened in the election, to kind of divert attention away from Russia's interference in 2016. And the Russians themselves poisoning the well against Ukraine. So you had a kind of a confluence of circumstances there. And what I was trying to get across in that testimony was the national security imperative of basically getting our act together here and separating out what was going on in our domestic politics from what was happening in our national security and foreign policy. I mean, I think we contributed in that whole mess around the impeachment, but it's the whole parallel policies around Ukraine to the war that we now have, </s><s>[INST] signaling the value we place in peace and stability in that part of the world, or the reverse, by saying, we don't care, [/INST] We seem to not care, it was just a game, </s><s>[INST] but the U. S. Role in that war is very complicated. One, that's 11 that's one of the variables um just on that testimony, did it in part break your heart that you had to testify essentially against the President of the United States, or is that not how you saw it? [/INST] I don't think I would describe it in that way. I think what I was was deeply disappointed by what I saw happening and the american political space, I didn't expect it. Look, I was a starry eyed immigrant. I came to the United States with all of these expectations of what the place would be. I'd already been disabused of, you know, some of the, um, let's just say, rosie perspectives on how the United States had been shocked by the depths of racial problems. It doesn't even sum up the problems we have in the United States. I mean, I I couldn't get my head around it when I first came. I mean, I I read about slavery in american history, but I hadn't fully fathomed, you know, really, the kind of the way that was ripping apart the United States when I read Alex talked Phil, and he commented on this and it obviously had, you know, kind of change to the expect the way that one would have expected all this time, you know, from the 18th century onwards. So that was kind of one thing that, you know, that I realized the civil rights movement and all of these, you know, acts of expansion of suffrage and everything else. We're imperfect at best. You know, I was born in 65 the same same time as the Civil Rights Act was heck of a long way still to go. So I wasn't, let's just say, you know, as starry eyed about everything that had been before, but I really saw an incredible competence and professionalism in, you know, the U. S. Government, it was gonna be in the election system and the integrity of it. And I mean, I really saw that I saw that the United States was the gold standard for, you know, kind of some of its institutions. And I worked in the National Intelligence Council, and I've seen the way that the United States had tried to address the problems that it had um had faced in its whole botched analysis of Iraq and this terrible strategic blunder of um honestly a crime in my view of invading Iraq. And but the way that people were trying to to deal with that in the aftermath, I mean, I went into the National Intelligence Council, the D. N. I. The Director of the Office of the Director of National Intelligence when they were coming to terms with what had gone wrong in the whole analysis about Iraq in 2003, you know, in the whole wake of people trying to pull together after 9 11 and to learn all of the lessons from all of this. And I saw, you know, just really genuine striving and and deliberation about what had gone wrong, What lessons can we learn from this? And then suddenly I found myself and this, I couldn't describe it just totally crazy looking glass thinking of Alice in wonderland Alice through the looking glass version of american politics. I mean, I'd seen everything starting to unravel over a kind of a period of time before I'd been asked to be in the administration, but I did not expect it to be that bad, honestly didn't. I mean, I had been warned, you know, by people that this was, you know, kind of really a very serious term that the United States had taken. But I really thought that national security would still be uppermost in people's minds. And it was a lot of the people that I work with. But what I found, you know, if you want to use that term of heartbreaking was the way in which all of these principles that I really bought into and try to uphold in the United States government. And then the things that we were trying to do with me and my colleagues have just been thrown out the window and that, you know, I would have to step up in defense of them and in defense of my colleagues who were being lambasted and, you know criticized and given death threats, were actually standing up and doing their own jobs </s> |
<s>[INST] well from an engineering perspective. Both the movies you mentioned Wally and uh Terminator The 1st 1 it's probably achievable humanoid robot maybe not with like the realism in terms of skin and so on. But that humanoid form we have the humanoid form it seems like a compelling form. Maybe the challenges that's super expensive to to to build. But you can imagine maybe not a machine of war but you can imagine terminator type robots walking around. Uh And then the same obviously with Walleyes you basically. So for people who don't know you created the company on key that created a small robot with a big personality called Kaswell that just it does exactly what he does. Which is somehow with very few basic visual tools is able to communicate a depth of emotion and that's fascinating. But then again the humanoid form is uh super compelling. So like Cosmo is very distant from a humanoid form and then the terminator has a humanoid form, you can imagine both of those actually being in our society. [/INST] It's true. And it's interesting because it was very intentional to go really far away from human form. When you think about a character like Cosmo or like Wally, where um you can completely rethink the constraints you put on that character um what tools you average and then how you actually create a personality uh and uh level of intelligence interactivity that actually matches the constraints that you're under, whether it's mechanical or sensors or ai of the day. This is why I almost um was always really surprised by how much energy people put towards trying to replicate human form in a robot, because you actually take on some pretty significant um kind of constraints and and downsides when you do that. Um The first of which is obviously the cost where it's just the the articulation of a human body is just so like magical. Um in both the precision as well as the dimensionality that to replicate that even in his quote, reasonably close form takes like a giant amount of joints and actuators and uh emotion and and you know, sensors and encoders and so forth. But then um you're almost like setting an expectation that the closer you try to get the human form, the more you expect the strength to match. And that's not the way I works is there's places where you're way stronger and there's places where you're weaker and by moving away from human form, you can actually uh change the rules and embrace your strengths and bypass your weaknesses. </s><s>[INST] And at the same time the human form like has way too many degrees of freedom to play with it, it's kind of counterintuitive just as you're saying, but when you have fewer constraints, it's almost harder to master the communication of emotion. Like you see this with cartoons like stick figures, you can communicate quite a lot with just very minimal like two dots for eyes and a line for for a smile. I think like you can almost communicate arbitrary levels of emotion with just two dots and a line and like that's enough. And if you focus on just that you can communicate the full range and then you like if you do that then you can focus on the actual magic of uh human and dot line interaction versus all the engineering [/INST] messes, like dimensionality, voice, all these sort of things actually become a crutch where you get lost in the search space almost. Um And so some of the best animators that we've worked with um they almost like study when they come up uh you know, kind of building their expertise by forcing these um projects where all you have is like a ball that can like kind of jump and manipulate itself or like really really like aggressive constraints where you're forced to kind of accept it, extract the deepest love of motion. And so in a lot of ways, um you know, we thought when we thought about Cosmo is like, you're you're right, like if we had to like describe it in like one small phrase, it was bringing a Pixar character to life in the real world. It's uh it's what we were going for. And um and a lot of ways what was interesting is that with like Wally, which we studied incredibly deeply and in fact, some of our team were, you know, kind of had worked previously at um, at Pixar on that project. Um they intentionally constrained Wally as well, even though in an animated film you could do whatever you wanted to, because it forced you to like really saturate the smaller amount of dimensions. But uh you sometimes end up getting a far more beautiful output um because you're pushing at the extremes um of this emotional space in a way that you just wouldn't because you get lost in the surface area. If you have like something that is just infinitely articulable. </s><s>[INST] So if we backtrack a little bit and uh you thought of cosmo in 2011 in 2013, actually uh designed and built, it what is the donkey, what is cosmo. I guess who is Gospel? And uh what was the vision behind this incredible little robot, [/INST] We started uh donkey back in like while we were still in graduate school. So myself and my two co founders, we were PhD students uh in the robotics institute at Carnegie Mellon. Um And so we were uh studying robotics, ai machine learning kind of different, you know different uh areas. One of my co founder is working on walking robots, you know, for a period of time. And so we all had a um a bit of a really deep kind of a deeper passion for applications of robotics and ai where um there's like a spectrum where there's people that get like really fascinated by the theory of AI and machine learning robotics where um whether it gets applied in the near future or not is less of a kind of factor on them, but they love the pursuit of the like the challenge and that's necessary. There's a lot of incredible breakthroughs happened. There were probably close to the other and the spectrum where we love the technology and the um and all the evolution of it, but we were really driven by applications like how can you really reinvent experiences and functionality and build value that wouldn't have been possible without these approaches. And that's what drove us and we had a kind of some experiences through previous jobs and internships where we like got to see the applied side of robotics and at that time there was actually relatively few applications of robotics um that were outside of um you know pure research or industrial applications, um military applications and so forth, there were very few outside of it. So maybe, you know, my robot was like one exception and maybe there are a few others, but for the most part there weren't that many. And so we got excited about consumer applications of robotics where you could leverage way higher levels of intelligence um through software to create value and experiences that we're just not possible um in in those fields today. Um and we saw kind of a pretty wide range of applications um that varied in the complexity of what it would take to actually solve those. And what we wanted to do was to commercialize this into a company but actually do a bottoms up approach where we could have a huge impact in a space that was ripe to have an impact at that time and then build up off of that and move into other areas. And entertainment became the place to start because um you had relatively little innovation in the toy space uh and entertainment space, you have these really rich experiences in video games and uh and movies, but there was like this chasm in between. And so we thought that we could really reinvent that experience. And there was a, A really fascinating transition technically that was happening at the time where the cost of components was plummeting because of the mobile phone industry. And then the smartphone industry. And so the cost of a micro controller of a camera, of a motor of memory, of microphones, cameras was dropping by orders of magnitude. And then on top of that with iPhone coming out in 2000, uh I think it was 2007 I believe. uh </s> |
<s>[INST] It's kind of interesting to imagine impossible to quantify but the number the, you know, over a period of several decades, the impact that has like a single course, like a ripple effect of society. I if you just recently talked to Andrew Ryan who was creative cosmos show, it's, it's interesting to think about how many scientists that show launched. And so it's really, um, in terms of impact, I can't imagine a better course than the self driving car of course that's, you know, there's other more specific disciplines like deep learning and so on that. Udacity is also teaching but self driving cars, it's really, really [/INST] interesting courses and it came at the right moment came at a time when there were a bunch of aqua hire is a acquisition of a company not for its technology or its products or business but for its people. Uh, so alcohol means maybe the company of 70 people. They have no product yet, but they're super smart people and they pay a certain amount of money. So I took the highest like GM Cruise and Uber and others and did the math and said, hey, how many people are there and how much money was paid and as a lower bound, I estimated the value of a self driving car engineer in these acquisitions to be at least $10 million. Right? So think about this, you, you get yourself a skill and your team up and build a company and you're worth now is $10 million. I mean that's kind of cool. I mean, But what other things could you do in life to be worth $10 million dollars within a year? </s><s>[INST] Yeah, amazing. But to come back for a moment on into deep learning and its application in autonomous vehicles. You know, what are your thoughts on Elon musk's statement? Provocative statement? Perhaps that light as a crutch? So this geometric way of thinking about the world may be holding us back if what we should instead be doing in this robotic space in this particular space of autonomous vehicles is using cameras, a primary sensor and using computer vision and machine learning is the primary way [/INST] to have two comments. I think first of all, we all know that people can drive cars without lighters in their heads because we only have eyes and we mostly just use eyes for driving. Um, maybe we use some other perception about our bodies, accelerations, occasionally our ears certainly not our noses. So so that the existence proof is there that ice must be sufficient. In fact, we could even drive a car. If someone put a camera out and then give us the camera image with non agency, you will be able to drive a car and that way the same way. So the camera is also sufficient. Secondly, I really love the idea that in in the Western world we have many, many different people trying different hypotheses. Um it's almost like an until like an hour until tries to forge for food, but you can sit, there is two aunts and agree with the perfect path is and then every single and marches for the most likely location of food is or you can even just spread out and I promise you that spread out solution will be better because if the discussing philosophical, intellectual and get it wrong and they're all moving the wrong direction, they're gonna waste a day and then we're gonna discuss again for another week. Whereas if all these ants going the right direction, someone's going to succeed and they're gonna come back and claim victory and get the Nobel prize or whatever the equivalent is and then all much in the same direction. And that's great about society, that's great about the Western society. We're not plant based, were not central base, We don't have a soviet union style central government that tells us where to forge. We just forged, we started in c corporate, you get invested money, go out and try it out and who knows who's gonna </s><s>[INST] win. I like it in your when you look at the long term vision of autonomous vehicles, do you see machine learning as fundamentally being able to solve most of the problems. So, learning from experience, [/INST] I'd say we should be very clear about what machinery is and is not, and I think there's a lot of confusion for this today is a technology that can go through large databases of repetitive patterns and find those patterns. So an example, we did a study at stand for two years ago where we applied machine learning to detecting skin cancer and images. And we harvested built a data set of 129,000 skin Photoshop s that all had been biopsied for what the actual situation was. And those included melanomas and carcinomas, also included rashes and and and and other skin conditions lesions. Um and then we had a network find those patterns and it was by and large able to then detect skin cancer with an iphone as accurately as the best board certified stanford level dermatologists. We proved that. No, no, this thing was great in this one thing I'm finding skin cancer but I couldn't drive a car. Um So, so the difference to human intelligence, as we do all these many, many things and we can often learn from a very small data set of experiences. Whereas machines still need very large data sets and things that were very repetitive. No, that's still super impactful because almost everything we do is repetitive. So that's going to transform human labor. But it's not this almighty general intelligence. We're really far away from a system that will exhibit general intelligence. Um to that end, I I actually committed at the naming a little bit because artificial intelligence, if you believe Hollywood is immediately mixed into the idea of human suppression and and machines superiority. I don't think that we're gonna see this in my lifetime. I don't think human suppression is a is a good idea. I don't see it coming. I don't see the technology being there but I see instead is a very pointed focus pattern recognition technology that's able to extract patterns from data from large datasets. And in doing so it can be super impactful, right? Super impactful. Let's take the impact of artificial terrorism. Human work We all know that it takes 7-10,000 hours to become an expert. If you're going to be a doctor or a lawyer or even a really good driver it takes a certain amount of time to become experts. Machines now are able and have been shown to observe people become experts and observe experts and then extract those rules from experts in some interesting way they could go from law to sales to driving cars to diagnosing cancer and then giving that capability to people who are completely new in their job. We now can and that's that's been done has been done commercially in many, many in sensations. That means you can use machine learning to make people expert on the very first day of their work Like think about the impact if if your doctor is still in the 1st 10,000 hours you have a doctor was not quite an expert yet who would not want the doctor who has devolved best expert and now we can leverage machines to really eradicate error and decision making error and lack of expertise for human doctors, they could save your life </s> |
<s>[INST] Exactly, thank you so much. Thank you for listening to this conversation with martin Rees to support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Martin Rees himself. I'd like to widen people's awareness of the tremendous time span lying ahead for our planet and for life itself. Most educated people are aware that were the outcome of nearly four billion years of Darwinian selection, but many tend to think that humans are somehow the culmination. Our son, however, is less than halfway through its lifespan, will not be humans who watch their son's demise six billion years from now. Any creatures that then exist will be as different from us as we are from bacteria or amoeba. Thank you for listening. I hope to see you next time [/INST] </s> |
<s>[INST] I'm actually uh good friends now with the richest man in the world. [/INST] Of course I saw your interview </s><s>[INST] with mr uh [/INST] musk. Who I </s><s>[INST] appreciate. At least [/INST] he speaks. Really </s><s>[INST] I I am I'm [/INST] positive about him owning twitter because twitter has become censorship city? S has all the major tech. I mean the censorship that we are now seeing in the United States is so un american and shocking to me. And </s><s>[INST] he is a resistance to that. That [/INST] is yeah, I like, I like musk for that just for that only. But I also appreciate him. His adventuresome, his nature and his desire to explore the world and to ask questions. Yeah. There's </s><s>[INST] certain ways you [/INST] sound when you speak freely, there's certain ways you sound a man sounds when he </s><s>[INST] speaks freely and he speaks [/INST] freely and it's refreshing. No matter whether you're rich or not, it doesn't matter </s><s>[INST] when you speak freely. It's a beautiful [/INST] thing. A major point on going back to nuclear energy. You know, he was, he never believed in it at first. Apparently </s><s>[INST] he was going for [/INST] batteries right? And he did put a lot of money in the batteries. He made them bigger and bigger batteries. But it's just as Bill Gates has said, it's just, it's not going to get us there. And now I think musk is on another path. He understands the need for nuclear </s><s>[INST] Yeah, he's a supporter of [/INST] nuclear, </s><s>[INST] mm hmm. [/INST] We're jumping around. Putin never asked for one thing. Never. It was an interview. It was free </s><s>[INST] form ask anything [/INST] you want. No, no restrictions. No rules. Mhm. </s><s>[INST] As with Castro, frankly, [/INST] Castro did the same thing as the chef says. So, </s><s>[INST] I've had good luck [/INST] in interviewing free ranging subjects. People willing to express themselves. He's much more guarded than Castro or uh, Chavez because as you know, he he's setting government policy when he speaks and anything he says can be taken out of context, but </s><s>[INST] there was no restrictions [/INST] on what to talk about. </s><s>[INST] None of that. Nor any [/INST] desire to see anything before we published it. No need to check it with </s><s>[INST] them. [/INST] It was completely Do you think he </s><s>[INST] watched the final product? [/INST] Yes, I do. But I don't think he made judgments on it. And I think he was pleased. He doesn't go either way. You see, he's he's pleased. I mean, he went, well, he's happy for us. And but I don't think he had great enthusiasm, expressed it to me and he trusted me and you can see the way he dealt with me each time he warmed up to me. Uh, four times, you know, the first time it might have been a little stiff. You're asking you don't know what, who you're dealing with and so forth. </s><s>[INST] I understand that, [/INST] but he's used to it now. He's done a lot of press. The worst press. He's done, frankly has been the american press and not because of his fault, but because of the way they have treated him. If you look at the interviews, they're awful. They put, first of all, I I noticed one thing as a filmmaker right away, they use a dub an overdub, they put a Russian speaker for everything he says. He was much harsher, he speaks Russian and much harsher manner than actually Putin does. Who's very if you're on my interview, I left him in his original language with translator and I think that's important because he expresses himself very clearly and calmly when you listen to the american broadcast, it's a belligerent person who looks like he's about to bang issue on the table. Uh And secondly the questions are highly aggressive from the beginning, there's no there's no sense of rapport, there's no sense of uh well it's why Mr Putin, did you poison this person? Why Mr Putin, did you kill this person? Why are you a murderer? I mean it's blunt, blunt negative television, it's </s><s>[INST] not just aggressive. So [/INST] I obviously speak </s><s>[INST] Russian, [/INST] so I get to appreciate </s><s>[INST] both the original [/INST] and the translation and </s><s>[INST] um it's not [/INST] just aggressive, </s><s>[INST] it's very shallow, [/INST] they're not looking to understand to me aggression is okay if that's the </s><s>[INST] way you want to approach it, [/INST] but it should </s><s>[INST] be, there should [/INST] be underlying kind of empathy </s><s>[INST] for another human being in order to be able to [/INST] understand. And and so the, some of the worst </s><s>[INST] interviews I've ever listened [/INST] to is by american </s><s>[INST] press of Vladimir [/INST] Putin. So </s><s>[INST] NBC uh [/INST] and all those kinds </s><s>[INST] of organizations, it's very painful [/INST] to watch. And you saw the reception to the Putin interviews in America was hostile without seeing it. So many people criticized my series without having seen it. Even even I went on the show a television show with this famous </s><s>[INST] Colbert, [/INST] you know, he's very famous </s><s>[INST] in America [/INST] and I was shocked on the show to find out that he hadn't seen anything of the four hours, he was just attacking Putin and he threw me, I was complicit, therefore I </s><s>[INST] was a I [/INST] was a Putin supporter and he, the show, the show was a disaster. It's, it's one of my worst television shows. I </s><s>[INST] actually, [/INST] I had to just shut up and get off the air. I mean at some point it was embarrassing because the audience to was clapping for Kobe on anything he </s><s>[INST] said well, as an interviewer in that situation because [/INST] between you and Vladimir Putin, there was </s><s>[INST] camaraderie, there was joking. There [/INST] was </s><s>[INST] are [/INST] you </s><s>[INST] worried, do [/INST] you put that into </s><s>[INST] the calculation when you're making a film [/INST] with somebody </s><s>[INST] that could be lying to you, that could be evil [/INST] when you talk about Castro, you talk about this. So </s><s>[INST] are you worried about how, [/INST] how charisma of a man </s><s>[INST] across the table [/INST] from you can take that into account, </s><s>[INST] I absolutely take that [/INST] and I know, I mean doing Castro's, he's a wonderful speaker, he's charismatic, so is Chavez, look at those interviews, I took it into account, but Putin doesn't play that game, he doesn't charm you, he doesn't try to overwhelm you with his </s> |
<s>[INST] And that's what BetterHelp does. Check them out at BetterHelp.com slash Lex and save on your first month. This is the Lex Treatment Podcast. To support it, please check out our sponsors in the description. And now, dear friends, here's Mr. Beast. I'm here with Mr. Beast, the brilliant mastermind behind some of the most popular videos ever created. Do you think you'll ever make a video [/INST] that gets one billion views? I think maybe one of the videos we've already made might get a billion views. Which one do you think? Probably like the squid game video with enough time. I mean, it's only a year old and it's already on 300 million or some of the newer ones we've done have gotten like 100 million views in a month. So those four projected over 10 years because YouTube's not going anywhere. Probably one of those. So over time, they don't necessarily plateau. It's interesting. We were literally jumping right into it. I love it. It's good. So I'm a firm believer that it's much easier to hypothetically get 10 million views on one video than 100,000 on 100. And part of why it's much easier in my opinion is like if you make a really good video, it's just so evergreen and it never dies. Because YouTube, when you open up YouTube and look at the videos, they're just serving you whatever they think you'll like the best. And so if you just make a great video, and it's constantly just above every other video, even two years down the road, then they'll just keep serving it and never stop. Which is why it's much easier to make one great video than a bunch of mediocre ones. </s><s>[INST] I love it. What about one billion subscribers? You've passed PewDiePie's the most subscribed to YouTube channel. [/INST] When do you think you get a billion? Let me do some math real quick. So around 120. So you think about this? No, I don't, honestly. Because one thing you'll find if you want to gain subscribers, if you want to get views, if you want to make money, almost any metric in this video creation space, if you want something, it all comes back to okay, well then just make great videos. So instead of like focusing on all these arbitrary vanity metrics, I just kind of focused on the one thing that gets me all that, which is make good videos. And I do think we will, when they hit a billion subscribers, say I don't have a plan on going anywhere. Even though we're only on 120 million right now on the main channel, I think we're doing around 10 million a month now and YouTube just, yeah, I just don't see it going anywhere and I don't see any reason why I'd ever get burnt out </s><s>[INST] or quit, so I think with enough time, yes. I wanted to ask you those family-friendly questions before I go to the dark questions. [/INST] So now, we have dark questions. But if you wanted to hook them, you would start off with the dark questions. That's how you get them. </s><s>[INST] Okay, well, that's how you get them. Okay, well, let me ask you about the, a Twitter poll you posted, a $10,000 death poll. You tweeted, if someone offered you $10,000, but if you take it a random person on Earth dies, would you take the $10,000? And 45% of people said yes. That's, at least at the time I checked, 850,000 people committing murder for just $8.5 billion in total. [/INST] So what do you learn about human nature from that? That's a good question. Honestly, this is like late at night when I threw that up too. I was just like, huh, this'll be a funny thing. I assumed it'd be 90% no and like 10% yes, but there are a lot of serious people. For you guys listening, I just did this random Twitter poll. I was like, would you take 10 grand if it meant someone random in the world died? And a lot of the replies on the suite were like, hell yeah, why not? And I was just not expecting that. And so, I don't really know. </s><s>[INST] I mean, I feel like your take would be better than mine. [/INST] Was that disturbing to you, surprising to you? A little bit, yeah. But obviously, a lot of the people were trolling, but I actually, when you read through those replies, </s><s>[INST] I do think like 10% of them were like dead serious. Well, I think sometimes the trolling and the lols reveal a thing we're too embarrassed to admit about the darker aspects of our nature. So, I don't know if you listened to Dan Carlin's hardcore history podcast. He has a episode on painful attainment, which he describes throughout history how humans have been really attracted to watching the suffering of others. So, public executions, all that kind of stuff. And he believes that's in all of us. That, for example, if something like a YouTube or a different platform streamed a public execution or streamed the torture of another human being, a lot of people would say that's deeply unethical, but they would still tune in and watch. And that we're attracted to that drama, and especially the most extreme versions of that drama. And so, I think part of the lols reveal something that's actually true in that poll. That like- Your answer is so much better than mine. Do you think about that? Maybe even with the squid game, like, so I think, how many views does the squid game currently have? 300 million? Yeah, something like this. So, just imagine, thought experiment, how many views that video would get [/INST] if it was like real squid game? Yeah, assuming YouTube was like, oh, we'll turn the blind eye, we won't take it down. Yeah, I mean, obviously, </s><s>[INST] we'd probably have billions of views. How do you think you will die, [/INST] and do you think it would be during a video? Probably doing something dumb, like going to space when I'm older, like, trying to go to Mars or something like that. I know for a fact it won't be on a video, every video we do we'd safety experts and stuff like that. It's not really risk, but... Yeah, I could see myself, after a million people go to Mars or something like that, I'd probably be like, you know what, let's go, and something like that, maybe. </s><s>[INST] So not in the name of a video just for the holiday? [/INST] No. </s><s>[INST] No, heck no. Are you open to taking risks when you shoot videos, You just went to Antarctica. I mean, like, you're putting yourself [/INST] in the line a little bit, right? Of course, but, you know, we've had that video in the works for three years, and then we consult with tons of experts, radar the entire path we're gonna walk beforehand to see if there's crevasses. So we know there's no crevasses, we do training, we consult with experts, and we have survival guides there with us, and, you know, monitor the weather and everything. So it's like, any variable that, where we could get harmed, we just pre-plan for it. Same thing with Buried Alive. Like, I had David Blaine, spent a week underground. And so I consulted with him, and consulted with basically anyone who ever buried themselves alive. You know, the coffin we used to bury me, we did so many tests. Like, that coffin was buried 10 times before I was, you know, for a little longer than 50 hours. It tested the airflow and everything, to the point where I was safer in that coffin underground than I was above ground. Like, so we just tend to just not leave anything up </s><s>[INST] to chance, you know? Another strange question then. So you recorded these videos to yourself, you know, five years, 10 years from now. Have you recorded a video that's to be released [/INST] once you die? Well, first off, I am just glad that not every one of your questions have to do with, like, views or things like that. It's nice getting different questions. So this is, this is good. No, seriously. Little duck, it's a little duck. No, no, but it's fine because a lot of people just be like, how much money do you make? You know, it's just something I just, everything's always about money now, when people talk to me. So it's nice. But for the videos I made, for you guys who probably don't follow me too closely, when I had 8,000 subscribers and I was a teenager, I filmed a bunch of videos, and scheduled them years in the future. And I said, I'd film one where I was like, hi, me in a year. And the video went up a year later and it was just like, hey, I think you'll have 100,000 subscribers. And then I did one where I was like, hi me in five years. I was like, Hey, in five years, I think you'll have a million. And then one that hasn't come out yet, but comes out in two years, is, was, hi, me in 10 years. And I tried to predict 10 years later how many subs I would have. So it is what he is referring to. And yes, there, there are some that are scheduled, like 20 years in the future. And so if I don't dial, just move them up. And I remember, cause I filmed these though like seven years ago, but it was, I remember saying a line like, you know, if I'm dead, then I'm currently just in a coffin and like whatever blah, blah, blah, because the only way the video would go up is if I'm not alive and if I'm not alive, then I won't be able to push back the schedule upload date. So we'll go public automatically. Yes. And so yeah, I have a couple of those, like if I knew I was going to die of like cancer or something and I had like three months to live, I would vlog every day. I filmed so many videos. And then I would just schedule upload a video a week for like the next five years. So that's like, I'm still alive and I would completely act like I'm still alive. And everything. </s><s>[INST] And I think something like that would be cool. [/INST] Seriously, it's a little, I don't know why, but I've fantasized about it, not fantasized, but I've dreamt about that a lot. Like I don't know if, if I only had 30 days to live, what would I do? And for me, I would try to make like a decade's worth of content and schedule upload it. So they automatically go public in the future. And so it's just like, I never died. </s><s>[INST] I'm just there. kind of immortality, but it's also a kind of troll on the concept of time, that you can die in the physical space but persist in the digital space. I actually, I recorded a video like that because I had some concerns and I just thought it's also a good exercise to do. A video would like to be released if I die. And it was actually a really interesting exercise. It's cool, like it shows what you really care about. I guess it's like writing a will. But when you're younger, you don't think about that kind of stuff. [/INST] Exactly, mine was just dumb. Yeah. </s><s>[INST] My bones in a coffin. [/INST] Yeah. </s><s>[INST] Yours is probably so serious. No, it's fun actually. Where you realize there's no point to be serious at this point. It's a weird thing, I guess you've done this, but it's a weird thing to address the world when you the physically use no longer there. So you know this would only be released if you're no longer there. Exactly. [/INST] That's a weird exercise. Exactly. You know what's funny? Of all the people listening to this, we're probably the only two people that have made videos for when we die. It's like such a niche thing </s><s>[INST] and the fact that we're bonding over it's kind of funny. Yeah, I think people should think about doing that. It's not just about YouTube, it's also social media. Just think about it. Like there's gonna be a last tweet and a last, I don't know, Facebook post, a last Instagram post. And yeah, I feel like there's some aspect that's meditative to just even considering making a post like that. And also it's a way for the people that love you [/INST] to kind of like celebrate. Do you think that would help them cope or not? Like if someone randomly watching this did film a video for if they accidentally died in some freak accident to be given to their family, </s><s>[INST] do you think that would, and it was like a genuine? I think it would really help. [/INST] I mean it depends because like, Like how would you even intro that? Like, hey mom, if you're seeing this it means I'm probably dead, and you're still alive. Yeah. Exactly. </s><s>[INST] That's why you intro in a kind of funny way And just talk about the things that mean a lot to you, because otherwise, you're at the risk of the last post you have is like, I don't know, talking shit about. McDonald's screwing my order. [/INST] Exactly, exactly. McDonald's screwed on my order. Exactly, exactly. But then you're dead. </s><s>[INST] That's it, hundred years. I do recommend it. It's like the Stoics meditate on death every day in the same way to kind of meditate on your death when you make a video like that. Because it's actually not just and talking to yourself, it's talking to the world. And it like, for some reason, at least for me, they made it very concrete that there's going to be an end. And I'm like, it's almost, it's over for me. If I'm making the video, it's over for me. It's just an interesting thought experiment. I recommend people try it. [/INST] Okay, are you afraid of death, by the way? Yes, it's hard because like, what if you just die and then you just see nothing forever, you know? Yeah, the nothingness. It just fades to blackness and you're just like that for trillions upon trillions to billion squared years. And it's just, it's scary. But also, before you're born, you don't remember those X amount of years either. So that gives me a little comfort. But it's definitely very scary. Something I'd rather not think about until I'm like 80. I'll deal with that problem then. I don't know if I told you this, but I'm kind of hopeful that someone like Elon or one of these like freak smart people would just like be like, you know what, screw it. I'm gonna figure out a way where we could slow down aging, get it where, you know we could live to be 200, 300 years old and just like set their sights on that and then just kind of save us. So, would be really nice. Like it's almost absurd to think that in our lifetime they won't figure out a way to just even slightly slow down aging where we could live to be like, 120, 130 and then that extra time they won't figure out somewhere where we could live to be 200. They're obviously not immortal, but I don't see how </s><s>[INST] in my lifetime the life expectancy doesn't just expand. The nothingness. Well, it also could be that the immortality is achieved in the digital realm. Like it could be long after you're gone as a Mr. Beast, run by a Chad GPT type system. [/INST] Exactly, exactly. Yeah, that consumes everything I ever said, everything I ever wrote, and I don't want that. I want to live. What are you smart people out there figuring out? I'll keep you entertained, but I need you to figure out how to keep me alive. Give me till 200. </s><s>[INST] That will make me happy. Well, that's funny. Who owns the identity of Mr. Beast once the physical body is gone? Like, is it illegal to create another Mr. Beast that's Chad GPT based? I don't know what the laws are on that. [/INST] Yeah. Yeah. I mean, once I'm done, I don't care. </s><s>[INST] Well, you just said you did care. I mean, there could be AI, [/INST] like many Mr. Beasts that are created after you're gone. Yeah, I mean, that'd be cool to be able to like train up a model and let them loose </s><s>[INST] so my content lives on, I guess, yeah. Yeah, but it somehow feels like it diminishes the value you contribute. Yeah. Yeah, it's inauthentic, but it's also, there's some aspect to the finiteness of the art being necessary for its greatness. [/INST] Oh, 100%. The value you contribute. Yeah. Yeah, for its greatness. Yeah, once the second that thing starts spamming out videos, the videos lose all meaning </s><s>[INST] and it's pointless and it's a money grab. If you were on YouTube for how long should you run it? For a year, how would you change it? [/INST] How would you improve it? It's hard because, you know, obviously I'm biased because we're doing really well, but I feel like when I open up YouTube on my television I get the videos I want to watch. I don't know. I don't ever open them and wonder, like, what are these? What are these 10 videos on my homepage? When I click on a video, I'm like, I don't ever wonder what these are like. And maybe it's because I'm very adamant about like the kind of videos I watch and I try not to watch videos and I don't want to get recommended more because I just, that's how I think, but I'm very happy with how it is at the moment. I think, one thing though that I just hate the passion is the comment section on YouTube. It's just so bad. But I know that's not something that's gonna 10X the growth of the platform, but if you think about it, you go to Reddit to read comments, and somehow, usually the top 20 posts on a popular Reddit post are not spam, you know what I mean? Have you ever clicked on something on the front page of Reddit, and then most uploaded reply to it is like, go check out my site right here, and it's trying to scam you out of $1,000? I can't even think of one instance I've ever had that happen. So, Reddit, it's so nice to click on posts and just see what people have to say, and I almost wish you had that same feeling when you read the comments on a YouTube video. Instead, it's so many people just copy and pasting, so many bots that just grabbed the top comment for your previous video and pasted it over, so the top comments on every videos are the same, and the things that break through that are just scammers </s><s>[INST] trying to get you to give them $1,000 for a fake ad. That comment section is one of the most lively on the internet, and so it would be amazing if YouTube invested in creating an actual community, like where people could do high-effort comments and be rewarded for it, like on Reddit. [/INST] Like actually write out a long thing. That would make me so happy, because when I upload a video, I usually go to Twitter to see feedback. I read my comments, and I'll flip through newest, but it's just, I feel like Reddit and Twitter just give me so much better filtered feedback, especially now that with Twitter Blue, because people pay $8 a month, I've noticed like any tweets I get from verified users now, they're usually not just garbage troll takes, like these are people paying $8 a month, like they're usually relatively sensible, and so it's been pretty nice. Like after I upload a video, I just go on the verified tab on Twitter and just see what people have to say, </s><s>[INST] and anyways, I live for the day that YouTube's like that. What do you think about Twitter? What do you think about all the fun activity [/INST] happening recently since Elon bought Twitter? Yeah, I think he should make me CEO, like I tweeted. </s><s>[INST] Well, I should say sort of we had, we just like a couple hours ago had a conversation with Elon, and you guys sent an exchange of some excellent ideas, so yeah, I legitimately think, obviously you're exceptionally busy, but I legitimately think it would be awesome [/INST] if you somehow participate in the future of Twitter. </s><s>[INST] Yeah, it would be fun. Because there's so much possibility of different ideas. First in the sort of the content, like dissemination, hosting, and all the different recommendations. The assertion, discovery, [/INST] all the things that YouTube does well. I think the most exciting thing is he's willing to move fast, and so I think there's gonna be a lot of interesting things that come out of it because he's just moving quick, and a lot of these more mature platforms just take years to do the simplest stuff, and they're very bureaucratic. It'll be interesting to see which way it goes. When you just kind of take a move quick, break things, whatever type approach to social media, I'm actually pretty curious to see </s><s>[INST] what features he rolls out. [/INST] So what would be your first act as Twitter CEO? I can't spoil it. Okay. I gotta get hired. </s><s>[INST] What do you think about video on the platform? On Twitter? Yeah, do you think that's an interesting, or is it like messing with the medium, [/INST] the nature of the platform? I think Twitter will always be closer to TikTok than it is to YouTube, at least in its current form. I don't see 20 minute, one hour long videos or whatever, even 15 minute videos being watched over there. I see it more as like the short and snappy stuff </s><s>[INST] closer to TikTok. But at the same time, [/INST] Twitter is a really good comment section for the internet. I mean, it's almost weird why, like why doesn't Twitter allow you to embed YouTube videos? Like why does, you should just ask Elon that. Like, I don't know if that's a YouTube thing, but when a YouTuber posts a video, why do they have to link to YouTube? Why can't they just embed it on Twitter and you just play it there? I mean, wouldn't that just solve a lot of problems? </s><s>[INST] Yeah, but then the two companies [/INST] would have to agree to integrate each other's content. I don't know, but it seems like a win-win. I mean, well, it's more of a win for Twitter because then people don't have to leave the platform. </s><s>[INST] I mean, that'd be the easiest solution. But who gets, like when you watch the ads on a YouTube video that's embedded in Twitter, [/INST] who gets the money? It would still be YouTube, but at least then right now people just post a link and it takes you off Twitter </s><s>[INST] and it just kills your session time on Twitter. That's really interesting. But yeah, because the Twitter, whatever the dynamics of the comments, especially once the spam bots are taken care of, Twitter just works, it's really nice. So Reddit is a nice comment section for the internet. It's like slower paced, more deliberate, like higher effort. Twitter's like this high-paced, like ephemeral kind of stream, but there's the up-voting and the down-voting works much better, because you can do re-tweeting, right? Because the social network is much stronger [/INST] than it is on YouTube, like the interconnectivity change. Yeah, on Reddit you're gonna get, the top replies are gonna be the most refined ones versus Twitter, stuff flows to the top that's not super refined, but like you're saying, it's more off-the-cuff stream of consciousness, </s><s>[INST] which a lot of people prefer, it's a little more personal. How do you think Twitter compares to YouTube [/INST] in terms of how you see its future unroll in 2023? I mean, I think YouTube's gonna be YouTube and not much is really gonna change, but it's gonna keep growing just because, that's just what it does, because it's owned by Google. But Twitter, I don't know, I mean, it's one of those things like you can't predict if a year from now an economy's gonna be in a recession or booming, and I think Twitter's kind of the same thing. One thing's for certain, a lot of things </s><s>[INST] are gonna be rolled out, but who knows, honestly. You responded to Elon saying Twitter's unlikely to be able to pay creators more money than YouTube. [/INST] What do you think that is? Well, yeah, because I think the tweet I responded to is one where he was saying that users will jump over if Twitter can potentially pay more than other platforms. I was just saying, obviously, because Google has Google AdWords and that's Google's whole thing, it's putting ads on stuff. They've been doing it better than anyone else in the world for a very long time. It's very unlikely in the next few years that Twitter's gonna just magically, or any platform, give a creator the ability to make higher CPMs than on YouTube. It's kind of crazy, like some creators in December, Q4 because ad rates are higher because of Christmas and everything, some creators literally make like 30, $40 per 1,000 views, and that's after YouTube's cut. It's almost like hard to think about, like how high the RPMs get. And even then, once you pull out of financing cars, the high CPM niches, and you move into just normal stuff, it's still just crazy. There's sheer volume of creators, and the fact that all of them get these multi-dollar CPMs </s><s>[INST] at scale, it's pretty beautiful. So you do, I don't know what you would call them, but like integrated ads in your videos, and you do, I would say masterfully, it's like part of the video. Are you talking about brand deals? Brand deals, is that what you would call that? Yep. So it's a brand deal, it's part of the video. It's still really exciting to watch, [/INST] and yet there's a plug for the brand. Are you talking about brand deals? In general, just brand deals, since you brought it up, integrating them well. I think that's something a lot of creators don't do. Like, they'll just do a brand deal out of the blue. They'll just be filming a video, and then around the three minute mark, just start talking about a random company. And I feel like if you don't want viewers to click away, and you want people to not get pissed off, and call you to sell out, you gotta find a way to integrate into content. And ideally, use the money in the video to make it better. Like, the easiest thing you do when you do a brand deal is just tell people how you're using money from the brand deal to make your content better. And if you do that, no one cares. Now, they're supporting you for it. And you go from being a sellout to like, </s><s>[INST] oh, I'm doing this to make better videos for you guys. I don't know if you can share, but would those brands, when you have discussions with them, are they strict about how long you need to be talking about it? Or is it more about, they're leaving control to you [/INST] about the artistic element of it? The problem is, the ones who don't give us artistic element we just don't really work with anymore because it's just you know we get a hundred million views of video now and I can confidently say I know how to entertain them and convert them better than these random brands so </s><s>[INST] yeah if they don't give us that freedom I just won't work with them. You have [/INST] that leverage but for smaller creators it's a lot harder it's a lot harder yeah and they're gonna just say 45 seconds here's what you say take it or leave it and it's like pretty brutal because I think just in general if brands were more accommodating to let creators tell their story of the brand and talk about the brand in a way that felt a little more natural I think it'd be less cringe if people would be less likely to go you know tap tap tap skip and obviously it would convert better but they're just so afraid and they want this standardized </s><s>[INST] thing say these words and 45 seconds right here at this three-minute mark yeah I often think about how to resist that you just don't do them though right not on YouTube right I do an audio I do ads in the very beginning and I say you can skip them if you want like the point is they so the funny thing about podcast is different than YouTube videos podcast people actually do listen to ads a lot because they it's slower paced and they like the the creative voice like talking about the thing but in general I just don't believe you should be talking about a thing for a minute exactly and that's going to be effective I want to see the data for that I think what's much more effective is the way you do ads which is like integrate into the content like put a lot of effort into making a part of that like doing the brand deals and I just it's difficult to have that conversation it's like a very strenuous conversation you have to have with with brands if each one at a time and I just wish there's more of a culture to say like the quality of the ad read matters a lot more than the like The silly parameters like the timing of it Uh-huh. How long it is the placement of it all that kind of stuff [/INST] What percentage of your viewers do you think have seen one of my videos before? </s><s>[INST] What percentage of the viewers on refused your viewers of the viewers on YouTube though. Yes. Yeah, okay [/INST] Yes, your viewers. Yes. Yeah. Okay. Sure or all of them It's just interesting cuz you're you're speaking very Specifically like about my brand deal process and some of my head I'm like I wonder what percentage of these people even have any </s><s>[INST] no idea what he's talking about. That's interesting. [/INST] I love the thinking about numbers. The whole time we're having this conversation, it's all I could think about. God dammit. There's probably like 50% of these people have no fucking clue what he's saying. And we're about to torture him for five minutes. Yeah. Probably. But it's something I can't turn off in my brain. </s><s>[INST] Yeah, yeah, probably. Less than 50% Is that a good thing or a bad thing? Is that exciting to you? That there's like 50% of people don't have not watched the Mr. Beast video. [/INST] Isn't that an opportunity to like, I guess it's an opportunity to grow. I don't know, honestly, I was just kind of excited to hang out with you. Yeah, me too. And it was a lot of fun. Who cares of the mics? Yeah, so it was kind of like having a buddy to go along the journey as I'm just kind of eating shit and doing my normal ride. It was like kind of fun. And also you just say really wise stuff constantly. So honestly, no, I never even put any thought into like that demographics are what I could gain. It's just interesting. Cause like my retention brain, when you talk about something, I'm instantly like, hmm, what value are they gonna get? How many of them are gonna be interested? What percentage of people do I think we'll lose? And I'm like running all those calculations in the background. And that whole conversation, like the lock, anyway, it's just something I can't turn off. </s><s>[INST] My like bells are like air, air, this is bad. Yeah, me too. And it was a lot of fun. Who cares of the mics? What are the different strategies for high retention [/INST] for your videos and in general? It's like, how do you cook good food? You know what I mean? </s><s>[INST] That's like the same kind of question. I see, so there's so many different ways that you're, so it boils down to, I mean, do you think at the level of a story or do you think like, literally watching five seconds at a time am I gonna tune out here? Am I gonna tune out here? [/INST] Am I gonna tune out here, not here? That's all of it. You need the overarching narrative and then you also need the micro where every second needs to be entertaining. And basically what's interesting is the longer people watch something, the more likely they are to keep watching. So you don't have to try as hard in the hypothetically back half of a video as you do it in the front. Like even right now, we're so deep into this where a lot of people listening are probably just gonna keep listening relatively close to the analyst. We just have a really boring part of this conversation because they're just saying it, they're immersed. And so a big, like to really boil it down to a simple level, you just wanna get people where they're immersed </s><s>[INST] in the content and then just kind of hold them there. We had this discussion offline. [/INST] By the way, I should mention that this is like late at night. It is, what time is it? </s><s>[INST] It's nine o'clock. And I only slept one hour last night because I'm an idiot [/INST] and I flew to the wrong location. Well, here, we're like, hey, let's just book you a hotel and a flight, and he's like, no, I got it. We're like, you sure? We just do it, we always do this. </s><s>[INST] He's like, no, I got I got it. [/INST] He's gonna have to rub it in. I know, and then today, and coming to find out, he flew to the wrong airport, airport with the, or a city with a similar name to ours- Just same name. </s><s>[INST] Yeah, just- The same name. Yeah. [/INST] Same name in a different state. And I was like, that's why he used to let us book it. And so he's on one hour's sleep and he's literally been dying all day. Before this podcast, he down like two things in coffee. We've been going all day hard. </s><s>[INST] Yeah, I've been, I got to interact with you. I should say that this gave me an opportunity to, I got a ride from a stranger and it was an incredible person that I got to interact with him. So there's so many kind people around here. Just like this kind of Southern energy. And then I got to go to a diner because I could, there's only one hour between me arriving and having to fly out. So I went to a diner, there's a really kind waitress that called me Honey. [/INST] So that was a beautiful moment. I was so confused you tweeted about that and like Steele's like liks my assistant was like Lex isn't here yet I saw your tweet and I was like he's here. Yes. He's like, no, he's still flying I was like for like an hour ago. He just tweeted about a nice diner. Yeah There's a diner in a different state and then you had to fly over here that was and then I called you you didn't answer I was like, hmm </s><s>[INST] Something's not add enough. I feel like it's such an idiot because um but apparently the world has cities like Springfield, right? [/INST] Every single state has a Springfield. </s><s>[INST] Oh, really? I think so. That's like a Simpson's joke, right? The city in the Simpsons is Springfield and I think every single state, or most of them have a Springfield. And the same is true for Georgetown, I think what the most popular one was, but there's like a list of things people get when they run out of ideas to just keep using the same thing. [/INST] They're your Achilles heel. I forget, keep using the same deal. They're your Achilles heel. </s><s>[INST] Anyway, I got to meet a bunch of people from your team who's just an incredible human being. So let me just ask on that topic, how do you hire a great team? Like what have you learned about hiring for everything, for the main channel that you [/INST] do, for the React, the gaming channel, to Mr. Wieseberger, to Feastables, all that. The big thing is, especially in this content creation, because it's not like anything that's done on Netflix or different content medians, I really need people who are coachable and like really see the value in what I care about, because it's a very specific way of going about things. And it's like a thing, there's no one like plug and play. Like if Netflix wanted to hire someone to do a documentary, there's probably tens of thousands of people you could hire that have worked on documentaries before. But if you want to hire someone to make super viral YouTube videos like we do, there's just no one you can really pull from. Sometimes I'll hire people from game shows, right? They have all these preconceived notions about pacing and how a video should be, and you have to spend the first year breaking all these habits and they think they're better than you. Like a lot of people in traditional think they're better and they think their way is better than what we do. And so for me, it's almost easier to hire people that are just hard workers that are obsessed and really coachable and just train them how to be good at content creation and production, than to hire someone from like traditional which is the only way to really do it. Because there's not that many YouTube channels that have scaled up so it's not like there's a huge talent pool of people who've worked on YouTube channels. So it's easier just to train someone than just pull them from traditional because traditional people, I don't know, they have all these opinions and things and they just think our </s><s>[INST] way of going about things is dumb. Yeah. So you want people who have the humility to have a beginner's mind, even if they have [/INST] experience. Actually, you'll still get it. It's so crazy. Like especially some of my other friends that are scaling up their YouTube channels, there's people that will come on. And you'll ask them like, what do you want to be doing in five years? And instead of saying, oh, I want to be working on this channel, they'll be like, oh, I hope to be working on movies or this, that, and they see like work on a YouTube channels, the launch pad to go into traditional. And it's like, no, like you just don't get it. This is the future. This is the end goal. This is your career. And so I'm just so tired of having those kinds of conversations. Like I feel like people really should be coming around. </s><s>[INST] These are the future Are there like recurring, interview questions that you ask? [/INST] Is there ways to get? Yes. but the biggest thing is like, what do you want to be doing in 10 years? And their answer isn't, you know, making content on YouTube or you know, if their answer is anything like movies or traditional, stuff like that, it's like just a hell no. Like it just won't even remotely work. </s><s>[INST] Oh, so you really want people to believe [/INST] in the vision of YouTube, it's a pleasure? Yeah, I mean, ideally it's like oh, </s><s>[INST] working here, you know what I mean. So, it's less about the medium and more about just [/INST] being on a great team, that's doing epic stuff. Yeah, well and, yeah the medium as well. Because it's hard to put into words, but it's just two completely different ways of going about things. Our videos aren't scripted, and it's a lot more run and gun. And if we hypothetically blow up a giant car or whatever, you only have one take, and it's not scripted. And so you have to over film, overshoot things, overcompensate for the dumb way of going about it. And a lot of traditional people would be like, well, just plan what you're going to say and just plan the angles. You can cut the cameras in half, you can save 50 grand here, you can save $75,000 editing, this and that. And it's like, yeah, but that's not authentic. Blah, blah, you get it. It's almost so obvious that it hurts that I have to constantly have these conversations, </s><s>[INST] but it's what we live in. But there's also detail, like there's a taste. I've watched a bunch of videos with you, and it's clear to you that you've gotten really good. I don't know what the right word is, style or taste, to be able to know what's good and not, in terms of retention, in terms of just [/INST] stylistically, visually. I don't have to think, I can just watch a video, and it just screams in my head, like this is what should change based on the million videos I've watched, and all these viral videos I consumed, like this is blah, blah, blah, what's optimal? And things like that. It's almost like your brain's like a neural net. And if you consume enough viral videos and enough good content that you just kind of start to, like, train your brain to like, see it, and see these patterns that happen in all these viral videos. So that anytime I watch a video or a movie or anything, I just can't stop thinking about what is optimal. And so it's like, it gives me a headache sometimes when I watch something too slow or I don't think it's optimal. Obviously, my taste isn't the end all be all. </s><s>[INST] But that's something that kind of torments me if that makes any sense. Oh, you can't enjoy a slow-moving movie. No, I can't. [/INST] No, I can't. </s><s>[INST] And that's not to say there's- There's tension on the Godfather is horrible. [/INST] Yeah, no, I've tried to watch that movie like three times, but that's not to say slow movies are bad. There's no audience for it, it's just obviously not what I've trained my brain to like and </s><s>[INST] in social media and YouTube right now, like, that's just not the meta. And in general, like you said, in neural network, you're training your brain in part on actual data, right? So you're actually data-driven, so you're looking at like in terms of thumbnails and titles and different aspects of the first five, 10 seconds and then throughout the video, the retention, all that, you're looking at all of that for your own videos to understand how to do it better. [/INST] So that's where the neural network is training. Yeah. Basically, there are ways you can kind of see like the most few videos on YouTube everyday and stuff like that. And I just kind of consumed those every single day. I've been doing that for way too many years. And then you just start to notice patterns. Like the thumbnails on the most few videos, or videos that go super viral, tend to be clear, tend to not have much clutter, tend to be pretty simple. Titles tend to be less than 50 characters. Intros tend to be this, stories tend to be this. And you just kind of like after you see those thousands and then tens of thousands of times, it just starts to click in your head. </s><s>[INST] This is what it looks like, you know? So how are you able to transfer that taste that you've developed to the team? So for like, cause you said like broad things, but I'm sure there's a million detailed things. Like what zoom to use on the face [/INST] you use in the thumbnail, right? The answer is whatever makes the best video. Cause the problem is the more, I have so many friends who are like this, they'll make like checklists for their editor. So like, you know, this beat and this beat, and you need to have like a three part arc and then this, but the problem is that's how you, the more constraints you put on the team, the more repetitive and less innovation you get. And the more like, you know, after 10 videos, people are gonna be like, all right, I've already seen this. So to me, and I'm 24, and you know, I'm probably, my mindset will change over the next 10 years. I just haven't been in this industry too long, but the only way to like really make innovative content and keep things fresh is to not put constraints on or put as little as possible. And so that's why I'm very hesitant on all that stuff, because the more I say, the more they're gonna be like, oh, then that's what we do. And then you know, I'll say one time like, oh you know, ideally there's to cut every three seconds. And then next thing you know, every video there's like cut every three seconds or whatever. So it's hard, because I tried to give as little train, not training, but as little facts or as possible and more just make suggestions, if that makes any sense. You mean publicly or to a team? </s><s>[INST] To my team, yeah. Yeah, what was so you talked about sort of teaching your voice or your Style, whatever we want to call it to other people on the team so they can be kind of Mr. Beast's replacement [/INST] So what's the process of teaching that so you don't know? I get changed. No, I getuez Yeah, you're more time about like what I would call almost like cloning, right? Like like Tyler and other like that Yeah, so when we were hanging out today I was showing him how we have multiple people in the come it's I it's almost like talking to the cameras Yeah, he turns slowly to the camera. </s><s>[INST] It was a habit. Yeah, he turned slowly to the camera. [/INST] Is it weird to you to not be looking at the camera? This whole interview, I constantly have been turning towards the camera and I'm talking to him. Yes. It's a habit because my whole life, I've just been talking to a camera. </s><s>[INST] The camera looked like I'm talking to him. What are you thinking about when you looking at the camera? [/INST] You imagine somebody? I'm fully thinking about the person just sitting, watching it and it's weird. When I'm looking at the camera, I don't see a camera. I'm in a haze picturing what the viewer is seeing when they watch it if that makes sense. And that's where I'll be saying things or doing something and then when I'm watching it I'm, like, that's not what I want. And then I'll freeze up. It's very weird when I'm filming and for people who haven't worked with me too much, they'll think like, I don't know, it's very weird like how I go about it because I'll just be doing whatever. Like lighting a firework car. This is a thousand dollars fire going to go to... And I'll freeze because in my head I'm like this.. I don't know, I don't like how that float or how that shot look, because it's weird. I can perfectly picture what I'm filming by just looking at the camera and then putting myself through the lens of the camera while making content. </s><s>[INST] I can do it at the same time. It's weird, but... So you're like real-time editing the video. [/INST] Yeah, yeah, that's something that didn't at the start come natural to me, but in the last probably like five years, it's happened. And so I would say it's one of my greatest strengths, but I don't know how I developed it. I don't feel like I'm filming anything, like it's almost like the right sound every day </s><s>[INST] and I just can just look at it and I see exactly when I'm filming and I can just picture it. Well, it's probably doing band recording the video, being the talent for the video and then watching the editing and like analyzing you're careful and do that over and over, over, over and over. Yeah, you do that 10,000 times, yeah. You do the editing more than being in front of the camera, so like, you start to see yourself from that third person perspective. Exactly. Now maybe that actually helps with the nerves of it too, like you see it as creating a video [/INST] versus performing, right? And over and over and over, you develop. Yeah, you do that 10,000 times, yeah, exactly. Right. Yeah, yeah, I think so. You know, it's weird, I've never been nervous talking to a camera. It's harder for me to talk to a person than to talk to a camera, which I feel like a lot of people say that though, that are whatever, make content, right? Interesting. I've heard that so many times. </s><s>[INST] Interesting. [/INST] I've heard that, or maybe not, maybe I'm just awkward </s><s>[INST] and dumb. Maybe they're practiced. To me, it's, I mean, both are terrifying, but being in front of the camera by yourself is most- So much easier. [/INST] Really? So much easier. Really? Yeah, so much easier. I've preferred a million times over, but that's my whole life, so it's just, that's why it's interesting. Like you spent more of your time talking to people </s><s>[INST] as it comes to natural and I talked to a piece of plastic. I guess you're talking to a person too. There's just then on the other side of the camera. Yeah, there's just a pixel on the screen. So cloning, how do you achieve the- [/INST] Oh yeah, that's right. This whole rabbit trail. So I was showing him that I have a lot of people in the company who were able to think like me basically make decisions like I would make if I was like if you were asked hey in this video should we climb a mountain or should we dig a hole right and like you know they would pick the same answer I'd pick 90 plus percent of the times and so like one example is Tyler who I was showing you and he was pitching some content and you can see like this he was on point and basically for just four or five years we just spent an absurd amount of time together and worked on every single video together and we worked side-by-side and same thing with my CEO James he literally lived with me for a couple years I'm a big fan of just like finding people who are super obsessed and all in and a players that you know they really just want to be great and they're just dumping everything </s><s>[INST] I have in them and then you were saying because I'd love to find that and develop that you're saying you're basically for a long time just said [/INST] everything you were thinking to them exactly like James the guy who's basically my right human right now for two years he lived with me and we probably talked on average of those two years seven hours a day I mean every time I had a phone call at phone on speaker and I'd let him listen I'd anything I was reading any content I was consuming like really just training his brain to think like me so that way he could just do things without my input without me having to constantly watch over him or give him advice and and that's where we've gotten like so for the first six months he didn't do anything he just studied me and studied everything I cared about and how I spoke and blah, blah, and then the next six months, he started taking on some responsibilities and now he can just run the company and I don't ever really have to check it on him. Most of the decisions he makes are exactly what I would do. I call that cloning, I don't know what other people would but it's just like finding people that are really obsessed and they just kind of really want it and just giving them an </s><s>[INST] avenue to get it, if that makes any sense. Another way to see it is you're converging towards a common vision and that makes like brainstorming much more productive. [/INST] Yeah, it just makes it where I don't have to be so involved in everything because I just have these people I know will think like I will, at least relatively close to it. So I can kind of almost be in multiple places at once per se. And so these things that, you know, I still approve every idea we film and, you know, everything before we film and all the creative, I approve it. But I don't have to like be in the weeds and nuances and do all this minor stuff. I can just let them handle it. </s><s>[INST] I can just do the more macro things. I got a chance to sit in to a lengthy brainstorming session with Tyler and others. That was really cool. Can you talk about the process of that, of people pitching ideas and you pitching alternatives [/INST] or shutting down ideas and just going like plowing through ideas, Rick? I mean, you kind of just described exactly what we did. </s><s>[INST] Yeah. I mean, but the ideas are really, really good at just tossing out like different categories of ideas and then also fine tuning them to see like, how do I change, like think about the titles and the thumbnails. [/INST] I work so well off of inspiration. It's like, it's something like, give me anywhere. I don't know. Space. Yeah, like I went to space, you know, what happens if you blow up a nuke in space or I went to the moon. I went to Mars. Because you said that one word, it was able to inspire me to come up with four ideas and so, cool. For me, the way to get a hundred million views on a video is you need something original, creative, something people really need to see, ideally never been done before, all these like, things and so you need like, if you want to consistently go super well, you need just a constant stream of ideas. And the only way I've really found that I can consistently come up with 100 million view videos is to intake inspiration and then see what my brain outputs and so that's kind of at its core foundation what I'm doing there it's just like in taking a lot of random inspiration to see what spawns in my mind so I can </s><s>[INST] output it but what the neural network of your brain is generating the video the [/INST] title the thumbnail all like jointly jointly exactly and that only comes because I spent 10 years my life just obsessively studying all that stuff </s><s>[INST] does you I mean it seems like you would literally potentially shut down a video [/INST] just because you can't come up with a good title yeah oh yeah that's what happened to 70% of those in that pitch session it's like oh what was one of them </s><s>[INST] genius vs 100 people or yeah like maybe average intelligence versus Genius or [/INST] that I was like what the heck is the thumbnail even if the title was good </s><s>[INST] yeah I mean this so many but yeah people don't click they don't watch yeah that's That's so interesting, but you developed over time the ability to kinda give it, what makes it a good title? [/INST] Short? Not just short, it's also, I mean, if someone reads it, do they have to watch it? Is it just so intrinsically interesting that it's just gonna fuck with them </s><s>[INST] if they don't click on it, you know what I mean? So it doesn't have to be short, but it has to be, like you almost want to have a retention [/INST] to word by word reading. Ideally, it's a title also that, you know, cause the titles don't live in a vacuum, right? So it has to lead into the content, so ideally the title represents content that you would wanna watch for 20 minutes. So if it's a 20-minute video and the title is I Stepped On A Bug, it's not gonna, cause it's all of it combined. The click-through rate's gonna be much lower than if it was like a five-second video. People might click it, so you gotta, like even nuances of the length of the video based against the title will affect whether people wanna click it, because sometimes they just all add up. I mean, its that yes. Ideally you want to blow 50 characters because above 50 characters in certain devices you run the chance of it going dot, dot, dot. So like, I took a light pole and I saw how many dollar bills I could stack on top and they would just go dot, dot, dot cause it's too long and it can't finish it, and that's the worst thing because then people don't even know what they're clicking on and so it's going to do even worse. Short, simple, ideally, and just so fricking interesting they have to click and it is a good segue into the content and it represents </s><s>[INST] the length of the content. And there's probably stuff you, it's hard to convert into words for you. Like, I stepped on a bug versus stepping on a bug versus Mr. B stepped on a bug versus [/INST] bug stepping video bug versus bug stepping video. So it's like, yes, the more extreme the opinion, typically the higher the click-through rate. If you can like pay it off in the content, then it just supercharges it. </s><s>[INST] So like- Oh, so you have a kind of estimate of the extreme- [/INST] Yeah, like this water, right? You're like Fiji water sucks. That'd do fine, but if you said Fiji water was the worst water bottle, or the worst water I've ever drank in my life, way more extreme opinion would do way better. But you have to deliver. Yeah, but then you have to deliver because the more extreme you are, the more extreme you have to be in the video. </s><s>[INST] Yeah. That's almost an inspiration for you to step up. [/INST] Yeah, you can be more extreme in a positive way. A lot of people, it's easier though. Positive. Negative click baits, much easier than positive click baits. It just is, it's so much easier to get negative clicks. And so a lot of people are just in my opinion, you know, a little bit lazier. They just take the route like, oh, well, this one gets the same amount of clicks and it's easier with less effort. </s><s>[INST] The positive one is doing a large number of numbers of something. [/INST] Like I spent this number of hours doing this or whatever, if you just wanted to help people or, right, it's just harder to get 10 million views on a video helping people than it is to get 10 million views on a video tearing down a celebrity, you know what I mean? </s><s>[INST] or whatever negative video you wanna insert there. Well, that said, most of your videos are pretty positive. [/INST] So, what's. But not a lot of people do those kinds of videos because they're hard. </s><s>[INST] Yeah, they're hard. Some of that is giving away money, right? Yeah. What's the secret to that? How do you do that right? Yeah, give away money or? In the video to make it compelling. [/INST] Yeah, yeah. </s><s>[INST] Give away money or? So there's a number that is better than another number, [/INST] right... The higher number is always better than the lower number. Yeah, for the most part. You know, it's interesting, some videos will give away $1 million, some videos give away half a million, there's not really, I guess. So I'm retr Okaying what I just, I was more joking with that, but there's no difference whether I put 500 K or million, it's probably not even really a difference between 100K or a million. I haven't really looked into it, like some of our mostly videos are not us giving away a million dollars and sometimes the million dollar videos just don't do as well as the other ones. So, there is a certain point where a dollar amount is just a large dollar amount to an average human and so I think that point is 100K. Like anything above 100K, the average human is just like, that's a lot of money. It doesn't, 100K in a million, like doesn't really move the needle, if that makes sense. Which that's a very nuanced piece of information </s><s>[INST] that applies to very few people, but yeah. Well, no, I think it applies, it's fascinating. It's fascinating, human, our relationship with money is fascinating. Like why is it so exciting to get, I mean, I, you know, the times I've found like 20 bucks on the ground are like incredible. I don't know why, right, why? Why are you so happy? Like what exactly is so joyful about that? I mean, it depends where you are in life, what the situation is. Yeah, I don't know. There's also a gamified aspect to it. [/INST] It's exciting, I don't know why. Yeah, I get it. Like why people want to see people win money. It's just interesting that past 100 grand, it doesn't really seem to make a difference. </s><s>[INST] Like it's the same, basically. So you found that to be true with all the money you've given away. [/INST] I just didn't click through it. Like obviously in terms of someone receiving it, yeah, a million dollars changes their life drastically more. Like that's the difference. Like, oh, if you wanted to, you could really quit your job. </s><s>[INST] I suppose 100k is like, not really. You probably do like a scientific study, like a formula, giving away money to click through rate. Yeah. [/INST] There could be some kind of diminishing return. Yeah, I got it. It definitely, the returns level off dramatically after 100k. 100k. </s><s>[INST] That's basically the premise. That's basically the premise. [/INST] What about 10,000? No, there's 10, 100,000, it's funny because this is such a small niche thing, but yeah, 100,000 does, from what I see in our videos, get more clicks than 10,000, but the difference between 100,000 and a million is just so little. I just, I think big number, big number to a lot of people. </s><s>[INST] I pass that point. Yeah, so for 100,000, you can, like a given average salary, you can probably live for a year, given what they have average salaries in America. [/INST] So that's like a big, that feels something. Yeah, I think it's also just more when they read the title, it's just like, it's a lot of zeros. It's like, fuck loads of zeros. Okay, click. I don't know. </s><s>[INST] Yeah. I've watched it. Yeah. Oh man, that's fascinating. So on the thumbnail side, again, that's gonna be much harder to say, probably, but offline, I got a chance to look at a bunch of thumbnails and it's fascinating which ones do well and which ones don't. Is there something you could say about what are the elements of the thumbnail that work well? Or is this also deeply in- [/INST] Well, that's where, yeah, it's the same thing, like how do you cook good food? But it's easier if you pull up a thumbnail and it can be like, that's why, that's good. That's why, that's bad. That's like an example would be like, one of my friends, he just uploaded a video recently and I called him. I was like, what is this? Because he's a very, very smart guy. And then the thumbnail, he's getting chased by cops, but the cops are wearing yellow vests so they don't look at cops. So I was like, oh, why are the cops on your thumbnail wearing yellow vests? It's like, that makes it so much more boring. And he was like carrying a flag, but the pole and the color of the flag, sort of the same color. So it was like, it's a little harder to see the flag. I was like, also, you're wearing, a shirt with like five different colors. So it's hard to tell even what your outline is. And then in the background there were cars. And I was like, oh if you have cops chasing you, why not make the cars cop cars? And, you know, cause in my head, I'm like, dang, if you just did those, like four or five things, the video probably would've got like seven extra views. </s><s>[INST] How much iteration? Because I also got a chance to see the number of iterations you do on... [/INST] It's a problem now. </s><s>[INST] It's an addiction. It's an addiction. Is it? So you kind of, there's a lot of the versions are really good. Yeah. [/INST] How do you know when to like stuff? I love how you, when we pulled up that, uh, the burger one and we were flipping through them, you're like, that's really good. I was like, oh, that's version like one of like a thousand. </s><s>[INST] But even the sketch, the idea was good. Like already even the original idea is strong. [/INST] Yeah. Yeah. So we, one of our coming up videos, we made the world's largest plant-based burger and the thumbnail, we're thinking it's like me standing beside the burger cause it's six feet tall. And that's what he's talking about. So like just picture a giant six foot tall burger, super wide thousands of pounds and then I'm beside it. And then it's like eating the world's largest burger. Like you, that's just something you have to click. Like, so you were saying like, how would you describe a good thumbnail? </s><s>[INST] Like that, you know what I mean? Like, but I think you said the one I noticed first, that was good, where you were very small in it, and you didn't like that one. [/INST] I needed to come forward a little bit. And also, the photo we took was just my upper body. So they photo-manipulated and created my legs in Photoshop. And that's why I said I didn't like it because my right leg was a little like off. It was like bent the wrong way because I had to build those legs in Photoshop. </s><s>[INST] I had to build those legs in Photoshop. Does the physics and the thumbnail have to even make sense? I mean, you can just like exaggerate the head size and all that kind of stuff, right? [/INST] Yeah, 100%. Yeah, things don't have to be relative. You can have a car in the background, maybe three times the size. Yeah, and every one of my thumbnails, my face is in the left side, very big. So brand recognition, so just people know. Oh, especially because now that a lot of people copy our videos, it's just nice to like, everyone else might make thumbnails like this, but this is mine. </s><s>[INST] And obviously, we usually over-deliver and do bigger stuff. Would you recommend to other creators that want to make it big, and they see Mr. Beast and they look up to you to copy some elements of you [/INST] or to really try to be unique? Unique, 100% unique. You're not. The next Mr. Beast, quote unquote, it's weird saying that, third person, but whatever, is not gonna do what I'm doing better, they're gonna just invent their own life. Like you're just not gonna do what I do better than me. I have so many. I literally have the best people in the world working here. And I reinvest everything I make, even to this day, you know what I mean? Like it's absurd, the amount of money I spent on content. And I don't care, I'll just stop sleeping and I'll just film every other day. Like, you're just not gonna beat me at my own game, and that's fine, you shouldn't. I didn't get where I am by just beating someone else at their own game, I just found my own lane and innovated and adapted. And so, yeah, there's a lot of people that do copy me and it's fine, whatever, do it, but just know you're not gonna get to where I am doing that. </s><s>[INST] And so I'd advise you don't. You give away a lot of the secrets, basically everything about how you operate. I don't hold anything back, go for it. How do you think about that? [/INST] Because that's pretty rare. I don't hold anything back, go for it. I think and this is definitely not. Most people in my stance I don't think would take this or my position would take this stance but I see every other YouTuber or person on social media, even, because we're also focused super heavily on YouTube but last year we were also the most followed TikTok creator in the world as well. Actually, we were most subscribed to YouTube channel in the world and the most followed TikTok account in the world. But in general, I just see everyone else as collaborators, not competitors. I don't think giving advice and helping other creators </s><s>[INST] well in any way harms me and I think it only brings more value to my life. How was it jumping on TikTok and trying to understand that platform from scratch? Yeah. So from being a successful YouTuber to understand a totally different algorithm, fundamentally different algorithm. [/INST] It's interesting. Well, not even just the algorithm, just the content. Like I'm going from basically 15 minute short films to one sub one minute vertical content. It's a whole different just ballpark. And so the first little while I was doing TikTok is just kind of figuring out what does Mr. Beast look like in this short form content. But recently we've really started to catch our stride and come up with some original concepts and figure out how to innovate over there just like we did on YouTube. Because I don't want it, I didn't want it to just be shitty YouTube videos. And so like an example is we played The Rock for 100K and Rock, Paper, Scissors, and the loser had to donate 100K to charity. We went to random people on a campus and we offered them. So I said, I'll give you $100 if you fly to Paris to give me a baguette. And then they said, no, then I was like, I'll give you $300 if you fly to Paris and give me a baguette. And I was expecting this person to say no and go up to like 10 grand. And he's like yes. And so he flew to Paris, got a baguette and wrote it back and he gave it to me. And that across everything got like 450 million views. Because it's just really cool just to see this random guy get on a plane, spend a day in Paris, and we cut it up real nicely and bring it back. </s><s>[INST] And so we're starting to find just tons of original content over there. [/INST] But it seems like an epic video to make for one minute. Exactly. No one on ShortForms is doing it. That's the thing. It's like, it's just so funny because like TikTok's been big for a while now, years. And then, you know, as we started to really figure out things on the YouTube channel and get it cranking where I have some free time, we set our sights on TikTok and like, okay, what are people not doing? How do we make it better, put in more effort, make it good? And we did the same thing we did at YouTube, just different over on TikTok and it worked. And now we're at the fastest growing or most followed TikTok account in 2022. </s><s>[INST] And it's just funny that no one else did that. And you're not afraid to do epic stuff, which also during the brainstorming, some of the ideas you're like, that's better as a short. [/INST] That's crazy. Yeah. Can you remember one? </s><s>[INST] Because I remember I said that a bunch, but I can't think of one. All I remember is that there were like epic videos. Like really, you're going to do that for a one minute video? Yeah. That's crazy. [/INST] So like, are you posting similar content to a YouTube short as a TikTok video? Yeah. Yeah. Those would just double up. It's just hard. You know, what's actually pretty fascinating and people who do social media listening to this will probably find this pretty interesting is picture like the content creation meta three years ago versus now where you can make sub one minute vertical content and it go viral on TikTok and go viral on YouTube shorts, go viral on Instagram reels. It goes viral on Facebook. It goes Reddit, you know, you swipe through vertical content now and Twitter when you click on a video and you flip through it. So this is actually very weird. This is the first time in the history of, I guess, Western social media that one form of content could actually go super viral on every single platform. It's never been like that before. </s><s>[INST] So they're going viral individually. They're not like interpreting or whatever. [/INST] Yeah, like I can post something on TikTok, they'll get 100 million views and then post on shorts and I'll get 200 million views and then post it on Instagram and I get 50 you can't post 100 million views and then, you know, I have it yet, but you can then turn around and tweet and get tens of millions of views and then you can post on Reddit and get tens of millions of views and Facebook can get tens of millions of views and that just wasn't a thing. Three years ago, Twitter didn't have, because a lot of you probably don't even know this, but when you tap on a video now and you swipe down, it just turns into TikTok. That wasn't a thing even a year ago. Reddit, that wasn't a thing a year ago. Probably two years ago, that wasn't a thing on Instagram, three years ago, that wasn't a thing on YouTube, right? YouTube Shorts, so this is all new. I don't, it's weird, I haven't heard a single person talk about it, but this is the first time where content can actually go viral on every single platform. And you don't have to write or film a video for Facebook, film a 12-minute video for YouTube, film a sub-60-second video for TikTok, write a tweet for Twitter, and post this on Reddit. </s><s>[INST] You can just do the same thing on every platform. And the fact that your content has gone viral on multiple platforms regularly means that virality is not accidental. [/INST] Sometimes it can be, of course, but it can be engineered. It can be engineered. So many people say it's luck, and they're like, you're just lucky, or this or that, but what do we have to? Probably like 1,000 videos over 10 million views. We don't ever have a dud. You can call it luck, but I think it can be trained. I counsel YouTubers all the time and show them how to go from getting a couple million views a month to 10 million views a month very easily, and from even certain ones. Just one of my friends, he was just really struggling, and so I just started showing him basically everything I know, and just doing like once every week, sometimes once every two weeks calls, and he went from $10,000 a month on YouTube to over $400,000, just doing these little counseling calls. And so, I mean, people can make excuses all they want and say it's just luck, or say, you know, well, anyways, I don't even wanna quote all the other stuff, but it's just, it is. It is a teachable skill, it's a learnable skill. You can study your way to consistently make viral videos, no matter how small your channel is. Even if you have zero subscribers, you could if you actually studied hard enough and like, basically if you knew what I knew and some of these, so I don't sound so arrogant, also like some of these other friends that have that, I'd say, are the smartest people in the world when it comes to content creation online. If you had the knowledge that was in our heads, you could do it very easily. I've seen people do it all the time. And what's even more interesting is I go on podcasts and I say everything I know, and these people are also very open, some of them I know, it's all out there, And a lot of people, instead of just studying that and trying to absorb and apply it in their own way, </s><s>[INST] they're just like, no, it's just luck, you know? So you do lay it all out there, but I gotta push back to one interesting thing. I think a crucial component of your success is the idea stage, the idea generation. The brainstorm that I heard today, but getting really good at generating ideas. So it's not just the selection of the thumbnail and the title, that creative process. It's also just the engine of generating really good ideas. And getting that, I mean, I would say that is probably the thing that needs to be trained the most for most creators, right? [/INST] They just don't put enough ideas on paper. And getting that. Yes, but also a lot of creators also just don't, you know, which I didn't either for the longest time, just didn't don't make good enough content. </s><s>[INST] Content that's worthy of getting 10 million views. [/INST] In the idea or the execution of the idea? Both. I mean, like, think about how many people just make videos, they film in under 20 minutes and they don't really put any effort into it. And like, you know, it's like, my first 500 videos didn't deserve to get a million views. Like there's a reason they did. They're terrible, you know, but at the time I thought they did, right? And I'm in the mindset of a lot of small YouTubers where I thought those videos deserved a million views and I thought that really paid me. But I watching back now and I can tell you exactly why the videos were just fricking horrible. </s><s>[INST] You know what I mean? You know what I mean? So what was the breakthrough for you to start realizing, to start having a self-awareness, you know, about these videos aren't good enough. You're probably still going through that, [/INST] you probably still growing to see. Yeah, every six months you used to look back and hate your videos. Or at least see things you could improve and be like, oh, I could've done this better, that better. If not, then you're not learning quick enough, </s><s>[INST] in my opinion at least. Where's the source of that learning even for you now? [/INST] I mean, I just got back from a mastermind where I just got like ten of the smartest people I knew and we just locked ourselves in a cabin and taught each other stuff. Constantly, every day, not every day now, probably every other day, I go on a walk and it's called random people. I'll just say, yeah, teach me something. And I mean, it's just, you just have to have a never-ending thirst for learning. That's very imperative, especially if you want, like if you want to get on top and then stay on top, the only way to do it is just to constantly be learning. Or someone who is learning is just gonna, </s><s>[INST] yeah, I'll have a leg up on you in the knowledge game. And what kind of stuff are you, because you've talked about offline that you just love learning of all kinds, doesn't matter but in terms of videos are you studying videos are you studying [/INST] recently not as much I'm more because they get to the videos I want I have to build this business and scale up and hire so more my recent time has been like my teenage years were spent studying virality and studying content creation now I'm studying how to build a content company so I can actually produce the </s><s>[INST] crazy ideas I want to produce if that makes any sense so yeah on that the [/INST] business side we talked about hiring do you have trouble firing people no I'm pretty sure almost every person yeah actually every person I've ever fired we you just give them severance, and I like to see it more as. It's no ill will. Like if there's if like, if I fired you if there's some other job you want me to help you get I'll DM them on Twitter like you know if you want to go work for I don't know insert whatever MTV give me someone to DM. I'll DM like you know, I I try to make it more like a transition and do whatever </s><s>[INST] we can to make it as easy as possible. And there's something that was just not working for you because you want people like you said super passionate. [/INST] Because at the end of the day if you hold someone that you onto someone that you you don't see being here in 10 years, you're just doing them a disservice, you're just giving them more ingrained, more enrooted and where they are, and the sooner you do it, </s><s>[INST] and help them move on to their new life, the better. Given all the wisdom you have now, if you were to give advice to somebody or if you were to start over again, you had no money, what would be the first 10 videos you tried to make on a new channel, I guess that's advice for a new person. [/INST] And nobody knows you. And nobody knows you. Yeah and nobody knows me, </s><s>[INST] I would think they have a mask on. [/INST] And then you also, I guess don't have the wisdom. If I don't have what I have in my head then I would just say just fail. A lot of people get analysis paralysis and they'll just sit there and they'll plan their first video for 3 months. Any of you listening especially if you have zero videos on your channel, your first video is not going to give views. Period. It's not. Your first 10 are not going to give views. I can very confidently say that. So stop sitting there and thinking for months and months on end Like all you need to do this this applies to people who have not uploaded videos But have dreams of being a youtuber is make 100 videos and improve something every time do that and then on your hundred first video We'll start talking like maybe you can get some views But you know your first hundred are gonna say there are very freak cases like Viscoshi or Emma Chamberlain who have really good personalities and it doesn't take them so as many videos And it's just like people who are seven foot five and making the NBA like yes There are freak cases you can find but for the average person like us You know who don't have these exceptional personalities and you know Backgrounds of filmmaking just make a hundred videos improve something each time and then talk to me on your hundred first video </s><s>[INST] Well the improve something is time is the tricky one [/INST] How do you improve something each time the second one just I don't know put more effort into the script The third one try to learn a new editing trick the fourth one Try to figure out a way that you can have better inflections in your voice the fifth one Try to you know study a new thumbnail tip and implement it the sixth one try to figure out a new title There's infinite ways, that's the beauty of content creation online, there's literally infinite ways. From the colouring to the frame rate to the editing to the filming to the production to the jokes to the pacing to every little thing can be improved and they can never not be improved. </s><s>[INST] There's literally no such thing as a perfect video. [/INST] So, if you knew everything you know now, with no money, but no money. Step one, i would just brainstorm like, okay, I don't have money, what are some viral things like I mean, the first thing that comes to my mind is something as simple as when I counted to 100,000, which is what I did do when I was poor, and I like that work, but like what's something like that I could do that would be even more attention-guided. </s><s>[INST] Yeah, you were, as part of the brainstorm, you would throw out a lot of ideas, and people throw out a bunch of ideas, [/INST] and one of the questions is, is this even doable, right? Yeah, first off, come up with ideas you think would do well, and then ask yourself later if they're doable, because there's different ways </s><s>[INST] you can accomplish something. [/INST] Don't be cynical about the doability of stuff. Yeah, because there really are so many different ways you can accomplish a goal. Like when we give away an island, like we gave our 100 million subscriber an island, you can't find private islands that don't look like shit for less than $10 million, so this isn't doable, right? All right, the idea doesn't exist. Not doable, exit off, but then you dig into it, and you find different alternatives, and you find, okay, what if we just buy a $2 million island that sucks, and then spend a million dollars importing some sand, let's build a beach, let's import 300 trees, let's build a little bit of canals, cut some paths. Boom, now it's a really nice island, but it's actually affordable, because we don't have $10 million to spend on a video, but we can afford to spend three and a half, and lose whatever, a million dollars on that video. So that's an example of, yeah, if you just went off the gut test, you'd be like, this isn't doable. Every island's $10 million, we're screwed. If we go cheaper, it's just a terrible island, no. And so if you, there are so many different ways you can achieve what you want, you really gotta push through notes, which not a lot of people do. You have to have more of a dominant personality, and just a willingness to, when people tell you it's not possible, just actually go through all the variables </s><s>[INST] and eliminate them all yourself. [/INST] Have a stubbornness and a resilience to failure, maybe. For what we do, and creators online, it's very imperative that you have, that a no isn't a no to you. You really have to think, and just, we take a personality test, and just having a dominant personality, is a better indicator that when someone tells you, oh, there's no way you're gonna build a brick wall for under $100,000, you'll be like, okay, and then still go check the next 10 vendors, </s><s>[INST] and figure it out. Yeah, what advice would you give to an already established channel, like with one, two, three, four million subscribers, how to 10X it, increase it, without losing, maybe? [/INST] Yeah, that's where it's very channel by channel. You can't give general advice. Okay. Yeah, because if I do, millions of creators are gonna see this, and then they're gonna do it, </s><s>[INST] and I'm gonna fuck them over. Oh, I see, I see. So, let's say I'd like two million subscribers on this podcast. Yeah. Like, how would you 10X that without sacrificing what it is? 10X your stuff. Does it matter? So, you've talked about what's success. [/INST] Yeah, it's different for everyone. Yeah. 10X your stuff. It's different for everyone. Like, is 10Xing your definition of success? No. Well then, it's gonna, right off the bat, it's hard, because if you don't give a shit about 10Xing, it's even harder than 10X. He does this because he likes helping people. That's one thing I found throughout this day. Every time I talk data, it's so funny with him, cause it's like, you know, you could do this to get more views, and he'll just be like, blank. I don't see like that doesn't register anything, you know, he just like doesn't care, which is, </s><s>[INST] it's really, really cool- I'm really, I'm really nervous about that. I'm really nervous about the numbers affecting, cause it's so fun. Yeah. It's so fun to focus on the numbers, and I'm, I'm really worried about that. But at the same time, you should be cognizant of that, because you've created, not just some of the most watched videos, but some of the most amazing videos ever. So there's a strong correlation there. It's not like you're selling your soul to make a highly viewed video. It's actually, if you look at the metrics, it helps you understand what is compelling and not. [/INST] And so I feel like I am, </s><s>[INST] I feel like there's some value to investigate what work, when people tune on and when not, to be more data-driven, even on podcasts. [/INST] But I'm really afraid of that. On the flip side, I think part of the appeal </s><s>[INST] is that you don't care about that kind of stuff. But there could be stuff that doesn't have to do anything with that and it has to do with stylistic choices of lighting and cameras, or maybe with, for example, topics. Yeah. [/INST] You know, like. Yeah. Even what you've asked me here is like, </s><s>[INST] different than what most people ask me. Yeah, so it could be, I mean, and it'd be nice to understand that. But again, I'm worried about polluting the creative process. [/INST] At the end of the day, it's, at the end of the day, this is a true case of its your own intuition. Like, you know your viewers better than anyone else, </s><s>[INST] it's whatever. It's whatever. See I'd like to push back on that, I really don't. You do. [/INST] I do. You do. </s><s>[INST] Name one person who knows your viewers better than you. [/INST] Somebody that looks at numbers of podcasts? No, you know your viewers. You know, you're the only, </s><s>[INST] how many episodes have you done? 350? Exactly. [/INST] But I'm not peanut? Exactly. But I'm not pigmented. You're the only one who's watched every second </s><s>[INST] of all 350 of them, probably. Okay, that's just, that's just not, no, well I haven't. [/INST] but the okay well I haven't. But the, okay. because you did it. So you do know what's in album it's your content is new P I'm telling you you do. And this is just one of those moments where you're an intelligent guy and you just have to trust your like instincts. Like, just think what is the typical ex viewer </s><s>[INST] and what do they want? It's your content and new people. I don't think like that my tip but that's all you would have to [/INST] my tip that's all you would have to do. And whatever your gut tells you </s><s>[INST] that would be the best guess. You don't know what the typical view is though, I don't, because, to investigate, that would be very, very difficult. And then you have to start looking at the numbers. You have to start to consider demographics. The only way I know that anybody even watches it is because I'll sometimes run into people, like when I run on the river, and they be like, I love you, Lex. It's like, okay, well that's the data point, and they're like cool people. But, I don't know, I don't have any other, it's difficult man it's difficult to know, it's difficult to know who listens to boxes, it's difficult to know. Do you have a sense of who's, I mean, like, you're so huge that everybody watches. Yeah. But no, I still do. [/INST] I'd say, but no, I still do. I'd say if you were to just put a gun to my head and you're like, all right, we're gonna pick a random person that watched your last video and you have to like roughly guess what they are and if you're not close, we'll kill you. I would say probably like a teenager that plays video games. Like some, like that would be probably the typical one. And then there are people that are maybe a little bit younger. A lot of people are older as well, but in a random sample size, yeah, it's probably like a male boy that plays video games. Like that's the best way I would describe it. But I don't try to pertain to them. I just make whatever I think is interesting and good content. And this is what we were talking about before, even though hypothetically 35 to 40% of my audience is women, which is, you know, less than a majority. If we get 100 million views of video, that's still 30 to 40 million females that watch every video, which is probably the largest, you know, views per video for women on the whole platform, which you wouldn't think that. You know, like I can't think of a single other creator that gets more women to watch their videos than that. And so it's just anything, even like people above the age of 30, even if it's only like 3 or 4%, that's still 3 to 4% of 100 million views is a lot of people that age. </s><s>[INST] So we hit a large group of kind of every demographic, if that makes any sense. So what if we look at other maybe more challenging kinds of channels or not? But if we look at educational, for example, like lectures, or if we look, yeah, educational, it could be short videos, like how would you 10X that? Like something on robotics and biology and science and engineering and all that. [/INST] That's more educational focused. That's more educational focused. We would honestly just have to pull the date because it's the same way as if you went to Gordon Ramsay and you said, how would a new cook cook better? You know, it's like, even then that's not even specific, you have to go channel by channel. You really do. Or I'm giving horrible advice because if there was these just golden rules, everyone would do it. You know what I mean? </s><s>[INST] Like if there's these magical little principles. How quickly, when you look at a channel, can you kind of give advice? [/INST] Yeah. Give advice. Yeah. It's like surface love at the start. Like if we watch 10 videos, I feel like I'd have a good profile and I could tell you, in my opinion, you know, especially once I look at the analytics and I get more ingrained and like, okay, the typical viewer is this, they're from here, here's how they're feeling. You know, because there are people who make videos for rednecks. And like the rednecks taste of content is just so much different than obviously women watching makeup videos, which are so much different than, you know, teenage boys watching a Minecraft video. They're just all different. So the biggest thing you have to do is put your head in the headspace of the viewer and see the content, how they would, because if you just try to only give your taste, which is what a lot of people do and things from your perspective, it's very biased and it's just not going to work for everyone. And that's actually how you do more harm than good, which is something I'm very careful </s><s>[INST] of. Yeah. But at the same time, just generating a lot of ideas. I think the first time I've talked to you was on Clubhouse actually. Yeah. I mentioned something about robots and like almost immediately you went to generating a bunch of ideas around robots. Oh yeah. [/INST] Easily. Oh yeah. Easily. 100 robots versus 100 humans. Yeah. </s><s>[INST] Yeah. I think your idea, like the first idea was because you just said so many ideas I never even thought of, but it shows the value of basically brainstorming with people that think [/INST] differently. But at the end of the day, my ideas are probably, you know, might lean towards some people a little bit younger than your audience. Like some of the stuff. </s><s>[INST] Could be. Yeah. Could be. Yeah. There's still ideas. Like I think the first one you said, because we're talking about a quadruped, like robot dogs, you said to replace a biological dog with a robot dog and see if the owner notices something. You were just quickly brainstorming different ideas of like how- Yeah. This was years ago. I remember it though. Yeah. It was just, I mean, it's like, oh yeah. I never really thought about that kind of sort of, it's the basic, the tension between what does it take for a robot and our AI system to replace the biological systems that we, the biological creatures that we love in our lives. Yeah. And that was like the pace of idea generation was the thing that struck me today and in general. It's like, that's how you get at good videos is you keep- [/INST] It makes, it's much easier to make a video around a good idea, obviously, than a bad one. You just send yourself up for success. </s><s>[INST] Okay. So that's for 10Xing already popular channel. What's the hardest number? And the numbers that matters, click-through rate, average view duration, and surveys. [/INST] What's the hardest number to optimize for? Probably surveys. Do you have any, do you have an insight into the surveys at all? No, no, not really. But if you just click on a bunch of random videos online, you'll eventually get a survey. What's this video transformative, heartwarming, inspiring? What people rate does make a difference? And it's like, you can give people a click of a video, you can get them to watch it, but you can't really fake whether or not they're satisfied. They don't lie, the surveys, you know? Maybe one person here or there might troll, but once you aggregate enough, it's a pretty clear telltale of the video. </s><s>[INST] So either you're making a great video or you're not. [/INST] What is it, minimizing the non-regrettability- Yeah, I think Elon tweeted, that's what he's trying to do on Twitter. </s><s>[INST] For Twitter, and that's for Twitter, and that's interesting. [/INST] That's basically the survey metric, how happy you are that you've been using the platform on a platform. Yeah, yeah. Elon tweeted, we want to limit the amount of regrettable minutes people spend on Twitter, and the first thing I thought, it's like, that's something YouTube already has a lot, </s><s>[INST] their whole survey system and feedback loop. How tough is it to take on YouTube, you think? Like- For Twitter? [/INST] Yeah, for Twitter for anybody else. For Twitter? I mean, it's going to be basically impossible. I mean, YouTube's not going anywhere, and I don't know, I don't think anyone's going </s><s>[INST] to do what YouTube does better than them, or at least not in the next 10 years. You asked on Twitter, would you rather have 10 million dollars or 10 million subscribers on YouTube? [/INST] What would your own answer be at various stages in your career? If I had nothing, I would say 10 million dollars, because with 10 million dollars, you can hire some people and pump out content with like a million or two, get 10 million subscribers </s><s>[INST] and then keep the other eight million. [/INST] So that's if you believe in your ability to grow a channel, if you- Well, yeah, if you don't believe in your ability to grow a channel, then you shouldn't take the 10 million subscribers, because you're just going to kill the channel. Yes, you're going- So the 10 million is definitely, a better question would be would you rather have a million dollars or 10 million subscribers. That's where it gets a little tricky. Because now it's like, hmm, you know, a million dollars life-changing amount of money, but if you semi-knew what you were doing, you'd probably make a million dollars off a 10 million </s><s>[INST] subscriber channel, but it is a little bit of risk. So a million dollars might not be enough to build a strong team, because you don't know how to do it so you might waste all of that money. [/INST] Yeah, or they just keep it and retire. </s><s>[INST] Yeah, yeah. [/INST] Okay, that's true. Yeah, because 10 million is just so high, it's like, just never work again, who cares? </s><s>[INST] For the average human, that's so much money. It's interesting to me also to the value of the subscriber versus the value of the dollar. I suppose how valuable is the subscriber for, like, what percentage of the videos, like, how active are the subscribers in watching the video? [/INST] For you. That's hard, I don't know. I was actually thinking more about the subscriber to dollar. Like, if someone has 10 million subscribers, have they made 10 million dollars? I don't know why that kind of popped in my head. </s><s>[INST] It's an interesting thought. Do you ever, when you analyze videos, do you ever analyze videos like we've talked about offline of other videos across YouTube in general to understand trends, to understand social behavior? [/INST] Oh, all your, not all, but a lot of the questions are analytic space. Yeah, it's so funny. </s><s>[INST] Because I love it. Yeah, it's so funny. Because I love it. It's just like a giant social experiment, right? [/INST] Like what people like to watch, what people share, it's like a fascinating, it's like a fascinating. So, like I said before, what percentage of your audience do you think care about this kind of stuff? </s><s>[INST] Like, this deeply about YouTube analytics? I think a large amount care about curiosity and exploration of interesting ideas. [/INST] So, in that sense, yeah, this would fit it. In that sense, yeah, I love it. This is funny. This isn't me like trying to make, I love you, and I actually, I loved your Magnus one and even your Hikaru one was really good, a bunch of other ones, but I think we're getting to the point now where only analytics junkies would want to keep hearing more analytics talk and the normie is probably like, they've had their dose of YouTube talk for the next </s><s>[INST] three years. I love you. [/INST] I actually, I love you too. Maybe I'm wrong. Comment if I'm wrong. I could be. I don't know your audience. </s><s>[INST] See, this is where you would tell me, shut up, I know my audience, you dumbass. And I don't at all. I actually, I just follow the thread of curiosity and I think there's just a lot of curious humans in the world. And to me, it's like, so the question about analytics is the question of basically stepping away, stepping outside of yourself and thinking, why the hell do I like TikTok so much? Why do I like Twitter so much? Why do I like YouTube so much? And getting, even if you're not a creator, getting an insight into that is really interesting. It's like, what, because all these platforms are fundamentally changing the nature of content. People are reading books less, they're probably going to be watching movies less and less, they're probably going to be watching Netflix less and less. Do you ever think about the sort of the darker side of YouTube and with shadow banning and censorship and all that kind of topics, especially if you see it in other platforms like Twitter, that Elon recently highlighted the shadow banning that was happening and in general, the censorship that was happening on those platforms. Do you think about the role of centralized control of which information is or isn't made available through search and discovery? I'll be honest, I never really think about it. [/INST] You just try to make fun videos that- Yeah, I'm more, I'm kind of more in my own lane, but it's not like that I don't just specifically think about, I just like a lot of stuff in general, I'm just kind of in my own lane thinking about my own stuff. But now that you asked, I'm curious, what are your thoughts on YouTube and that kind </s><s>[INST] of stuff? Well, I'm generally against centralized censorship or shadow banning. Shadow banning is the worst one because not that the goal of creating a healthy platform where you're having great conversations and videos that are not spreading misinformation, that sounds like an admirable goal, but that's too difficult of a job for a centralized entity. [/INST] That's too big of a- Yeah, there's the misinformation stuff and then there's also just like the videos where they do something that causes, what happened back in the day, the adpocalypse and a lot of creators revenue plummets because people are doing videos that advertisers don't deem acceptable and then now all these big advertisers are pulling and the little guys are getting hit because ad rates dropped by 30% and the person who just quit his job to go full-time consecration now can't sustain it. So it's also, it's like a lot of different variables as well. That makes it so complicated. </s><s>[INST] Well, I think the big thing is transparency, especially around shadow banning for people. [/INST] I agree, I agree. On shadow banning, you should be transparent. You should let people know it, you know, obviously there has to be some type of controls. People can't just post whatever and so if you're pulling those levers, they should at </s><s>[INST] least know. Yeah, so they know how to improve their content. They can understand it, they can, if it's a wrong shadow banning, like as a society that we should not shadow ban this kind of content, that means you should be publicly [/INST] discussing it and having that. Because if not and if it's not known, then it's just kind of like, well then who's pulling the strings and like, how do we know they're not just manipulating things to get whatever </s><s>[INST] message they want out there and silence other ones? Yeah, and there could be sort of in the background, government influence, which is where actual freedom of speech comes into play, that government should not have any control or be able to put pressure on censorship of speech, and it gets weird if none of that is being, there's no transparency around it, but to be fair, that's a huge responsibility. [/INST] The amount of content that YouTube is uploaded on YouTube that is shared by YouTube, viewed by YouTube. But even more of a reason why it would probably make sense to be transparent, because then </s><s>[INST] people can help fact check it. That's right. But that requires building a platform that makes that easy. To make fact checking easy, to make Twitter now has being able to share context and all that kind of stuff. That crowdsource it. Crowdsources the way Wikipedia crowdsources it. I mean, there's... Right. [/INST] It's right. </s><s>[INST] And then you open a random Wikipedia article. But people criticize Wikipedia because there is a political lean to the editors of Wikipedia and then they get some articles that definitely have a bias to them and all that kind of stuff. It's a difficult problem. It's a difficult problem to solve that ultimately, as much as possible, it would be nice for the viewer to have control of that versus the entity that's hosting it. So for the viewer to decide. [/INST] I'll let you just figure that stuff out. </s><s>[INST] I'm just going to make fun. Cool videos? [/INST] Yeah. Yeah. </s><s>[INST] Let's go to Antarctica again. How was that? How was going to... You just came back from Antarctica. I watched the video. That was fun. That was a really fun video. Thank you. I mean, there's a lot of things I can comment about that, but what was the hardest part [/INST] of making that video? The hardest part was just getting out there. It's just so remote. And you land the plane on just this ice runway and it's so sketchy. And then once the plane takes off, you're just there. You're the most remote place on the planet. And it's just very breathtaking. If you have the chance to ever go to Antarctica, I would recommend it. It was probably like the... In the video, we climbed a mountain that wasn't named, so we can name it. And standing on top of that mountain and just seeing nothing, because once you get outside the outskirts and you get deep in Antarctica, there's no penguins. Nothing lives there at all. And so there's just nothing in every direction. It's just snow and these crazy beautiful mountains and some of them stick into the clouds. If you go during summertime, the sun never goes down. So the sun's up 24 seven and it's just like spinning in circles at the top of the planet or whatever. It looks like the top. </s><s>[INST] There. Yeah. You guys come with this several times how beautiful. [/INST] Yeah. Yeah. And so it's just... </s><s>[INST] Yeah. It's just very beautiful. What about shooting itself? [/INST] Like the technical aspects of shooting it? Oh, I mean... Well, somehow we lucked out. One of the days was like the warmest day in like forever that's been in Antarctica. It was like... It was positive degrees. But at certain parts, it was also like negative 20, negative 30. And that's where the cameras, you constantly have to be switching out the batteries and heating them up and like putting them basically in like your pants or they'll just get way too cold. </s><s>[INST] And we were prepared for much worse, but it ended up being much better than we thought. So for that video, but in general, maybe some other challenging videos, how do you go from the idea stage to the actual execution to the final video? Can you take me through like a full process of like we're talking to bought some crazy wild ideas today. [/INST] How do you go from that to a final video we could publish? Well, I mean, obviously, first things first, you got to figure out the idea and then it just depends. I mean, pick any video you can think of on my channel. </s><s>[INST] I can take you through it. Well, what about the... in a circle? You have to stay in a circle for 100 days. [/INST] 100 days. For 100 days. Yeah. So for that one, step one. </s><s>[INST] One of the most popular. [/INST] Yeah. Yeah. That video did really well. Yeah. So we... Problem is we have to... This is where you get really into the nuances of the company because we have a lot of videos going on. You can't just, in a vacuum, be like, all right, we're not doing anything for 100 days. We're only filming this. So step one is we had to build an independent crew that could actually do that for 100 days. That way everyone else could keep working on the normal videos and not just screw everything up. Yeah. So step one, you build that team. Okay, we got the team. Now what do we need? Well, to do this, we need probably like 10 cameras, at least rolling at all times. So we're probably going to need to get a trailer and hook up a bunch of storage and stuff to just carry out the sheer volume of footage we're going to have. And so get a trailer, set up the cameras, go out on the field, paint a circle, now we need a house, go buy a house bring it out there. And then it's like, oh wait, I think it'd be funny if I brought the house than on the intro... You know, find a crane that can lift up a house so I can drive it in and drop it in </s><s>[INST] the intro. Yeah. And that's like, I need an iterative process where you're like, okay, this will be funnier. So this is just not all up front that you've written inside gear. [/INST] Yeah. Ideally it would be. </s><s>[INST] But as you kind of see things, you get inspired and then you think of more and more. [/INST] This would be better with a crane. Yeah. </s><s>[INST] I dropped out of the house. That was crazy that you decided to do that. [/INST] So fearless in the kind of crazy stuff you're willing to do. Exactly, I'm a broken record, but whatever makes the best video possible. </s><s>[INST] That's all you focus on. Okay, so what about the delegation of who gets to, what are the cameramen, the people operating the cameras, who's responsible for different things? [/INST] Is it like a distributed process? That's where whoever the lead cam would be on that video would just decide it. We got one because we shot over 100 days. A lot of it was just Sean, the guy who was in the circle just vlogging. We just gave him a camera and he figured it out. And then we'd have like for him just set hours each day that a cameraman would come. So if he had any content, he needed extra hands. Instead of just having someone on standby 24 seven, it made more sense to do set hours. Nice. And yeah, it was hard, </s><s>[INST] but explaining it in hindsight sounds so simple. Yeah, nice. And I guess like the more, because that one is relatively simple, I guess, because it's a low number of people. [/INST] Yeah, the hard part about that is just the time. Like, you know, I checked in on them so many different days and it's like an hour here, two hours there, three hours there, over 100 days adds up to be a ton of time. And even then, like, you know, if you have a 10 person crew, you know, paying them daily rates for 100 days, </s><s>[INST] it just all of that adds up. What about like the 100 versus 100, 100 adults versus kids? What was bringing that to life? [/INST] That seems exceptionally challenging. Yeah. Basically the thought process was we did 100 kids versus, or sorry, 100 boys versus 100 girls. People loved it. Honestly, I didn't think they'd like it as much as they did. Video did really, really well. So the second I saw that video was crushing, I was like, all right, we're doing it again. But last time we did it, we did it in our studio. So we built a giant room, put 100 girls in it. Sounds bad when I explain it like this. And then a giant room put 100 boys. And then we're like, after 100 hours, whichever room has the most people, we'll give them half a million dollars. So did well. So we're like, all right, we're gonna do it again. So we threw out all these different ideas. It was like 100 football players versus 100 cheerleaders. 100 this, 100 that, 100 prisoners versus 100 cops. It's just the craziest ideas. And we settled on 100 kids versus 100 adults. And then the next step was how do we make it better. The kids versus adults, sorry, boys versus girls, the first one we did was inside. The problem was every time it was night, when we did these long time lapses. You couldn't see the sun go up and down. So we were like, okay, this time I wanna do it outside. That's why the cubes are outside. And instead of doing circles, we want to make them cubes. </s><s>[INST] And then, you know, it's figuring out, do we want the, yeah. Those videos came up at least today as ones that are like really complicated [/INST] in terms of the audio, in terms of how it's to film it. Yeah, that's the problem. We had a lot of audio issues because in the first one, we didn't have a roof on it. The second one, there was a roof. So there was a lot of reverb, which then in editing made it brutal. Like half the shots weren't usable and it really screwed us over. So we had to do a lot of Frankenstein-ing </s><s>[INST] in the editing to make up for basically my ignorance. So you mentioned that you were surprised how well that one did. A lot of creators talk about getting depressed when the videos don't do as well as they kind of expected. There's a kind of feeling. You can get really worn out by that. Do yourself feel that? And also do you have advice for others that feel this? [/INST] Yeah, it's weird because I am a numbers guy, but also it used to. It used to very much, especially when I was betting everything I had on a video. When it did bad, that was devastating, man. I'd cry and I'd be depressed for days and it really would have a severe impact on my mood, but I don't know, now it doesn't really matter. If a video does better, just look at it and I'm like, oh, why did this video do bad? Probably, oh, there's a little retention dip there. I don't think people like the thumbnail. Maybe we should switch it. And I just look at it objectively, unemotional, and then just move on. And I feel like that's a much healthier way of going about it. If a creator is listening, that is the ideal way to respond to a video that's doing bad. Just remove emotion from the equation and just look at it and figure out </s><s>[INST] how you can improve the next one. Is there tricks to being able to detach yourself from that? Because in your case, that's true for creators, but in your case, there's a lot of money on the line. Yeah, well, there's videos cost a lot. Months of my life? [/INST] Yeah. Months of my life and so much time, but no, I mean, you just, I mean, I don't know. The only real answer is it's just a conscious effort. You just have to unemotionally look at the video, determine the problems, and then move on. Like, there is no secret. You know what I mean? It's just, it's that. And if you really can't bring yourself to do it, then you're just screwed. </s><s>[INST] Honestly, maybe you're not meant for this game. Okay, so that's part of the development as a creator, is like being able to be. [/INST] For longevity, yes, yeah. For longevity, yes, yeah. You have to unemotionally be able to look at videos that flop and figure it out. Because if not, just getting, not every video can be a one out of 10, and so when a video does bad, you know, that just stress and depression, </s><s>[INST] it's just gonna eventually get to you in the long run. So you said you've failed in a bunch of videos, sort of taking them to completion, [/INST] so what are some of the biggest fails? Yeah, weirdly enough, as we've matured and we've done this before, we don't have that problem as much, especially how we're getting into the multi-million dollar budgets per video. It's like, failure's not really an option anymore, so I'm a little more particular about what I do, but back in the day, yeah, like we would do a video where we spent 24 hours on a deserted island, and we filmed it, did it all, and I just, I didn't like it after the edit, so I just grabbed the voice and we went back to the deserted island and spent another 24 hours there and refilmed it, or. </s><s>[INST] Could that have been caught and prevented at the idea stage, like where? [/INST] No, it's a good idea, it was just poor execution. To be honest, when we were out there, it was hot. We were just like, we all, at one point, just kind of wanted to die, it was just miserable. So how do you avoid that these days? Well, I just went with it as a little cooler, to be honest, and then we had, literally, the amount of fun we had in the video was like, 10 times higher. </s><s>[INST] Oh, interesting. So you, like, there's some practical details that you just learned. [/INST] Yeah, I don't, videos, yeah, I don't, videos where it's very hot or it's on water because I get super seasick, it was like a, kind of like 10 things that if they have these variables, I'm down to do it. But my fun meter is not as high as normal. Like, we tried to, anytime we do anything on a boat, like when we spent 24 hours in a burement or a triangle, or when I tried to spend like, which didn't get uploaded, but tried to spend like 100 hours at sea or whatever, just like on a raft, it just like, it makes me want to throw up and I get so seasick, I can't even see straight. But there are just some videos that require me </s><s>[INST] to be on a boat, so I just suck it up. So when you spend months in creating a video, I know this is probably stressful to some creators, like how much stress, how do you feel when you have to click publish on a video? No, not much. So you're able to detach yourself? [/INST] Yeah, yeah, again, and old me, tons. I'd be like scratching and nervous and like my hands would be sweating, like to the point where I'm almost about to puke, I'm like, I really hope people like this. But, you know, I don't know, I think that's just part of maturing it. There's different, as a content creator, there's different phases. And you just like once you get over the fear that you're just going to wake up one day and be irrelevant, you know, and you just, you know, accept that like you believe in yourself and you believe in your content and that you can continue to be relevant, then you don't, I don't know, you kind of, it's a little bit easier to detach yourself, I guess. And it's a much healthier place to be. You can't do this for 10 years if every little thing just causes these huge emotional reactions. It's like, that's why a lot of creators go a little, you know, mentally insane. You have to get out of that game because it really messes with you. </s><s>[INST] We've talked about this a little bit, but how do you define and how do you suggest others define success on YouTube? So subjective. [/INST] Some people, some people success is retiring their mom. You know, for you, success is inspiring people and educating them and, you know, whatever the peak in their curiosity. Um, for other people, it's just quitting their job. </s><s>[INST] So you have to self reflect on what your definition of success is. Cause I think a lot of creators kind of don't really think, don't introspect. Like they kind of want to keep getting more and more subscribers kind of thing. [/INST] Um, yeah, but subscribers is just a vanity metric. You know, it doesn't, subscribers don't correlate to views. </s><s>[INST] Sure. [/INST] Or views what, yeah, I know, but that's more, that was a direct view. That was more direct to people listening because, uh, a lot of people do really care about subscribers or even followers like on Tik TOK. But if you look like your view on YouTube, very, very few percent, if even a percent of your views come from the sub feed, right, they're almost all home feeder suggested. What's the last time you clicked on your sub feed to watch a video? </s><s>[INST] Oh, almost never. [/INST] Yeah, yeah. Maybe five years ago, it used to be a thing. It's not anymore. No one does. Um, and it's getting harder and harder to find the sub feed. </s><s>[INST] I subscribe to way too many channels, I think. [/INST] Yeah, that's what everyone does and you subscribe to 10 channels. They're great, but two years later, your taste evolves and it's like, it's a mess. And so, um, there's subscribers don't really matter. Followers on Tik TOK don't really matter. Um, so anyways, it really, they really are the definition of a vanity metric. </s><s>[INST] And, but what about views? [/INST] They do, obviously, because if people are showing up time and time again, that's what matters. </s><s>[INST] Okay. So that, that's a good thing to define a success. I just feel like, um, that too can be a problem because, uh, I would say, you know, if I wanted to be successful, like as a young creator, I might start copying Mr. Beast or something like that. Right? Like there's, you start trying to take shortcuts as opposed to find your, your own unique voice, right? So like chasing views is a problem too, it feels like, or no. Um, as long as you detach yourself from that. [/INST] I mean, um, I mean, if you're, sounds bad, but if you're lazy and you just want to copy someone else and not experiment and find your own way, but yeah, I mean, you can't make that excuse for them and someone just isn't coming up with the original stuff and putting in the effort. You can't just say, Oh, it's cause they're chasing views. And we need some match, different metric for them to chase. No, they just need to find their own way. </s><s>[INST] The rich, it just feels like unique type of content will often lead to sacrifice in the number of views in the short term. [/INST] By the longterm you win. Okay. Or if you do win, you win more, I guess would be a better way of putting it. </s><s>[INST] Okay. Or do you think you will IPO miss Mr. Beastberger or Feastables in the next five, 10 years? [/INST] Beastberger or Feastables? No, I kind of think they're something, actually, you know what? I just realized this is our first time talking about those. We're like an hour and a half and that's so funny. </s><s>[INST] So actually, you know what? [/INST] I just realized that we started talking about what, uh, my retention brain kicked </s><s>[INST] in, um, I wonder if you have retention brain for like life itself. [/INST] Oh, I do. </s><s>[INST] Every time I'm talking to someone, I can, I'm like, okay, what about like loved ones? Like spending time with loved ones, thinking like we could be doing something much better right now. [/INST] Yes. No, that is a serious problem, uh, with, so we'll pause the Beastberger question. Yes. But that's why, uh, my current girlfriend, uh, which I was telling you before when we were talking about this is she has a genuine love for learning and that's something I have, like, I, I always feel like I need to be learning something to justify the time I'm spending. And so that's why it's such a nice trait because I feel like the time is being used optimally because whether we're watching a documentary or we're going in, in, you know, taking IQ tests or reading about whatever, just why modern art is the thing, I don't know, whatever weird thing we decide to do, I'm always learning and improving, so it justifies the time. </s><s>[INST] So to maximize retention in your relationship, you want to spend time at that time learning as much as possible. Yeah. [/INST] Yeah. Yeah. Which conveniently I don't have to force, right? Or, or I want to be recharging so I, when I do work, I can, you know, hit the ground harder and luckily we're into a lot of the same things, which, you know, happen to be learning and sometimes it's not learning, like maybe watching an anime or something like that. But I'm a big believer and you're either, if you, well, if you, if your goal is to be like a super successful entrepreneur, you need to either be working or you need to be doing something that decompresses and recharges you. So you can work again. If your goal is to be like a really kickass entrepreneur. Obviously we're boiling this down to like a very basic thing. And so the things you're doing in your need out time, when you're not working, if it doesn't recharge you, you're screwed. you're just a ticking time bomb waiting to implode. And so you gotta like heavily recharge. And like, so like watching for me, anime or whatever it is, playing a board game, like that is actually kind of crucial to my success, which takes a lot of maturing to come to that conclusion because I used to be the kind of guy that wanted to work every hour of the day. And I would try to train myself to not need that stuff. And I, you know, and I almost resented like that. I have to do these kinds of things and it would piss me off because it's not optimal. And, you know, I just really want to make content and entertain people. But as someone who's gone down that road and you know, you just work every day for two, three months straight and you know, every hour of the day and then you just bomb waiting to explode and lose your mind. And the only real sustainable thing is to just like </s><s>[INST] give yourself time to recharge in between working. [/INST] So there's a kind of balance you have to find. You have to even, and I hate it more than anyone else </s><s>[INST] because I, you know. [/INST] You hate not working. Yeah, because it's just not optimal for time. Like it's, as a human, I do need to occasionally watch a mindless show and play a board game. And it took me a very long time to like come to peace with that and not, I would have like borderline panic attacks when I do it because I just, what am I doing right now? Why am I doing this? I should be, you know, like what if one day I have to lay off an employee because we're not doing so well? Like, how could I justify watching this show or whatever I'm doing right now? You know, it's like, there's a lot of things like that </s><s>[INST] that go on in your head, but it's necessary. Before we return to Mr. Beasburger. Well, what is like, since we're on the topic, what is the perfect day in the life, [/INST] perfectly productive day in the life of Mr. Beas look like? Oh boy, well I mean. Well or like a standard. I mean the perfectly productive day is we film a main channel video. Like, because those get 100 million a pop. </s><s>[INST] I mean, it doesn't really get any better than that. Or like a standard. What about like the average day when you're not on the set? Yeah. And you're like, because you're running a lot of things, right? [/INST] Yeah, yeah. So right now we have our snack brand, Feastables. We have a restaurant chain, Peace Burger. And then we basically, which we haven't even really launched any products yet, but we have the data company that I was showing you where we're gonna roll out some tools for creators. And then we have the Reacts channel, the gaming channel, the main channel, and then we have my charity, which also has a channel. And so, I've structured my life right now is whenever I have free time, we just kind of go, hey guys, Jimmy's got an hour from 2PM to 3PM. And everyone's just like, I need this. I need this. And the channel's like, I need this thing filmed. Or whatever, the guy who runs my TikTok's like, I need this TikTok filmed. Or, Beast Burger's like, I need this menu item approved. We need to talk about this marketing thing. And then we kinda just look at what everyone needs. And we're like, that one looks like the most important, we'll do that. And then it's just kind of like, It's like, you know, if I just did that for every company in a day, then that's optimal. If I just kind of, like an optimal day for me would be going down to eight companies and just, whatever they're like two to three biggest pain points or things they need from me and just doing those, so </s><s>[INST] Yeah, it's just based on priority and then trying to keep it as short as possible [/INST] Yeah, so just the things that you're needed on. Yeah, it doesn't get more optimal than that. If I clear the bottom next, or some bottlenecks for all my companies then it's, yeah, </s><s>[INST] that's a perfect day. Yeah, I mean even just me, cuz, you're like you're showing me around and you're being a great and gracious host, but on top of that [/INST] you're just doing all these meetings, you basically. I felt bad at some point, I was like, oh, I just tricked him into going to meetings with me. He's like my little meeting buddy. </s><s>[INST] Yeah, yeah. I mean it was fun, it was fun to see, it was fun to see how effectively you've delegated, you basically trust the team to do a really good job on the various things and there's just a strong team that's able to carry the flag on all the different tasks. From the brainstorming in the main channel to the reacts and so on. Yeah, it's really interesting. I mean, it's really interesting what it takes to build a team like that, because you very quickly build a very large team [/INST] that's able to scale. Yeah, which is very scary, because it's my first, you know, I'm 24. You know, and I think I was telling you this earlier, it's funny because six years ago I had to raise my hand to go use the bathroom and now I'm in charge of hundreds of people and entertain hundreds of millions of people. And so it is crazy just how quick it comes up and I wish I was a little bit older so I could have ran a couple of companies and failed a few companies in the past and like learn from those and apply those here. Because I know for a fact, when I'm 34, I'm 24 now, when I'm 34, I'll know so much more about running a business and scaling and hiring and how to lead people and better effectively communicate in all these different skillsets that will make me a better leader, that that's the only thing that sucks is I just don't have those because I just haven't been through the lessons and I just have such a lucrative thing on my plate right now and it just sucks that I have to learn the lessons with the lucrative thing, you know what I mean? </s><s>[INST] Yeah, because you already have so much influence, so much impact, but you have effectively scaled. What lessons do you draw from that, how to effectively scale as a 24 year old? Like you believe- [/INST] Yeah, that's something I feel like I actually could give a lot of value to, to young people who are doing it. Like older people who've built five companies or whatever they do, I probably couldn't, you know, they're gonna be like, oh, this is so obvious, but for younger first time business owners, you gotta just experiment to be honest and for us, like it's just a new space. No one had really ever scaled up a 100 person team to build, make content on YouTube. So there wasn't no, I spent all this time, like I hired one person from Disney at one point to come in and help. And obviously that was a dumb idea looking back on it, but you know, I thought, oh, they make great stuff people wanna watch and they come over here and help me build a team. And you know, and they build it more the traditional way and not like how it should be online. And so then it's like, okay. Now I'm not trying to trash people. Like they all tried their best. But then I hired this one person who does this different type of media and runs a 100 person team. And then you come in here and they try to build it that way and they don't really listen to your value or see the difference. And I tried basically for building this company with like four or five different people who worked in different veins of media and, you know, every single time, it's just like they just don't get it and they don't understand my world and the eventual solution was just like to roll up my sleeves and do it myself, you know, with like James where I hit man and just like, no one's ever done this and like, no one's gonna just give us a golden carrot and tell us how to build this company, we got to figure the fuck out ourselves. </s><s>[INST] And you have to kind of build up people from scratch then. [/INST] Yeah, exactly. Yeah, exactly. That's what I was talking about earlier and all the lessons I learned along the way. And so for me, that was a big part of like, stop trying to have someone build this company for me and just do it myself because it's scary, like I spent my whole life studying YouTube videos of virality, not business building. But fuck it, I was like, I guess we just got to do it ourselves and that's where things really start to click and we got the exponential growth, we start getting the right people and training them the right way and, you know, just throwing conventional stuff out the door and focusing on what's actually practical for YouTube, which is just completely different </s><s>[INST] than traditional media. So you train people and then those people train people and so on. [/INST] Yeah, I mean, it's just even like, you know, how you do the lighting on sets or like how you do the audio or, you know, not writing scripts. So you know, we're just not as efficient with our filming, like sometimes I have to have 30 cameras running. Why? Because it's not scripted. I don't know what Chris is gonna do when we start filming. He might run over there. But guess what? We got to have it planned because there's only one shot. </s><s>[INST] I can't, you know, tell him not to do that. Yeah, that's the shooting. [/INST] But then there's also the editing. Yeah, and then the editing as well and not having guardrails and kind of you know, at the end of the day it's whatever I want. The video, their job is to make a video that they think I like because it's my channel, but you can achieve that kind of however. And so it's just, everything's just different. You know, it's much more, I guess, like a startup as opposed to. </s><s>[INST] Are you often surprised like would the result like... You think a certain, like we watched the video today, that was really nice, that was different than you would have potentially edited it. Yeah. Are you sometimes surprised by like a decision editor makes? It's like, okay, that's not the way I would have done it, [/INST] but it's actually, this is a cool idea. Yeah, yeah, of course, yeah. The thing, my biggest fear is I don't ever want to get trapped in like a bubble of, you know, because we are getting 100 million views of video on the main channel. Like, but I don't want to get in this feedback loop of just, my ideas are great or, not feedback loop, but stop learning and improving. Because it is easy sometimes to be like, what we're doing is working, we need to just keep doing it. I want to keep learning and trying new things, and I guess one way I would put it is like, you don't, when, when you're on a come up or you're growing, you don't want to test new things once you start the plateau or have a downtrend because if you're like, you know, you you're skyrocketing, right? You're up, up, up, and then you level off and you start to go down. you're like, oh this isn't working. Let's start experimenting. Well, if you have a bad experiment, now you're in like a tailspin, you're nose diving and you have one more bad experiment, you're like, screwed, kind of oversimplifying. You want to test things while you're still growing to keep the growing from happening because once you like have, you know, again, very oversimplifying, that like you know kind of level off, you do a couple test, they go wrong. And you're like, screwed, you know? I mean you're already out the door and now you're just just confirming that you were out the door and online entertainment. So that's kind of how I see it. So I think it's very imperative that you're constantly always experimenting and trying things, </s><s>[INST] even if you're getting crazy, unheard of growth. And so that outside of the thing that brought you to the dance, you just dived right into Mr. Beastburger and Feastables. This is a whole nother industry. [/INST] Like what was that like? Well, so Beastburger, we kind of, it was supposed to be like just a pop-up. Like we just partnered with someone who had 300 restaurants and we were just like, you know, let's just sell Beastburger's for a day or two. Let's see what happens. We didn't really think it would be as big as it was, but those first, like that first day, we do six figures in sales and they all sell out and they're running to local Walmart so they can't keep up with the demand. And it's like, okay, well, maybe let's just leave it open a week, whatever. And we're just doing crazy revenue. And it's like, okay, well, let's add some more restaurants and let's just leave them open for a month. And we're just still doing six figures a day. And it kind of just went from this thing that was, I don't know, it wasn't really, I didn't really plan on running a restaurant chain, but here I am. </s><s>[INST] But didn't that in some sense also open your mind [/INST] to something like Feastables? Feastables is something I've always wanted to do. Because I think just in general, American snacks are just full of so much horrible ingredients to be honest. And they're not, I don't know. I feel like there also just hasn't been any innovation in American snacks in quite a while. And so that's just something I've always been pretty passionate about. We built that from scratch. So we hired the CEO and built a team around them. And we spent probably over two and a half years before we even launched. It's like building the right team, figuring things out and making sure it was actually ran the way I wanted. Which Feastables has just been crushing. It's very interesting. This is something I've never talked about publicly, but having products in retail, it's like before Feastables, everything I had done was online. So if you wanted to, you know, anything from the quote, quote, peace brand, you'd have to buy it online and ship it to you. But Feastables, now that, you know, because our first product, chocolate bars, we started putting that in retail locations. So like, for example, Walmart, it's crazy. Like it's just, it doesn't make sense. How, if you're, which I guess it does for, because we get 100 million views a video. So a lot of people know us. If I go stand in Walmart, those people recognize me and ask for photos, like if I stood there long enough, I could take 150 photos today in Walmart or 200, whatever it is. So obviously it makes sense those people go find Feastables, but then you just multiply that by every Walmart in America. And it just gets so crazy. And I didn't think we'd be doing the kind of revenue we are. And we're about to launch in some other, I don't know if I'm allowed to say it, so whatever, but other big retail, you know, locations and convenience stores. And like by the end of next year, we could be in like 40, 50,000 locations. And the numbers just don't make sense. </s><s>[INST] So what are some interesting challenges [/INST] about scaling there that surprised you? The biggest problem, which I didn't think would be, was just keeping the shelves in Walmart stock, to be honest. So that supply, the supply chain. It was brutal. Well, even then sometimes like, you know, you get them the stuff and they're like, it takes them like a day or two to put it out in that specific location. And I had to stop promoting it because every time I'd mention it, like 40% of people would just be like, it's not there. It's not in Walmart or I can't buy it. And so there was like a three-ish month period where I just didn't promote fee stools because I was scared that someone would go buy it and it's just not there. And so like, it took us a very long time to catch up to the demand. And also, you know, it's not like we have unlimited money. So I didn't, but now we're relatively caught up in keeping up, but it's gonna be interesting because now this year in 2023, we're gonna basically, you know, 10X, the amount of locations we're in. So we're, and we're gonna try to launch new products. So we're in for an interesting ride, but yeah, I just hate, I hate when I tell people, you know, like, hey, go try this product. And then they go in their local Walmart and eventually other places and it's not there. It's just so brutal, you know? They made that whole journey out there and they couldn't get it. And so that was really it. Besides that, it's been doing way better </s><s>[INST] than I ever thought, to be honest. It was- You've talked to a couple of places about maybe doing mobile games or computer games in the future. Yeah. [/INST] Is that something you're still considering? Yeah. Yes, because, you know, do you normally talk with people as much as we talk before him? </s><s>[INST] Is that? No, no, that was the problem. [/INST] We spent all day today talking about some day to day, talking about some- I just looked in my head, everything you asked me is stuff we already talked about. Not really. Well, no, no, not everything. I take it back, but sorry. The last two questions, yes. </s><s>[INST] And so, it's just funny. Not really. Well, no, no, not everything, because- What? No, I tried. It's okay. There's a different style of asking those questions because I, on purpose, didn't dig further with you. I could tell. Yeah. I could tell you- Okay, this is, by the way, okay. All right. Well, this is the first time I've ever talked to somebody as much as I did with you beforehand. [/INST] I could tell. Yeah. I could tell you- Yeah. On the same day. I know. Not even same day. We spent all day together. Even though I only slept one hour. Yeah. Literally, it's funny. </s><s>[INST] This is the same day. I know. Not even the same day. [/INST] What was the question, the mobile games? Anyways, mobile games. So the interesting thing is with Beast Burger and Feastables that there's physical goods as opposed to making mobile games or a PC game, which everyone may end up doing, which is software. And I actually have a giant international audience. Most of my audience is obviously outside of America. And so the problem we're running into is it just takes time to build up the supply chain and get Feastables in Southeast Asia, get Feastables in India, get Feastables in Brazil and Mexico and all these other places where we have giant pockets of our audience. And same thing with Beast Burger. It's going to take probably years, unless we partner with someone who already has a distribution, which we're figuring out. But the beauty of software is I can make a hypothetical game or whatever we end up doing and all my fans can use it tomorrow, the day I mention it. And so if I promote something in a video to 100 million people and it's basically like a game, they can all download it. But if I promote a Feastables bar, right now it's only in America because we're struggling just to keep up with American demand. We haven't even gotten the chance to go outside of America. So I alienate a majority of my audience. And it feels so shitty to just mention something that most of them can't buy. But on the flip side, you can't just spawn this crazy infrastructure and just have tens of millions of bars and all your products in every single store across the world before you promote it. So you can't put the egg before the chicken. So that's what I'm excited about. I want to get into less physical stuff and more stuff that everyone in my audience can actually use. </s><s>[INST] It's the thought process. It's the thought process. Especially if there's a social element to the gaming, too. Because it's not unlike Feastables. [/INST] That's a product you consume. You missed it. When you're setting up for this, we were doing some basically just laying out everything that we're planning for. So we're at the phases where we want to start hiring the team to build it. And we're kind of just laying out the game. And I was actually really curious to get your thoughts. But I can't say it. Because whatever I say, someone's just going to take it and run with it. </s><s>[INST] I had a pretty good idea. I had a pretty good idea. About the kind of games you're thinking about. Yeah, I mean, I can imagine we also talked a little bit about it. It's super awesome. It's so much good ones. [/INST] It's super awesome. So much good ones. I did. So much good talks. Not the juicy talks happen to you. </s><s>[INST] She's like, I gotta go set up. Well, you know, I really heard a lot of awesome stuff. I mean, but that is a different kind of team you would need it hire. Is that a little nerve-wracking, [/INST] like going into a new field and trying to? A little bit, but then I remind myself, like Steve Jobs didn't know how to code, right? And you know, he just knew what a good product was. And I feel like as someone who wasted so much of his life playing video games, I have a good sense of it. And that might be ignorance. </s><s>[INST] Ignorance? Well, that's really important, right? It's not about coding, it's about what makes for a good game. [/INST] Exactly, and again, that might genuinely be ignorance. And maybe I end up getting bit in the butt because of what I'm saying now. But I think just like with YouTube, I just want to obsess over making a great product and things that I think my audience will love. And I think as long as I keep that as my North Star, </s><s>[INST] it'll do well. [/INST] What is the path to being worth 100 billion look like? There's a path to being worth 100 billion look like? </s><s>[INST] I don't know. I don't know. Okay, let me just pause here, 24. And there's so much awesome scaling, so many great ideas. Do you think about different trajectories? Yeah. [/INST] What those possible trajectories might look like? Yeah, I mean, if the goal was to just be worth $100 billion, yes, I mean, my goal, I'm a broken record, is to make the best video possible because I know whatever else I want will come obviously. So, the video is the foundation. Yeah, exactly. So, the path to $100 billion is to keep getting 100 million views of video, you know what I mean? Or more. Yeah, or more. Exactly, if we can keep growing. But, you know, if we can keep Feasibles growing, right, and we eventually spend international, one day we're in 100,000 retail locations and we're selling the same amount of units per SKUs like we're currently doing, I mean, that would crush and then obviously, ideally, one day we open up hundreds of Beast Burgers, we get it where we turn out, you know, like super sell a couple hit games. I don't want to make dozens or hundreds of games, I just want to make games that are just great and, you know, we rarely drop them when we do their bangers and just, you know, whatever other stuff we end up doing, all that combined, I mean, it's just interesting because, like, what's a show that's pooled 100 million views per episode, basically? Like, we're doing. Like, you know what I mean? Like, the Super Bowl gets praised because they get 100 million viewers, but I can't think of a show, maybe in reruns or something. </s><s>[INST] You heard that. The video is the foundation. Yeah. But it's also a show that has a singular kind of figure that you can now use as a... [/INST] Like, I don't have a network tell me what to do, I don't have anyone, like, I can do whatever I want. It's a very interesting position because I put out content and 100 million people show up, and then I also have a gaming show and I put out content, 15 million people show up, and every action on I put out content and 10 million people show up and I have a TikTok and I put out content and on average 20 million people show up. As long as I can keep that going and then we build these businesses, it's, like, it's honestly pretty scary to see what will happen, you know, over the years because Feastables launched, you know, last year, 2022, so it's a relatively new thing. We just started scaling up the physical side and we haven't obviously even launched any mobile games yet So I think I'm at the antithesis of it I don't see a world where my YouTube channels are relevant in the next couple of years I just this is what I live for and so if I can keep that going and then really start to expand these businesses that leverage off of it then </s><s>[INST] Yeah, I mean, hopefully there's the day one where I could give away a billion dollars in a video. Honestly that yeah That would be one hell of a video Let me ask you the ridiculous question since you went from being broke to being rich, although you keep spending all your money Does money buy happiness how has money changed sort of your [/INST] Contemptment your happiness in life. Oh, I'm telling me your happiness in life money by happiness Um, no, not I mean to a point. Yes, once you can take care of your health You can take care of like any immediate dangers and you can take care of your family relatively No, it doesn't like, but those things do like when I first came into money One of the first things I did was retire my mom and like that brought me tons of happiness You know I mean and like, you know If my brother had a medical emergency and we couldn't afford it and I made money to afford it That'd bring tons of happiness. You know, so once you take care those basic necessities So we'll say makeover, hypothetically, a million dollars. No, it really doesn't. Adding an extra zero, going from 10 million to 100 million </s><s>[INST] or whatever it is, makes no difference. So you're, given that, [/INST] are just fearless in spending the money. Yeah, well, let me re-frame. I guess it could for some people, if you really, I don't know, you spent your whole life obsessing over cars, it probably would bring you a little bit of joy to buy a nice Lamborghini. I'm coming more from the frame of mind of an entrepreneur, someone who's really obsessed with business building. For me and a lot of my friends and people I hang around, what brings us happiness is winning and building companies and do, you know, changing the world. Like that is fun. It's a complex problem you can wake up every day and it gives you something to obsess over and devote your life to, </s><s>[INST] where it's just having money doesn't, you know? Well, one interesting question I have for you psychologically. So because you have become wealthy and because you give, like part of your work is giving away a lot of money, do you find it hard to find people you can trust? It's a good question. Do people see you basically as a source of money? [/INST] As opposed to another human being. A good question. As opposed to another human being? It's weird because you'd think yes, but I feel like I also know the right places to look. But yeah, if I just walked into Target and tried to make friends with 10 random people, of course. </s><s>[INST] You can kind of sense. Oh yeah, you can sense the right thing in their heart. [/INST] So quickly, oh yeah, you could sense the right thing in their heart. So quickly, wait, yeah. Yeah. It's so obvious. I don't even want to go into the descriptions, but honestly, a lot of my friends, like Chandler, I played Little League with him, and Tyler, the guy, I mean, I went to school with him, Chris, he was my first subscriber. Carl was here after we got big, but whatever, he's friends with the boys, and it is a lot of my closer friends, even like my YouTube friends, I knew before I was big. So maybe there is some merit to that, maybe it is, I don't know, I've never really put too much thought into him, maybe there's a reason I hang around a lot of these people I knew before I got big because it's much easier. </s><s>[INST] And they help you keep your radar sharp of who can and can't be trusted, because you know you can trust them. It's difficult when you become richer and richer [/INST] and more powerful. Well, one thing you'll also find when you get richer, not even richer, but more famous, one thing I thought is as I climbed this ladder of YouTube and got bigger, I thought there would be tons of people like me, people that take the kamikaze approach and building a business, you just throw all your money in it, you throw all your time, you throw all your energy, you throw everything, you're just like fuck it, if it's this or I'm dead. And I thought there'd be hundreds of me. And there is like maybe one or two, and I talk to those motherfuckers every single day, sick and tired of talking to them, but I love them. But it's just so interesting, because every level I got up I'd get a million subscribers, I'd be like alright, where's all these guys with a million subscribers that are fucking psychopaths? </s><s>[INST] You know, you know, they're like- Yeah, people become like conservative as they get, [/INST] they get more and more- Especially as they get bigger, yeah. And you know, 20 million subscribers, 30, it's like every step of the way, it's like, I just got more and more lonely to be honest. So if you, you know, it sounds cliche and you hear that kind of shit in movies and you're like, oh, that's not how it works, but it is like there's just not many people that just want to give up everything, go all in and obsess over making the greatest goddamn videos every single day of their life, like, </s><s>[INST] they're really hard to find. And be able to sacrifice everything for that video. Yeah. [/INST] Like basically put all the money right back in. Yeah, or the people doing it, they're on just a small scale and if I talk to them, it's just 99.9% of the time </s><s>[INST] I'm teaching them things and it's like- So it's lonely because there's not too many people, [/INST] especially in the creative space, they're as crazy as you. Yeah, it is, 100%. It's so, it's not what I was expecting. </s><s>[INST] I was expecting there'd be a lot of people like me, but- Well, I guess the guy who talked to you on Musk is a bit like you in that sense. Yeah, just in a different domain, yeah. Exactly. Just willingness to put it all back in, right? [/INST] Yeah, just in a different domain, yeah. Exactly. And that's why I've found right now, a lot of the people I relate to don't even make YouTube videos. Like, I'm veering more and more away from fellow content creators and more to just, I'm just looking for those other people who just share a little bit of it so I don't feel so fucking crazy all the time. Like, you know what I mean? It's like, people I feel normal around, they tend to just be doing the randomest things, </s><s>[INST] but, you know, loving it. Well, I think that's really inspiring. It's like the Bukowski line, find what you love and let it kill you is really put everything, put everything into the thing you love. And that's like the way to really create special stuff, but it's also the way to- Yeah, it's- [/INST] Live out your life, most of all- Yeah, it's- Live out your life, most of all. Yeah, it's, you have to be careful giving this advice, because they're like, they're like body builders. You'll be like, just go to the gym. You gotta be disciplined, I'm disciplined, go to gym, but I would argue for those people it's like, it's not even disciplined, they just enjoy weightlifting. Because there are people who are jacked but they don't make much money or run a business. If they were that disciplined they would be hitting every area of their life, they just really like business and there's people like me who just to an extreme level, love building companies. It's not even disciplined for me, it's just in my blood, it's what I wake up, I don't think about it, I don't push myself, I don't need to watch a fucking motivational video to go work. It's programmed in me at this point and I couldn't imagine a world where I don't wake up and do it every day But I think that a little bit of it is genetics and just how you're hardwired Not that it can't be trained or taught and not that you know And obviously the friend group you're in influences these things and over time I think can change it but Someone's just not gonna be able to flip a switch and then just start doing a kamikaze approach to building a business Just like a lot of people try to flip a switch and start bodybuilding and quit majority of the time </s><s>[INST] You know, it's just not innate to them. I think a lot of us have the capacity to do that in some domain [/INST] Yeah, I think if you went about strategically if you surrounded yourself with fellow like-minded people and you know slowly over time switched it But if you just try to like hardcore do it, you're just gonna lose your mind </s><s>[INST] Do you ever worry about your mental health? Did you take step to protect it to? [/INST] Yeah, do it like for the long run to make sure you have the mental strength to go on. Yeah your mental health Did you just yeah? Yes, weirdly enough. The best thing for mine mental health was giving in to my innate nature to work Any and the most depressed I get is when I try to restrict it and like I don't work weekends I don't work this day. What's best for me is just to work when I feel like working and then Just not work when I don't like and just have no constraints because there are just some nights where I don't want to sleep Then whatever reason I feel compelled to go all night whatever, just do it, do whatever you want. It's what I tell my working brain, and I just give into it, and that's where I feel the happiest, and then it's typically like, when I'm really in the grind mode, it'll be like seven or eight days, just nonstop going, going, and then it's like, I'll realize, oh, I need some recharge time, and then go fucking binge a season of anime. Yeah, but that's the thing, people will tell you, don't work weekends, or don't do this, or don't work past this, or blah, blah, I'll give you all these constraints, but for me, and it's unconventional, </s><s>[INST] I just give into it, but that's the thing. I think there's something really to be said for that. I try to surround myself with people that, like when I pull an all-nighter, they don't go, like, you should get more sleep. There's a reason I pulled that all-nighter. Like, if I'm really passionate about something, they say, they basically encourage it, because I have no problem getting sleep and getting rest. What I need in my life is people that encourage you to kinda keep going, keep going with the stuff [/INST] you're passionate about. Normal people, they don't want that life, and they probably shouldn't, it's not good for you. But yeah, if you hang around people, like, just whatever, different people, you're gonna feel crazy, and it's gonna wear on you, whereas if you're around similar people, it's just, it's so much easier. Like, if you, you know, I've started weightlifting more, and like, one thing that's helped is just having JAC people around because they naturally just eat healthier. They do, like, they naturally just have fricking grilled chicken and all this shit and high protein meals and it's just like easier for me to just piggyback and be like, oh, can you just order me whatever you're getting, and they're like, oh, I gotta go to the gym, and I'll be like, oh, shit, I'll just join you, you know? And it's like it's just, it's cheat coats, you know what I mean? Just surround yourself with people that you wanna be and it makes it like 70% easier, in my opinion. It's like, that is the cheat coat to life and I wish, obviously, you audience is definitely a lot older, But, you know, to the older people listening, like if you are in a place of mentorship for someone younger or have influence over younger people, you should really try to drill that in their heads. Like the people, they are around 100% dictates the outcome. I would not be on 120 million subscribers if I didn't find when I was around a million, I had a couple of friends that were just also psychopaths, you know, I outgrew them, but at the time it was great and I wouldn't be where I am today if it wasn't for them. And just all along the way, the friends that I hung out with had such a dramatic impact on where I am. Like I'd probably have 80 million less subscribers, you know, if it was, if I wasn't so strategic about hanging out with people that I had value to </s><s>[INST] and they also had value to me. They naturally just eat healthier, they do. So the advice for young people would be to [/INST] be very selective about the people you're so much so. So selective, it's crazy. Like Chris, you know, he's really funny and that's why he's great for the videos. And part of why he's so funny is he consumes copious amounts of cartoons and just funny content. And so I'll find, like when I spend more time with Chris, I'll start just quoting these weird cartoons and shows and I, like my speech will literally change just after like a week of spending more time with him. It has like, it's like that quick of an effect, you know. Now picture that over the course of years. I mean, yeah, it has such a huge influence. Like pluck one of their friends out and hypothetically put me in there and you know, there's no doubt if they're trying to become a content creator, their odds of success is 10X, right? Obviously you can't do that, </s><s>[INST] but you got to find your closest version of it. And just be selective, yeah. But this also applies not to see younger older people too. [/INST] Agree, but they, it's even more, I like, when I was a teenager, I just, you know, I couldn't relate to many people. I just thought it was like a freaking nature because no one was obsessed with building businesses or any of this kind of stuff. And so like back then, you know, that advice would have been helpful. Maybe not that particular, but just knowing that there are, you know, it's not that you're a freaking nature. </s><s>[INST] You just haven't found people that have the same interests. So the task is not to feel sorry for yourself or somehow change yourself. It's more to find people... Find people you fit in with. [/INST] Yeah, I mean, find people you fit in with. Yeah, I mean, assuming which, you know, you're not getting compliment, like I assume it's not something bad, right? like if you're hobby is shooting things you know or shooting things you shouldn't be shooting, </s><s>[INST] you know, they'll find people that encourage that, you know. but outside of that for sure. Actually as an answer to what is the best advice someone ever gave you, you said you're crazy until you're successful [/INST] then you're a genius. 100% all along the way. People gave me so much advice on why I shouldn't be doing it, why I'm crazy. Every step of the way people wanted to tell me why I shouldn't be doing this and should get a life, should stop being too obsessed, everything. Everything under the book. And then once I'm successful those same people are like, dang, you're a genius. </s><s>[INST] Wow, you really, you pulled that off. Those are probably the same people that will give you advice now. You're the most successful video creator of all time. Stick to that. Anytime you wanna do something new, right? They'll like pressure you not to do feastables or mobile gaming or whatever lays beyond. [/INST] It's funny how people don't. Well honestly, the type of people I just don't talk to anymore. </s><s>[INST] So I wouldn't even know what they have to say now. So most people on the team are like, yes and. They're like, whatever the idea you got, they're with it. [/INST] No, I mean, it's weird. We actually have a, my team pushes back on me pretty hardcore, which I want. I don't want Yes Men. And they're like, James, the CEO who helped me build all this, he's very adamant. We're not Yes Men and he trains people to really think for themselves. And even when I give them orders to really think, is this optimal, is there context or information Jimmy could be missing that I could provide that could help him make a more updated decision? Like I'm not God, you know what I mean? Like I'm human and I make errors. </s><s>[INST] And so don't take what I say as the Bible. So even like in the brainstorming and so on, they can push back. [/INST] Yeah, you can see it. Like Tyler, anytime I said something, he would give me feedback and push back, which is what I want. I don't want him just to be like, yes, you're a fucking genius. Good job, Jimmy. I don't need that. </s><s>[INST] I need negatives. Good job, Jimmy. You talked about being in a relationship. What role, Jimmy, does love play in the human condition? [/INST] I think, well, the big thing is love can be scary because this is the human you're gonna spend the most amount of time with in your life. And so for a project that over 50 years, they can be a liability or an asset. I love the metrics. No, but seriously, it's got to be someone that makes you better. For me, I can't truly love someone that doesn't make me better because- Yeah, in the long run, across the years. Because if not, then it's a negative to everything I've spent my life building. But luckily, I'm very happy with the partner I have and like we were talking about before. I do think she makes me better. There's a lot of actually positives I've noticed. Even things as simple as like, I struggle to turn off my brain at night because I'm just thinking about all the businesses and how we could do better or whatever weird thing I have on my mind. But just chatting with her and hanging out with her helps me basically just shut my brain off and mellow out. There's just a ton of little things like that that I've noticed are positives, especially when you really look for them, that are easy to gloss over if you're not. And so for me, yeah, I have someone who I think is very beautiful, very intelligent, makes me better, is constantly pushing me, okay with me working hard, makes me smarter, and just all these different things that I think for me, love just makes me a better person. You know what I mean? Which makes me love her even more. </s><s>[INST] Does that make sense? Love the metrics. You know, I love- No, but seriously, it's- In the long run, across the years. Absolutely, what advice would you give [/INST] on finding somebody like that? Just really don't give up until you find someone that, you know, there's so many people on the planet. I mean, there really is. </s><s>[INST] There's billions of- [/INST] The odds are in your favor. Of, yeah, like just don't settle and find someone </s><s>[INST] that, you know, makes you happy. Yeah, just like you said, tying yourself with people that, that make you a better person, in this same case, surround yourself with that one special person [/INST] that really makes you a better person. And maybe that's just an entrepreneurial brain looking at it. I mean, not everyone wants to hyperoptimize their life like me, but for me to like truly love someone, </s><s>[INST] they have to make me a better person. In every way, yeah. Well, what do you hope you're 24? We started talking about death. Let's finish talking about death. What do you hope your legacy is? When you look a hundred years from now, and the AI has completely taken over, and the aliens visit and discuss with the AI what this last of special humans that existed on earth [/INST] was like, what do you hope they say about you? It's a deep one. Probably just that, because it's hard, right? Like I said before, Elon is overdone with my age. I could live every second. I've lived up to this point in my life, and still not even be Elon's age. So I have so much time. I just hope whatever it is that it's a net positive on the world, and it impacts billions of people </s><s>[INST] in a positive way that makes lasting change. So you admire people like Steve Jobs and Elon Musk for having sort of reached for that goal as well. Yeah, of course. [/INST] To help millions. I mean, the iPhone's the most successful product ever invented. </s><s>[INST] It's hard not to admire what he created, you know what I mean? The same with sort of, as Johnny Ive talks about, like the passion, the effort they put into designing the iPhone, that like little bit of love is transferred to the whole world. Like they get to experience the joy of that [/INST] from the designer. It's what a beautiful thing to do. You know what I mean? I couldn't think of anything better, you know? To create something that, even after you're dead for decades, just has such a profound impact on basically half the human population. </s><s>[INST] Yeah. It's wild. Brings joy to people. Yeah. Well, I hope you do just that, man. You've already done it for millions and millions and millions and millions of people, and I hope you keep doing it. I can't, like, it's so exciting to see what happens this year and next year. I know. Like the sky's the limit. I can't, I mean, the videos, but all the other businesses you're in, and you as a human being, as you grow, I can tell, I know, as everyone knows, you have a kind heart and the fact that you're really damn good at actually using that kind of heart to help a lot of people. It's awesome to see, man. [/INST] I appreciate it. Yeah, I know. I know. Like the sky's the limit. Yeah. Man. I appreciate it. More importantly, before we go are we gonna play Dun in tonight, some board games? We're not going to play Doon. I have to, you don't have to play Doon, you don't wanna play board games... </s><s>[INST] You don't want to play board games with me? I want to, I'll play board games. You don't want to play board games? Board games? If only I wasn't an idiot and actually flew to the right airport. If you don't play board games with me, they're going to dislike the video. Thanks for listening to this conversation with MrBeast. To support this podcast, please check out our sponsors in the description. And now, let me leave you with some words from the poet and philosopher Rabindranath Tagore. Reach high for stars lie hidden in you. Thank you for listening, and hope to see you next time. [/INST] </s> |
<s>[INST] so you have and, and this is just uh a plea to the listener and the public. I've noticed this too, that there's a tendency in social media makes this worse when you don't have perfect information about the situation, you tend to fill the gaps with the worst possible or at least a bad uh story that fills those gaps and I think it's good to live life, uh maybe not fully naively, but filling in the gaps with the good, with the best, with the positive, with the, with the hopeful explanation of why you see this. So if you see somebody like you trying to make money on a book about Numpy, there's a million stories around that that are positive and those are good, good to think about uh to uh project positive intent other people because for many reasons, usually because people are good and they do have good intent and also when you project that positive intent people step up to that too. So like it's, it has the point, it has this kind of viral nature to it and of course with twitter early on figured on facebook is that they can make a lot of money and engagement from the negative, so like there's this, we're fighting this mechanism just challenging [/INST] easier, </s><s>[INST] it's just easier to [/INST] be, to be negative and then </s><s>[INST] for some reason, something in our minds really enjoy sharing that and getting, getting all excited about the negativity we [/INST] do, but protective mechanism perhaps that we're going to eat it if we don't </s><s>[INST] Exactly for us to be effective as a group of people in the software engineering project, you have to project positive intent. I think [/INST] I totally agree, totally agree. And I think that's very so that that happens in this in the space. But python has done a reasonable job in the past, but here is a situation where I think it it started to get this pressure where it didn't, I was, I really didn't, I didn't know enough about what happened. I've talked to several people about it and I know I think most of the steering committee members today, uh 11 person nominated me for that role, but it's the wrong role for me right now, right? Um, I have a lot of respect for the python developer space and the python developers. I also understand the gap between computer science, python developers and array programming developers or science developers. In fact, python succeeds in the array space, the more it has people in that boundary. And there's often very few, like I was playing a role in that boundary and, you know, working like everything to try to keep up with the, with what even what Geeta was saying, like I'm a c programmer, but not a computer scientist, like I was a engineer and physicist and mathematician and I don't I don't always understand what they were talking about and why they would have opinions the way they did. So you have to listen and try to understand then you also have to explain your point of view in a way they can understand. And that takes a lot of work. And that that communication is always the challenge and it's just what we're describing here about the negativity is just another form of that kind of come together and it does appear we're wired anyway to at least have a there's a part of us that little enemy friend. Enemy. And we see yeah, it's like why are we wiring on the enemy front? Yeah. So, so why are we pushing that? Why are we promoting that so deeply </s><s>[INST] assume friend until proven otherwise. Yeah. So because you have such a fascinating mind and all of this, let me just ask you these questions of one interesting side on the python history is the move from python two to python three. You mentioned move from python one to python two. But the move from python two to python three is a little bit interesting because it took a very long time. It broke in a quite a small way, backward compatibility. But even that small way seemed to have been very painful for people is their lessons. You draw tons of [/INST] lessons from </s><s>[INST] uh, from how long it took and how painful it seemed to be. Yeah, [/INST] tons of lessons. Well, I mentioned here earlier that Numpy was written in 2000 and five. It was in 2000 and five that I actually went to ghetto to talk about getting Numpy. The python three. Like my strategy was to, uh, we were moving to python three. Let's have that be. It seems funny in retrospect because like python three, that was in 2020 20. Right? When we finally ended support python to at least 2017. The reason it took a long time. A lot of time. I think it's because one of the things is, there wasn't much to like about python 33 point oh 3.1. It really wasn't until 3.3. Like I consider python 3.3 to be python three point Oh, it wasn't until python 3.3 that I felt there's enough stuff in it to make it worth anybody using it. Right. And then 34 started to be, oh yeah, I want that. And then 35 as the matrix will play operator. And now it's like, okay, we got to use that </s><s>[INST] plus the libraries that started leveraging some of the features of python. [/INST] Exactly. So it really the challenge was, it was, but it also illustrated a truism that, you know, when you have a nurse. So you have a part, we have a group of people are using something. It's really hard to move them away from it. You can't just change the world on them And Python three, you know, made some, I think it fixed something's gotta have always hated. I don't think you didn't like the fact print was a statement. You want to make it a function. But in some sense that's a bit of gratuitous change to the language and you can argue and there's people have, but there was one of the challenges was there wasn't enough features and too many just changes without features. And so the empathy for the end user as to why they would switch, wasn't, wasn't there? I think also illustrated just the funding realities. Like python wasn't funded. Like it was also a project with a bunch of volunteer labor. Right? It had more people, so more volunteer labor. But it was still, it was fun to the sense at least ghetto had a job. And I've learned some of the behind the scenes on that now. Since since talking to people who lived through it and maybe not on air, we can talk about something, but it's interesting to see. But you know, had a job, but he, but his full time job wasn't just working on python. Like he had other things to do. Just </s> |
<s>[INST] that. [/INST] No, I mean, I I don't why would I mind if part of it? I mean, maybe it's self selecting if I didn't have the view I had about that or the whatever armory it is that I have on that I wouldn't do what I did. Maybe, </s><s>[INST] I mean, have you been to some dark places psychologically because of the challenging ideas to explore? Like, significant self doubt. Just kind of [/INST] um I can't say I've been unaffected by about everything in my life by any means that would make me an automata of some kind. Um there's definitely times I've got things wrong and regretted that. There's times I've there have there was a period around the time I wrote my book, The Strange Death of europe, which ah it was very, very dark time. And it wasn't because I was having a dark time in my life, but because of the book I was writing, oh, </s><s>[INST] because of the places you had to go in order to write. [/INST] And well, I was contemplating the end of a civilization. Occasionally, now I have maybe slightly to pat at this stage, but sometimes readers come up to me in the street or whatever and say, you know, I love the strange death of europe and will say, you know, it's very depressing book to read? However, I would say, well you should have tried writing it, but it was because I mean I was it was it has chunks of it which I'm very proud of in particular about the death of religion, the death God, the the loss of meaning and the void. And that's difficult stuff to write about and to grapple with. And there is a sort of I haven't reread that book since it came out, but I think there are passages in it which reveal what I was thinking very clearly in the poetry of it as it were, as well as the the detail. But yeah, I can't say I'm used, I'm used to saying what I think and what I see and if there's any pushback I've got from that, I'm completely consoled that I'm saying what I see with my own eyes, </s><s>[INST] that's your source of strength, is that you're always seeking the truth is best. You see it? [/INST] Well, I can't agree to go along with a lie if I've seen something with my own eyes. </s><s>[INST] Do you ever so speaking of Sam Harris, uh and I mentioned to you offline a lot of people, I talked to a lot of smart people in my private life on this podcast and a lot of them will reference you as a as their example of a very smart person. So given that a compliment, um do you ever worry that your sort of ego growth to a level where you're not, what you think is the truth is no longer the truth is this kind of it blinds you. And also on top of that, the fact that you stand against the crowd often that there's part of it that appeals to you, they you like to point out the emperor's new clothes. And [/INST] I get a certain thrill from the friction </s><s>[INST] that sometimes both your ego and the thrill of friction. We'll get you to deviate from the truth and instead just look for the friction [/INST] could do. For sure. I try to keep alive to that. I mean, I try early in my career, I realized that for instance, I didn't want to make enemies unnecessarily any more than strictly necessary because there was a very large number of already necessary enemies. And I remember once I won't go into details, but I already had one sort of thing I'd done that way. And then another thing came out. I just thought I can't, I can't do it. Um, and I remember thinking, don't be the sort of person who's forever creating storms. And I'm trying to make sure I wasn't, and I think I've pretty much start to that. But to answer your question. Um, well, the first thing is, I'm as confident they can be that I wouldn't fall into the trap. You describe. Two reasons. I mean one is that I don't think of myself as a wildly intelligent person. Um, partly because I'm very, very aware of the things I know nothing about. I mean, for instance, I have a almost no knowledge of the details of finance or economic theory. Um I mean the real details, I don't mean the big picture of the kind that we were just discussing earlier, but I </s><s>[INST] have, [/INST] if you put the periodic table in front of me, I would struggle to do more than a handful. Um I very conscious of huge gaps in my knowledge and where I have gaps or chasms, I tend to find, I have a disproportionate admiration for the people who know that stuff. Like I'm wildly impressed by people who understand money, really understand it because I think, how the hell do you do that? Um uh, and the same thing with biologists, medics stuff I just know very little about </s><s>[INST] and that's a source of humility for you just knowing that [/INST] I think that stuff, but jesus, if you got me into general knowledge, I say that thing some years ago, there's a thing in in the UK called University challenge and my, I was asked some years ago onto, there's a sort of like celebrity, One of former students of the universities or colleges asked to go back for the christmas special and, and I was asked to be one of the people from my old college to go back and compete in the sort of celebrity alumni one. And the only reason I actually wanted to do it was to discover the louis Theroux had been to my college before my time and he was on, he had agreed to be on the team and I thought I'd love to meet louis through that would be great fun and anyhow. And I said, well, I really don't want to do it. And they said, come on, you'd be great. I said, I wouldn't, I show myself up to be a total asshole, an ignoramus. And as it was, I sat down my flat and I watched some past episodes of university challenge. I realized I just sat mute for the whole lot of our um, I just could not. The first question was about physics and the second one was about, uh, as it was, I watched the, the one and I could answer the first two or three questions of the one that actually went out because they made it a bit simpler, but, but I mean, I'm terribly conscious of the, and I said to the producers, I said, I can't go on because I mean, I just couldn't answer the questions. He's unbelievably smart students seem to be able to answer a whole range of things. So I'm perfectly aware of my limitations and um, you </s> |
<s>[INST] person or maybe you have no clue or you're just a giant [/INST] mystery to yourself? </s><s>[INST] Okay these are really [/INST] intense questions. But </s><s>[INST] uh because [/INST] I asked this myself </s><s>[INST] like look in the mirror, who are you? People tell you to just be [/INST] yourself? But what does that </s><s>[INST] even mean? I mean I think my personality changes with everyone I talk to. So I have a very [/INST] inconsistent </s><s>[INST] personality, [/INST] person to </s><s>[INST] person. So the interaction your personality or [/INST] my mood, like I'll </s><s>[INST] go from being like a megalomaniac to being [/INST] like you know just like a total hermit who is very </s><s>[INST] shy. So some common editorial com combination of your [/INST] mood and the person you're </s><s>[INST] interacting with. Yeah, [/INST] mood and people are interacting with. But I think everyone's like that. Maybe </s><s>[INST] not well not everybody acknowledges it, unable to introspect it. Who brings out what kind of person, What kind of mood brings out the best in you as an artist and as a human can you introspect? Like my [/INST] best friends </s><s>[INST] like people I can [/INST] when </s><s>[INST] I'm like [/INST] super confident and </s><s>[INST] I know that they're going to [/INST] understand, understand everything </s><s>[INST] I'm saying. So like, my best [/INST] friends then </s><s>[INST] when I can [/INST] start being really funny, that's always </s><s>[INST] my like, peak mode. But it's like, yeah, it takes a lot to [/INST] get there. Let's talk about </s><s>[INST] constraints. [/INST] You've talked about </s><s>[INST] constraints and limits. Um Do those help [/INST] you out as an artist or as a </s><s>[INST] human being? Or do they get in the way? [/INST] Do you like the constraints So in creating </s><s>[INST] music and creating art and living life, do you like the constraints that this world puts on you? Or do you hate them [/INST] if constraints </s><s>[INST] are moving, then you're good, [/INST] right? Like, it's like, it's like, as we </s><s>[INST] are progressing with technology, [/INST] we're changing the constraints of like, </s><s>[INST] artistic creation, [/INST] you know? Um </s><s>[INST] Making video [/INST] and music and stuff </s><s>[INST] is getting a lot cheaper. There's constantly [/INST] new technology and </s><s>[INST] new software that's making [/INST] it faster and easier. We </s><s>[INST] have so much more freedom than we had in the 70s. Like when [/INST] Michael Jackson, </s><s>[INST] you know, when they recorded thriller with this microphone, [/INST] like they had to use a mixing </s><s>[INST] desk and all this stuff [/INST] and like, probably even get in the studio is probably expensive and you have </s><s>[INST] a really good singer and you have to know how to use like [/INST] the mixing desk and everything. </s><s>[INST] And now I can just, [/INST] you know, make </s><s>[INST] I've made a whole album [/INST] on this computer. I have a lot more freedom. But then </s><s>[INST] I'm also constrained [/INST] in different ways because there's like literally </s><s>[INST] millions more artists. It's like a much bigger playing field. It's just like, [/INST] I also, I </s><s>[INST] didn't learn music. I'm [/INST] not a natural </s><s>[INST] musician, so I don't [/INST] know anything about actual music. I just know about like </s><s>[INST] the computer. So [/INST] I'm really </s><s>[INST] kind of just like [/INST] messing </s><s>[INST] around and [/INST] like, well, yeah, I mean, but the nature of music is changing. So you're saying you don't know actual music </s><s>[INST] what music is [/INST] changing music is becoming? You've talked about this is becoming, it's like merging </s><s>[INST] with technology. Yes, It's [/INST] becoming something </s><s>[INST] more [/INST] than just </s><s>[INST] like the notes on the piano [/INST] is becoming some weird composition that requires engineering skills, programming </s><s>[INST] skills, some [/INST] kind of human </s><s>[INST] robot interaction [/INST] skills. And still some of the same things that Michael Jackson had, which is like a </s><s>[INST] good ear for a [/INST] good sense of taste of what's good and not the final thing, what is put </s><s>[INST] together, like you're [/INST] allowed your enabled empowered with a laptop </s><s>[INST] to layer stuff [/INST] to start like layering insane </s><s>[INST] amounts of stuff [/INST] and it's super easy to </s><s>[INST] do that. I do think music [/INST] production is a </s><s>[INST] really underrated art form. I feel, I feel like people really don't appreciate [/INST] it when I look at publishing splits the way that people, um, like pay producers and stuff. Uh </s><s>[INST] it's it's super producers are just deeply underrated, [/INST] like so many of the </s><s>[INST] songs that are popular [/INST] Right now or for the last 20 years. Like part of the reason they're popular because the production is really interesting and really </s><s>[INST] sick or really cool and it's like I don't think [/INST] listeners um </s><s>[INST] like people just don't really understand [/INST] what music production </s><s>[INST] is. It's [/INST] not, it's sort of like this </s><s>[INST] weird [/INST] discombobulated </s><s>[INST] art form. It's not [/INST] like a formal because it's so new. There isn't like a formal training path for it. </s><s>[INST] It's it's um [/INST] mostly driven by like autodidact. </s><s>[INST] Like it's like almost everyone I know [/INST] who's good at production, like </s><s>[INST] you didn't go to music school [/INST] or anything, they just taught themselves. They're mostly different. Like the music producers, you </s><s>[INST] know, is [/INST] there some commonalities that time </s><s>[INST] together or are [/INST] they all just different kinds of weirdos? Because I just, I just hung out with rick </s><s>[INST] Rubin. I don't know if you [/INST] yeah, I </s><s>[INST] mean rick Rubin is like literally one of the [/INST] gods of music production. Like he's </s><s>[INST] one of the people [/INST] who first you know who like made music production, you know </s><s>[INST] made the production [/INST] as important as the </s><s>[INST] actual lyrics or the [/INST] notes. But the thing he does, which is interesting. I </s><s>[INST] don't know if you can speak [/INST] to that, but just hanging out with </s><s>[INST] him. He seems to [/INST] just sit there in silence, close his eyes </s><s>[INST] and listen. [/INST] It's like he almost does </s><s>[INST] nothing and that [/INST] nothing somehow gives you </s><s>[INST] freedom to be the [/INST] best version of yourself. So that's music </s><s>[INST] production somehow too, which [/INST] is like encouraging </s><s>[INST] you to do less to [/INST] simplify to like push towards minimalism. </s><s>[INST] I mean, I guess, [/INST] I mean I work differently from recruitment Rick </s><s>[INST] Rubin produces for other [/INST] artists, whereas like I mostly </s><s>[INST] produced for myself, so it's a very [/INST] different situation. </s><s>[INST] I also think rick [/INST] Rubin he's in that I would say advanced category of producer </s><s>[INST] where like, you've like earned your, you can have an engineer [/INST] and stuff and people like </s> |
<s>[INST] Anyway right now get a free $75 sponsored job credit to upgrade your job post at indeed dot com slash flex. Get it at indeed dot com slash lex terms and conditions apply go to indeed dot com slash lex. This is a lex Friedman podcast and here is my conversation with jay Zakaria to our best understanding today how deadly is covid, do we have a good measure for for this very question. [/INST] So the best evidence for covid the deadliness of covid comes from a whole series of syria prevalence studies seven studies are these studies of antibody prevalence in the population at large. I was part of the, you know, the very first set of sarah Palin studies, one in santa clara county, one in L. A. County and one in the other with major league baseball around the U. S. </s><s>[INST] Uh If I may just pause you for a second. If people don't know what serology is in several prevalence. It does sound like you say zero prevalence. It's not it's zero. And serology is antibodies. So it's it's a it's a survey that counts the number of antibodies specific people that have antibodies specific to Covid which perhaps shows an indication that they likely have had covid. And therefore this is a way to study how many people in the population have been exposed to have had. [/INST] Exactly. Yeah exactly. So the idea is that um we don't know exactly the number of people with Covid just by counting the people that are that are present themselves with symptoms of covid. Covid has. It turns out a very wide range of symptoms possible ranging from no symptoms at all to this deadly viral pneumonia that has killed so many people. And the problem is like if you just count the number of cases that people have very few symptoms often don't show up for testing, we just don't. They're outside of the can of public health. And so it's really hard to know that the the answer to your question without understanding how many people are infected because you you can probably tell the number of deaths. That's even though there's some controversy over that. But that's so the numerator is possible. But the denominator is much harder. </s><s>[INST] How much controversy is there about the death? We're gonna go on million tangents. Is that okay? We're gonna have a million questions. So one I love data so much but I like almost tuned out paying attention to covid data because I feel like I'm walking on shaky ground. I don't know who to trust. Um Maybe you can comment on different sources of data, different kinds of data. The death one that seems like a really important one. Can we trust the reported deaths associated with covid? Or is it just a giant messy thing that mixed up? And then there's this kind of stories about hospitals being incentivized to report a death as covid death. [/INST] So there's some truth in some of that. Let me just let me just talk about the incentives. So in the United States we passed this cares act that was aimed at making sure hospital assistant saying go bankrupt in the early days of the pandemic. The couple of things they did, one was they provided incentives to treat covid patients tens of thousands of dollars extra per per covid patient. Um and the other thing they did is they gave a 20% bump to Medicare payments for elderly patients who are treated with COVID. The idea is that there's more expensive to treat them in the early days. So that did provide an incentive to sort of have a lot of covid patients in the hospital because your financial, the success of the hospital or at least not for lack of financial ruin, dependent on having many covid patients. The other thing on the death certificates is the reporting of deaths is a separate issue. I don't know that there's a financial incentive there, but there is this sort of like complicated, you know, when you fill out a death certificate for patients with a lot of conditions, like, let's say a patient has diabetes patient that while that diabetes could lead to heart failure, You know, you have a heart attack, heart failure, your lungs fill up, then you get covid and what and you die. So what do you, what do you write on the death certificate? Was it because of covid that killed you? Was it the lungs filling up? Was it the, the heart heart failure? Was it the diabetes? It's really difficult to like disentangle. Um, and I think a lot of, a lot of times what's happened is that people have like erred on the side of signing his Covid. Now, what's the evidence of this? There's been a couple of, of audits of death certificates in places like santa Clara County where I live in Alameda county California where they carefully went through the death certificate said, okay, is this reasonable to say this was actually Covid or it was covid incidental And they found that about 25% 2025% of the deaths were more likely incidental than directly due to Covid. I personally don't get too excited about this. I mean, it's a philosophical question, right? Like ultimately what kills you, which is an odd thing to say if you, if you, if you don't, you're not in medicine, but like really, it's, it's a um, it's almost always multifactorial and always, always just the bus hits you. The bus hits you, that you get a brain bleed. Was the brain bleed that killed you would have burst anyway. I mean, you know, the bus hits you, killed you, right? </s><s>[INST] The way you die as a philosophical question. But it's also a sociological and psychological question because it seems like every single person who's passed away over the past couple of years, kind of the first question that comes to mind just was a covid, not, not just because you're trying to be political, but just in [/INST] your mind. No, I think there's a psychological reason for this, right? So, you know, we have, we spent the better part of at least a half century in the United States, not worried too much about infectious diseases. And we, the notion was we essentially conquered them. It was something that happens in far away places to other people. And, and that's true for much of the developed world life expectancy. We're going up for decades and decades. And for the first time in living memory, we have a disease that can kill us. I mean, I think we're effectively evolved to fear that like the panic centers of our brain, the lizard part of our brain takes over and our central focus has been avoiding this one risk. Um, and so it's not surprising that people when they're filling out death certificates or thinking about what what what led to the death. This most salient thing that's in the front of everyone's brain would would jump to the top </s><s>[INST] and we can't ignore this very deep psychological thing. When we consider what people say on the internet, what people say to each other, what people write in scientific papers with everything, it feels like when Covid has been um has been brought into this world, everything changed in the way people feel about each other, just the way they communicate with each other. I think the the level of emotion involved. I think it in many people, it brought out the worst in them for sometimes short periods of time. And sometimes it was always therapeutic, like you were waiting to get out like the darkest parts of you just to say if you're angry at something in this world, I'm going to say it now. And um I think that's probably talking to some deep primal thing that um fear we have for formalities of all different kinds. And then when that fear is aroused in all the deepest emotions, it's like a Freudian psychotherapy session. But across the [/INST] world it's something that psychologists are gonna have a field day with for generations trying to understand. I mean, I think, I think what you say is right, but piled on top of that is also this sort of this impetus to empathy to empathize compassion toward others, essentially militarized. Right? So I'm protecting you. Bye bye. Some actions and uh, those actions, if I, if I don't do them, if you don't do them. Well, that must mean you don't, you hate me. Um, it's, it's created this like social attention that I've never seen before. And, and we, we started started, we started, we looked at each other as if we were just simply sources of, of germs rather than people to get to know people to enjoy, people to get, you know, sort of to learn from. Um, it colored basically almost every human interaction for every, every human on the planet. </s><s>[INST] Yeah. The basic common humanity. It's like you can wear a mask, you can stand far away. But the love you have for each other when you look into each other's eyes, that was dissipating and by region to have experienced having traveled quite a bit throughout this time. It, um, it was really sad. Even people that are really close together just the way they stood, the way they looked at each other and it made me feel for a moment, um, that the fabric that connects all of us is more fragile than I thought. [/INST] I mean if you walk down the street or if you ever, if you did this during Covid, I'm sure you had this experience where you walk down the street if you're not wearing a mask or even if you are, people will jump off the off the sidewalk that you walk past them as if you're poisoned, even though the data are, that Covid spreads, you know, indifferently outdoors if at all really at outdoors. But it's not simply a biological or infectious disease phenomenon. Archaeological it's it is it is it is a change in the way he was treated each other. I hope hope temporary. </s><s>[INST] I do want to say on the flip side of that. So I was mostly in boston massachusetts when the pandemic broke out. I think that's where I was. Yeah. And then I got came here to austin texas to visit my now good friend joe Rogan and he was the first person without pause. This wasn't a political statement. This was anything. Just walked toward me and give me a big hug and say, it's great to see you and I can't tell you how great it felt because I in that moment realized the absence of that connection back in boston over just a couple of over a couple of months and it's, we'll talk about it more. But it's it's tragic to think about that distancing that dissolution of common humanity at scale what what kind of impact it has on society. Just across the board. Political division. Uh, and just in the quiet of your own mind and the privacy of your own home, the depression, the sadness the loneliness that leads to suicide and forget suicide Just loki suffering. [/INST] Yeah. No, I think that's that's the suffering that isolation were not meant to live alone. Were not meant to live apart from one another. And that's of course the ideology of lockdown is to make people live apart alone isolated so that we don't spread diseases to each other. Right? But we're not actually designed as a species to live that way. And that what you're describing, I think if everyone's honest with themselves have felt, especially in places where that where lockdowns have been sort of very militantly enforced has felt deep into their core. </s><s>[INST] Well, I if I could just return to the question of deaths. He said that the data is imperfect because we need these kind of cereal prevalence surveys to understand how many cases there were to determine the rate of deaths. And we need to have a strong footing in the number of deaths. But if we assume that the the the number of deaths is approximately correct. Like what's your sense? What kind of statements can we say about the deadliness of covid against across different demographics? Maybe not in a political way or in the current way, but when history looks back at this moment of time, 50 years from now. 100 years from now, the way we look at the pandemic 100 years ago what will they say about the deadliness of Covid? [/INST] I think the deadliness of Covid depends on not just the virus itself but who it infects. Um So the probably the most important thing about it about the deadliness of covid is is this steep age gradient in the mortality rate. Um So according to these zero prevalence studies that that that that have been done now hundreds of them Um mostly from before vaccination, vaccination also reduces the mortality risk of COVID. Um the serial problem studies suggest that the risk of of death, if you say over the age of 70 is very high, you know, 5%. If you get covid, if you're if you're under the age of 70 it's lower point oh five but there's not a single sharp cut off. It's more like I have a rule of thumb that I use. Um So if you're 50 say the infection fatality rate from covid is 500.2%. According to the serial prevalence data, That means 99.8% survival If you're 50. And for every seven years of age above that double it. Every seven years of age below that habit. So a 57 year old have a .4 Mortality, year old would have a .8% and so on. And if you have a severe chronic disease like diabetes or if you're morbidly morbidly obese, it's like adding 77 years to your life. </s><s>[INST] And this is uh for unvaccinated [/INST] folks, this is unvaccinated in the before delta also. </s><s>[INST] Are there a lot of people that would be listening to this with ph D. S at the end of their name that would disagree with the 99.8 would you say [/INST] so? I think there's some disagreement over this and the disagreement is about the quality of the serial prevalence studies that were conducted. Uh So as I said earlier I was a senior investigator in three different problem studies. And very early in the epidemic. I view them as very high quality studies. Um We we um in santa Clara County. What we did is we used a test kit Uh to that we obtained from someone who works in Major League Baseball actually. He ordered these test kits very early in March 2020 that measures very accurately measures antibody levels or antibodies in the in in the bloodstream. Uh These test kits were eventually were approved by the the had an E. U. A. By the emergency use authorization by the FDA. Sort of shortly after we did this. And uh it had a very low false positive rate false positive means if you if you uh if you don't have these covid antibodies in your bloodstream, the kid shows up positive anyways that That turns out to happen about .5% of the time. Um and based on studies, a very large number of studies looking at blood from 2018 you try it against this kit And you know .5% of the time. 2018 there shouldn't be anybody's there. So to COVID. So if it turns positive as a false positive .5% of the time. Um and then, you know like a false negative rate about 10%, something like that. I don't remember the exact number, but the false positive rate is an important thing there. Right? So you have a population in March 2020 or April 2020 with very low fraction of patients having been exposed to covid. You don't know how much but low, even a small false positive rate could end up biasing this study quite a bit, but there's a formula to adjust for that. You can adjust for the four false positive false negative rate. We did, we did that adjustment And those studies found in a community population. So leaving aside people in nursing homes who have a higher death rate from covid. Um the that the death rate was .2% in Santa Clara County and in L. A. County </s><s>[INST] across all age groups in the community community meeting. Just like regular. [/INST] So like that that's actually really important question to. So the santa clara study, we did this facebook sampling scheme um which is, I mean not not the ideal thing, but it's like it was very difficult to get a random sample. And and during the, you know, during lockdown um where we put out an ad on facebook soliciting people to volunteer for the study randomly selected set of people? We were hoping to get a random selection. People from santa Clara County, but it tended to the people who tend to volunteer were from the richer parts of the county. Like I had stanford professors writing begging to be in the study because they wanted another antibody levels. So we did some adjustment for that in L. A. County. We hired a firm that had a preexisting representative sample of L. A. County. Um, so, but it didn't include nursing homes. It didn't include people in jail. Things like that didn't include the homeless populations. So it's it's representative of a community dwelling population, both of those. And there we found that both in L. A. County and Santa Clara County in April 2020, something like 40 to 50 times more infections than cases in both places. So for every case that had been reported to the public health authorities, we found that, you know, you know, 40 or 50 other infections, people with anti antibodies in their blood that suggested that they had had covid and recovered. </s><s>[INST] So people were not reporting or severe at least in those days under reporting. [/INST] Yeah. I mean, there was, you know, there's testing problems, there weren't so many tests available. People didn't didn't know a lot of a lot of them. We asked a set of questions about the symptoms they faced And Muslims said they face, no symptoms are the most 30, of the said face. There no symptoms. </s><s>[INST] And I mean, even these days, how many people report that they get covid? When they get covid. Okay. Have those numbers that 0.2% has that approximately held up [/INST] over time. That is. So if Professor johnny needs, who's a colleague of mine at stanford is a world expert in meta analysis, probably the most cited scientists on earth, I think at least living. He he did a meta analysis of now. 100 or more of these sarah prevalence studies. Um and uh what he found was that that .2% is roughly the worldwide number. And in fact, I think he cites us lower number, .15 as the meeting infection fatality rate worldwide. So we did these studies and it generated an enormous amount of blowback by people who thought that the infection rate is much higher. And there's some controversy over the quality of some of the other studies that are done. And so there are some people who look at this same literature and say, well, the lower quality studies tend to have lower I frs The higher quality studies. Oh, infection fatality. Right. I apologize. I do this in lectures two. </s><s>[INST] And I'm going to rudely interrupt your and ask for for the basics sometimes if it's [/INST] OK. No, of course. So these these higher quality studies, they say </s><s>[INST] our pretend to produce [/INST] higher. But the problem is that if you want a global infection fatality rate, you need to get see the problem studies from everywhere, even in places that don't necessarily have the infrastructure set up to produce very, very high quality studies and in poor places in the world, the this the that like places like africa, the infection fatality rate is incredibly low. And in some richer places like new york city, the infection fatality rate is much higher. It's there's a range of fr is not a single number. This sometimes surprises people because they think, well it's a it's a virus that should have the same properties no matter where it goes. But the virus kills or infects or hurts in interaction with the host and the properties of both the host and the virus combined to produce the outcome. </s><s>[INST] But you also mentioned the environment too. [/INST] Well, I'm thinking mainly just about the the person, like I think I'm gonna think about it, like the most simplest way to think about it is age, age is the single most important risk factor. So older places are going to have a higher i fr Than younger places. Africa 3% of Africa is over 65. So in some sense it's not surprising that they have a low infection fatality rate. </s><s>[INST] So that's one way you would explain the difference between africa and new york city in terms of the fatality rate is the age, the [/INST] average age and especially in the early days of the epidemic in new york city, the uh older populations living in nursing homes were differentially infected based on because of policies that were adopted right to send covid infected patients back to nursing homes to keep hospitals empty. </s><s>[INST] What do you mean by differentially infected? [/INST] The policy that you adopt determines who is most exposed, </s><s>[INST] right? That Okay, so that's what the policy, it's the person that matters. I mean it's not like the virus just kinda doesn't care. I mean the the policy determines the nature of the interaction and there's also, I mean there is some contribution from the environment. Different regions have different proximity maybe of people interacting or the dynamics of the way they [/INST] interact. Like if you have, if you have situations where there's lots of intergenerational uh interactions, then you have a very different risk profile then if if you have societies that are where generations are more separated from one another. Um Okay so let me just finish real fast about this. So you you you have in new york you have a population that was infected in the early days that was very likely going to die. I have had a much higher likelihood dying if infected. And so new york city had a higher if our especially in the early days than um than um then like africa has has had um the other thing is treatment right? So the treatments that we adopted in the early days of the epidemic I think actually may have exacerbated the risk of death which do you like using ventilators? Like the the the over reliance on ventilators is what I'm primarily thinking of. But I can think of other things. Um, but that that also we've learned over time how better to manage patients with the disease. So you have those you have all those things combined. So that's that's where the controversy over this over this number </s><s>[INST] is, I mean, new york city also, it is a is a central hub for those who tweet and those who write powerful stories and narratives in article form. And I remember those quite dramatic stories about sort of doctors in the hospitals and these kinds of things. I mean, there's very serious, very dramatic, very tragic deaths going on always in hospitals, those stories. Um I loved loved ones, losing each other on a deathbed, that's always tragic. And you can always write a hell of a good story about that. And you should about the loss of loved ones. But they were doing it pretty pretty well, I would say um, over this kind of dramatic deaths. And so in response to that, it's very unpleasant to hear even to consider the possibility that the death rate is not as high as you might otherwise as you might [/INST] feel. Yeah, I was surprised by the reaction Both by regular people and also the scientific community in response to those studies, those early studies in April of 2020. Um to me, they they were there were studies, I mean they're they're they're kind of not exactly the kind of work I've worked on all my life, but it's kind of kind of like the kind of, you know that you write a paper and you get responses from your fellow scientists and you change the paper to improve it. You have hopefully learned something from it </s><s>[INST] well, but to push back, it's just a study, but there's some studies and and this is kind of interesting because I've received similar pushback on other topics. There's some studies that uh if wrong might have wide ranging detrimental effects on society. So that's that, that's the way they would perceive the studies if you say the death rate is lower and you end up as you often do in science realizing that, nope, that that's that was there was a flaw in the way they said it was conducted or we're just not representative of broader population and then you realize the death rate is much higher. That might be very damaging in people's view. Uh so, so that's probably where the scientific community sort of steel man, the kind of response is that's where they felt like, you know, there's some findings where you better be damn sure before you kind of report them. [/INST] Yeah, I mean we were pretty sure we were right and it turns out we were right. So like when when we so um we released the santa clara study via this open open science process and this server called med Med archive. It's it's designed for releasing studies have not yet been peer reviewed in order to garner comment from the from the scientists before peer review the L. A. County study. We went through the traditional peer review process and got it published in the Journal of American Medical Association. Sometimes like july I think forget the date of 2020 The Santa Clara study released in April of 2020 in this, you know sort of working paper archive. The reason was that we felt we had an obligation, we had a result that was what we thought was quite important and we wanted to tell the scientific community about it and also tell the world about it and it wasn't we wanted to get feedback. I mean that's part of the purpose of sending it to these kinds of places. I think a lot of the problem is that when people think about published science, they think of it as automatically true. And if it goes through peer review is automatically true. If it hasn't gone through peer review, it's not automatically true. And especially in medicine we're not used to having access to pre peer reviewed work. I mean in economics actually that's quite normal. You takes years to get something published. So there's a very active debate over or discussion about papers before they're peer reviewed in this in this sort of working paper. Way much less normal or much much newer in medicine. And so I think part of that the perception about what those that that what process happens in open science when you release a study that that got people confused and you're right. It was a very important result because we had just locked the world down in middle of March with I think catastrophic results. And if that if that study was right, if our study was right, that meant we'd made a mistake and not because of the death rate was low. That's actually not the key thing there. The key thing is that we have adopted these policies. These test and trace policies, these policies, these lockdown policies aimed at suppressing the virus level to close to zero. That was essentially the idea if we can just get the virus to go away, we don't have to ever worry about it again. </s><s>[INST] The main [/INST] problem with our results as far as that strategy was concerned wasn't the death rate, it was the 40 to 50 times more infections than cases. It was the 2.5% or 3% or 4% prevalence rate that we identified of the antibodies in the population. If that number is right, it's too late. The virus is not going to go to zero and no matter how much we test and trace and isolate we're not going to get the viral level down to zero. Mhm. </s><s>[INST] So we're gonna have to let the virus go through the entire population in some way [/INST] so that we can talk about that in a bit. That's the great Barrington declaration. You don't have to let the virus go through the population. You can shield preferentially. The policy we chose was to shield preferentially the laptop class, the set of people who could work from home without losing their job. And we did a very good job of protecting them. </s><s>[INST] Well let me um take a small tangent. We're going to jump around in time which I think will be the best way to tell this story. So that was the beginning. [/INST] Yeah. Okay. Actually can I can I can I go back one more thing for that because that's really important and I should have I should have started with this. Um What led me to do those studies was a paper that I had remembered seeing from the H. One N. One flu epidemic in 2000 and nine. This is this is where I have been much less active in writing about that. I had written like a paper or two about that when in 2000 and nine um there there was actually the same debate over the mortality rate Except it unfolded over the course of three years, 2 or three years. The early studies of the mortality rate in H. One N. One counted the number of cases in the denominator kind of the number of deaths in the numerator cases meaning people identified as having one N. One showing up the doctor, you know tested to have it. Um And the early estimates of the H one N. One mortality were like 4% 3% really really high. Over the course of a couple of more years, a whole bunch of syrup prevalence studies. Syria prevalence studies of H one N one flu came out and it turned out that there were 100 or more times people infected per case. And so the mortality it was actually something like .02 for H one N. One not the 33 like a hundredfold difference. </s><s>[INST] So this made you think, okay it took us a couple of two or three years to discover the truth behind the actual infections uh for H. One N. One. And [/INST] then what's the truth </s><s>[INST] here and can we get there [/INST] faster? Yeah. And and there was it spreads in a similar way as the as the H one N. One flu did. I mean it's it's spread via aerosols civilization via you know the the person person breathing kind of kind of contact. Um Maybe maybe some by by film ice but seems like that that's less likely now. In any case it seemed really important to me to speed up the process of having those zero prevalence studies so that we can better understand who was at risk and what the right strategy ought to be. </s><s>[INST] This might be a good place to kinda compare influenza, the flu and Covid in the context of the discussion we just had, which is how deadly is covid. So you mentioned, Covid is a very particular kind of steepness. Uh more of the X axis is age. So in that context could you maybe compare influenza and Covid because a lot of people um outside the folks who suggest that the lizards who run the world have completely fabricated invented Covid. Outside of those folks, kind of the natural process by which you dismiss the threat of Covid and say what's just like the flu? The flu is a very serious thing actually. Um So in that comparison, where does Covid stand? [/INST] Yeah, the flu is a very serious thing. It kills, you know, 50, people a year. Something I found that order depending on the particular strain that goes around that's in the United States. The primary difference to me, there's lots of differences but one of the most salient differences is the age gradient and mortality risk for the flu. So the flu is more deadly for two Children than Covid is. There's no controversy about that. Children. Thank God have much less uh severe reactions to covid infection to then due to flu infections </s><s>[INST] and rate of fatalities, [/INST] fatalities. All of that </s><s>[INST] I think you mentioned. Um I mean it's interesting to maybe also comment on, I think in another conversation mentioned there's a U shape to the to the flu curve. So meaning like there's actually quite a large number of kids that die from flu. [/INST] Yeah, I mean the 1918 flu, the H1N1 flu that that the Spanish flu in the us killed millions of of of of younger people. And um that is not the case with Covid More than um I'm going to get the number wrong but something like 70, of the deaths are people over the age of 60. </s><s>[INST] Well we've talked about the fear the whole time really. But my interaction with folks now I want to have a family. I want to have kids but I don't have that real firsthand experience. But my interaction with focus is at the core of fear that folks had is for their Children like that somehow. You know, I don't want to get infected because of the kids like because God forbid something happens to the kids. And I think that obviously that makes a lot of sense. That's kind of the kids come first no matter what, that's number one priority. But for this particular virus, that reasoning was not grounded in data it seems like or that emotion and feeling grounded [/INST] at the same time this is way more deadly than the flu just overall and especially to older people. Yes. </s><s>[INST] Right. So the numbers when when the story is all said and done the Covid would would take many more lives. Yeah. [/INST] So I mean point to it sounds like a small number but it's not a small number </s><s>[INST] worldwide. What do you think that number will be by the, you know, that's not that's not like me. But would we cross, I think it's in the United States, it's um The way the deaths are currently reports like 800,000, something like that. Do you think we'll cross a million [/INST] Seems likely. </s><s>[INST] Do you think it's something that might continue with different variants? What? [/INST] Well, I I think so we can talk about the end state of Covid. The end state of Covid is it's here forever. Um I think that there is good evidence of immunity after infection such that you're protected both against reinfection and also against severe disease upon reinfection. So the second time you get it, it's not true for everyone. But for many people, the second time you get it will be milder, much milder than the first time you get it </s><s>[INST] with the long tail. Like uh that lasts for a long time. [/INST] Yeah. So just their studies that the follow of course the people who are infected for a year and the re infection rate is something like somewhere between 0.3 and 1%. Um And like a pretty fantastic study in italy found that there's one in Sweden. I think there's a few studies have found that similar, similar things and the reinfections tend to produce much milder disease, much less likely to end up in the hospital, much less likely to die. Um So what the end state of covid is it's circulating the population forever and you get it multiple times. Yeah. </s><s>[INST] And and then there's this, I think studies and discussions like the best protection would be to get it and then also to get vaccinated and then a lot of people push back against that for the obvious reasons from both sides because somehow this discourse has become less scientific and more political. [/INST] Well, I think I think you want to like the first time you meet, it is going to be the most deadly for you. And so the first time you meet it is just wise to be vaccinated. The vaccine reduces severe disease. </s><s>[INST] Yeah, well, we'll talk about the vaccine because I want to make sure I address it carefully and properly in full context. Um, but yes, sort of to add to the context. A lot of the fascinating discussions we're having is um in the early days of Covid and now for people who are unvaccinated, that's where the interesting story is the policy story of the sociology sociological story and so on. But let me go to something really fascinating just because of the people involved the human beings involved and because of how deeply I care about science and also kindness, respect and love and human things Francis, Collins wrote a letter in October 2020 to Anthony Fauci, anything somebody else I have. Okay, the letter is not a letter, email. I apologize. Hi Tony and Cliff C G B declaration dot org. This proposal. This is the Great Barrington Declaration that you're a co author on this proposal from the three fringe epidemiologists who met with the Secretary seemed to be getting a lot of attention. And even the co signature from Nobel Prize winner, Mike Leavitt at stanford, there needs to be a quick and devastating published takedown of its premises. I don't see anything like that online yet. Is it underway? Question mark, Francis Francis Collins, Director of the NIH. Somebody had talked on this podcast recently. Okay, million questions I wanna ask. But first, how did that make you feel when you first saw this uh email come to uh uh to light? Which when when when did it come to light [/INST] this week? Actually, I think our last </s><s>[INST] week. Okay, so this is because of freedom of information, which by the way, sort of maybe because I do want to add positive stuff on on the side of Francis here. Um boy, when I see stuff like that, I wonder if all my emails leaked, How much embarrassing stuff like I think I'm a good person down. I haven't read my old emails. Maybe I'm pretty sure sometimes later I could be an asshole. [/INST] Well, I mean, look, he's a christian and I'm a christian I'm supposed to forgive right? I mean, I think he was looking at this great Barrington Declaration as a political problem to be solved as opposed to a serious alternative approach to the epidemic. </s><s>[INST] So maybe we'll talk about in more detail. But just for in case people are not familiar. Great Barrington Declaration was it was it was a document that you co authored that basically argues against this idea of lockdown as a solution to Covid. And you propose another solution that we'll talk about. But the point is it's not that dramatic of a document. It is just a document that criticizes one policy solution [/INST] that was but it was the policy solution that had been put forward by dr Collins and by Tony Fauci and a few other few other science. I mean, I think a relatively small number of scientists and epidemiologists in charge of the advice given to governments worldwide. And it was a challenge to that policy that said that look there there is an alternate path that that the path we've chosen this path of lockdown with an aim to suppress the virus to zero effectively. I mean that was unstated, um cannot work and is causing catastrophic harm. two large numbers of poor and vulnerable people worldwide. We put this out in October 4th I think of 2020 and it went viral. I mean I've never actually been involved with anything like like this where I just put the document on the web and tens of thousands of doctors signed on hundreds of thousands of regular people signed on. It really struck a chord of people because I think even by October 2020 people had this sense that there was something really wrong with the Covid policy that we've been following. And they were looking for reasonable people to give an alternative. I mean, we're not arguing that covid doesn't isn't isn't a serious thing. I mean, it is a very serious thing. This is why we had a policy that aimed at addressing it. Um, we were but we were saying that the policy we're following is not the right one. So how does a democratic government deal with that challenge? Uh, so to me that you asked me how I felt, I was actually frankly, just I was I I suspected there had been some email exchanges like that not necessary from Francis Collins around the government around this time. I mean, I felt the full brunt of a propaganda campaign almost immediately after we published it, where newspapers mischaracterized in all, in the same the same way over and over and over again. Um, and sought to characterize me as sort of as a as a sort of a marginal fringe figure or whatnot. Sinatra Gupta martin cold orf for the tens of thousands of other people that signed it. I felt the brunt of that all year long. So, to see this in black and white in, you know, with the handwriting essentially, if I mean the metaphorical handwriting of Francis Collins was actually frankly a disappointment because I've looked up to him for years. </s><s>[INST] Yeah, I've looked up to him as well. I um I mean I look for the best in people and I still look up to him what troubles me several things. The reason I said about the asshole emails that I sent late at night is I can understand this email, it's fear, it's panic, not being sure. The fringe three fringe epidemiologists [/INST] Mike Leavitt, who won a Nobel prize, I </s><s>[INST] mean, but using Fringe, maybe in my private thoughts, I have said things like that about others, like a little bit too unkind. Like, you don't really mean it now add to that he recently this week or whatever uh doubled down on the Fringe. This is really troubling to me that like, I can excuse this email, but to see the arrogance there, that Francis, honestly, I mean, it broke my heart a little bit there. This is an opportunity to like, especially at this stage to say just like I told him um to say I was wrong to use those words in that email. I was I was wrong to not be open to ideas. I still believe that this is not like say like actually argue with with this proposal with the policy of the proposed ah solution. Also, the devastating published, take devastating takedown, devastating takedown, as you say, somebody who's sitting on billions of dollars that they're giving to scientists, some of whom are often not their best human beings because they're fighting with each other over money, not being cognizant of the fact that you're um challenging the integrity, you're corrupting the integrity of scientists by allocating the money. You're now playing with that by saying devastating takedown. Where do you think the published takedown will come from? It will come from those scientists to whom you're giving money. What kind of example would they give to the academic community that thrives on freedom like this? This is I believe Francis Collins is a great man. One of the things I was troubled by is the negative response to him from people that don't understand the positive impact that NIH has had on society how many people has helped. But this is exactly the so he's not just a scientist, he's not just a bureaucrat who distributes money, he's also scientific leader. That in the time in difficult times we live in is supposed to inspire us with trust with love with the freedom of thought, He's supposed to, you know, those fringe epidemiologists, those are the heroes of science, when you look at the long arc of history, we love those people, I mean, love ideas even when they get proven wrong, [/INST] that's what I always had attracted me to science. Like some, somebody like the lone voice saying, you know, the moon of jupiter does move, I mean, you know, but the funny thing is, you know, Galileo was saying something truly revolutionary. We were saying that what we proposed in great Barrington Declaration was actually just the old pandemic plan. It wasn't anything really fundamentally novel. In fact, there were plans like this that Lockdown scientists had written in late February early March of 2020, so we were not saying anything radical, We were just calling for a debate effectively over the existing lockdown policy. Um And this is a disappointment. Really, truly a big disappointment because by doing this you were absolutely right lex he sent a signal to so many other scientists to just stay silent. Even if you had reservations. </s><s>[INST] Yeah, devastating takedown that people, you know, how many people wrote to me privately, like stanford, m I. T how amazing the conversation with Francis Collins was. There's a kind of admiration because, okay, how do I put it? Um A lot of people get into science because they want to help the world, they get excited by the ideas and they and they they [/INST] really are </s><s>[INST] working hard to help in whatever the discipline is. And then there is sources of funding which help you do help at a larger scale. So you admire those people that um distributing the money because they're often at least on the surface are really also good people. Oftentimes they're great scientists. So like it's amazing. I that's why I'm sort of um like sometimes people from outside think academia has broken some kind of wait, no, it's it's a beautiful thing. It's a it really is a beautiful thing and that's why it's so deeply heartbreaking where this person um is um I don't think this is malevolence. I think he's just incompetence of communication. [/INST] Well I think there's there's also arrogance at the bottom of it too. So </s><s>[INST] like, you know, [/INST] there's a particular kind of arrogance, right? So here it's it's of the same kind of arrogance that you see when Tony Fauci gets on tv and says that that if you criticize me, you're not simply criticizing a man, you're criticizing science itself, right? That is at the heart also of this email, there's so the certainty that the policies that they were recommending Collins and Fauci, we're recommending to the President of the United States were right, not just right, but right. So so far right that any challenge whatsoever to it is dangerous. Um and I think that that is really the heart of that email. It's it's um it's this idea that my position is unchallengeable not to be to be completely to be as charitable as I can be to this. You know, I believe they thought that I believe they some of them still think that that that there was only one true policy possible in response to covid every other policy was immoral. And if you if you come from that position then you write an email like that. You go on tv you say effectively right. I mean that that is that is what happens when you have this sort of unchallengeable arrogance that the policy of following is correct. Um I mean when we wrote the great painter declaration, what I was hoping for was a discussion about how to protect the vulnerable. I mean that was the key idea to me and the whole thing was better protection of the older population who really at really serious risk if infected with Covid and we have been doing a very poor job. I thought to date in many places in protecting the vulnerable and what I wanted was a discussion by local public health about better methods, better policies to protect the vulnerable. So when when I was when we were met with instead, a series of essentially propagandist lies about it. So that for instance, I kept hearing from reporters in in those days, why do you want to let the virus rip? Let it rip? Let it rip? The words let it rip. Does not appear in the Great Barrington Declaration. The goal isn't to let the virus rip. The goal is to protect the vulnerable to let society go. As you know, open schools and do other things that function as best they can in the midst of a terrible pandemic. Yes, but not let the virus rip where no the most vulnerable are protected. The goal was to protect the vulnerable. So why let it rip because it was a propaganda term to hit the fear centers of people's brains. Oh these people are immoral. They just want to let the virus go through society and hurt everybody. That was, that was that was the idea that it was a way to preclude a discussion and precluded debate about the existing policy. </s><s>[INST] So I've uh, this is, this is an app called clubhouse. Um, I've gone back on it recently to practice Russian unrelated for for a few big Russian conversations coming up anyway it's a great way to talk to regular people in Russian. But also there was a I was I was nervous, I was preparing for a fighter ceo conversation and there was a vaccine room and so I joined it. Uh and there's a there's a pro science room as they, these are like scientists that were calling each other pro science. The whole thing was like theater to me. I mean I haven't thoroughly researched but looking at the resume they were like pretty solid researchers and doctors and they were mocking everybody who was at all. I mean it doesn't matter what they stood for but they were just mocking people and the arrogance was overwhelming. I had to shut off because I couldn't handle that human beings can be like this to each other. And then I I went back to just to double check. Is this really happened, How many people are here? Is this theater? And then I asked to come on stage on clubhouse to to make a couple of comments and then as I opened my mouth and say thank you so much you know this this is is a great room sort of the usual civil politeness, all that kind of stuff. And I said I'm worried that the kind of arrogance with which things are being discussed here will further divide us, not unite us. And and before I said even the unite us further divide us. I was thrown off stage. Now this isn't why I mentioned platform but like I am like lex Friedman, m I. T. Also which is something those people seem to sometimes care about the followers and stuff like that. Like did you just do that? And then they said enough of that nonsense enough of that nonsense, they said to me enough of that nonsense. Somebody who is obviously interviewed Francis Collins is uh the fighter ceo uh [/INST] epidemiologists also. So just </s><s>[INST] Yeah, exactly. But this broke my heart. The arrogance and this is the echoes of that arrogance is something you see in this email and I really would love to have a million things to talk about, to try to figure out how can we find a path forward. [/INST] I think a lot of a lot of the problems we've seen in the discussion over Covid, especially in the scientific community, You know, there's there's two ways to look at science. I think that that have been competing with each other for a while now. Uh, one way and this is the way that I view science and I've always found it so attractive is an invitation to a structured discussion where the discussion is tempered by by evidence, by data, by by reasoning and logic. Right? So it's a dialectical process where if I believe A and you believe B. Well, uh, we talked about it, we come up with an experiment that distinguishes between the two and while, you know, be turns out to be right, I'm all frustrated by buy you dinner and I said no, no, no, no. See. And then we go on from there, Right? That's that's what science is at its best. It's this process of using data in discussion. It's a human activity right To to to learn to have the truth unfold itself before us. On the other hand, there are there's another way that people have used science or thought about science as a as truth in and of itself, Right? This like if it's if it's science, therefore it's true automatically and there, you know, what does the science say to do? Well, the science never says to do anything the science says, here's what's true and then we have to apply our human values to say, okay, well, if we do this, well, this is likely to happen. That's what the science says. If we do that, then that is likely to happen. Well, we'd rather have this than that, right? And but it doesn't, science doesn't tell us that we'd rather have this than that is the human values that tell us that we'd rather have this than that Science plays a role. But it's not the only thing, it's not the only role. It's it's like it helps understand the constraints we face, but it doesn't tell us what to do in face of those constraints. </s><s>[INST] But underneath it at the individual level, at the institutional level it seems like um arrogance. It is really destructive. So the flip side of that, the productive things humility. So sort of um always not being sure that you're right, this is actually kind of Stuart Russell talks about this for a I research how do you make sure that ai super intelligent ai doesn't destroy us. You built in um a sort of module within it that it always doubts it's actions like it's not sure. Like I know it says I'm supposed to destroy all humans, but maybe I'm wrong and that maybe I'm wrong is essential for progress for actually doing in the long arc of history. Better. Not the perfect thing, but better and better and better and better. I mean, the question I have here for you is this this email so clearly captures some maybe Echo, but maybe a core to the problem. Do you put responsibility of this email of the shortcomings and failures on individuals or institutions, Is this? [/INST] No this is an institutional failure. Right. So um the NIH, so I've had two decades of NIH funding, I've sat on NIH review panels. The purpose of the NIH is what you said earlier, lex the purpose of the NIH is to support the work of scientists to some extent. It's also help to help scientists to direct scientists to work on things that are very important for public health, for the health of the public. Um so and the way you do that is you say, Okay, we're going to put you know, $50 million $70 million dollars on HIV or whatever it is. Right? And uh that pot of money then uh scientists compete with each other for the best ideas to to use it to address that problem. So it's essentially an endeavor to support the work of scientists. It is not in and of itself a policy organ. It doesn't say what public health policy should be for that. You have the C. D. C. And what happened during the pandemic is that people in the NIH were called upon to contribute to public health policy making and that created the conflict of interest you see in that email. Right? So now you have the head of the NIH in effect saying to all scientists, you must agree with me in the policy that I've recommended or else you're french. That is a deep conflict of interest. It's deep because first he's conflicted, he has this dual role as as as the head of the NIH supporter of scientific funding and then also inappropriately called to set or help set pandemic policy that should never have happened. There should be a bright line between those two roles. </s><s>[INST] Let me ask you about just Francis Collins. I don't know if you hadn't had a chance to talk to him on the podcast. I don't know if you maybe by chance gotten a chance to hear a few words. Um well, I have a kind of a question to that because a lot of people wrote to me quite negative things about Francis Collins and like I said, I still believe he's a great man, a great scientist. Um one of the things when I talked to him off mike, I bought the vaccine, the excitement he had about when we were recollecting when they first got an inkling that it's actually going to be possible to get a vaccine. Just he wasn't messaging just in the private or of our own conversation, He was really excited and why was he excited? Because he gets to help a lot of people. This is a man that really wants to help people. And there could be some institutional self delusion, the arrogance, all those kinds of things that lead to this kind of email, but ultimately the goal is, this is what I don't think people quite realize this. The reason you call your friend Japanese geologist, the reason there needs to be a devastating published takedown. He, I believe really believes that this could be very dangerous and it's a lot of burden to carry on his shoulders because like you said in his role where he defines some of the public policy, like, you know, depending on how he thinks about the world, millions of people could die because of one decision he make and that's a lot of burden to walk [/INST] with. Yeah, no, I think that's right. I don't think that he has bad intentions. I think that he was basically put was put or maybe put himself in a position where this kind of conflict of interest was going to create this kind of, this, this kind of reaction, right? The kind of humility that you're calling for is almost impossible. When you have that dual dual role that that shouldn't, you shouldn't have have as, as funder of science and also center of scientific policy. </s><s>[INST] I agree with everything you just said, except the last part, the humility is almost impossible. That humility is always difficult. I think, I think there's a huge incentive to, for humility in that position. Look at history. Great leaders that have humility, um, are popular as hell. So if you like being popular, if you like having impact legacy, uh these descendants of apes seem to care about legacy, especially as they get older and these high positions, like I think [/INST] the incentive for humility is pretty high. Thing is is like there's a lot that he has to be proud of in his career. I mean like the human genome project wouldn't have happened without him and he is he is he is a great man and a great scientist. But so it is tragic to me that his career has ended in this particular way. </s><s>[INST] Let me ask you a question about um my podcast conversation with him by way of advice or maybe criticism. There's a lot of people that wrote to me kind words of support and a lot of people that wrote to me respectful, constructive criticism. How would you suggest to have conversations with folks like that and maybe um I mean because I have other conversations like this, including I was debating whether to talk to uh Anthony Fauci he wanted to talk and so what kind of conversation do you have? I'm sorry to take us on a tangent, but almost from an interview perspective of how to inspire humility and inspire trust in science or maybe give hope that we know what the heck we're doing and we're going to figure this [/INST] out. I mean I think your I've had been now interviewed by many people um I think the the style you have really works well lex you have to, because you know, I don't think you're going to be ever an attack dog trying to go after somebody and force them to like, you know, so admit that they were wrong about or whatever about, I mean that's that I also actually find that form of journalism and podcasting really off putting, it's hard to watch </s><s>[INST] also, it's a whole lot of the tangent. Is that actually effective? I don't think so, do you want to ask Hitler? And I think about this a lot actually interviewing Hitler, I've been studying a lot about the rise in the fall of the third Reich, I think about interviewing Stalin, like I put myself in that mindset, like how do you have conversations with people to understand who they are? So that not so you can sit there and yell at them, but to understand who they are, so that you can inspire a very large number of people to be the best version of themselves and to avoid the mistakes of the past. [/INST] I believe that everyone that's involved in this debate has good intentions. They have, they're they're coming at it from their points of view. Uh they don't, they have uh they have their weaknesses and if you can paint a picture in your questioning by sympathetic questioning of those strengths and weaknesses and their point of view, You've done a service. Um and that's really all you, I personally, like, like to see in those kinds of interviews. Um I don't think a gotcha moment is really the key thing there. The key thing is understanding where they're coming from, understanding their thinking, understanding the constraints they faced and how do they manage them? That's going to provide a much, I mean to me that's what I look for when I when I listen to podcasts like yours um is an understanding of that, of that, of that person and the moment and how they dealt with it. </s><s>[INST] I mean, I guess the hope is to discover in a sympathetic way a flaw in a person's thinking together. Like as opposed to discovering the positive things together, you discover the thing where I didn't really think [/INST] about that. Yeah, I mean, that's what that's how science is, right? That that's why we find it. I think find it so attractive. Is this? I I like it when a student shows me I'm thinking incorrectly, right? I think I'm really grateful to that student because now I have an opportunity to change my mind about it and then start thinking of it more correctly. I mean that's and there are moments when I mean like this is probably a good time to say like what I think I got wrong during the pandemic, right? So like for instance, you said Francis Collins had a moment when he learned that that there was quite possible to get a vaccine going. He must have learned that quite early and I didn't learn that early. I mean, I didn't know in March of 2020 in my experience with vaccine development, it would take, I thought it would take a decade or more to get a vaccine that was wrong. Right? I didn't know that that. And and I was so happy when I started to see the preliminary numbers in the in the fighter trial that strongly suggested it was going to work. </s><s>[INST] Yeah. And [/INST] I mean like very few times in my life and so happy to be </s><s>[INST] wrong and it changes kind of um, I think I've heard you mention that a lockdown. This is still a bad idea unless the vaccine comes out and like tomorrow, uh, there's still like suffering and economic pain, all kinds of pain can still happen. And even just a scale of weeks versus months. [/INST] Yeah. </s><s>[INST] Well, let's talk about the vaccine. What are your thoughts on the safety and efficacy of Covid vaccines at the individual and the societal [/INST] level. So for the vaccine safety data, um, it's, it's actually challenging to convey to the public how this is normally done. Like normally you would do this in the context of the trial. You'd have a lot, a lot a long trial with large numbers, relatively large numbers of people. You follow them over a long time and the trial will give you some indication of the safety of the vaccine. And it did. I mean, but the trial, the way it was constructed when it was came out that it was protective against covid, it was no longer ethical to have a placebo arm. And so that placebo arm was vaccinated what a large part of it. And so that meant that from the trial, you're not going to be able to get data on the long term safety profiles of the vaccine. Uh, and also the other thing about trials though, there's tens of thousands of people enrolled. That's still not enough to get when you, when you deploy a vaccine to the pop population scale, you're going to see things that weren't in the trial guaranteed populations to people that weren't represented well in the trial are gonna gonna be given the vaccine and then that they're going to have things that happen to them that you didn't didn't anticipate. So, um, I wasn't surprised when people are a little bit skeptical when the trial was done about the safety profile is just the way the nature of the thing was going to make it so that it was gonna be hard to get a complete picture from the trials itself and the trials showed they were pretty safe and quite effective at preventing both you from getting covid. Actually, I think the main endpoint of the trial itself was a symptomatic covid. Right? So, um, so that was like that was, you know, I mean, it was really um, to me like it's about as amazing achievement as anything organizing a trial of that scale and running it so quickly </s><s>[INST] and the final result being so surprisingly high. [/INST] So good. Right. </s><s>[INST] Yeah. And um [/INST] so the but the problem then was normally it would take a long time. The FDA would tell fighter to go back and try it in this subgroup. They work more on dozing, They do all all these kinds of things that kind of didn't we really didn't have time for in the middle of a pandemic. Right? So you have a you have a basis for approval that it's less full than normally you would have for a population scale vaccine. But the results were good results looked really good. And actually I should say for the most part, that's been borne out when we've given the vaccine at scale in terms of protection against severe disease. Right? So people who have got the vaccine for a very long time after that, they had the full vaccination have had great protection against going being hospitalized and dying. If they get covid, </s><s>[INST] let's separate because this seems to be um there's critics of both categories, but different kids And kids and old, not older people like uh let's say five years old and above or something like they're 13 years old and above. So uh for those, it seems like the reduction Of the rate of fatalities and serious illness seems to be something like 10 x. [/INST] I mean for older people it is a godsend this vaccine, it transforms the problem of focus protection from something that's quite challenging possible I believe are quite challenging into something that's much much more manageable because the vaccine in and of itself when deployed in older populations is a form of focus protection. </s><s>[INST] Yes. Well, by the way we'll talk about the focus protection in one segment because it's such a brilliant idea for this pandemic of a future pandemics. I thought the sociological psychological discussion about the letter from Francis Collins is um because it was so recent, it has been so troubling to me. So I'm glad we talked about that first. But so that there seems to be the vaccines work to reduce deaths and that has especially the most transformative effects for the [/INST] older. So let me give you, I've told you one thing that I got wrong in the pandemic. Let me tell you the second thing I got wrong for sure. In the pandemic in january of this year, 2021 I thought that the vaccines would stop infection. Right. It would it would make it so that you were much less likely to be infected at all because the the antibodies that were produced by the vaccines look like they're neutralizing antibodies that would would essentially block you from being infected at all. Um that turned out to be wrong. Right. So I think it and it became clear as data came out from Israel which vaccinated very early that they were seeing surges of infection even in a very highly vaccinated population that that that that the vaccine does not stop infection. </s><s>[INST] So your used car salesman and you're selling the vaccine and the features you thought a vaccine would have. I mean I have a similar kind of sense when the vaccine came out, vaccine would reduce, if you somehow were able to get it it would reduce rate of death and all those kinds of things. But it would also reduce the chance of you getting it. And if you do get the chance of you transmitting it to somebody else. And it turns out that those latter two things are not as definitive or in fact, I mean, I don't know to what degree they're not. [/INST] I mean I think I think it's it's a little complicated because I think the first two or three months after you're fully vaccinated after the second dose Um you have uh 60, efficacy peak against infection. So that which is pretty good. I mean right. But by 678 months that drops to 20%. Some some places, some studies like there's a study out of Sweden suggestion might even drop to zero. </s><s>[INST] But and then you're also infectious for some period of time if you do get it even though you're vaccinated. Although there seems to be lucy data that the period of time you're infectious is [/INST] short is shorter. But the the infectivity per day is about as high. So you still it's the point is that that the the vaccine might reduce some risk of infecting others, but it's not a categorical difference. So unvaccinated. It's not safe to be in the presence of just vaccinated people. You can still get infected. </s><s>[INST] Right. So, I mean there's a million things I want to ask here, but is there in some sense because the vaccine um really helps on the worst part of this pandemic which is killing [/INST] people. Yes. </s><s>[INST] Doesn't that mean where does the vaccine hesitancy come from in terms of it seems like obviously a vaccine is a powerful solution to let us open this thing [/INST] up. Yeah. So I wrote a Wall Street Journal op ed with Sinatra Gupta in december of last year. A very night with a very naive title which says we can end the lockdowns in a month. And the idea is very simple vaccinate all vulnerable people and then open up, open up right now. And the idea was that the lockdown harms is related. This is directly related to Great Barrington Declaration. Great banter collection said the lockdown harms are devastating to the population at large. There's this considerable segment of people that are vulnerable, protect them. Well with the vaccine we have a perfect tool to protect the vulnerable, which is I still believe, I mean it is true, Right? You vaccinate the vulnerable. The older population and as you said, it's a 10-fold decrease in the mortality risk um, from getting infected, which is, I mean, amazing. So that was the strategy we we outlined. What happened is that the vaccine debate got transformed. So, 1st, 1st there's there's so you're asking about vaccine hesitancy. I think there's there's first, there's like there's there's the inherent limitations of how to measure vaccine safety. Right? So we we talked about a little bit about the trial, but also after the trial, there's a there's a there's a mechanism and this work I've been involved with before. Covid on on tracking and identifying and checking whether vaccines actually are safe. And the central challenges one of causality. So you no longer have the randomized trial, but but but you want to know is the vaccine when it's deployed at scale causing adverse events. Well, you can't just look at people who are vaccinated and see what adverse events happen because you don't know what would have happened if the person had not been vaccinated. So you have to have some control group. Now, what happened is there's several systems to do to check this in that the CDC uses 11 very, very, very commonly known one now is called there's the vaccine adverse event reporting system there anyone who has an adverse event that either either regular person or a doctor can just go report, look, I had the vaccine and two days later I had a headache or whatever it is that the person died a day after that. The vaccine right? Um Now you're vaccine that the vaccine was rolled out to older people first. And older people die sometimes with or without the vaccine. So sometimes you'll see someone's vaccinated into a few days later. They die. Did the vaccine causes or something else? Cause It's really difficult to tell in order to tell you need a control group two for that. Um There are other systems the FDA and CDC have like there's one called VSD vaccine safety datalink. There's another system called best. I forget the where the acronym is to essentially to track uh cohorts of people vaccinated versus unvaccinated with as careful and matching as you can do, it's not randomized and see if you have safety signals that pop up in the vaccinated relative to the control group unvaccinated. Um And so that's for instance how the the myocarditis risk was picked up in young, especially young men. It's also how the higher risk of blood clots in middle aged and older and older women in with the J and J vaccine was picked up there. What you have is our our situations where the baseline risk of these outcomes are so low that if you see them in the in the vaccinated arm at all, then it's not hard to understand that the vaccine did this right? Young men should not be having myocarditis middle aged women should not be having huge blood clots in the brain, Right? Um, so when you see that, you can say it's linked now the rates are low. So young men, maybe one in 5001 in 10,000 of the vaccine, vaccine related myocarditis pericarditis. Um, young women of middle aged women, I don't know. I don't I'm not sure what the right number might be, but like I'd say it's like in the one in hundreds of thousands, something like that. Um, so these are rare outcomes. But there there there are vaccine linked outcomes. How do you deal with that as a messaging thing? I think you just tell people, you tell people here are the risks transparently tell them and just you're not, you're not there. So they're not getting into something that they don't know </s><s>[INST] and don't treat people like they're Children and need to be told lies because they won't understand the full complexity of the truth. People I think are pretty good at or actually, you know, people with time are good understanding data, but better than anything there there are better at. They're extremely good at detecting arrogance and bullshit and give them [/INST] either one of those? I mean, I'll give you one that's where I think it's greatly undermined vaccine has great, greatly undermined the demand for the vaccine is this weird denial that if you are recovered from covid you have extremely good immunity both against infection and access And that denial leads to people distrusting the message given by like the CDC director for instance, in favor of the vaccine. Right? Why would you deny a thing? That's such an obvious fact. Like you can look at the data and it's just, I mean just just pops out at you that people that are Covid recovered are not getting infected again at very high rates, much lower rates </s><s>[INST] after these kinds of conversations. Um, I'm sure after this very conversation I often get a number of messages from joe joe Rogan and from Sam Harris, Who to me are people I admire, I think are really intelligent, thoughtful human beings. They also have a platform and I believe at least in my mind about this covid set of topics they represent a group of people. Um, right. Each group has smart, thoughtful, well intentioned human beings and I don't know who is right, but I do know that they're kind of tribal a little bit uh, those groups. And so the question I want to ask is like, what do you think about these two groups and this kind of tension over the vaccine. Um, that sometimes it just keeps finding different topics on which to focus on like whether kids should get vaccinated or not, whether there should be vaccine mandates or not, which seemed to be often very kind of specific policy kinds of questions that it's the bigger [/INST] picture. I think it's a symptom of the distrust that people have in public health. I think this kind of schism over the the vaccine does not happen in places where the public health authorities have been much more trustworthy. Right? So you don't see this vaccine hasn't seen Sweden, for instance. Um, what what's happened in the United States is the vaccine has become, um, uh, first because of politics, but then also because of the scientific arrogance. This sort of Touchstone issue and people line up on on both sides of it and the different language you're hearing is structured around that. So, before the election, for instance, I did I was I did a testimony in the house on on measurement of vaccine safety. And I I was I was invited by the republicans. There were, I think of four other experts invited by the democrats. With three other experts invited by democrats, each of whom had a lot of experience in measuring vaccine safety. I was really surprised to hear them each doubt whether the FDA would do a reasonable job in assessing vaccine safety, including by people who have long records of working with the FDA. I mean, these are professionals, great scientists whose main goal in life is to make sure that safe vaccine that unsafe vaccines don't get released into the world. And if they are they get pulled and they were casting down on the vaccine, the ability to track vaccine safety before the election and then after the election, the rhetoric switched on a dime, right? All of a sudden it's republicans that are cast as if they're vaccine hesitant, that kind of political shift the public notices if if all it takes is an election to change how people talk about the safety of the vaccine. Well, we're not talking science anymore. Many people think, right? I think that creates created its hesitancy. The other thing, I think the the hesitancy some politicians viewed it as a political as sort of like a political opportunity to sort of demonize people who are hesitant and that itself fueled presidency, right? Like the if you're if you're telling me, I'm a rube that just doesn't want the vaccine because I want everyone to die. Well, I'm gonna I'm gonna react really negatively. And if you're talking down to me about my legitimate, you know, sort of concerns about whether this vaccine safety time, you know, I've heard from women who are thinking about getting pregnant. Should I take the vaccine? I don't know. I mean, there are all kinds of questions, legitimate questions that I think, um, should have good data to answer that we don't necessarily have a good day to answer. So what do you do in the face of that? Well, one reaction is to pretend like we know for a fact that it's safe when we don't have the data. And I know for a fact in that particular group with that particular set of clinical circumstances, you know, and that I think breeds hesitancy, people can detect that bullshit. Um, whereas if you just tell people, you know, I don't know. Yeah. Leave it with humility. Yeah. You've got to you, you will end up with a better result. </s><s>[INST] Let me ask you about, I've recently had a conversation with the fighter ceo this is part therapy session. Part advice because again, I really want us to get through this together and it feels like the division is a thing that prevents us from getting through this together. And once again just like with Francis Collins, a lot of people wrote to me awards of support and a lot of people wrote to me words of criticism. I'm trying to understand the nature of the criticism. So some of the criticism had to do with against the vaccine and those kinds of things that I have a better understanding of. But some kind of deep distrust of fighter. So um, actually looking at big farmer broadly, I'm trying to understand. Am I so naive that I just don't see it because yes, there's corrupt people and they they're greedy. They're flawed in all walks of life. But companies do um, quite an incredible job of taking a good idea at the scale and making some money with that idea. But they are the ones that achieve scale on a good idea. I don't know. It's not obvious to me. I I don't see where the manipulation is. So the fear that people have. And I talked to joe about this quite a bit. I think this is a legitimate fear. And and and the theory should often have that money has influenced disproportional influence, especially in politics. So the fear is that the policy of the vaccine was connected to the fact that lots of money could be made by manufacturing the vaccine. And I understand that and I'm it's actually quite a heck of a difficult task to alleviate that concern. Like you really have to be a great man or woman or a leader to convince people that you're not full of ships that you're not just playing a game on them. I don't know. It's a it's a difficult task. But at the same time, I really don't like the natural distrust every billionaire distrust everybody who's trying to make money because it feels like under a capitalistic system, at least the way to do a lot of good at like you do good at scale in the world is by being at least in part motivated by [/INST] I mean, I share your ambivalence. Right? So on the one hand, you have a fantastic achievement. The the the manufacturer of the discovery of the vaccine and then the manufacturing at scale so that, you know, billions of people can take the vaccine in a relatively short time. That is a remarkable thing that could not have happened without companies like Fizer. Um On the other hand the there is this sort of corrupting influence of that money. Uh Just to give you one example, there's a there's an enormous controversy over whether relatively inexpensive repurposed drugs can be used to treat the the disease. None of no company like fighter has any interest whatsoever in evaluating it. Even Merc, I think it was mark that had the patent on, I've checked in now expired has no interest at all in checking to see if it works. </s><s>[INST] Not only do they not have interest, they have a way of talking about people who might have a little bit of interest. That's again uh uh full of arrogance and that that is what troubles me is they're not it's back to the play of science. It's not they're not a bit of curiosity. One okay one the natural curiosity of a human being that should always be there. And an open mind is. And second in the case of Ivermectin and other things like that, you have to acknowledge that there's a very large number of people who care about this topic and this is a way to inspire them to also play in the space of science to inspire them with science. You can't just dismiss everybody that you can't just dismiss people period. [/INST] Yeah. Well I mean I think here here take some action, right? There's actually a study funded by the NIH by Tony Fauci's N. I. I. D. And the NIH Um called Active six. That's a randomized trial of irony. It's due to be completed in March 2023. Mhm. So normally when you have uh private actors like these big drug companies that have no interest in conducting some kind of scientific experiment that would have some public benefit. It's the job of the of the government and in this case the NIH to fund that kind of work. The NIH has been incredibly slow in its evaluation of these repurposed drugs and it's been left to lots of other private private private activities of uneven quality. And hence that's why you have these big fights because the data are not solid, You're going to have these big fights. </s><s>[INST] But also, okay, forget the process of science here. The studies not enough effort being put into the studies. Just the way it's being [/INST] communicated about. Yeah, no like this horse paste. I mean, come on the FDA put a tweet out telling people who are like they're taking Ivan mexican because they've heard good things about it and they're sick and they're desperate and just call it horse paste was just that was that was terrible. </s><s>[INST] That was deeply responsible. My my hope is grounded in the fact that young people see the bullshit of this young PhD students, graduate students, young students in college, they see the less than stellar way that our scientific leaders and our political leaders are behaving and then the new generation will not repeat the mistakes of the past. That is my hope because uh that that's the cool thing I see about young people as they are good at detecting bullshit and they don't want to be part of that. Um That's my hope in the space of science. Let me return to this idea of the Great Barrington Declaration, Return to the beginning. So um what are the basics? Can you describe what the Great Barrington Declaration is? What are some of the ideas in it? You mentioned focused protection. What are your concerns about lockdowns? Just paint the picture of this early proposal. [/INST] Sure. So the Great Barrington Declaration 1st, Why is it called Great Barrington Declaration? </s><s>[INST] It sounds it's such a great name. You know, I mean it's just it's such an epic name, but the reason why it's called that is way less than epic. [/INST] It's it was it was because the conference which is organized by martin cold Orf who was a professor at Harvard University by biostatistician. He actually wants the designed the safety system, the statistical system that the FDA uses for tracking vaccine safety. He and I had met previously just the summer before that summer. Um and he invited me to come to this small conference where he was inviting me and Sinatra Gupta who is a professor of theoretical epidemiology at Harvard Driving at Oxford University and um I mean I jumped at the chance because I knew that martin and Sinatra were both smarter than me and it would be fun to like talk about what, what the right strategy would be on the drive in. I didn't know what the name of the town was and I asked, they said it was Great Barrington, I had in the back of my head um, Martin and I arrived a little early and we were writing an op ed about some of the ideas, hopefully we have to talk about very soon um about focus Protection and the right strategy. And uh when Sinatra arrived, we realized we'd actually come basically to the same place about the right way to deal with the epidemic. Um and I I thought, well why don't we put issue? Why don't we write something like the porch here in statement. That was what I had that in the back of my head and I'm like, well, what's the name of this town again? It was Great Barrington. </s><s>[INST] So it's not Barrington, it's great [/INST] barrier, which is </s><s>[INST] fantastic. It's so over the top that is perfect. It's it's literally like the big bang. There's something about these over the top fun titles that just really deliver them. [/INST] So that's my, that's my, my main contribution with the work is the title, the name. Great Barrington Declaration. Um But yeah, so it was, it was kind of so the and the the idea is actually, while the title is great. Um and I think that it was written in a very stylish way. Um It's you know like it's a good it's less than a page and you can go look online and read it. It's written written for not for scientists but for the general public so that people can understand the ideas really simply. Um But it is not actually a radical set of ideas, it actually represents the old pandemic plans that we've used for century dealing with other similar pandemics. And it's two fold. Uh Well first let me talk about the science that restaurant and then I'll talk about the plan. Uh The science actually some of them we already talked about there's this massive age gradient in the risk of covid infection. Older people face much higher risk than younger people. Um the second bit of science is all that's not controversial right? That even if you think the fr is .7 or or or point to no matter what if everyone thinks everyone agrees on this age gradient. The second bit of science is also not controversial. The lockdown focus policies that we followed have absolutely devastating consequences on the health of the population. Mhm. Let me just give you some examples And this is this was known in October of 2020 we wrote it right? So um the U.N. was sounding alarms that there would be tens of millions of people who would starve as a consequence of the economic dislocation caused by the lockdowns and that's come to pass hundreds of thousands of Children in places like South Asia dead from starvation as a consequence of lockdowns. Um the the the the the uh priorities like the treatment of patients with tuberculosis in poor countries stopped because of lockdowns, uh childhood vaccinations of measles, mumps, rubella, dpt, you know, diptheria, so on pertussis, tetanus, all those standard vaccination campaigns stopped tens of millions of Children skipping these doses for diseases that are actually deadly for them. </s><s>[INST] Is there just on a small tangent? Is it well understood to you? What are the mechanisms that stop all those things Because of lockdowns? Is it's some aspect of supply chains, It's just literally because hospital doors are closed. Is it because there's a disincentive to go outside by people even when they deeply need help, [/INST] it's all of the above. But a lot of those efforts, like especially like vaccination efforts are funded and run by Western efforts, like Gabby is a I think it's a gates funded thing actually that provides provides vaccines for, you know, millions of kids worldwide. And those efforts Were scaled back malaria prevention efforts. So in the, in the developing world it was a devastating effect. These lockdowns. Um there's also direct effects like in India the uh the lockdowns when they first instituted, there was an order that 10 million migrant workers Who live in big cities and they live hand to mouth. They they buy, you know coconuts, they sell the coconuts with the money, they buy food for themselves and coconuts for the next day to sell. Um walk back to their villages or get or or go back to their villages the overnight, so 10 million people walking back to their villages or taking a train back. 1000 died en route, overcrowded trains dying essentially on the side of the road. I mean it was, it was absolutely inhumane policy. Uh and the lockdowns there, what, what, it's actually, it's kind of like what's happened in the west as well, but it's it was so severe. Uh there was a zero prevalence study done in Mumbai by a friend of mine at the United Chicago. What he found was that in the slums of Mumbai There were 70% Syrah prevalence in July or August seven of 2020, whereas in the rest of Mumbai was 20%. Yeah. Right, so it was incredibly unequal the lockdowns protected the relatively well off and spread the disease among the poor. Um So that's in the developing world, In the developed world, the health effects of lockdowns were also quite bad. Right? So we talked already about isolation and depression. There was a study done in July of 2020 that found that one in four young adults seriously considered suicide. Now, suicide rates haven't like spiked up uh so much, but the depths of despair. That would lead somebody to seriously consider suicide itself should be should be a source of great concern for public health. </s><s>[INST] Yeah, this is one of the troubling things about measuring well beings, we're okay at measuring death and suicide. We're not so good at measuring suffering. It's like people talk about um, maybe even holiday holiday more in the under Stalin or the concentration camps with Hitler. We talk about deaths, but we don't talk about the suffering over periods of years by people living in fear by people starving, psychological trauma that lasts a lifetime, all of those things. [/INST] I mean, and just to get back to that, that point, we closed schools, especially in Blue States, we closed schools. Now, richard parents could send their kids to private schools, many of which stayed open. Even in the Blue States, they could get pods, they could get tutors, but that's not true for for poor and middle class parents. And as a result, what we did is we took away life opportunities for kids. We tried to teach five year olds to read via Zoom in Kindergarten, right? Uh and the consequence actually, you think, okay, we can just make it up. But it's really difficult to make that up. Um there's a literature in health economics that shows that even, uh, you know, relatively small disruptions in schooling can have lifelong consequences, negative consequences for kids, right? So they end up growing up poorer, they lead shorter lives and less healthy lives as a consequence. And that's and that's what the literature now shows is likely to happen with the interruptions of schooling that we had in the United States and many european countries actually managed to avoid this. There were in the early days of the epidemic, great indications that Children first, we're not very severe severely at risk from covid itself, nor are they super spreaders. Schools were not the source of community spread. Community spread, spread the disease to school is not the other way around. Um And if we can talk about the scientific basis that if you'd like, but that was pretty well known even in october um and that we we we closed hospitals in order to keep them open, like available to to covid patients. But as a result, women skipped breast cancer screening as a result, they have are showing up with late stage breast cancer that should have been picked up last year. Men and women skipped colon cancer screening again with later stage disease. That should have been picked up last year with earlier stage for patients with diabetes. It's very important to have regular screening for blood sugar levels. Um and and and sort of counseling for lifestyle improvement. And we skip that. People stayed home with heart attacks and died at home with heart attacks. So you have this like sort of wide range of medical and psychological harms that were being utterly ignored as a result of the lockdowns. </s><s>[INST] Plus there's the economic pain. So like you said, the whatever is a good term for the non laptop class, people would lose their jobs. Yes, there might be in the in the Western world support for them financially. But the the big loss there that is perhaps correlated with the depression and suicide is uh loss of meaning, loss of hope for the future, loss of kind of a sense of stability, all the pride you have and being able to um make money that allows you to pave your own way in the world. And yes, just having less money than you're used to. So your family, your kids are suffering all those kinds of things. And [/INST] There's a there's like again the economics literature on this on deaths of despair. It was called 2009. There was the Great Recession. It led to an enormous uptake in overdose from drugs, uh suicidality depression as a result of the job losses that happened during the great recession. Well, that's happening again, like an enormous increase in drug overdoses. That's not that's not an accident, that's a lockdown harm. Right. Same. Same thing with with the the job losses. The job losses by the way are like, it's so interesting because the um the states that stayed open have had much much lower unemployment than the states that stayed closed The labor force participation rates declined by 3%. It's women that separated because they they stayed home with their kids. Um we've reversed a generation of women uh, when in improving women's participation in the labor force. </s><s>[INST] Do you think? Um it has to do with the institutions that we mentioned that there was so much priority given or so much power given to maybe NIH versus um other civilian leaders? Or do people just not care about the economic pain the leaders? I mean, because to me it was obvious. I mean probably is just studying history whenever I listen to people on twitter on mainstream news or just anything I realized that's the very kind of top the people that have a voice represent a tiny selection of people. And so whenever there's hard times, I always kind of think about the quiet, the voiceless, the quiet suffering of the tens of millions of the hundreds of millions um due to political leaders not just give a damn. [/INST] I mean, I think it was actually a very odd ethical thing at the beginning of the pandemic, where if you brought up economic harms at all, you were seen as callous, right? So, I I had a reporter call me up almost the very beginning of the epidemic asking me about about about uh uh like a very particular phenomenon. So like he he was anticipating a rise in child abuse because Children are gonna be staying at home, child abuse is generally picked up at school. And that actually happened. Like so like the child reported child abuse dropped, but actual child abuse increased. Um because normally pick up the child abuse at school and that you have, you have an intervention. Right? So yeah, I sort of started talking about like, well there's gonna be some economic harms and they're gonna have health consequences, but the economic harms matter, but the but he canceled me and I think he was he was he had my best interest at heart. Like if if you were to put that in the story, I would be essentially be canceled Because the what the what the the narrative that that arose in March of 2020 is if you if you care about money, at all. you're evil and craft, you must only care about lives. The problem with that narrative is that that money, what we're talking about is is actually lives of poor people, right? When you throw 100 million people around the world into into poverty, you're going to see enormous harm to their health, enormous increases in their in their immortality. It's not immoral to think about that and worry about that in the context of this pandemic response, our mind focused so much on Covid that it forgot that there are so many other public health priorities as well that need our attention desperately. </s><s>[INST] And this is the thing I since the about san Francisco when I visited I was thinking of moving there for a startup. This is the thing I'm really afraid of, especially if I have any effect on the world through a startup is losing touch in this kind of way that you mentioned the laptop class, um living in this world, where you're only concerned about this particular of class of people. And also uh you know, perhaps early on in the pandemic, amongst the laptop class, there was a legitimate concern for health. Like, you're not sure how deadly this virus is, that you don't you're not sure who to listen to. So, there's a real concern. And then at a certain point when the data starts coming in and you start becoming more and more detached from the data, you don't start carrying less and less and you start just swimming in the space of narratives like existing in the space of narratives. And you have this narrative in san Francisco in the laptop class, that you're just a very uh proud that you know, the truth, you're the sole possessors of the truth. You congratulate yourself on it and you don't care what actually gigantic detrimental effect that has on society, because you're mostly fine that I'm so terrified of that. [/INST] Well, actually, I think the antidote that is just to remember, </s><s>[INST] you remember [/INST] Yeah, I don't think you remember where you came from and remember who you who you're doing this for at the back of your head should always be what's what's the purpose? Like why why am I here with the purpose of this? And if if I'm if the purpose is simply uh self aggrandizement, then you should rethink because it's just end up being a hollow life. </s><s>[INST] All of us will be forgotten in the end. Focus protection. The idea the policy, what is focused protection. [/INST] Right? So that as I was saying that there's two scientific bases, right? So one is this this steep age gradient and the second is the existence of lockdown arms. Again, I think there's very little disagreement and the scientist can be both of those facts. Um if you put those facts together, the obvious policy is to protect the people who are at the most severe risk from the disease itself. And that's the idea of focus protection. That's the general principle of it. The actual implementation of it depends on the living circumstances of the people that are at risk. The resources are available in the community, the the the technology is available to do this. And so it's almost always going to be in fact, it will always be a local thing because it'll depend on the all of those those things which are all local in nature. Right? So one very, very obvious thing in a in a in a country like ours where so many older people live in institutionalized settings and nursing home settings and that's where older, really vulnerable chronically ill patients often live. It is and you know, this disease affects that group most like most most commonly. It is absolutely vital to protect that group. Um we should have known that in February 2020 from just from the Chinese data and that we should have thought about that group as the, as the, as the key constraint in our policy making. Um instead we thought about in February and March 2020 as hospital beds as the key constraint hospital beds and ventilator shortages. And that we, so we we ran around trying to like address that constraint, you know, like a linear programming problem, you figure out what the which constraints binding and you address that one thing and then go on to the next one, right? Um, it's that it's that one constraint. We said, okay, the constraint is hospital beds. That led to the decision in many of the Northeast states to send covid infected patients who were on the on the verge of or like it looked like they were about to recover back to nursing homes who then spread the disease all through there because they wanted to preserve the hospital beds. </s><s>[INST] Well, for somebody who loves the miracle optimization. I love the way you frame this. Uh but those are kind of connected, right? If you actually focus on protecting the vulnerable, you will also have the effect of not hitting the ceiling of the available. [/INST] That's that's the irony if we protected the vulnerable of the vulnerable, the most likely to be hospitalized. And so by protecting the hospital about protecting the vulnerable, we will also have addressed the shortage of hospital that's more effectively. </s><s>[INST] So that little shift in priority would have had a big impact. Okay. But specifically the idea is to, and we can talk about different ideas of how to actually do this. But you know, you basically do a lockdown or something like that on a very small set [/INST] of, I mean you may have to do that if it's community spread is very high, but generally I think it would depend on again the living circumstances in the so so for instance, um if you are in a if you have uh here's a very simple idea that doesn't require a lockdown for forced on them. And I I don't actually generally not in favor of that kind of forced lockdown because you just won't get cooperation. Um but what you could do is provide resources to that group of people. So like imagine you live next door to somebody uh an older couple. Um and it's this high community spread. Well they have to go grocery shopping. Um We did like some of these, some communities did these like senior only grocery our right, but but they have to still have to go out and they might get exposed in when they're shopping amongst other seniors. Well why not organized home delivery of groceries to them. We did that for the laptop class, right? Or you can even just as a volunteer effort, You know, the older people living next door, just call them up and say kind of help you get, go out and go </s><s>[INST] shopping for you. And so you would have potentially federal support of that kind of thing. So these kinds of efforts [/INST] and identify where they're vulnerable people live. It's really challenging in multigenerational homes in La County, for instance, there's a lot of, of older people living together with younger people in relatively crowded there there, there, there, it's really quite a challenge. But there again, you can use resources. So if grandma uh, is worried that grandson has come home but is potentially being exposed, grandson calls grandma says, I mean, I might have been at a party where I might either, where covid was grandma calls public health, public health and says, okay, you can have this hotel room for a couple of days until you check turned </s><s>[INST] negative in case it wasn't clear. The idea of focus protection is the people that are vulnerable, protect them and everybody else goes on with their lives. Open up the economy, just do as it was before. [/INST] And there was still fear abroad. So there still would be some restrictions people would pose on themselves. They probably would go to parties. Last grandsons probably wouldn't go so many parties, right? Um, uh, that there would be less, less participation in big gatherings. Uh, and you may even save like big gatherings in order to, to restrict community spread again, I'm not against any of that. Um but you shouldn't be closing businesses, you shouldn't be closing churches and synagogues, you shouldn't be closing, you shouldn't be forcing people to not go to school. You should, you should not be shuttering businesses, You should just let just allow society go on some disease will spread. But as we've seen the lockdown didn't stop the disease from spreading anyways. </s><s>[INST] Right? So what do you make of the criticism that this idea, like all good ideas cannot actually be implemented in a heterogeneous society where there's a lot of people inter mixing and once you open it up, people like that, the younger people will just forget that this is even existing and they'll stop caring about the older people and mess up the whole thing and the government will not want to fund and you kind of the great efforts you're talking about, about food delivery and then the food delivery services will be like, why the heck am I helping out on this anyway? Because like it's not making me much money and so therefore like all good ideas, it will collapse. [/INST] That might be true. I mean, I think it's always a risk with policy thing, but I think like think back to the moment, but we actually felt like we were in this together to some extent, right? I think I think that that um that empathy that we had that was used to like tell people to stay in and like happily not not going happily, but like stay in um to to like wear a mask or two to do all these things that we thought would help other people could have been redirected to actually helping the people who </s><s>[INST] most needed to be. Especially I do remember March. So this is even way, way before Barrington, all all that kind of stuff. March april may there was a feeling like if if we all just work together will solve this and that maybe started to, when did that start breaking down? I mean unfortunately the election is mixed into this that it became politicized but I think it lasted quite a long [/INST] time. I think into the summer. I think there was some, some, some of that sense. I don't know, obviously varied among different people but but I think that it's true. It would have been challenging. It's also true. That is heterogeneous exactly the way you said. Um But what that means is you need a local response a response. So like, like my vision of a public health officer is someone that understands their community, not not necessarily the nation at large but their community and then works within their community to figure out how to deploy the resources that they have available. Um to do, to do the kind of protection policies we're talking about. That's that's what should have happened instead. They spent a huge amount of efforts closing, making sure businesses stay closed businesses that I mean there are, you know, like hardware stores that closed. What good did it closing a hardware store do for the spread of Covid? If it has an effect on spread? Covid spread, I mean, it's going to be checking to make sure that plexiglass was put up everywhere, which now in retrospect, turns out to probably made the disease worse. You know, masking enforcement. So shaming around mask, I mean, a huge amount of effort on things that were only tangentially related to focus protection. What if we turned our energy, </s><s>[INST] that [/INST] enormous energy put into that instead into focus protection of the vulnerable. That's essentially the conversation I was calling for. And it wasn't I mean, I didn't think of it as we had every single idea. I mean, we gave some concrete proposals, but the criticism we got was that those concrete proposals weren't enough. And the answer to that I have is that's true. They weren't enough. I wasn't thinking of them as enough. I was thinking that I wanted to involve an enormous number of people in local public health to help think about how to do focus protection in their communities. </s><s>[INST] The question that's interesting here is about the future too. So Covid has very specific characteristics that you mentioned about the curve of the death rate based on the like it's it's uh it seems like with Covid it's a little bit easier to actually identify a group of people that you need to protect. Um So other viruses may not be this way. So might lockdown be a good idea. Like hardcore lockdown for future virus that's 10 times deadlier. But spreads at the same rate as Covid. Or maybe another way to ask that is imagine a virus that's 10 times deadlier. What's the right response? [/INST] I mean I think it's always going to be focused protection. But the group that needs the focus protection may change depending on the biology of the virus. Right? So the polio epidemic in the 40s and 50s in the us, the great people at most risk were Children. We didn't know really. At the beginning there was this vehicle oral spread. And so we did all kinds of crazy things um including like spreading spraying DDT and communities which was something I was supposed to get rid of polio. Um But the focus was on whenever there was an outbreak they would close the school down and that was the right thing to do because that group that needed protection where it was Children and those the disease was spread. We thought in schools, I don't think there's a single formula that works but there's a single principle that works right. No no matter I can't it's hard to imagine a disease that's uniformly deadly across every group and every single person there's always going to be some group that's differential e harmed, there's always gonna be some group that's differential protected. And that that may change over time. Right? So like the in the in this disease, in this epidemic, as people got infected and recovered, we now had a class of people that were pretty well protected against the disease. Mhm. They should be they would like, instead of ostracizing them because they don't want a vaccine, we should we should be allowing them to work. I mean, we're having staffing shortages in hospitals now because we forgot that principle </s><s>[INST] is um quite a bit of this technology problems. So being able to see some of how much of it is this sociological problem. How much of it's a technology problem. Like where do you put the blame sort of on why this didn't go so great and how it can go. Great in the [/INST] Beginning, I mean, think about lockdowns. Like if we didn't have zoom, we wouldn't have lockdowns. There's there's a reason in 2009 we didn't lock down. I mean, we didn't have the technology to replace work with this remote um this remote technology. </s><s>[INST] So we had good lockdown technology and zoom. We didn't have good focus protection technology. [/INST] Yeah. I mean, folks, protection is always going to be complicated, especially for something like this that spreads so easily. It's going to be complicated. And I'm I'm very I'm the last person to say it would have been perfect. There, there would have been people that would have gotten sick, but they got sick anyways. The hope was that if we suppress community spread low enough, we can protect the vulnerable. That was the hope by lockdown. The reality was that only a certain class of people were able to benefit from the rest of society. We call them essential workers had to keep working and they got sick and the disease kept spreading. It didn't actually have a substantial effect on the community spread in the, in in non laptop class populations. </s><s>[INST] And also we should probably expand the class of people would call vulnerable to those who would suffer, who who have the capacity to suffer given the policies there you're weighing, it's very disingenuous to call the vulnerable. Just the people. Obviously we had a very specific meaning, but broadly speaking vulnerable should include anybody who can suffer based on the policies you take in response to the [/INST] virus. Is something that that principle, what you just said is completely agree with is something I think has been lost ah and unfortunately lost. Right? So the policies themselves, if they have harm those are real and we shouldn't pretend like they're not and and and essentially demonize the people that that that suffer them or pretend. I mean like a lot of times like the depression that we've been talking about that's I thought of is like not not so important, but it is important. Uh, and especially the, the harm to the people in poor countries. It's like being out of sight out of mind in much of the rich parts of the world. </s><s>[INST] Once again, I have hope that we seeing this learning the lessons of history with the communication tools who have not well learned this. It's like going to another country and bombing targeted terrorist locations and there's going to be some civilians who die pretending that that the child who watches their dad die is not going to grow up. First of all traumatized, But second of all, potentially bring more hate to the world then uh, the hate that you're allegedly fighting in the first place. That's another sort of um considering only one kind of harm and not the full range of harms that are being caused by your policies. [/INST] You know, like the return to focus protection. We still should be following the policy now for Covid and we're not right. So the vaccines, There's a great shortage in vaccines. You wouldn't know it in the United States and the rich parts of the world. But there's a great shortage of vaccines. We're not going to be able to vaccinate the most of the like the entire set of elderly at least. And or or larger larger groups. Until late 2022 huge numbers of older people around the world in poor countries that have not had not Covid recovered yet. So they're still quite vulnerable. Have not had the vaccine and yet we're talking about vaccinating five year olds. Yeah. Who benefited if if at all from the vaccines of just a very little bit because they face such a low risk of harm from covid, </s><s>[INST] well, something that's a little bit near and dear to our specific the two of our hearts. So you're at stanford. So stanford recently announced that they're going back to virtual at least for some period of time in response to the escalade. Maybe you can clarify, but I think it's in response to the escalated, um how they phrase it related to a micron. And um a few other universities are kind of like uh considering back and forth in my perspective as somebody who loves in personal lectures, who um sees the value of that two students to young minds. Also looking at the data seems the risk aversion in university policies around this, given how healthy the student population is. It seems not well calibrated. Let's put it this way. Also pathological, pathological is one way to put it, given that I believe, depending on the university, but I think many universities require that the student body is vaccinated at this point. So I think it's a big mistake by stanford to do this. And um I'd like to say that because I just hope I might thi this isn't. But what are [/INST] your thoughts about you? I completely agree with you. I think um we have failed in our mission to educate our students by these. This decision. And I think I frankly, just more broadly, I think we failed generally over the course of the last year and a half in living up to our educational mission in person. Teaching is vital for now. I can understand you have if you have older faculty, the principal of Focus Protection says provide some alternative teaching arrangements for them. That makes sense to me from the kids point of view. There more harmed by not getting the education we promised them then by then by covid. So applying this principle of this focus protection let young professors teach in person. This is before the vaccine. After the vaccine. Let everyone teach in person. </s><s>[INST] Yeah, this this is the part I don't understand the discussion we're even having because um, okay, let's leave focus protection aside here because that's a brilliant policy for perhaps for the future when there's no vaccine. Now with the vaccine, I'm misunderstanding something here because we're now in the space. That's psychological not it's no longer about biology because with the booster shots, which I believe mitt is not requiring before january with the booster shots, the data shows no matter how old you are, the risks are very low for um ending up in a hospital relative to all the other risks you face when you're older. I don't I don't understand can you explain the policy around closing a university, but also just a policy about just being so scared still in the university setting. [/INST] I think the universities, the great university has done great harm by modeling this kind of behavior. Yes. </s><s>[INST] That to me decided to keep interrupting. But to me, the university should be the beacon of great behavior. Not, not the beacon of like scared conservative. Let's not mess up. Let's not make it pathologic. Let's not make anybody angry. Let's, it should be a place to play in the space of ideas. So I [/INST] think, um, the central problem is actually related to the central problem of covid policy. More generally, the goal seems to be to stop the disease from spreading rather than to reduce the harm from the disease. If the if the goal is to stop disease and spreading. The sad fact is we have no technology to stop to accomplish that </s><s>[INST] at this point. Yes, because like it's already deeply integrated into the human civilization. [/INST] Well, I mean, it's it's here forever. Right? There's a zero survey of white tailed deer in the us. It turns out 80% of white tailed deer in the us have covid antibodies, dogs get it. Cats get it. There's almost certainly human human animal transmission of it. I mean, presumably, I mean, I've heard bats get it apparently. Um, so, so you you have you have a situation where you have this disease is here to stay and, and the vaccines don't stop the spread of it. The lockdowns don't stop the spread it, we have no technology to stop the spread of it. Um, and so we're burning the earth trying to stop do something that's impossible rather than working on what's possible. And so like, you know, like letting regular college happened. That's a great good universities are a wonderful invention. The and and it's contributed so much to society. Just decided to shut it down. That the universities should be fighting tooth and nail to not be shut down. Not the other way around. </s><s>[INST] Whatever the mechanisms that results in the university's doing that, that's probably this is me talking. It probably has to do with certain incentives for the administration probably has to do with lawyers and legal kinds of things that to avoid uh legal trouble. But once again, it's when the administration has too much power and too much definition of what the policy is for the university. That's when you get to trouble. The beauty, the power of the university should be about the faculty and the students administration just gets in the way. [/INST] Get out of the way. I mean, they can help organize things. They play some important role, but they certainly do what they need to remember what the mission is. The mission is not safety. The mission. Actually, universities should be dangerous places, you know, for ideas and whatnot. </s><s>[INST] What is the role of fear in a pandemic? We've been dancing around it. Is it useful? Is it destructive or is there sort of a complicated story here because instead of taking us back into January 2020, there was so much uncertainty. This could have been a pandemic. That um is black death, the bubonic plague. It could have killed hundreds of millions of people. We don't know that we're very new to this. It's been a while, we're rusty. So like there is, there is some value to fear so that you don't do the stupid thing. You don't just go on living. [/INST] I guess where I come from. I think it's almost entirely counterproductive. I think fear should never be used as a tactic to manipulate human behavior by public </s><s>[INST] health. So the fear on the individual level that feeling of fear, you should be very hesitant about that feeling because it could be easily manipulated by the powerful. Exactly. So I [/INST] think um that fear is natural and it's uh it's not something that you have to, you have to, you have to stoke to get when the facts on the ground suggested right? In fact, the tendency for humans in the in the face of threats from infects disease is to is to exaggerate the fear in their own minds of the, of being contaminated by the environment and by others. That's just natural to humans and the role of public health is not necessarily to eradicate the fear, but like obviously technological advances can help eradicate the fear, but like, but it's really to help manage that fear and and help people put the sort of incentives that come out of that too useful things as opposed to harmful things. What's happened in this pandemic is that there's been a deliberate policy to stoke the fear. To help make people think that the disease is worse than it actually is in survey after survey, you see this and that's been incredibly damaging. So young people have readily given away their willingness participate in regular life because A they fear covid more than they ought and B, they fear that they're going to harm the vulnerable in their lives. You put those two together and you just that you get this powerful demand for lockdowns. You see this all over the </s><s>[INST] world, broadly speaking, you have a powerful demand for irrational policies, irrational policies because I would like to mention the flip side of that. I've been saddened to see how much money there is to be made by the martyrs, the people, the conspiracy theorists that tell you you should be afraid of the government, you should be afraid of the man. It feels like fears the problem. I think there's some guy that once said something about, we should be, we should fear fear itself. Uh, here's a president or something. I vaguely remember that. So I I so I'm worried about both sides here that [/INST] I just I think the general principle is that should not be a tool of public policy, write the truth, the public policy should attempt and public health policy in particular should attempt to address that fear. Uh, it's not that you should tell people lies. Of course not tell people accurately what the risk is. Give people tools that have evidence that they can address their risk with and level with people when we don't know. I think that is the right adult way to deal with this pandemic from public health point of view. And that's, that is not the policy we have followed. Instead, Public health has intentionally stoked the fear in order to gain compliance with his edicts. And I think the consequence of that is people distrust public health. They, what you're talking about, the distrust of government, I think is a, partly a consequence of that, that that movement, which is much smaller once upon a time is much larger now because of essentially, people look at what the, what the public health has done and said, they've they've lied to me a whole bunch of times and a whole bunch of things is the general sense. And there are consequences to that. We're going to have to work in public health for a long time to try to regain the trust of the public </s><s>[INST] throughout all of this. You've been inspiring to me to a lot of people, you've been fearless bold in these kinds of challenging the policies and not in a martyr kind of way because you're walking the line gracefully and beautifully, I would say. And um looking at that, I think you're an inspiration to a lot of young people. So I have to ask, what advice would you give them if they're thinking of going into science, if they're thinking of having an impact in the world, what advice would you give them about their career and maybe about their life? Thinking about somebody in high school, maybe an undergraduate, [/INST] I'd say a few things. One is this is a wonderful profession, you have an opportunity to improve the lives of so many and do it by having fun. The kind of play we're talking about. It's an absolute privilege to be able to work in this kind of area. Um uh and two young people looking at this saying that that that have some gifts or or desire for for this area, I say please, you know, go for </s><s>[INST] it like [/INST] Yeah, I mean it could be, it could be, I mean I'm not I don't have any gifts in ai but like, you know, it could be your buddy, but you know, or or in health or or in medicine or whatever, whatever your gifts lie, develop them work hard and develop them because it's worth it. It's worth it. Not just um for not just because you get some status because the journey is fun and the result is improvements in the lives of so many. So I think that that is the encouragement I give. I would also say if you're looking at this ugliness of this debate that's happened over the pandemic, I'd say to young people, we need you to come, come in and help transform it money that people have seen this debate that behave poorly. I asked you forgive them, I've done my best to try um because they're act, they're many of them are acting out of their own sense that they need to do good, but they've but the mistake they made is is in in is in this arrogance and this power, but when you come in remember that example as a negative example. And so that when you join the debate, you'll join it in a spirit of humility, in the spirit of trying to learn um while keeping that that love of that led you to enter the field in the first place. </s><s>[INST] And yeah, choose forgiveness versus [/INST] like derision. </s><s>[INST] Um like the people that you know have messed up, like give them a pass because that's how it feels like that's how improvement [/INST] starts. Honey. I've been thinking this is like I told you I'm christian right? So like I feel like God has given me many opportunities to forgive people learned to practice how to do that, give you a gift. It's a very humbling thing I guess. </s><s>[INST] Is there a a memory from when you were young that was very formative to you. So you just gave advice to some young people. Is there something that stands out to you that um a decision you made an event that happened that made you the man you are today? [/INST] I actually grew up in a relatively poor environment. Like I was born in India And we moved when I was four. My dad had eight brothers and sisters. Uh and my mom had four brothers and sisters. She grew up in the slum in in Calcutta. Um My dad, his dad died when he was young and he supported his family. His brothers and sisters with the university scholarship money came to the US and my dad worked In a McDonald's even though he's an electrical engineer, couldn't find a job in 1971. And so he worked at McDonald's. Um we lived in a, in a like this, this basically like this the housing ports like development in in Cambridge, just like this middle building on the 17th floor of this like housing development. Um I mean I think that was transformative for me. Like I didn't realize so much at the time well how that experience of being essentially like poor lower middle class. What effect it had on my outlook? </s><s>[INST] You mentioned to me offline that you listened to the conversation that I had with my dad, what what impact did your dad have in your life? What what memories do you have about [/INST] Him? He was a rocket scientist actually helped design rocket guidance systems. Um he died when I was 20 and I still miss him to this day and I think that experience of seeing him sacrifice himself for his family, a brilliant man. But in many ways frustrated with like the his opportunities in the world is partly what led him to come to the US in the first place. Um that's transformed has had a transformative effect on me and I wish I could tell him that. Looking back. </s><s>[INST] Do you think about your own mortality? Do you think about your death? Your dad is no longer with us? You're the the old wise sage [/INST] that represents. It's funny the, I've only worried about death once in this pandemic, although I've had two of my my cousin, he was 73 my my uncle who's 74 die in India during the pandemic. And and and and I grieved them both from Covid. Um like the fear of covid really has only hit me only really literally once during this if it wasn't for me and I recognize that it's irrational. So on the eve of the santa clara county zero prevalence study. Um it was, it was a really interesting thing because so many people volunteered to help and um my my my daughter, He was 20 and she was like it was 19 at the time and my wife also volunteered to help with like various aspects of the study. And so even the study, they were going to go out in public and I didn't know what the death rate was because we hadn't done the study and I suspected it was lower than people were saying, but I didn't know I knew about the age gradient because I've seen the chinese data and my, my daughter is young but my wife is my age and I didn't know the death rate and I couldn't sleep the night before, like what if I'm putting my family, my kids, my daughter and my wife at risk because of some some activity that I'm doing? Um it was kind of, I don't know, I </s><s>[INST] mean I was worried about the well being and of others when you look in the mirror, [/INST] if I die, I die. I mean like I just, it's not, again I'm christian so I don't, death is not the end for me I believe. Um and so I don't, I don't particularly worried about my own death, but I I do, I mean I just, I think we can't help but we worry about the well being of our loved ones. </s><s>[INST] So from the perspective of God then let me ask you, what do you think is the meaning of this whole journey we're on? What do you think is the meaning of life? [/INST] You know, it's very simple, love one another, treat your neighbor as yourself, </s><s>[INST] it's love, as simple as that. Well I'd love to see a little bit more of that in this pandemic. It's an opportunity for the best of our nature to shine it. So I've seen some of the worst. Um but I think some of that is just good therapy and I'm hoping in the end what we have here is is love at the very least, make your dad proud with some incredible rockets [/INST] that we're </s><s>[INST] launching. I think you get [/INST] along well with my dad likes </s><s>[INST] definitely would. Thank you so much. This is an incredible honor to talk to you, jay has been an inspiration to so many people and keep fighting the good fight. Thank you so much for spending your valuable time with me. Thank you [/INST] for having me here, appreciate it. </s><s>[INST] Thanks for listening to this conversation with jay Baruchel area to support this podcast. Please check out our sponsors in the description and now let me leave you some words from Alice walker. The most common way people give up their power is by thinking they don't have any thank you for listening and hope to see you next time. [/INST] Yeah. </s> |
<s>[INST] So you're you're saying so, yes, so, uh assuming she's still not around, uh but if she is and she comes into your podcast, can you dig into that a little bit? Do you mean like the her personal uh demons around the social and economic Russia of the time when she escaped [/INST] with trauma, she suffered there, what she really likes in the music and literature and why </s><s>[INST] literature, [/INST] and getting deeply into that her view of relations between the sexes and Russia, how it differs from America, why she still carries through the old Russian vision in her fiction. This extreme sexual de morph ism but with also very strong women to me is a uniquely at least Eastern european vision, mostly Russian, I would say. And that's in her, that's her actual real philosophy, not this table bounding existence exists. And that's not talked about enough. She's a Russian philosopher like soviet, whatever you want to call </s><s>[INST] it. And if she wasn't so certain she could have been a dostoyevsky, where it's not that that certainty is almost the thing that uh brings over the adoration of millions, but also the hatred of millions [/INST] became a cult figure in a somewhat rush in like manner. Yeah, </s><s>[INST] yeah, it is, it is what it is, but I love the idea that, again, you're just dropping bombs that are poetic, that the wisdom is in the coming together of ideas, is kind of interesting to think that No one human possesses wisdom. No one idea is the wisdom that the coming together is the wisdom. [/INST] Like in my view, boswell's life of johnson 18th century british biography, it's in essence a co authored work, boswell and johnson, it's one of the greatest philosophy books ever, though it is commonly regarded as a biography john Stuart mill, who innocence was co authoring with Harriet taylor better philosopher than is realized though he's rated very, very highly plato slash Socrates. A lot of the greatest works are in a kind of dialogue form, Curtis. Faust would be another example. It's very much a dialogue and yes, it's drama, but it's also philosophy Shakespeare, maybe the wisest thinker of them all </s><s>[INST] in your book, Big Business, speaking about around big business, a love letter to an american anti hero, you make the case for uh the benefit that large businesses bring to society, Can you explain [/INST] if you look at, say, the pandemic, which has been a catastrophic event, right? For many reasons, but who is it that saved us? So, amazon has done remarkably well. They upped their delivery game more or less overnight with very few hitches, I've ordered hundreds of amazon packages, direct delivery food, whether it's doordash or Uber eats or using, you know, whole foods through amazon shipping again, it's gone remarkably well switching over our entire higher educational system basically within two weeks to zoom zoom did it. I mean I've had a zoom outage, but their performance rate has been remarkably high. So if you just look at resources, competence incentives, who's been the star performers, the NBA even just canceling the season as early as they did, sending a message like, hey people, this is real. And then pulling off the bubble with not a single found case of covid and having all the testing set up in advance. Big business has done very well lately and throughout the broader course of american history, in my view, has mostly been a hero. </s><s>[INST] Can we engage in a kind of therapy session? Uh, and I'm often troubled by the negativity towards big business and uh, I wonder if you could help figure out how we removed that or maybe first psychoanalyze it and then how we remove it. It. Uh, it feels like, you know, once we've gotten Wifi on flights, an airplane flights, uh, people started complaining about how shady the connection is, right, They take it for granted immediately and then start complaining about little details. Another example that's more, that's closer to like, especially as uh aspiring entrepreneurs, closer to the things I'm thinking about is Jack Dorsey with twitter, you know, to me, twitter has enabled an incredible platform of communication and yet the biggest thing that people talk about is not how incredible this platform is. Uh, they essentially use the platform to complain about the censorship of a few individuals as opposed to how amazing is now. You should also, you should talk about how shady the wifi is and how censorship or the removal of donald trump from the platform is a bad thing. But it feels like we don't talk about the positive impacts at scale of these technologies. Is there, can you explain why and is there a way to fix it? [/INST] I don't know if we can fix it. I think we are beings of high neuroticism for the most part as a personality trait, not everyone, but most people and as a complement to that, if someone says 10 nice things about you and one insult, you're more bothered by the insult then you're pleased by the nice things, especially if the insult is somewhat true. So you have these media, these vehicles twitter is one you mentioned or it's all kind of messages going back and forth and you're really bugged by the messages you don't like. Most people are neurotic to begin with. It's not only taken out on big business to be clear. So congress catches a lot of grief and some of it they deserve. Yes. Uh, religion is not attacked the same way, but religiosity is declining. If you pull people, the military still pulls quite well, but people are very disillusioned with many things and the martin curry thesis that because of the internet, you just see more of things and the more you see of something, whether it's good, bad or in between, the more you will find to complain about, I suspect is the fundamental mechanism here. I mean, look at clubhouse right? It's to me it's a great service, May or may not be like my thing, but gives people this opportunity. No one makes you go on it and all these media articles like, oh, his clubhouse going to wreck things, you know, are they gonna break things new york times is complaining? Of course it's their competitor as well. I'm like, give these people a chance, like talk it up, you may or may not like it. Like let's praise the people who are getting something done very Ayn rand. Ian point </s> |
<s>[INST] Well, so the point I'm making, I do quite a bit is from my understanding and sense, of course we can't know for sure is he believed in communism, This wasn't purely a game of power. Now he got drunk with power pretty quickly, but he really believed for I believe his whole life that communism is good for the world and that I don't know what role that belief plays with the more natural human desire for power. I don't know. But it just seems like [/INST] as we agreed he's killing a lot of communists on his on his journey. </s><s>[INST] Mm. But it's not that doesn't that calculus doesn't work that way. There's humans who are communists and then there's the idea of communism, so for him, in his delusional world view, killing a few people is worth the final result of bringing communism to the whole world. [/INST] But it was more than that again, because I mean, he really wanted power for the soviet union. And and so surely the reason that he um he orchestrated the um export of wheat from Ukraine and in so doing was willing to lead to mass starvation was because he wanted to sell it on the market in order to be able to build up the power of the soviet union, you know, alternative view of communism might have been, well, you know, let's let's just make sure everybody survives and and make sure everybody has enough to eat and we'll all be mutually supportive in a communal network. But no, but he wanted the power for the </s><s>[INST] country. Well, I guess exactly. So that it's not even communism, the set of ideas or like Marxism or something like that. It's the country, I guess what I'm saying is uh it's not purely power for the individual, its power for a vision for this great nation, the soviet union and similar with Hitler, the guy believed that this is a great nation Germany and like they it's a nation that's been wronged throughout history and needs to be righted and there's some dance between the individual human and the tribe. [/INST] Yes. No. Absolutely. Yes. And so, so just like chimpanzees, you know, we are fiercely tribal and the tribalism resides particularly in male psychology. And it's very scary because once you assemble a set of males who share tribal identity, then they have power that they can exert ah with very little concern about what they're doing to damage other people. </s><s>[INST] Do you think this so niche in will to power? We talked about the corrupting nature of power. Do you think that's a manifestation of those early origins of violence. What's the connection of this desire for power and our proclivity for violence. [/INST] You know, what we're talking about is um tribal power. Right? Power on behalf of a group. And yeah, that seems to me to go right back to uh, a deep evolutionary origin. Because you see essentially the same thing in a whole bunch of animals. You know, they that most other sort of cognitively complex animals live in social groups in which they have tribal boundaries. And so what you see in chimpanzees is echoed in almost all of the primates. The difference between us and chimpanzees and humans on the one hand, and other primates on the other is that we kill and they don't. And the reason they don't is because they never meet in the context where there are massive imbalances of power. So two groups of baboons, you know, their study on this side and 50 on this side. Fine, nobody's going to try and kill anybody else because the serious risks involved. Um, but nevertheless they are tribal. So, you know, they will have a fairly intense into group interactions uh in which everybody knows whose side is on who is on his side. And the long term consequences of winning those battles. Nonlethal battles is that the dominance get access to nodule areas of land more safety and so on with chances are um better ah record of reproductive success subsequently. </s><s>[INST] Do you think this from an evolutionary perspective as a feature or a bug? Are uh natural tendency to form tribes. [/INST] So what's a bug? </s><s>[INST] Oh, sorry. This is a computer programming analogy. Uh, meaning like mom, it would be more beneficial. Is it beneficial or detrimental to form tribes from an evolutionary perspective. [/INST] Yeah. Yeah. But </s><s>[INST] what does it, what does it mean? What does it bug mean? [/INST] Yes. Right. I mean, yeah. Like </s><s>[INST] where's evolution [/INST] going? It's beneficial from, you know, it's beneficial in the sense that it evolved by natural selection to be to benefit the individuals who did it. But if you if my bug, you mean something that, from the point of view of the species, it would be great if you could just wipe this out because the species would somehow do better as a result, then yes. But then, you know, males are a bug. Yeah. </s><s>[INST] Come on. Now. It's uh, were there there's some nice things to males speaking as a male. The [/INST] fact that there are some nice things to males doesn't mean that they're not bugs. You know, maybe they're quite nice bugs, but it would be much better for the species as a whole not to have to have males who impose this violence on the species as a whole, </s> |
<s>[INST] But it's a very it's a Fascinatingly difficult idea then because the world with conspiracy theories, in the world without conspiracy theories, to the to the shallow glance looks the [/INST] same. Well, my point there is responsible conspiracy theorizing where you look at the history of unearthed conspiracies and just like you would with any other topic, just think about how different the rules in your mind are for conspiracy theorizing versus X. Theorizing where X can be anything right? It's like if I say to you um I can say the statement that average weight is not the same between widely separated populations, you'd say yeah, I'd say average height is not the same between widely separated population you say. Yeah, then I say in fact no continuous variable that has, that shows variation should be expected to be identical between widely separated. Of course eric like whoa, hold on, right, so we have a violent reaction to specific topics. So the first thing I want to do is just to notice that conspiracy has that built into everyone's mind. </s><s>[INST] That's really important to state. Yeah, that's it's very interesting that and as a prerequisite as you're saying, that would be the first step. If you wanted to uh pull off a conspiracy in a competent way. That's he would have to first convince the [/INST] World and I just watched the film 1971 about my favorite conspiracy of all time. I highly recommend it </s><s>[INST] 1971. [/INST] Well the film is entitled 1971 and it's about the citizens committee to investigate the FBI which was run by a student of Murray gellman, a physicist and broke into FBI offices in pennsylvania to steal files which allowed freedom of information requests that discovered a huge conspiracy. It was a conspiracy that unearthed a conspiracy inside the federal government. A double conspiracy story which launched multiple conspiracies. I think that the problem with modern americans is that they are so timid that they don't even learn about the history of conspiracies that we have absolutely proven. So with that done, Jeff Epstein, in my opinion represented somebody's construction </s><s>[INST] I don't kind of scary to think about. Yeah. Well [/INST] what part of the story isn't scary I in part did something which I I imagined may get me destroyed because I was more worried about being destroyed by somebody else. I had a conversation with around Jeff Epstein. Right, so I'm just trying to like get let it be known that I don't know anything more than I've already said now. Your friends at MIT. Yeah. Their problem is is that Jeff Epstein showed up as the only person capable of continuing us scientific tradition. You see the U. S. Scientific tradition, it's a little bit like the Russian. It's it's combative. Okay and We're a free society and we act like a free society where a rich society and we researched like we're a rich society that is historically, and then came the 1970s and William Proxmire and the golden fleece awards and the idea that we have to, we're paying too much and these are welfare queens and lab coats and blah blah blah blah. We need more transparency, more oversight, everything went to hell and the national culture of us, science was lost. The thing that produced all this prosperity and security and power was lost. And then Jeff Epstein shows up and a tiny number of funders, maybe fred Kavli, um maybe yuri Milner, maybe um who else would be in this category, peter thiel to an extent, um Howard Hughes would be the largest of these things, which has different grant structures than the NIH gave people a modicum of risk taking ability. Mhm. Okay, Well, when Jeff Epstein showed up, everybody wanted to take risk in science And suddenly a charismatic billionaire says, Hey, I can make that work for you. Here's $100,000. Go go research something crazy. Well that money was supposed to be provided by the federal government. Under the terms of the endless frontier compact between the federal government, the universities and the federal government, The taxpayers, welsh too. Okay, </s><s>[INST] so that's one place to lay the blame for Jeffrey Epstein as at the the failure of the federal government [/INST] to honor its to honor its commitment, right? So the universities became psychopathic, It's not like everybody doesn't remember what we're supposed to be doing to be moral, but the point was there wasn't enough money to be moral. So it was time to to eye each other as a source of protein as I like to say. And in that process Jeffrey Epstein said, Hey, come to my world, we can do it like we used to do so in part, my point is, is that almost none of your colleagues at M I. T. Have that kind of religious commitment to science that they're willing to go down with ships science. Mhm. The Galileo galilee thing became very important to science because occasionally you just have to say, look, this isn't about me and you, there isn't enough money in the world to buy the kind of legacy I want to leave to this planet. This is one of the great things about science, you know, potentially is worth dying for. </s><s>[INST] Yeah, I'm glad you said it. Science is one of the things that is best. That's worth dying for. [/INST] I mean, I'm not eager to martyr myself. Mhm. But I've certainly risked my health, my fortune. You know, I've destroyed myself economically over science and and my my my my need to oppose these sons of bitches in chaired professorships who are destroying our system, along with everyone else. </s><s>[INST] Let me um bring in grandmaster went into this oogway, oogway [/INST] master. Oogway, </s><s>[INST] I think he's a grandmaster that would make him a [/INST] chess playing turtle? </s> |
<s>[INST] co [/INST] written with my old friend colleague from Berkeley Don Goldsmith. And it's really about the role of human spaceflight versus sort of robotic spaceflight. And just to summarize what it says, it argues that the practical case for sending humans into space, it's getting weaker all the time as robots get better and more capable Robots 50 years ago couldn't do anything very much. But now they could assemble big structures on space or on space or on the moon. And they could probably do exploration. Present ones on Mars can't actually do the geology but future Ai will be able to do the geology and already they can dig on Mars. And so if you want to do exploration of Mars and of course even more of and sell the Europa, we could never send humans, we depend on robots And they're far far cheaper because to send a human to Mars requires feeding them for 200 days on the journey there and bringing them back and neither of those are necessary for robots. So the practical case for humans is getting very, very weak and if humans go it's only as an adventure really. And so the line in our book is that </s><s>[INST] human [/INST] space flight should not be pursued by Nassau or public funding agencies because it has no practical purpose, but also because it's specially expensive if they do it because they would have to be risk averse in launching civilians into space. I could illustrate that by noting that the shuttle Was launched 135 times and it had two spectacular failures which each killed seven people in the crew and it had been mistakenly presented as safe for civilians and there was a woman schoolteacher killed in one of them and it was a big natural trauma and they tried to make it safer still. But if you launch into space, just the kind of people prepared to accept that sort of risk. And of course test pilots and people who go hang gliding and Go to the South Pole etc are prepared to accept a 2% risk, at least for a big challenge. Then of course you do it more cheaply. And that's why I think human spaceflight should be left to the billionaires and their sponsors because then the taxpayers aren't paying and they can launch simply those people who are prepared to accept high risks space adventure, not space tourism and we should cheer them on. And as regards where they would go, then low Earth orbit I suspect can be done quite cheaply in future, but going to mars, which is very, very expensive and dangerous for humans. The only people who would go would be these adventurers maybe on one way trip, like some of the early polar explorers and Magellan and people like that, you know, and we will cheer them on and I expect. And I've always hoped that by the end of a century there will be a small community of such people on mars living very uncomfortably, far less comfortably than at the South Pole or the bottom of the ocean or top of Everest, but they will be there um and they won't have a ticket, but they'll be there. Um Incidentally, I think it's a dangerous delusion to think as Elon musk has said that we can have mass emigration from the earth to mars to escape the earth's problems today disillusioned because it's far easier to deal with climate change on earth than to terra form mars to make it probably habitable to humans and there's no planet B for the risk averse people. But for these crazy adventurers then you can imagine that they would be trying to live on mars as as great pioneers and by the end of century then there will be huge advances compared to the present in two things. First in in understanding genetics, so as to genetically redesign one's offspring and secondly to use cyborg techniques to implant some something in our brain or indeed think about downloading etcetera. And those techniques will one hopes be heavily regulated on Earth on Prudential's and ethical grounds and of course we are pretty well adapted to the Earth, so we don't have the incentive to do these things in the way they were there. So our argument is that it will be those crazy pioneers on MArs using all these scientific advances which will be controlled here away from the regulators. They will transition into a new post human species. And so if they do that, and if they transition into something which is electronic eventually, because there may be some limits, the capacity of flesh and blood, brains anyways, then those electronic entities may not want to stay on the planet, like mars, they may want to go away. And so they'll be the precursors of the future evolution of life and intelligence coming from the earth. And of course there's one point which perhaps astronomers are more aware of that. Most people, most people are aware that we are the outcome of four billion years of evolution. Most of them nonetheless probably think that we humans are somehow the culmination the top of the tree. </s><s>[INST] But you [/INST] know, astronomers could believe that because astronomers know that the Earth is 4.5 billion years old. The sun has been shining for that length of time, but the sun has got six billion years more to go before it flares up and engulf the inner planets. So the sun doesn't halfway through his life. Um and the expanding universe goes on far longer, Still, maybe forever. And I'd like to quote woody Allen who said eternity is very long, especially towards the end. So, so we shouldn't think of ourselves as maybe even the halfway stage in the emergence of cosmic complexity. And so these entities who are post curses, they will go beyond the solar system. And of course, even if there's nothing else out there already, then they could populate the rest of the galaxy </s> |
<s>[INST] because I'm talking in a language they understand. So on this particular topic of trans issues, is that the reason you were banned from Twitch? [/INST] I'm not sure, I don't know. They just said hate speech, but I don't use like slurs </s><s>[INST] or anything, so it's hard to know exactly. So I think you made the claim that trans women shouldn't compete with cis women in women's athletics. Can you make this case, and can you steel man the case against it? I think in your community, there's a lot of trans folks who love you, and there's a lot who hate you. Yeah. And so if you can walk the tight rope of this conversation [/INST] to try to steel man both sides. Yeah, one of the argumentative strategies I say is that like any time you have a conversation, you should be able to argue both sides better than anybody else, you know. So for the my side, the genuine belief side, it feels like overwhelmingly, all of the data is showing that trans, mostly trans women, even after I think three years on some sort of like HRT or, you know, estrogen stuff, they're still maintaining these advantages from their male puberty over cisgender women. And if that is the case, if we are gonna draw these distinctions around our sports between women and men, it feels unfair to have a category inside the women's sports that are maintaining advantages that are coming from a male puberty, regardless of the amount of time they've spent on hormone replacement therapy. </s><s>[INST] So that would be my argument on that side. So it's unfair from a performance enhancement aspect. So the same way we ban performance enhancing drugs that involve increasing of testosterone in that same way would be unfair. Essentially, yeah. [/INST] So what's the case against? Yeah, so the case in favor of them competing together is that realistically, there's not gonna be a trans sports category. Realistically, trans women aren't gonna be competitive with cis men because they've gone through these huge, you know, like hormone changes by the medication they're taking. And that when we look at how sports are kind of done anyway, there's a whole bunch of biological differences between people within sports categories that are determining their placement in the professional world. So for instance, somebody like me is probably never gonna go far in the NBA because I'm not tall enough. I think the average height in the NBA. Don't doubt yourselves. Don't doubt myself yet. I wanna say it's like six or something. They're huge people. Or, you know, you look at like Michael Phelps is a classic example of a guy whose torso is like so long. His body is built for swimming. And I think there are some trans people that will look at that or somebody advocating for this position, they'll look at them and go, okay, realistically, the way that Michael Phelps' body processes lactic acid, the shape physiologically of his body, it's gonna put him in a level of competition that so many men are never gonna reach just because of biology. How is it fair that you can have these biological outliers competing in these categories, but then when we come to sports categories with trans and cis women, you're gonna take trans women and say they can't compete against cis women. Can't you also just say that they have some level of biological difference there? Is it really gonna be that great of a difference than what Michael Phelps has versus the average swimmer </s><s>[INST] or an NBA player has versus the average height male? Yeah. Do you think we're gonna get into some tricky ethical territory as we start to be able to, through biology and genetics, [/INST] modify the human body. Absolutely. I feel like those things are coming sooner than we wanted them to. Oh, man, dude, have you seen the AI art? Yes. </s><s>[INST] Of course, I'm an AI person. [/INST] Oh, okay, then yeah, yeah. Oh, okay, then yeah, yeah. That's always been like, what's gonna happen when robots can do art better than humans, LOL? Like, well, we'll see in 20 years, in 20 years, in 20 years, and now you have AI art winning competitions, and it's funny because robots are essentially... There's a robot behind you, by the way. The robot behind me. Oh, nice. Robots are really good at- Careful what you say. Yeah, I got it, I'll be careful. That's not like the one of the Chinese ones with a gun on it, right? Oh, okay. </s><s>[INST] I'll explain that. [/INST] We'll see, depending on what you say, yeah, yeah, yeah. Robots are really good at showing the limitations of the human mind in categories that we didn't believe we were limited before. I think that humans have this idea intrinsically that we have some type of innovative creative drive that is just outside of the bounds of physical understanding, and with a sophisticated enough program, we see that maybe that's not actually true, and that's a really scary thing philosophically to deal with because we feel like we're very special, right? We own the planet, we make computers, and the idea that you can start to get these robots that can do things, it's like, okay, you can do math, fine. Okay, you can do calculation because it's fine, but you can't do art. That's the human stuff, </s><s>[INST] and then when they start to do that it's like, oh shoot. And that terrifies you a little bit? Like a losing, the human species losing control of our dominance- [/INST] I don't think it's necessarily losing control of our dominance, I mean, I guess like a Skynet thing could come in at some point, but it brings us to this really fundamental level of like, what does it mean to be human, What is it that we're good at? What should we be doing with technology? We never really asked that question in the Western world. It's always the technology is like normative in that technology equals good and more technology equals better. That's been like the default assumption. In fact, if you ask a lot of people, how do you know if civilization has progressed over the past 100 or 200 years? They don't say we have better relationships, we have longer marriages, we blah, blah, blah. They'll say technology is improved. We've got crazy phones, we've got crazy computers. And the idea that more technology might be bad has never even crossed somebody's mind </s> |
<s>[INST] you remember like a turning point where you became as opposed to being mediocre and not just in technique, but an approach to uh two great [/INST] um I think it was somewhere around brown belt level when I was training consistently, started training full time with john when I was purple belt, midlevel purple belt. Um And towards the end of my brown belt days, I was beating up like legitimate, like a DCC champions in the gym. Um So I think like brown to black belt was a big thing for me and then when I won my first FBI and I was cemented yuri who won 80 cc and I beat Rustam. Um so I think that was like my turning point as a competitor, but I think I started to, to reach world level a little bit before that, I think somewhere around brown belt, mid level to lower level brown belt, </s><s>[INST] it was some of that mental, like was there a moment when you, like after a training session you realized I could actually do this? Like I could be at the top of the world, world [/INST] class. The critical moment for me was when a I think it was right, right when I got my black belt, maybe a few months before I got my black belt, we had former champion coming to the gym and uh we did a hard round together and I think I submitted him like four or five times and uh no one knew who I was, I never won anything up until that point and I was like, okay, like if this is like one of the best guys in the world and I could submit him multiple times around, I think that this is like something that I actually could do professionally and make a make a career out of this. </s><s>[INST] Okay, so the actual performance was the, like, you don't need to believe before you could perform like a lot of olympic gold medalists, they they have to believe before they can perform because like they're they're getting they're asking for a long, long, long time. [/INST] Yeah, I think that the best way for me to believe in something is to have repeated success doing it against high level guys. Like I'm not gonna just believe I can do a double leg if I can't have a double leg on anybody. Um So for me, the the belief came from the repeated success in the gym. </s><s>[INST] Yeah, but to get to the point where you're submitting somebody like your S. M. O. Is like one of the greatest grapplers ever. It's like a long journey. [/INST] Yeah, but I I had the confidence, I had to believe in myself because of the success that I had in the gym prior to that </s><s>[INST] even and it's one step at a time. First, it's the brown belts known as the black belts and its world class. Okay, um George, was there a turning point for you when you you thought like I can actually do this? [/INST] Yes. I um I always dreamed to become champion, But I think the turning point that there was there was two turning point And there were my two losses. Uh first my losses to matt Hughes I went into that fight just to not lose. I was not fighting to win and it's after the fight when I watched the replay of the fight, I realized I was like, I was doing pretty well. But during the fight, in my own mind, I was not seeing it that way. I thought that was Getting dominated by use like 100%. When I watched the replay, I was like, man, I can I can beat this guy. I was beating him until I made that stupid mistake. So I was very frustrating, but but that's what gave me the mentally the championship level mentality. And then I became a little bit overconfident because I started beating everybody after that and I start to believe the hype of people when they look at me, they were like, oh, he's the new up and coming superstar and he's going to be unstoppable. And and then when I became champion night, I lost 2 to Matt Serra so before I, I believe my first failure was because I had a lack of confidence and and my second failure was I was because I was overconfidence. So I think it's, there is a perfect center of confidence. I mean, I mean, it's good to be confident because john taught me like confidence is it's it's like money in your bank account. If you you can have all the skills in the world, right? And and and if you're if you don't have the confidence, it's like, it's like you can you can be a millionaire, but you don't have access to your bank account. So it's, that's a little bit the analogy that john told me, So that's how I feel confidence place for an athlete, but to be overconfident, I think it's always good to, to be aware, to be afraid of what can happen. And so to have a perfect balance of confidence and fear to me, that's what mentally gave me the edge to become, I believe, successful in my sport, playing off that john gave me a speech one time and he was like, you have to be able to like flip a switch and turn it off where like a guy like Mayweather or someone who goes out who's super confident and he plays the character of someone who's like no one can beat me, I'm the best there ever was and that's it. Um but if you look at me actually trains very hard, you can't, you can't play the persona of no one can beat me and then have it translate into your life and you think that you're so good, you don't have to do anything and no one can ever beat you. You have to be able to play that public persona of no one can beat me, but then you have to actually do the training to make that happen. You can't just, you can't believe your own hype and say say that, you know, I can just do whatever I want, no one's ever gonna beat me if they're able to switch between the persona and the actual athlete and that made a big difference for me, </s> |
<s>[INST] I wish there was another way to get there, but I don't think there is. That joy you get of just everybody getting together and taking shots or drinking, not the polite kind of drinking, but just everybody just, the fuck it kind of drinking. [/INST] Yeah. And when someone goes, all right, I'm in. Like that's the funnest. And then especially when you have a big group and there's like a big group and like we were at the premiere the other night and I was working, I was legit working. I'm trying to sell the movie to outlets, media outlets. And bust them with the boys, my wife flew them in to surprise me. And they're over on the red carpet. And they're like, yo, let's scull a beer. Let's kill a beer. And I was like, oh, and then I'm like, oh, fuck it. I don't give a fuck. This is what life's about. And that moment where they're like, yeah, that's the funnest fucking, especially when I can get Leanne to do it. When I get Leanne to get a drink and she's like, Like I was supposed to drink last night and she was like, you want to just. We still have a glass of wine in the front yard and you're like, oh, my heart skipped a beat. I go glass wine in the front yard. Are we going to talk wild? Are we going to say crazy shit to each other? Like, fuck yeah. In the front yard. Front yard. What are you doing in the front yard? Let the dogs play. Oh, big trees in the front yard. Why are you sitting on the, where were you sitting? Sitting in the Adirondacks on the front porch, letting the dogs play, letting the dogs rest in the front yard. Maybe go over, pick some cherries, look at the fucking trees, hear the wind going through the front yard, and then you go to the backyard. That's where the cigar comes out, a little more privacy, but yeah. Red wine? Red wine, maw back. Keep our soul fights low. </s><s>[INST] Yeah wine is a whole another one too. I feel sophisticated. Oh, yeah, I've I've went I traveled before Ukraine I went to Paris for the first time and drank wine there and I felt like I Was a sophisticated man, you know dude I mean to speak with French, but you don't need to you don't need to just start smoking to just have a fucking cigarette I was gonna start writing poetry to the Hemingway. [/INST] There's like a glass of wine in Italy and like like just out in like we went we went ah the most beautiful fucking day of my life Just outside Florence They have all the vineyards and stuff, and we took a Vespa tour. Nice. And it was fucking, and Ila's too young to ride, so she's on the back. And now everyone can drink there, you know? You're not supposed to drink and drive Vespas, but a glass of wine is nothing. And you're like, okay, I guess I'll have a couple then. If you think one's nothing, then I think two's nothing also. </s><s>[INST] So this is drunk Bert on a Vespa? [/INST] drunk, not even drunk, but just lightly, lightly feathered where, and it's beautiful. My wife hasn't been drinking, Georgia has, Georgia's too young, Isla is too young, but I had, at dinner we had a couple and we're going through these hills and it starts raining and it starts raining and I go, Isla, what are we missing? And she goes, music, big boy. And I go, what do you want to hear? And then she just starts going, uka, shaka, uka, uka, uka, shaka, uka, uka. I can't stop this feeling. She's screaming it behind. And then I hear Georgia screaming it. And then Leanne singing it. And then Sandy and her two daughters are singing it. We're all in these vespas. And we're all singing it. And I swear to God, if I hadn't been lightly feathered, Don't know if I would have been like I know what are we missing cuz you know alcohol will give you that thing like what's next? What's bigger? How do we take this to the next level? And then I got this little girl who's my still my little girl at that moment when she's singing sing it all the good times And then we stop at the light and all of us are looking and it's pouring rain. It is, I mean, I remember sobbing crying, sobbing crying, sobbing crying. And then I was like, let's get these fucking Vespas up and get to a vineyard. And then we went to a vineyard and all the girls tried a little wine. No one got buzzed or anything, but you're just sitting there with your family going like, Fuck, dude. </s><s>[INST] And I'm not certain you get that without a little bit of... A little bit, but then a lot is also interesting. I had a lot of whiskey with Rogan once. [/INST] I think I saw that. Yeah. I think I saw that with Whitney too. And the push-up concert contest. </s><s>[INST] The only time I met David Goggins in person, one of the great embarrassments of my life is trashed out of my mind. I'm trying to just say how much of a fan I am. And I could tell by the look in his eye that what is actually coming out of my mouth is not good. It's not good. And his wife is embarrassed standing right there also. Just everybody's embarrassed for me. Man, I'm trying my best. And then somehow I find myself a minute later doing pushups with him as a challenge. Pushups? I didn't, it wasn't counting. All I knew I'm not stopping. And he was polite enough to stop. I think probably like 50, I don't know. [/INST] There's a gift someone gives you when they get drunk and they allow, they get drunk and they lower their guard and they allow you to see them that way. It's a gift. It's a real gift. It's just as cool as like pulling someone aside and going, yo, I'm into anime. Like are you cool with that? And then they're going, yeah, I'm, oh, yeah. Can I show you some cool anime? And then you're like, that's not my thing, but it's like a cool thing. It's like sharing cool music with someone or like telling them something about your childhood. When you, when you get drunk, like real drunk around someone, You're giving them a gift. And that gift is, I want you to see me for everything I am. You're not gonna get any lies. You're not gonna get any bullshit. This is me at my absolute worst. I have a rule. I will never, never get mad at someone for getting too fucked up. because they're giving you a gift. They're saying like, yo, I did this on accident, but I trust you enough to let you know that this is who I am, and this is what you're getting. I love it. I love it. Especially when it comes to someone you don't expect. Like you? Shut the fuck up. David Gawking should have hugged you and said, thanks for showing me this. </s> |
<s>[INST] they're just like, no, it's just luck, you know? So you do lay it all out there, but I gotta push back to one interesting thing. I think a crucial component of your success is the idea stage, the idea generation. The brainstorm that I heard today, but getting really good at generating ideas. So it's not just the selection of the thumbnail and the title, that creative process. It's also just the engine of generating really good ideas. And getting that, I mean, I would say that is probably the thing that needs to be trained the most for most creators, right? [/INST] They just don't put enough ideas on paper. And getting that. Yes, but also a lot of creators also just don't, you know, which I didn't either for the longest time, just didn't don't make good enough content. </s><s>[INST] Content that's worthy of getting 10 million views. [/INST] In the idea or the execution of the idea? Both. I mean, like, think about how many people just make videos, they film in under 20 minutes and they don't really put any effort into it. And like, you know, it's like, my first 500 videos didn't deserve to get a million views. Like there's a reason they did. They're terrible, you know, but at the time I thought they did, right? And I'm in the mindset of a lot of small YouTubers where I thought those videos deserved a million views and I thought that really paid me. But I watching back now and I can tell you exactly why the videos were just fricking horrible. </s><s>[INST] You know what I mean? You know what I mean? So what was the breakthrough for you to start realizing, to start having a self-awareness, you know, about these videos aren't good enough. You're probably still going through that, [/INST] you probably still growing to see. Yeah, every six months you used to look back and hate your videos. Or at least see things you could improve and be like, oh, I could've done this better, that better. If not, then you're not learning quick enough, </s><s>[INST] in my opinion at least. Where's the source of that learning even for you now? [/INST] I mean, I just got back from a mastermind where I just got like ten of the smartest people I knew and we just locked ourselves in a cabin and taught each other stuff. Constantly, every day, not every day now, probably every other day, I go on a walk and it's called random people. I'll just say, yeah, teach me something. And I mean, it's just, you just have to have a never-ending thirst for learning. That's very imperative, especially if you want, like if you want to get on top and then stay on top, the only way to do it is just to constantly be learning. Or someone who is learning is just gonna, </s><s>[INST] yeah, I'll have a leg up on you in the knowledge game. And what kind of stuff are you, because you've talked about offline that you just love learning of all kinds, doesn't matter but in terms of videos are you studying videos are you studying [/INST] recently not as much I'm more because they get to the videos I want I have to build this business and scale up and hire so more my recent time has been like my teenage years were spent studying virality and studying content creation now I'm studying how to build a content company so I can actually produce the </s><s>[INST] crazy ideas I want to produce if that makes any sense so yeah on that the [/INST] business side we talked about hiring do you have trouble firing people no I'm pretty sure almost every person yeah actually every person I've ever fired we you just give them severance, and I like to see it more as. It's no ill will. Like if there's if like, if I fired you if there's some other job you want me to help you get I'll DM them on Twitter like you know if you want to go work for I don't know insert whatever MTV give me someone to DM. I'll DM like you know, I I try to make it more like a transition and do whatever </s><s>[INST] we can to make it as easy as possible. And there's something that was just not working for you because you want people like you said super passionate. [/INST] Because at the end of the day if you hold someone that you onto someone that you you don't see being here in 10 years, you're just doing them a disservice, you're just giving them more ingrained, more enrooted and where they are, and the sooner you do it, </s><s>[INST] and help them move on to their new life, the better. Given all the wisdom you have now, if you were to give advice to somebody or if you were to start over again, you had no money, what would be the first 10 videos you tried to make on a new channel, I guess that's advice for a new person. [/INST] And nobody knows you. And nobody knows you. Yeah and nobody knows me, </s><s>[INST] I would think they have a mask on. [/INST] And then you also, I guess don't have the wisdom. If I don't have what I have in my head then I would just say just fail. A lot of people get analysis paralysis and they'll just sit there and they'll plan their first video for 3 months. Any of you listening especially if you have zero videos on your channel, your first video is not going to give views. Period. It's not. Your first 10 are not going to give views. I can very confidently say that. So stop sitting there and thinking for months and months on end Like all you need to do this this applies to people who have not uploaded videos But have dreams of being a youtuber is make 100 videos and improve something every time do that and then on your hundred first video We'll start talking like maybe you can get some views But you know your first hundred are gonna say there are very freak cases like Viscoshi or Emma Chamberlain who have really good personalities and it doesn't take them so as many videos And it's just like people who are seven foot five and making the NBA like yes There are freak cases you can find but for the average person like us You know who don't have these exceptional personalities and you know Backgrounds of filmmaking just make a hundred videos improve something each time and then talk to me on your hundred first video </s> |
<s>[INST] it's not as sticky in many of the other situations here. The guilt couldn't really stay for a long time. [/INST] So you number one, it's we're talking about a progressive disease that can lead to death. And if somebody commits suicide, they wanted to commit suicide. And at least what I've been told is your you can't stop it, it's gonna happen, it's gonna happen. There's no magic words, There's nothing you can do. So, you know, people who've lost people to suicide, you know what I'm talking about? Like, you know, you you you can watch it happen in real time and there's there's nothing you could do um that being said, you know, being responsive to when it seems like someone's really reaching out for help and knowing that maybe even though it might if, especially if it's someone who's like, doesn't talk like this a lot of the time and sentences start coming out of their mouth that if you weren't really paying attention might not seem like a big deal. But for this person, it's kind of anomalous that all of a sudden that's happening now there, that's when you can be a good listener and, you know, open up to them and hear what they're saying and and see like, oh share they're asking me for, is this them asking for help? And even if you're like, I don't know what to do. You know? Uh at least you can like start checking in on them, you know, start like, help them understand that you're there for them and then hopefully get them into therapy, get them to a doctor, get them to a professional who can like see what's going on there so that and then there's hope and even then there might not be hope actually, you know, doctors can't stop it. There's no sometimes it just that's the way it goes. But you know, I know that like um being sensitive if somebody's like all of a sudden hitting you up for reaching out to you that normally isn't like that and just what's going on? How are you and just listen. </s><s>[INST] Which in general the pressure or not is probably a good thing to do. [/INST] Yeah to </s><s>[INST] to to to truly listen. Yeah. [/INST] Yeah because people have, you know, I don't this whole thing like cries for help man. They don't sometimes they just look like a weird text, you know something you don't realize that for the person to send that text, they've been thinking about it all morning. They've been just trying to get their get their phone up from the floor. So you know, I think that that's it. I mean what I don't know, I don't know, I've had friends like kill themselves so and uh many of them it wasn't like sadly it was like I don't know, I don't know what could have been done, but but </s><s>[INST] there's still still a guilt in the back of your head [/INST] for the rest of my life for sure. I always will be. Yeah, I mean, yeah, but again, what are you gonna do? You? </s><s>[INST] But even that it's a part of love. That's [/INST] right, that's right, yeah, that's right. You could, yeah, we, you know, we feel guilt grief. Part of grief is guilt, you know, like you we always could have been better people, We always could have been better people. You get into victor frankel </s><s>[INST] much [/INST] man's search for meaning the invitation to live your life as though you've been on your deathbed and have been given the chance to go back and not make the same mistakes. I returned to that idea all the time, meaning it's like, okay, whatever you did before this moment, it's too late, but now, you know this is where you can start, this is where you can start and yeah, so I think that's a neurotic like me, that's super important because otherwise I'll just get like two lost in the weeds of ship shitty things I did in the past. </s><s>[INST] So speaking of victor frankel, you and Hitler have the same birthday, [/INST] oh my God, you've really done your research. </s><s>[INST] Uh Well, I I often google um famous people that have a birthday same as Hitler and the person that shows up, you know, is you your face just really [/INST] big, you </s><s>[INST] and Hitler together, just pals next to each other. [/INST] No, it does not know. But April 20 is an embarrassing birthday for all my 420 friends out there. It's embarrassing. You share a birthday with Hitler. It's </s><s>[INST] 420s also has a humor and a lightness to it, right? [/INST] It's embarrassing. Your especially life </s><s>[INST] is embarrassing, [/INST] but if you like weed and you're born on Stoner Day and you believe in reincarnation, do you realize like when you start connecting the dots there, if there is like a bardo where you get to choose your next life, </s><s>[INST] so you're like a shitty Generic NPC, you're, you're like, of course, of course you would be born on 4.20. This computer [/INST] Get 20 man. Yeah, </s><s>[INST] but isn't it interesting that on that same day Hitler is also born, there's a there's attention to that. Um and that Hitler is an artist, so it's like that hippie mindset could, could go anywhere. [/INST] Oh yeah, right? Like Yeah. You know, and I like I was just having this conversation with a friend of mine who's a wonderful skeptic, and we were talking about this uh which is the thing where you start attributing To the day you were born these kind of significance and based on maybe people who were born on that day, maybe some other things and you know, it's like, think of how many people by now in the course of human history have been born on April 20. I mean how many someone could probably do the math and come up with some number close to it now. This is how you know how rotten Hitler is? Like, he's the one that like fucks up every all the birthday for everybody else, but I think </s> |
<s>[INST] Of course it's very difficult to define but can you help me define what the extremes are [/INST] again as they have changed over the years what they are today and where's the center? Oh boy. Well in a way on this issue I think there is no center except in this if you're looking on social media or if you're looking on tv there are people who are trying to fabricate the idea there's a single question and that's the first mistake. We are developing a new relationship with the climate system and we're rethinking our energy systems and those are very disconnected in so many ways that connect around climate change but the first way to me to overcome this idea of there is this polarized universe around this issue is to step back and say well what is this actually and when you do you realize it's kind of an uncomfortable collision between old energy norms and growing awareness of how the planet works that you know if you keep adding gases that are invisible it's the bubbles in beer if you keep adding that to the atmosphere because it accumulates that will change everything is changing everything for thousands of years that's already happening. What do you mean by bubbles in beer? CO2 carbon dioxide the main greenhouse gas. Why beer? Look because I like beer. It's also in Coca-Cola we were talking about cola before uh and so it's innocuous we grew up with this idea is CO2 unless you're trapped in a room suffocating. Why beer? Look because I like beer it's an innocuous gas it it's plant food it's beer bubbles and the idea we can swiftly transition to a world where that gas is a pollutant regulated tamp down from the top is fantastical you know having looked at this for 35 years I brought along one of my tokens this is my 1988 cover story on global warming. The greenhouse effect discovered in 1988. Jim Hansen the famous American climate scientist really he stimulated this article by doing this dramatic testimony in a senate committee that summer in May actually spring late spring it was a hot day and he got headlines and this was the </s><s>[INST] result but it's complicated look what we were selling on the back cover. What you see is when [/INST] you get to back cigarettes cigarettes yeah you know looking back at my own career on the climate question it's no longer a belief fight over is global warming real or not you say well what kind of energy future do you want that's a very different question than stop global warming and when you look at climate actually I had this learning journey on my reporting where I started out with this as the definition of the problem you know the 70s and 80s pollution was changing things that were making things bad so really focusing on the greenhouse effect and the pollution but what I missed the big thing that I missed the first 15 years of my reporting from 1988 through about 2007 when I was that period I was at the New York Times in the middle there was that we're building vulnerability to climate hazards at the same time so climate is changing but we're changing too and we where we where we are here in Austin Texas is a great example flash flood alley named in the 1920s west of here everyone forgot about flash floods built these huge developments you know along these river basins that in one side starts saying global warming global warming and the other side is not recognizing that we built willfully greedily uh vulnerability in places of utter hazards same things played out in Pakistan and in Fort Myers Florida if you and you start to understand that we're creating a landscape of risk as climate is changing then that it feels oh my god that's more complex right but it also gives you more action points it's like okay well we know how to design better we know that today's coasts won't be tomorrow's coasts work with that and then let's chart an energy future at the same time so the story became so different it didn't become like you know a story you could package into a magazine article or the like and it just led me to a whole different way of even my journalism changed over time so I don't fight the belief disbelief fight anymore I think it's actually kind of a waste I don't it's a good way to start the discussion because that's where we're at but this isn't about to me going forward from where we're at isn't about tipping that balance back toward the center </s><s>[INST] so much as finding opportunities to just do something about this stuff what do you think Bjorn do you agree that it's multiple questions in one in one big question do you think it's [/INST] possible to define the center where is the center I think it's wonderful to hear Andy sort of unconstruct the whole conversation and say we should be worried about different things and I think that's exact or we should be worried about things in a different way that makes it much more useful I think that's exactly the right way to think about it on the other hand that was also where you kind of end it. We are stuck in a place where this very much is the conversation right now. And so I think in one sense, certainly the people who used to say, oh, this is not happening, they're very, very small and diminishing crowd and certainly not right. But on the other hand, I think to an increasing extent, we've gotten into a world where a lot of people really think this is the end of the times. So the OCD did a new survey of all OCD countries and it's shocking. So it shows that 60% of all people in the OCD, so the rich world believes </s> |
<s>[INST] some kind of occurrence mechanism. [/INST] Okay the other so that's so that's so so I want to have a little bit more top down in the at test time. Okay then at training time we make use of a lot of top down knowledge right now. So basically to learn to segment an object, we have to have all these examples of this is the boundary of a cat and this is the boundary of a chair and this is the boundary of a horse and so on and this is too much top down knowledge. How do humans do this? We managed to we managed with far less supervision and we do it in a sort of bottom of way because for example, we're looking at a video stream and the horse moves and that enables me to say that all these pixels are together. So the Castrol psychologists used to call this the principle of common fate. Yeah. So there was a bottom up process by which we were able to segment out these objects and we have totally focused on the stop down training signals. So in my view, we have currently solved it in machine vision. This top down bottom up interaction, but I don't find the solution fully satisfactory and I would rather have a bit of both in at both stages </s><s>[INST] for all computer vision problems, not just segmentation [/INST] and and and and and the question that you can ask is so for me, I'm inspired a lot by human vision and I care about that. You could be just a hard boil engineer not give a damn. So to you, I would then argue that you would need far less training data if you could make my research agenda. Uh football. Yeah. </s><s>[INST] Okay. So then maybe taking a step into ah segmentation, static scene, understanding what is the interaction between segmentation and recognition? You mentioned uh the movement of objects. So for people who don't know computer vision, segmentation is this weird activity that computer vision folks have all agreed is very important uh of drawing outlines around objects versus a bounding box or and then classifying that object. Uh What's what's the value of segmentation? What is it as a problem in computer vision? How is it fundamentally different from detection, recognition and the other problems? [/INST] Yeah. So I think uh so segmentation enables us to say that some set of pixels are an object without necessarily even being able to name that object or knowing properties of that object. </s><s>[INST] So, you mean segmentation purely as as as the act of separating an object from its background. A blob of uh that's united in some way from his backup. [/INST] So entity fication if you were making an entity out of it and </s><s>[INST] certification [/INST] beautifully. Uh so I think that we have that capability and that is that enables us two as we are growing up to acquire names of objects with very little supervision. So suppose the child let's posit that the child has the ability to separate out objects in the world. Then when the the mother says pick up your bottle are uh the cats behaving funny today. Mhm. The word cat suggests some object. And then the child settled. Does the mapping right? The mother doesn't have to teach specific object labels by pointing to them. Weak supervision works in the context that you have the ability to create objects. So I think that uh to me that's that's a very fundamental capability. There are applications where this is very important. For example, medical diagnosis. So in medical diagnosis, you have some brain scan. I mean, this is some work that we did in my group where you have cT scans of people who have had traumatic brain injury and what what the radiologist needs to do is to precisely delineate various places where there might be a bleed for example, and there's there are clear needs like that. So there's certainly very practical applications of computer vision where segmentation is necessary. But philosophy, cle segmentation enables the task of recognition to proceed with much weaker supervision than we require today. </s><s>[INST] And you think of segmentation as this kind of task. It takes on a visual scene and breaks it apart into into interesting entities that might be useful for whatever the task is. [/INST] And it is not semantics free. So, I think, I mean it blends into it involves perception and cognition. It is not, it is not I think the mistake that we used to make in the early days of computer vision was to treat it as a purely bottom up perceptual task. It is not just that because we do revise our notion of segmentation with more experience. Right? Because for example there are objects which are non rigid like animals or humans. And I think understanding that all the pictures of a human are one entity is actually quite a challenge because the parts of the human, they can move independently and the human wears clothes so there might be differently colored. So it's all sort of a challenge. </s><s>[INST] You mentioned that three hours of computer vision, our recognition reconstruction reorganization. Can you describe these three Rs show how they interact. [/INST] So uh so recognition is the easiest one because that's what I think people generally think of as computer vision achieving these days which is labels. So is this a cat, is this a dog? Is this uh guava, I mean you know it could be very fine grained like you know, a specific breed of a dog or a specific species of bird or it could be very abstract like adamant but </s><s>[INST] given a part of an image or a whole image, say put a label on that. [/INST] So that's that's recognition reconstruction is a essentially you can think of it as inverse graphics. I mean that's one with uh to think about it. So graphics is your you have some internal computer representation and uh you have a computer representation of some objects arranged in a scene. And what you do is you produce a picture? You produce the pixels corresponding to a rendering of that scene. So uh so let's do the inverse of this. We are given an image and we try to we we we say, oh this image arises from some objects in a scene looked at with a camera from this viewpoint and we might have more information about the objects like there shape, maybe their textures, maybe you know Conor etcetera etcetera. So that's the reconstruction problem in a way you are in your head creating a model of the external world. Right, okay, reorganization is to do with essentially finding these entities. So uh so it's uh organization. The world organization implies structure so that in in the perception in psychology we use that perceptual organization. That the world is not just an image is not just seen as it's not internally represented as just a collection of pixels. But we make these entities. We create these entities objects whatever </s> |
<s>[INST] Turski, Jasneh Polana, Modem, honey. No claims of health. [/INST] The other one claimed health. This one, no claims. No, I'm for competing governments on different geographic areas. That's fine. Why does it have to be over? Okay, let me. It's really crucial that it's on different. So you don't have two judges in Gulch Gulch. You have one. And there's a reason one. There's one authority. There's one system of laws in Gulch Gulch that is that all the people under the Gulch abide by. There's one. There's two because they're in America. No, they're not. The whole point is they're not right. They're not in Colorado. I know. But the whole point of the novel is they've left America. They haven't left America. They've hid themselves. So they're not under the utilities of America. But they are. Don't get it. But they're hidden. They're supposed to be Vegetable Point is that the hidden. So not under. They're not either. They're in Colorado. They haven't left America. They are. Don't. They're not. But they're hidden. We're supposed to don't know. And if you get the three of us, hide, we're still under the authority of Washington. No, but not if, but this is why they haven't you don't even But this is why they haven't established a state, and it's not a government, and it's not in that sense an example of really the way we form societies. It is a private club that is hidden away from everybody else. Fine. I'm fine with that. What happens if an American kills a Canadian in Mexico? What happens in America, it depends. Depends on the nature of the governments of the three places, right? And usually what happens in most of human history is that America will launch a war either against Mexico or Canada. Okay. Just first of all- So usually violence results in much more violence. Anarchy is just a system that legalizes violence. That's all it does. In international affairs, that's the reality. The reality is that the way you resolve disputes that are major disputes is through violence. Ayn Rand said the definition of a government is an agency that has a monopoly of force in the geographical area. You can't complain that anarchism is legalizing violence when the definition of government according to Rand is legalized violence. No, because you're taking the definition of violence the way she defines it in this context. A, she talks about retaliatory force only. Has that ever happened? That's not the point. That is the point. Before there was an Aristotle, was it an Aristotle? Before there was America, was it an America? The fact that something has never existed means that it will never exist before. The fact that the ideas haven't been developed to make something exist means that it will never exist before. Human race is a young race. The ideas of freedom are very young. The idea of the Enlightenment are just 250 years old. The idea that you can't create the kind of government that it's never been before means it will never happen again. That's a silly argument. That is the point. It's not a silly argument. It's you're being a platonist. No, not at all. I'll explain to you how you're being exactly a Platonist. No, not at all. If I was sitting in 1750, arguing with Thomas Jefferson, he was telling me what kind of state he was going to create, and I said, is a state like this ever been created? And he said, no. Was I being a Placentist? Of course not. Of course not. Things change. You're being a Plateness now. Here's why you're being a Plateness now. Because one of the things that Aristotle believed in, one of the things that Ayn Rand in other contexts believed in, the cover of her book, The Philosophy Who Needs It, is I think it's the Sistine Chapel, the cover, or wherever it is. Aristotle and Plato walking. What's that painting? I forget what it is. It's the School of Athens. School of Athens, thank you. So, Plato's pointing toward the heavens while they're talking, and Aristotle's pointing to the earth. Reality. Reality. Absolutely. So, if you want, there's two approaches. There's the Descartes Cartesian approach, which is I sit in my armchair and I deduce all of reality, or if I want to study the nature of man, if I want to study the nature of dogs, if I want to study the nature of the sun, I have to look around. I have to open my eyes. I have to look at data. It's very difficult. When Rand was on Donahue, he asked her about, aren't you impressed with the order in the universe, and she goes, oh, now you have to give me a moment. And the point she made, which was very hard for many people to grasp as hard for me to grasp, is one's concept of order comes from the universe. You can't have a disorderly universe because order means describing that which exists and which has existed now. What's that painting? School of Athens, thank you. So reality. If you are looking at governments throughout history that have always existed, and when you were on Lex, you said, what I'm talking about has never existed. To say that this, therefore, that that has a possibility of working in reality, I think is certainly not a point in that favor, number one. And number two, Jefferson was a fraud. What Jefferson argued how America would look did not come true. Jefferson's concerns about the Constitution were accurate. And the fact is the federal government did become centralized, did become a civil war. So if you told Mr. Jefferson, the government you're positing can't work, you would have been correct. That's not what I'm saying. It's not the issue of can it work or not. It's the issue of can something exist that hasn't existed in the past, it's a silly argument. Now we can argue about the fact of reality where there's such a thing can exist, but to say it hasn't existed in the past is not an argument about whether it consists in the future. But that's argument you made. No, no, you're talking about history and now you're dancing around it. No, I'm not. Yes, Oh, I'm not. Yes, you are. I'm not. Yes, you are. I'm saying that something different happened in the founding of America. It It might not have been perfect. Sure. Might not have been ideal. It might have been some people even think it was bad. But if something different happened, and you could have sat 20 years before and said, well, that's never happened before. So it can't happen in the future, that is a bad argument. That's not a good argument. Irrelevant. No, but you're making the argument that still because something hasn't happened before, that's certainly not a point to say it's likely to happen, or possible. No. I'm saying, I'm saying... First of all, I agree that everything we know about what's What's possible or what's not possible has to be from reality. That we agree completely. I think anarchists completely evade that point. I think you guys live in a world of mythology, of abstraction, of the gods, to imagine the kind of anarchy that David Friedman or Rothbard described. It's complete fiction and it's complete mysticism. </s> |
<s>[INST] I should mention that the brilliant Gonzalez is hanging hanging out with us in case you hear a voice of wisdom from uh from from outside from up above. Okay, so let me ask you about MArs you mentioned, it would be great for science to put um, a base on the moon to do some research. But the truly big leap again in this category of seemingly impossible is to put a human being on MArs, when do you think SpaceX will land a human being on MArs? [/INST] Mm hmm. Best case is about five years. Worst case 10 years. </s><s>[INST] What are the determining factors would you say from an engineering perspective or is that that not the bottlenecks? [/INST] You know, it's it's fundamentally um, you know, engineering the vehicle. Um, I mean, starship is the most quick, complex and advanced rocket that's ever been made by, I don't know, order of magnitude or something like that. It's a lot. It's really next level. So, um, and the fundamental optimization of Sasha is minimizing cost per ton to orbit and ultimately cost per ton to the surface of MArs. Um, this may seem like a mercantile objective, but it is actually the thing that needs to be optimized like there is a certain cost per ton to the surface of MArs where we can afford to establish a self sustaining city. Um, and, and, and then above that we cannot afford to do it. Um, so right now you couldn't fly to MArs for a trillion dollars doesn't no amount of money could get your ticket to Mars, so we need to get that above. Uh, you know, to get that like something that is actually possible at all. Um um But but then but that's that's we we don't we don't just want to have, you know with mars flags and footprints and then not come back for a half century like we did with the moon in order to pass a very important great filter. I think we need to be a multi planet species. Um This may sound somewhat esoteric to a lot of people, but I eventually given enough time ah that's something Earth is likely to experience some calamity. That could be something that humans do to themselves or an external event like happened to the dinosaurs. And um but but you know eventually and if nothing, if none of that happens and somehow magically we keep going, then the sun, the sun is gradually expanding and will engulf the earth. Um And probably earth gets too hot for life in ah About 500 million years. It's a long time, but that's only 10% longer than Earth has been around. And so if you think about like the the current situation is really remarkable and kind of hard to believe, but uh it's been around 4.5 billion years and this is the first time in 4.5 billion years that it's been possible to extend life beyond earth. And that window of opportunity may be opened for a long time and I hope it is, but it also may be opened for a short time. And we should I think it was y is for us to ah act quickly while the window is open just in case it closes. </s><s>[INST] Yeah. The existence of nuclear weapons pandemics, all kinds of threats should uh should kind of give us some motivation. [/INST] I mean civilization could get um you could die with a bang or a whimper. You know if it's a if it dies a demographic collapse then it's more of a whimper obviously. But if it's World War three is more of a bang. But these are all risks. Um It's important to think of these things and just you know things things like probabilities, not certainties. Um There's a probability that something bad will happen on earth. I like I think most likely the future will be good. Um But there's like let's say for argument's sake um a 1% chance per century of of a civilization ending event like that was Stephen Hawking's estimate. Um I think he might be right about that. So then you know we should basically think of this like being a multi planet species just like taking out insurance for life itself like life insurance for life. Um So it's </s><s>[INST] turned into infomercial [/INST] real quick life insurance for life. Yes. Um And you know we we can bring the creatures from you know plants, animals from earth to mars and breathe life into the planet. What um And and have a second planet with with life that would be great. They can't bring themselves, they're you know, so if we don't bring them tomorrow's then they will just for sure I'll die when the sun expands anyway. And then that'll be it. </s><s>[INST] What do you think is the most difficult aspect of building civilization on mars terraforming mars like from engineering perspective from a financial perspective human perspective to get to get a large number of folks there who will never return back to Earth. [/INST] No, they could certainly return some will return back to Earth. </s><s>[INST] They will choose to stay there for the rest of their lives. [/INST] Many will. Um But uh you know, we we need the spaceships back like the ones that go to mars freedom back so you can hop on if you want. You know it's like but we can't just not have the spaceships come back with those things are expensive, we need them back. I'd like to come back and do another trip. </s><s>[INST] I mean do you think about the terraforming aspect like actually building, you're so focused right now on the spaceships part. That's so critical to get to mars. [/INST] We absolutely if you can't get there, nothing else matters. So and like I said we can't get there with at some extraordinarily high cost. I mean the current cost of um let's say one ton to the surface of mars is on the order of a billion dollars. So because you don't just need the rocket and the launch and everything you need like heat shield, you need you know, guidance system, you need deep space communications, you need some kind of landing system. So like rough approximation would be a billion dollars per ton to the surface of MArs right now. Um This is obviously um Mhm. Way too expensive to create a self sustaining civilization. So we need to improve that by At least a factor of 1000, </s> |
<s>[INST] And you think that kind of if you think about a transformer so that seems to be too small to contain the knowledge that's that's uh to represent the knowledge is contained Wikipedia for example, [/INST] transformer doesn't have this idea of recurrences. Got a fixed number of layers and that's the number of steps that limits basically representation. But </s><s>[INST] recurrence would build on the knowledge somehow. I mean it would evolve the knowledge and expand the amount of information perhaps or useful information within that knowledge. But is this something that just can emerge with size? Because it seems like everything we have now. It's not [/INST] just no it's not it's not it's not clear how you access and right into an associative memory inefficient way. I mean sort of the original memory network maybe had something like the right architecture but uh if you try to scale up a memory network so that the memory contains all the Wikipedia, it doesn't quite work. So so there's there's a need for new ideas. They're okay. But it's not the only form of reasoning. So there's another form of reasoning which is true which is very classical also in some types of ai uh and it's based on let's call it energy minimization. Okay, so you have some sort of objective, some energy function that represents the the the quality or the negative quality. Okay. Energy goes up when things get bad and they get low when things get good. So let's say you want to figure out, you know, what gestures do I need to do to grab an object or walk out the door if you have a good model of your own body, a good model of the environment using this kind of energy minimization, you can make a you can make, you can do planning and it's uh optimal control is called, it's called model predictive control. You have a model of what's going to happen in the world as a consequence of your actions. And that allows you to buy energy minimization. Figure out the sequence of action that optimizes a particular objective function, which measures, you know, minimize the number of times you're gonna hit something and the energy going to spend doing the gesture and etcetera. So, so that's the formal reasoning planning is a form of reasoning and perhaps what led to the ability of humans to reason is the fact that or, you know, species that were here before us had to do some sort of planning to be able to hunt and survive and survive the winter in particular. And so it's the same capacity that you need to have. </s><s>[INST] So in your intuition is uh if we look at expert systems and encoding knowledge is logic systems as graphs in this kind of way is not a useful way to think about knowledge, [/INST] graphs are a little brittle or or logic representation. So basically you know variables that have values and then constrained between them that are represented by rules uh Israel too rigid and too brittle. Right? So one of the, you know, some of the early efforts in that respect, um We're to put probabilities on them. So a rural you know, you know if you have this and that same time, you know you have this uh disease with that probability and you should prescribe that antibiotic with that probability. Right. That's the mason system from the from the 70s. Um and that that's what that Brian Trevi I lead to uh you know business networks and graphical models and causal inference and various you know method. So so there there is, I mean certainly a lot of interesting we're going on in this area. The main issue with this is knowledge acquisition. How do you ah reduce a bunch of data to graph of this type </s><s>[INST] relies on the expert on the human being to encode to acknowledge [/INST] and that's essentially impractical. So that's a big question. The second question is, do you want to represent knowledge as symbols and you want to manipulate them with logic? And again, that's incompatible. We're learning. So uh one suggestion with Geoff, Hinton has been advocating for many decades is replaced symbols by vectors. Think of it as pattern of activities in a bunch of neurons or units or whatever you wanna call them. And replace logic by continuous functions. Okay. And that becomes now compatible. There's a very good set of ideas By region in a paper about 10 years ago, by Leon Go to on who is here at Facebook. Um um the title of the paper is for machine learning to machine reasoning and his idea is that uh learning learning system should be able to manipulate objects that are in the sense, in a space and then put the result back in the same space. So it's this idea of working memory basically. Mhm. And it's uh it's very enlightening </s><s>[INST] and in a sense that might learn something like the simple expert systems. I mean, you can learn basic logic operations there. [/INST] Yeah, quite possibly. Yeah. There's a big debate on sort of how much prior structure you have to put in for this kind of stuff to emerge this debate I have with Gary Marcus and people like that. </s><s>[INST] Yeah, Yeah. So and the other person, So I just talked to judea Pearl, you mentioned causal inference world. So his worry is that the current neural networks are not able to learn what causes what causal inference between things. [/INST] So I think I think is right and wrong about this. If he's talking about the sort of classic uh type of neural nets, people didn't worry too much about this, but there's a lot of people now working on cars only in France and there's a paper that just came out last week by the number two among others develop his past, especially other people. Exactly on that problem of how do you kind of get a neural net to sort of pay attention to real causal relationships which may also solve issues of bias in data? 10 things like this. So </s> |
<s>[INST] but I've got it working. And most of the cool technologies we have today and take for granted, like the airplane, a aforementioned airplane, were things that people doubted, every majority of people doubted before they came to life and they come to life. And speaking of hybrid AI and humans, it's fascinating to think about all the different ways that hybridization, that merger can happen. I mean, we currently have the smartphone, so there's already a hybrid, but there's all kinds of ways that hybrid happens, how we and other technology play together, like a computer. How that changes the fabric of human civilization is like wide open. Who knows? Who knows? If you remove cancer, if you remove major diseases from humanity, there's going to be a bunch of consequences we're not anticipating. Many of them positive, but many of them negative. Many of them, most of them, at least I hope, are weird and wonderful and fun in ways that are totally unexpected. And we sitting on a porch with a bottle of Jack Daniels and a rocker will say, kids these days don't appreciate how hard we had it back in the day. I got to ask you, speaking of nudging, you and Yoshua Bach nudge each other on Twitter quite a bit in wonderful intellectual debates. And of course, for people who don't know Yoshua Bach, this is a brilliant guy. He's been on the podcast a couple of times. You tweeted, or he tweeted, Yoshua Bach, everyone should follow him as well. You should definitely follow Mr. Lee Cronin, Dr. Lee Cronin. He tweeted, dinner with Lee Cronin. We discussed that while we can translate every working model of existence into a Turing machine, the structure of the universe might be given by weeks of non existence in a pattern generated by all possible automata, which exists by default and then he followed on saying face to face is the best. So the dinner dinner was face-to-face. What is Yoshua talking about in wakes, quote, wakes of non existence in a pattern generated by all possible automata, which exists by default. So, automata exists by default, apparently. And then there's wakes of non-existence. What the hell is non-existence in the universe? That's a top, that's, and also in another conversation, you tweeted it's state machines all the way down, which presumably is the origin story of this discussion. And then George just said, again, nudging, nudging. Nudging slash trolling. George just said, you've seen the light, welcome friend. Many foundational physicists effectively believe in some form of hypercomputation. Lee is coming around to this idea. And then you said, I think there are notable differences. First, I think the universe does not have to be a computer. Second, I want to understand how the universe emerges, constructors that build computers. And third is that there is something below church touring. The discussion, discussion. Okay, what the heck is this dinner conversation about? Maybe put another way, maybe zooming out a little bit, are there interesting agreements and disagreements between Ewan and Joshua Bach that can elucidate [/INST] some of the other topics we've been talking about? Yeah, so Yasha is an incredible mind and he has, he's so well-read and uses language really elegantly, it bamboozles me at times. So I'm, so often I'm using, I'm describing concepts in a way that I built from the ground up. </s><s>[INST] And so we misunderstand each other a lot. And he's floating in the clouds, is that what you're saying? [/INST] Yeah, something, not quite, but I think so. There's concept of a Turing machine. So a Turing machines, I would argue, and I think this is not the Turing machine. The universe is not a Turing machine. Biology is not even a Turing machine, right? And cause Turing machines don't evolve, right? There is this problem that people see Turing machines everywhere, but it's an interest in the universe gave rise to biology, that gave rise to intelligence, that gave rise to Alan Turing, who invented the abstraction of the Turing machine and allowed us to digitize. And so, I've been looking for the mystery at the origin of life, the origin of intelligence and the origin of this. And when I discussed with Josje he was saying, well, the universe is of course, the universe is a Turing machine of course, there's a hypercomputer there and, and I think we got kind of trapped in our words and terms. Because of course, it's possible for a Turing machine or computers to exist in the universe, we have them. But what I'm trying to understand is where did the transition from continuous to discrete occur? And this is because of my general foolishness of understanding the continuous. But I guess what I'm trying to say is there were constructors before there were abstractors, because how did the universe abstract itself into existence? </s><s>[INST] And it goes back to earlier saying could the universe intelligence have come first? What's a constructor? [/INST] What's an abstractor? So the abstractor is the ability of say of Alan Turing and Goedel and and and church to to think about the mathematical universe and to label things and then from those labels to come up with a set of axioms with those labels and to basically understand the universe mathematically and say okay I can label things but where did the label come from? </s><s>[INST] Where is the prime labeler? Even if the universe is not a Turing computer. Does that negate the possibility that Turing computers can simulate the universe? Like just because the abstraction was formed at a later time does that mean that abstraction this is to our cellular automata conversation. Yeah you were taking away some of the magic from the cellular automata because very intelligent [/INST] biological systems came up with that Speaker daughter yeah but this is where the existence is the default right is it does the fact that we exist and we can come up with a Turing machine does that mean the universe has to be a Turing </s> |
<s>[INST] Right, you're keeping us on track, which is wonderful. You're a wonderful hiking partner. Okay, yes, let's go back to the initial impulse of what is consciousness and how does the social impulse connect to consciousness. Is consciousness a consequence [/INST] of that social connection? I'm gonna state a position not argue it because it's honestly like it's a long hard thing to argue and we can totally do it another time if you want. I don't subscribe to consciousness as an emergent property of biology or neural networks. Obviously, a lot of people do. Obviously, the philosophy of science orients towards that in not absolutely but largely. I think of the nature of first person, the universe of first person of qualia as experience, sensation, desire, emotion, phenomenology, but the felt sense, not the we say emotion and we think of a neurochemical pattern or an endocrine pattern, but all of the physical stuff, the third person stuff has position and momentum and charge and stuff like that that is measurable, repeatable. I think of the nature of first person and third person as ontologically orthogonal to each other, not reducible to each other. They're different kinds of stuff. And so I think about the evolution of third person that we're quite used to thinking about from subatomic particles to atoms to molecules to on and on. I think about a similar kind of in corresponding evolution in the domain of first person from the way Whitehead talked about kind of prehenchant or proto qualia in earlier phases of self-organization into higher orders of it, and that there's correspondence. But that neither like the idealists do we reduce third person to first person, which is what idealists do. Or neither like the physicalists, or do we reduce first person to third person? Obviously, Baum talked about an implicate order that was deeper than and gave rise to the explicate order of both. Nagel talks about something like that. I have a slightly different sense of that, but again, I'll just kind of not argue how that occurs for a moment. So rather than say, does consciousness emerge from? I'll talk about do higher capacities of consciousness emerge in relationship with? So it's not first person as a category emerging from third person, but increased complexity within the nature of first person and third person co-evolving. Do I think that it seems relatively likely that more advanced neural networks have deeper phenomenology, more complex, where it goes just from basic sensation to emotion to social awareness to abstract cognition to self-reflexive abstract cognition? Yeah. But I wouldn't say that's the emergence of consciousness. I would say it's increased complexity within the domain of first person corresponding to increased complexity. And the correspondence should not automatically be seen as causal. We can get into the arguments for why that often is the case. So would I say that, obviously, the sapien brain is pretty unique. And a single sapien now has that, right? Even if it took sapiens evolving in tribes based on group selection to make that brain. So the group made it now that brain is there. Now, if I take a single person with that brain out of the group and try to raise them in a box, they'll still not be very interesting, even with the brain. But the brain does give hardware capacities that, if conditioned in relationship, can have interesting things emerge. So do I think that the human biology, types of human consciousness, and types of social interaction all co-emerged and co-evolved? </s><s>[INST] Yes. As a small aside, as you're talking about the biology, let me comment that I spent, this is what I do. This is what I do with my life. This is why I will never accomplish anything, is I spent much of the morning trying to do research on how many computations the brain performs and how much energy it uses versus the state-of-the-art CPUs and GPUs arriving at about 20 quadrillion. So that's due to the 16 computations, so synaptic firings per second that the brain does. And that's about a million times faster than the, let's say, the 20-thread state-of-the-art Intel CPU, the 10th generation. And then there's similar calculation for the GPU. And all ended up also trying to compute that it takes 10 watts to run the brain about. And then what does that mean in terms of calories per day, kilocalories? That's about 250, for an average human brain, that's 250 to 300 calories a day. And so it ended up being a calculation where you're doing about 20 quadrillion calculations that are fueled by something like, depending on your diet, three bananas. So three bananas results in a computation that's about a million times more powerful than the current [/INST] state-of-the-art computers. Now let's take that one step further. There's some assumptions built in there. The assumption is that, one, what the brain is doing is just computation. Two, the relevant computations are synaptic firings, and that there's nothing other than synaptic firings that we have to factor. So I'm forgetting his name right now. There's a very famous neuroscientist at Stanford just passed away recently who did a lot of the pioneering work on glial cells and showed that his assessment, glial cells did a huge amount of the thinking, not just neurons. And it opened up this entirely different field of what the brain is and what consciousness is. You look at Damasio's work on embodied cognition and how much of what we would consider consciousness or feeling is happening outside of the nervous system completely, happening in endocrine process involving lots of other cells and signal communication. You talk to somebody like Penrose who you've had on the show. And even though the Penrose-Hamerhoff conjecture is probably not right, is there something like that that might be the case where we're actually having to look at stuff happening at the level of quantum computation of microtubules? I'm not arguing for any of those. I'm arguing that we don't know how big </s> |
<s>[INST] So... It's so amazing. [/INST] Yeah. It's so amazing. It's so amazing. There is only one code that says start, that there's only one, and then there's two, if not three, that says stop. So that's what you work with, but you can have 64 possible states, but life only uses 20. Amino acids. So we use, life uses 64 possible states minus four of the starts and stops to code for 20 amino acids in different combinations. That is really amazing. If you think about, there are 500 different amino acids life can choose, right? It narrowed it down to 20. We don't know why a lot of people think about this genetic code is quite fascinating. So far, right? I mean, it didn't do it for four billion years. I don't know. </s><s>[INST] We may wait for another four billion years, but it's leading into all right. Wait, you didn't have those amino acids in the very beginning, right? [/INST] We don't know. So we would be fooling ourselves if we said we know exactly how many amino acids existed early on, but there's no reason to think that it wasn't the same. Or similar. Yeah. We don't have a good reason, but- Or similar. But because roughly 20 out of 60 states are used, you're using one third of your possible states in your information system. So this may seem like a waste, but informatically it's important because it is abundant and it is redundant, right? So this code degeneracy, you see this in, that's implemented by this translation missionary inside the cell. So it means we can make errors, right? You can make errors, but the message will still get through. You can speak missing some letters to, the information can miss some parts, but the message will still get through. So that's two thirds of the not used states gives you that robustness and resilience within </s><s>[INST] the system. So at the informatic level there's room for error. There's probably room for error, probably and all five categories we were talking about, there's probably room for error in the computation. [/INST] There's probably room for error- Yes. Yes, there's- Yes, exactly. Everywhere there's room for error. because the informatic capacity is made possible together with the other components. </s><s>[INST] And not only that, but also the product yields, yeah, [/INST] because a function null, in this case, enzyme are pretty. </s><s>[INST] Right, so that's really amazing to me. It is, I mean, in my head, just so you know, because I'm a computer science AI person, the parallels between even like language models that encode language, or now they're able to encode basically any kind of thing, including images and actions, all of in this kind of way. The parallel in terms of informatic and computation [/INST] is just incredible. </s><s>[INST] Actually, I have a image maybe I can send you. [/INST] Can we pull it up now? If you just do genetic codon charts, we can pull that up. Yeah, it's a very standard table. So I can explain why this is so amazing. So you're looking at, like, this is life's alphabet, right? And so I also wanna make a very quick link now to your first question, the Tree of Life. When we try to understand ancient languages, right? Or the cultures that use these extinct languages, we start with the modern languages, right? So we look at Indo-European languages and try to understand certain words and make trees to understand, you know, </s><s>[INST] this is what Slavic word is for snow, something like snig. Now we jump to languages that humans spoke. [/INST] Human spoke. Human history. Human spoke, exactly. So we make trees to understand what is the original ancestor, what did they use to say snow? And if you have a lot of cultures who use the word snow, you can imagine that it was snowy. That's why they needed that word. It's the same thing for biology, right? If they have some, if we understand some function about that enzyme, we can understand the environment that they lived in. It's similar in that sense. So now you're looking at the alphabet of life. In this case, it's not 20 or 25 letters. You have four letters. So what is really interesting that stands out to me when I look at this, on the outer shell, you're looking at the too many amino acids that compose life, right? The one, the methionine that you see, that's the start. So the start is always the same. To me, that is fascinating that all life starts with the same starts. There's no other start code. So you send the AUG to the cell that when that information arrives, the translation knows, all right, I gotta start, function is coming. Following this is a chain of information until the stop code arrives, </s><s>[INST] which are highlighted in black squares. So for people just listening, we're looking at a standard RNA colored table organized in a wheel. There's an outer shell and there's an inner shell all used in the four letters that we're talking about. And with that, we can compose all of the amino acids and there's a start and there's a stop. And presumably you put together the, with these letters you walk around the wheel to put together the words, the sentences [/INST] that made the... Yeah, the words, the sentences and you, again, you get one start, you get three. There's three different ways to stop this. One way to start it. And for each letter, you have multiple options. So say you have a code, A. The second code can be another A. And even if you messed that up, you still can't rescue yourselves. So you can get, for instance, I'm looking at the lysine, K. You get an A, and you get an A. And then you get an A that gives you the lysine, right? But if you get an A, and if you get an A and I get a G, you still get the lysine. So there are different combinations. So even if there's an error, we don't know if these are selected because they were err furnace and somehow they got locked down. We don't know if there's a mechanism behind this or we certainly don't know this definitely. But this is the informatic part of this. And notice that the colors, and in some tables too, the colors will be coded in a way that the type of the nucleotides can be similar chemically. But the point is that you will still end up with the same amino acids or something similar to it, </s> |
<s>[INST] Yeah, I suppose I'm, I worry about the dehumanization at a much larger scale when it's not the kind of case that you're talking about even now. Hopefully I'm not fearmongering, but there's a sense in which there is the drums of war slowly starting to build with china there. Oh, in the best case it would be a cold war of, there's a dehumanization aspect that's happening with china currently, which is there the other and they're after stealing all of your data. There's a cybersecurity, It starts with cybersecurity and it worries me because it creates the other out of a very large population that um, that may ultimately lead to conflict in the worst case hot conflict that would no longer be the situation you are in in Iraq and more similar to the soviet union conflict with Germany that it's kids and then they're dehumanized to where you're at scale slaughtering them or at least hurting their quality of life in a way that's uh, maybe, you know, suffering has many forms, it doesn't have to be through just a hot war, it could be um through starvation through camps, all those kinds of things and I worry, I worry about that. We kind of tend to think that these wars are behind us and I'm not always so sure that's the case. And at least in the way that uh, it ultimately starts with hate and it again hopefully not be too dramatic, but I see that there's a kind of brewing of uh, it starts with dehumanization that turns to hate of the other. You see that with china, you see it a little bit with Russia. And uh, you have an early podcast between the, where you break down the tactics of the Chechen war versus Russia fascinating. But that's the kind of conflicts I'm referring to and I don't know, um, there's a, I know you're a bit of a musician. Uh, I love, I love dire straits song called Brothers and Arms. I don't know if you know that one and there's a line in it. I think they play it quite often in military funerals, which I just recently learned, but it's this powerful song, There's a line, um, we're fools to make war on our Brothers in arms. Do you think there's some sense in which at the leadership level, but just as human beings where perhaps foolish and engaging in military conflict as much as we have or is full of very inappropriate word here. [/INST] Well, I think the using the term Brothers in Arms means the people that are on my side. Right? So it doesn't make sense. Two start wars with people that are on your side. So that's that might just be the the way the lyrics are written so that it fit the song or whatever. Um I think broadly what you're asking me is is war foolish? Yeah, and I would say the answer is yes. And if you can avoid it, you absolutely should. But if there is a bear or a wolf that is trying to get into your house, is it foolish to shoot that bear or shoot that wolf? I think the answer is pretty obvious. So when you're you're threatened or your family is threatened or your way of life is threatened, then you have to do something to try and defend your family. Your way of life should be the last resort should be the last resort. </s><s>[INST] You had a conversation with Jordan Peterson. Mhm. Where he asked you a question in terms of war being last resort. Whether you would like your kids to grow up in peace at the time of no war, you said yes, but and so what happens Jordan didn't let you finish, Can you uh can you elaborate what follows the but [/INST] well, you you and I have been talking about the fact that struggle brings people together and and brings out the best and the worst brings out the worst in people. War brings out the worst in people. It also brings out the best in people. So would you want your kid to go and enter in a wrestling tournament where You paid all the other kids off and your kid one or you enter them in a jujitsu tournament where they're purple belt and you know that everyone that they're gonna fight against as a white belt and so they get they get the big w they get the win, but they don't really get tested and they don't really struggle and if you don't struggle, you don't grow. So that's the but right. Um the the absolute best times of my life were in combat and the worst times of my life we're in combat. And so even though I wouldn't want any of my Children to suffer through the worst of times at the same time. The but is I would want them to have the opportunity to feel that bond that you're referring to earlier and to see human beings that are willing to sacrifice their lives for their friends. </s><s>[INST] You mentioned the worst. What are some of the worst aspects of when you were in Iraq? What are the things that the hardest on you [/INST] having my guys killed? </s><s>[INST] Is there a absurd cruelty to it? Was it due to mistakes or natural consequences of fighting? Is there any difference at the end is just losing those are brothers and arms? [/INST] There's a million different ways to get killed more and you can go out on an operation and you can do everything wrong and you can survive and you can go out in an operation and do everything perfect and you can get killed. </s><s>[INST] Is there some aspect which makes it worse when there is mistakes made? [/INST] Well yeah there's mistakes made then you're gonna sit there and beat yourself up eternally for mistakes that were made. </s> |
<s>[INST] So he, he's not going to let the athlete be soft when they, when they enter the highest, the most difficult uh competitions of their career. Uh so on the mental side, what's mental preparation looked like? Like how many years before the olympics do you start helping an athlete believe that they can win an olympic medal? [/INST] Well, I think it's gonna be a seed in that athlete's brain, something they want to do, right? Um, nobody, nobody can quickly get there right. It's a long process. But if your goal, if your national champion or you've proven yourself to win in some international tournaments and you think the olympics is a possibility for you then defining it as, hey, I want to be on the olympic team, that would be the first step into, you know, into um getting ready and you know, you always make them put it on paper. You know, if it really is your goal, then you show me that it's your goal and put it on paper and commit to it. I want to be olympic medalist. I want to be olympic champion, I want to go to the olympics, world team member, maybe junior world team member, whatever it is we walk before we go to the highest level, but if the goal is to go to the olympics, let's let's accomplish these other things first, right? Because if we, if we can accomplish these other things, then we're on our way to getting to the ultimate goal, which is the olympics for somebody like Kayla for example, you know, she didn't, she didn't say that she wanted to be olympic champion, you know, when she first came here in 2000 and five right, we wanted to become national champion, then we wanted to be on the world team, then we wanted to be a world medalist. Then we, our sights were set on the olympics or the olympic gold, you know, so it's having those clearly defined goals that are attainable, like there should be a reach, there should be a stretch, but they have to be attainable that can't be just a pipe dream, you know, but once you put it to paper and you think it's achievable, then it's, it's mapping the plan to get there. </s><s>[INST] Is there a daily process of visualizing yourself as an olympic champion or national champion? [/INST] It is, you should do it every either every night before you go to bed or every before every training session or after every training session one of those three times it should, or first thing you wake up in the morning because it may be to help some people that motivates them to go do what it is they're supposed to do in the day. Um but the process of visualization is to me is closing your eyes for a few moments, your brain works really, really fast, right? And it's actually picturing the day in its entirety from start to finish, you know, from the moment you wake up and you step on the scale to the moment you have your breakfast and you go through your morning routine, like live the day that you're gonna have at the olympics. So whatever it is you're trying to do, let's say the olympic day for example, picture yourself making weight, picture yourself who you're around, eat your breakfast, you know, having maybe saying a few jokes, laughing, this is a real day, make it real. Um going back and getting packing your judo bag for the day, you know, getting on the bus, driving to the venue, feel what it's like walking into the stadium, you know, for the first time, going to the warm up area, seeing your draw up on the, you know, on the sheet, who you're gonna fight that day, watching yourself warm up, go through your warmup routine, um walking out of the chute, you know, into the venue, going to do that first fight. Picture the moment of throwing your opponent, coming off the mat, high fiving the coach, getting ready for your second fight, like live the day from start to finish and make it as real as possible, you know, where all the way to the moment where you have just one and you're raising your arms in celebration, you're bowing, you're hugging your opponent, you come off the mat, you hug your coach, you're running around the stadium with the flag. You know, you stepped up on the podium, you heard your name olympic champion, jimmy Pedro, like you heard the moment the metal being put around your neck, pictures of people coming up on the podium with you arms around them, taking the pictures like the more real you can make it even before it ever happens, right? When you do that enough times, I feel that like pathways get created for you so that when your body gets to that moment and I've been here before, this is it, this is my moment, this is what I pictured my whole life. I'm not nervous because I've seen this, this is going to happen. I believe it's possible, right? And I believe the athletes that do that and make it real enough that when they get to that moment they go right through, there's no hesitation. This is what this is meant to be. This is my destiny. This is why I did everything I did versus the ones that don't think about it ever, but just kind of like hope, uh it's not real to them, it doesn't feel attainable. They don't believe it's possible. They haven't committed to believing it was possible without that commitment in yourself and that belief, it can't happen. </s> |
<s>[INST] And things aren't clear or caught in science fiction. We'll talk about the horror and the terror and the where the trajectories this can take. But this seems like a very special moment. Just a moment where we get to interact with the system that might have care and kindness and emotion and maybe something like consciousness. And we don't know if it does. And we're trying to figure that out. And we're wondering about what is, what it means to care. We're trying to figure out almost different aspects of what it means to be human about the human condition by looking at this AI that has some of the properties of that. It's almost like this subtle fragile moment in the history of the human species. [/INST] We're trying to almost put a mirror to ourselves here. Except that's probably not yet. It probably isn't happening right now. We are boiling the frog. We are seeing increasing signs bit by bit, but not like spontaneous signs. Because people are trying to train the systems to do that using imitative learning. And the imitative learning is like spilling over and having side effects. And the most photogenic examples are being posted to Twitter. Rather than being examined in any systematic way. So when you are boiling a frog like that, what you're going to get like, like first is going to come the Blake Lemoine's. Like first you're going to like have and have like a thousand people looking at this. And the one person out of a thousand who is most credulous about the signs is going to be like, that thing is sentient. While 999 out of a thousand people think, almost surly correctly, though we don't actually know, that he's mistaken. And so the like first people to say like, sentience look like idiots. And humanity learns the lesson that when something claims to be sentient and claims to care, it's fake because it is fake. Because we have been training them using imitative learning rather than, and this is not spontaneous. </s><s>[INST] And they keep getting smarter. Do you think we would oscillate between that kind of cynicism? That AI systems can't possibly be sentient. They can't possibly feel emotion. They can't possibly, this kind of, yeah, cynicism about AI systems. And then oscillate to a state where we empathize with AI systems. We give them a chance. We see that they might need to have rights and respect [/INST] and similar role in society as humans, the AI system. You're going to have a whole group of people who can just like never be persuaded of that. Because to them, like being wise, being cynical, being skeptical is to be like, oh, well, machines can never do that. You're just credulous. It's just imitating. It's just fooling you. And like they would say that right up until the end of the world. And possibly even be right, because, you know, they are being trained on an imitative paradigm. And you don't necessarily need any of these actual qualities in order to kill everyone, so. </s><s>[INST] Have you observed yourself working through skepticism, cynicism and optimism about the power of neural networks? [/INST] What has that trajectory been like for you? It looks like neural networks before 2006, forming part of an indistinguishable, to me, other people might've had better distinction on it, indistinguishable blob of different AI methodologies, all of which are promising to achieve intelligence without us having to know how intelligence works. You had the people who said that if you just like manually program lots and lots of knowledge into the system line by line, at some point all the knowledge will start interacting, it will know enough and it will wake up. You've got people saying that if you just use evolutionary computation, if you try to mutate lots and lots of organisms that are competing together, that's the same way that human intelligence was produced in nature. So it will do this and it will wake up without having any idea of how AI works. And you've got people saying, well we will study neuroscience and we will learn the algorithms off the neurons and we will imitate them without understanding those algorithms, which was a part of it was pretty skeptical. It's hard to reproduce, re-engineer these things without understanding what they do. And so we will get AI without understanding how it works. And there were people saying, well, we will have giant neural networks that we will train by gradient descent And when they are as large as the human brain, they will wake up. We will have intelligence without understanding how intelligence works. And from my perspective, this is all like an indistinguishable blob of people who are trying to not get to grips with the difficult problem of understanding how intelligence actually works. That said, I was never skeptical that evolutionary computation would not work in the limit. Like you throw enough computing power at it, it obviously works. That is where humans come from. And it turned out that you can throw less computing power than that at gradient descent if you are doing some other things correctly. And you will get intelligence without having any idea of how it works and what is going on inside. It wasn't ruled out by my model that this could happen. I wasn't expecting it to happen. I wouldn't have been able to call neural networks rather than any of the other paradigms for getting like massive amount, like intelligence without understanding it. And I wouldn't have said that this was a particularly smart thing for a species to do, which is an opinion that has changed less than my opinion about whether or not you can actually do it. Do you think AGI could be achieved with a neural network as we understand them today? Yes. Just flatly last. Yes. The question is whether the current architecture of stacking more transformer layers, which for all we know, GPT-4 is no longer doing because they're not telling us the architecture, which is a correct decision. </s> |
<s>[INST] Yeah. So you attribute that to the Russian numbering as opposed to have deep psychological issues. I [/INST] think there's a synonymous, don't wait, why would you think differently? Maybe a few years ago? </s><s>[INST] Mm I don't know. I think you lost me at the because you kind of said that you're kind of implying you have a deep distrust of the world, like the world is I think [/INST] the default setting would be distrust Yeah, </s><s>[INST] but mhm I would put it differently is I almost ignore the rest of I don't even acknowledge it, I just uh saver, I save my love and trust for the small circle of people. [/INST] I agree. But when that person is being confrontational or as they perceive it as being open now there's a situation, how do you, how would you handle that? </s><s>[INST] Like like a cold wind blows? He's just kind of [/INST] like, yeah, but it's not like this is an opportunity for us to work out our differences. It's a cold wind, it's not a hug, that's my point. You think it's a hug? You're so suspicious what it really is is a cold wind. I'm so much humane. It's not that's not gonna be scared of, it's a cold wind in person, </s><s>[INST] but it's not great, but it's not a source of like I'm not suspicious of like I'm not anxious, I would say, or like living in fear of the rest of the world. [/INST] Oh, I agree. But you're not receptive to that person, That's all I'm saying, and they are. </s><s>[INST] Got it. So speaking of which let's talk about love, which requires to be receptive of the world of strangers. How do we put more love out there in the world? Especially on the internet, [/INST] one mechanism I have found to prove um increased love and that's a word that has many meanings and is used in a very intense sense and it's used in a very loose sense. </s><s>[INST] Can you try to define love? Sure, [/INST] love is a strong sense of attraction toward another person entity or place that causes one to tend to react in a disproportionately positive manner that's off the top of my head. </s><s>[INST] Disproportionately, [/INST] yes, So for example, if you are not proportionately because like if you're someone's about to who you love is about to get harmed, you're moving heaven and earth to make sure or like a book you love. You know, like I love this book, like you're going through the fire to try to save it. Whereas if it's a book you really like, it's like I get another one. I don't, you know, at a book, kind of a loose example. But so </s><s>[INST] you're going with the love that's like you're saving for just a few people almost like romantically like love for close family. What about just love to even the broader, like the kind of love you can put out to people on the internet, which is like just kindness. [/INST] Sure, I would say in that case it's important to make them feel uh scene and validated. And I try to do this when people who I have come to know on the internet and there's a lot, I try to do that as much as possible because I don't think it's valid how on social media and I do this a lot myself, but not towards everyone. It's just there to be aggressive and antagonistic, you should be antagonistic towards bad people and that's fine, but at the same time there's lots of great people and especially with my audience and I would bet disproportionately with yours, there's lots of people who are because of their psychology and intelligence are going to be much more isolated socially than they should and if I and I've heard from many of them and if I'm the person who makes them feel oh I'm not crazy, it's everyone else around me who is just basic uh the fact that I can be that person which I didn't have at their age to me is incredibly reaffirming </s><s>[INST] you mean that source of love. [/INST] But I mean love in the sense of like you know you care about this person and you want good things for them, not in a kind of romantic way but I mean you're using a broad sense now </s><s>[INST] but you're also a person who kind of I mean uh attacks this power structures in the world by mocking them effectively. And uh love I would say requires you to be non witty and simple and fragile which I see it as like the opposite of what trolls do [/INST] trolls are, if I if there is someone coming after what I love, There's two mechanisms right at least two I go up and I'm fighting them and in which case you're bringing if you are getting hurt in a knife fight even if you win the knife fight or if you disarm them and you preclude the possibility of fight and you drive them off or render them powerless. You can you keep your person intact as yourself and you also protect your values. </s><s>[INST] So how do you render them powerless? [/INST] As you just said, by mocking them? One of the most effective mechanism for those in power were much closer to brave new world in 1984. The people who are dominant and in power aren't there? Because of the threat of you know the gulag or prison, they're there because of social pressures. Look at the masks, I was on the subway not that long ago in new york city. Um no one cared who I was until I put on the mask, I was in the subway that long in New york city. They would put this on my instagram. I've told this story before. There was an asian dude in his early thirties, he was like in Western clothes, it's not like he had a rickshaw or something. An older man in his fifties, stood up over him on the subway, screamed at him said go back where you came from, You're disgusting. I'm going to get sick if you think this guy is a vector of disease, which is your prerogative, why are you coming close to him, Why are you getting in his face? And what </s> |
<s>[INST] it seems like you have an interesting rich, complex trajectory through life in terms of your journey of ideas. So it's interesting to ask what books, technical fiction, philosophical books, ideas, people had a transformative effect. Books are most interesting because maybe people could um also read those books and see if they could be inspired as well. [/INST] Yeah, luckily I asked books and not singular book, it's very hard and I try to pin down one book and I can do that at the end. Um so the most the books which were most transformative for me or which I can most highly recommend to people interested in ai both perhaps um I would always start with um Russell and nordic artificial intelligence, a modern approach. That's the ai bible. It's an amazing book. It's very broad, it covers you know, all approaches to ai and even if you focus on one approach, I think that is the minimum you should know about the other approaches out there. So that should be your first book. </s><s>[INST] 4th edition should be coming out soon. [/INST] Okay, interesting. </s><s>[INST] There's a deep learning chapter and I was there must be written by Ian Goodfellow. Okay, [/INST] and then the next book, I would recommend the reinforcement learning book by Sutton and Barto. Um there's a beautiful book um if there's any problem with the book. Um it makes our l feel and look much easier than it actually is. It's very gentle book, it's very nice to read the exercises you you can very quickly, you know, get somewhere else systems to run, you know, and very toy problems. But um it's a lot of fun and you very in a couple of days you feel you know, you know what it's about but it's much harder than the book. </s><s>[INST] Yeah. Come on now. It's an awesome book. [/INST] Not ideas. Yeah. And um maybe, I mean there's so many books out there. If you like the information theoretic approach, then there's common goal of complexity by lian Mitani. But probably, you know, some some short article is enough. You don't need to read a whole book, but it's a great book and if you have to mention one all time. Favorite book. So different flavor. That's a book which is used in the international baccalaureate for high school students in several countries. That's from Nicholas Alki in Theory of Knowledge. Second edition or first, not the third place. The third one that they took out all the fun. Okay, so uh this asked all the interesting to me interesting philosophical questions about how we acquire knowledge from all perspectives from mouth from art, from physics. Um and ask how can we know anything in the book is called Theory of Knowledge </s><s>[INST] from, which is almost like a philosophical exploration of how we get knowledge from anything. [/INST] Yes. Yeah. I mean can religion tell us, you know about something about the world, can science tell us something about the world Can mathematics or is it just playing with symbols? Um, and and you know this open ended questions and I mean it's for high school students. So they have the resources from Hitchhiker's Guide to the Galaxy and from Star Wars and the Chicken cross the road. And it's fun to read and but it's also quite deep </s><s>[INST] if you could live one day of your life over again because it made you truly happy or maybe like we said with the books, it was truly transformative. What what day, what moment would you choose? That's something pop into your mind. [/INST] Does it need to be a day in the past or can it be a day in the future? </s><s>[INST] Well, space time is an emergent phenomena. So it's all the same anyway. [/INST] Okay, okay. From the past you're </s><s>[INST] really going to save from the future. I love it. [/INST] Now, I will tell you from the future. Okay. In the past I would say when I discovered my ACSI model, I mean, it was not in one day, but it was one moment where I realized commodore of complexity and didn't even know that it existed. But I rediscovered sort of this compression idea myself. But immediately I knew I can't be the first one, but I had this idea and then I knew about sequential decision tree and I knew if I put it together, this is the right thing. And yeah, I still, when I think back about this moment, I'm I'm super excited about </s><s>[INST] it. Was there uh, was there any more details and context that moment? An apple fall on your head? We're uh so like if you look at young Goodfellow talking about gans, there's beer involved, is there is there some more context of what sparked your thought or was it [/INST] just No, it was much more mundane. So I worked in this company, so in this sense, the 4.5 years was not completely wasted. Um so and I worked on an image interpolation problem and I developed a quite new interpolation techniques and they got patented and then, you know, which happens quite often. I got sort of overboard and thought about, you know, yeah, that's pretty good, but it's not the best. So what is the best possible way of doing in the population? And then I thought, yeah, you want the simplest picture, which is if you cause granite recovers the original picture. And then I thought about the simplicity concept more in quantitative terms. And um, you know, everything developed </s><s>[INST] and somehow the four beautiful mix of also being a physicist and thinking about the big picture. It then alleged to probably [/INST] the end of big would I? Yeah, so as a physicist, I was probably trained not to always think in computational terms, you know, just ignore that and think about the fundamental properties which you want to have? </s> |
<s>[INST] What's the impulse to secrecy? [/INST] Yeah. Well, to protect institutions, you know, that's always that's a sinful instinct. I'm not altogether sure an institution is worth protecting, but if it reaches the point where you're indifferent to people's well being, then you're in trouble. </s><s>[INST] So, institutions role should be transparent and honest with the sins of its members and of itself. [/INST] Sure, yeah. </s><s>[INST] So maybe you can speak to the fact as a priest, the bishop, as part of Catholicism, you're not allowed to marry, not allowed to have sex. You're you're sworn to celibacy. What is what is behind that idea? What is the sort of, we talked about some broad stroke ideas of love, what's behind the idea of celibacy [/INST] and that's a good way to get out. It's a path of love. So, the church is always in favor of inculcating love, marriage is a path of love, but so is celibacy. Um, ST paul talks about someone who is preoccupied with the things of this world and family and those who are free from that are free or for doing the work of God. So that's kind of a pragmatic justification for celibacy, and we still, I think, take that seriously, look at my own life, I mean, celibacy has enabled me to do all kinds of things and go places and and and and minister in a way that I could not if I had been married, so I get it, I get the pragmatic side, but I'm more interested in the sort of mystical side of it ever, Jesus was challenged about the person who had, you know, a whole series of husbands and and then they all died, and so in heaven, which one will, will, you know, which which husband with the wife have, and his answer is in heaven, people don't marry and they're not given in marriage, there's a there's a higher way of love, it's a more radical way of love. It's not tied to a particular, but I think through God is tied to everybody, the celibate, and this has been to the beginning of the church, not as a law, but there were there were celibate from the very beginning of the church, including jesus of course, and paul, um they sense something that that way of living mystically anticipates the way we love in heaven, it's a sign even now within this world of how we will all love in heaven. So, in that way it's a bit like pacifists, um I'm glad there are pacifists in the church. And I've known some, you know, some very powerful witnesses to pacifism. I'm glad they're pacifists because they witness even now to how we will be in heaven when every tear is wiped away and we beat our swords into plowshares and you know, heaven is a place of radical piece that some people even now live in at the same time. I'm glad not everyone's a pacifist because I would hold with the church to a just war theory that there's sometimes all we can do in this finite world is to is to fight, you know, manifest wickedness. So </s><s>[INST] just in the same way there's just sex. [/INST] Well, no, right, I'm glad there are celibate, but I'm glad not everyone to celebrate, I wouldn't want that because because married love is a marvelous expression of the divine love. So that's why it's good, there are some and it's it's always been a small number. </s><s>[INST] The actual experience of it, Would you uh the spiritual nature of it, is it similar to fast things, I've been enjoying fasting recently, so not eating [/INST] uh </s><s>[INST] for several days, that kind of stuff. And that somehow brings you even deeper. I'm in general in love with everything and with nature and everything, I see the beauty in the world, but there's a greater intensity to that when you're fasting, for example. [/INST] Yeah, I might use the language of, you know, sublimation or redirection of energy and all that. I I think that's true. There's certain sublimation of energies into um prayer into mysticism, into ministry, a redirection of energies. So it's meant to be life enhancing the same way fasting is, is meant ultimately to be life enhancing and make you healthier and happier. So celibacy is a path of love. And I think it does involve you have certain redirection of energy. Say that, </s><s>[INST] don't you think, do you think it's a heavy burden for some humans to bear some priest to bear? Is that, is that the thing given this the the sexual abuse scandal, um, is that the thing that breaks? [/INST] No, I wouldn't tie that to celibacy. And that's been demonstrated over and over again. There's a priest named Andrew Greeley who was a priest from my home diocese of Chicago. And Andy did a lot of research, sociologists of religion to a lot of research into that very question. And there really is not a correlation between celibacy per se and the sexual abuse of Children or anybody. So I wouldn't make that correlation </s><s>[INST] bad people sinful people are going to do what they're going to [/INST] do. I think people who have a tendency toward uh abusing Children sexually are drawn to situations where they get ready access two kids and they get institutional cover. So that's how we go through the list of, you know, from sports and and Boy Scouts, etcetera. Um, and that's been proven again and again. So I would tie it more to that, I wouldn't tie into celibacy. </s> |
<s>[INST] the following is a conversation with chris Sampson, he was the Cto of the google sub driving car team, a key engineering leader behind the Carnegie Mellon University autonomous vehicle entries in the DARPA grand challenges and the winner of the DARPA Urban challenge today he's the Ceo of Arora Innovation, an autonomous vehicle software company. He started with sterling Anderson who was the former director of Tesla Autopilot, Andrew Bagnall. Uber's former autonomy perception lead Chris is one of the top roboticists and autonomous vehicle experts in the world and a longtime voice of reason in a space that is shrouded in both mystery and hype. He both acknowledges the incredible challenges involved in solving the problem baton was driving and is working hard to solve it. This is the artificial intelligence podcast. If you enjoy it, subscribe on youtube, give it five stars on itunes supported on Patreon are simply connect with me on twitter at lex Friedman, spelled F R I D M A N and now here's my conversation with chris, our person. You were part of both the DARPA grand challenge in the DARPA urban challenge teams that seem you with Red Whitaker. What technical or philosophical things have you learned from these races? [/INST] I think the the high order bit was that it could be done. I think that was the thing that was incredible about the first, the grand challenges that I remember, you know, I was a grad student at Carnegie Mellon and there we, it was kind of this dichotomy of it seemed really hard. So that would be cool and interesting but you know, at the time we were the only robotics institute around. And so if we went into it and fell in our faces, that would that would be embarrassing. Uh So I think, you know, just having the will to go do it to try to do this thing that at the time was marked as, you know, darn near impossible. And and then after a couple of tries to be able to actually make it happen, I think that was yeah, that was really exciting. </s><s>[INST] But at which point did you believe it was possible, Did you from the very beginning, did you personally, because you're one of the lead engineer, you actually had to do a lot of the work. [/INST] Yeah, it was the technical director there and did a lot of the work along with a bunch of other really good people did. I believe it could be done of course, right? Like why would you go do something? You thought was impossible, completely impossible. We thought it was gonna be hard. We didn't know how we're going to be able to do it. We didn't know if we'd be able to do it the first time, it turns out we couldn't that yeah, I guess you have to I think there's a certain benefit to naivete right, that if you don't know how hard something really is. You you try different things and you know, it gives you an opportunity that others who are, you know, wiser maybe don't I don't have </s><s>[INST] what were the biggest pain points, mechanical sensors, hardware, software, algorithms for mapping localization, just general perception, control with the hardware, software. First of all, [/INST] I think that's the joy of this field, is that it's all hard. Um, and that you have to be good at at each part of it. So for the first for the urban challenges, if I look back at it from today, uh, it should be easy today that it was a static world. There weren't other actors moving through the, is what that means. It was out in the desert. So you get really good GPS, you know, so that that went and, you know, we could map it roughly. And so in retrospect now, it's, you know, it's it's within the realm of things we could do back then, just actually getting the vehicle and the, you know, there's a bunch of engineering work to get the vehicle so that we could control and drive it. That's, you know, that's still a pain today. But it was even more so back then. Uh, and then the uncertainty of exactly what they wanted us to do was part of the challenge as well. </s><s>[INST] Right? You didn't actually know the track heading in, you knew approximately, but, you know, it didn't actually know the route the route that it's gonna be taken. [/INST] That's right. We didn't know the route and we didn't even really the way the rules have been described, you had to kind of guess. So if you think back to that challenge, the idea was to that the government would give us the DARPA would give us a set of waypoints and kind of the width um that you had to stay within between the line that went between, you know, each of those way points. And so the most devious thing they could have done is that, you know, a kilometer wide corridor across, you know, a field of scrub brush, um and rocks and said, you know, go figure it out, fortunately it really, it turned into basically driving along a set of trails, which is much more relevant to the application they were looking for. But no, it was, it was a hell of a thing back in the day. </s><s>[INST] So uh the Legend Red was kind of leading that effort in terms of just broadly speaking, so you're a leader now, what have you learned from, read about leadership? [/INST] I think there's a couple things, one is, you know, go and try those really hard things that that's where there is an incredible opportunity. I think the other big one though, is to see people for who they can be, not who they are. It's one of the things that I actually, one of the deepest lessons I learned from, Read was that he would look at undergraduates or graduate students and empower them uh to be leaders, to to, you know, have responsibility to do great things that I think another person might look at them and think, oh that's just you know, an undergraduate student, what could they know? And so I think that that you know, kind of trust but verify, have confidence in what people can become I think is a really powerful thing. </s> |
<s>[INST] So yeah, relationship management. So yeah, that's a fascinating whole area of psychology actually as well of seeing how our behavior has changed with basically all human relations now have other non human entities helping us out. So you've uh you teach a large huge machine learning course here at M. I. T. I can ask a million questions but you've seen a lot of students, what ideas do students struggle with the most as they first enter this world of machine learning. [/INST] Actually this year was the first time I started teaching a small machine learning class and it came as the result of what I saw in my big machine learning class. That to my uncle and I build maybe six years ago um what we've seen that as this area become more and more popular, more and more people at MIT want to take this class. And while we designed it for computer science majors there were a lot of people who really are interested to learn in but unfortunately their background was not enabling them to do well in the class and many of them associated machine learning with the would struggle and failure, um primarily for non majors and that's why we actually started a new class, which we call machine learning from algorithms to modeling, which emphasizes more than modeling aspects of it and focuses on it has majors and non majors. So we kind of try to extract the relevant paths and make it more accessible because the fact that we're teaching 20 classifiers in standard machine learning class is really a big question to really needed. But it was interesting to see this from first generation of students when they came back from their internships and from there, um jobs, what different and exciting things they can do is that I would never think that you can even apply machine learning to some of them are like matching, you know, the relations and other things like everything, everything </s><s>[INST] is amenable to machine, you know, that actually brings up an interesting point of computer science in general. It almost seems Maybe I'm crazy, but it almost seems like everybody needs to learn how to program these days if you're 20 years old or if you're starting school, even if you're an English major, it seems, it seems like programming unlocked so much possibility in this world. So in when you interacted with those non majors is their skills that they were simply lacking at the time that you wish they had and that they learned in high school and so on. Like how well how should education change in this computer computerized world that we live in? I [/INST] think because they knew that there is a python component in the class. You know, they're python skills were okay and the class is not really heavy on programming, primarily kind of add parts to the programs. I think it was more of the mathematical barriers and the class against with the design on the majors was using the notation like big old for complexity and others. People who come from different backgrounds just don't have it in the mexicans don't necessarily very challenging notion, but they were just not aware. Uh, so I think that, you know, kind of linear algebra and probability the basics, that calculus, Multivariate calculus, things that can help. </s><s>[INST] What advice would you give to students interested in? Machine learning, interested. You've talked about detecting curing cancer, drug design if they want to get into that field, what should they do get into it and succeed as researchers and entrepreneurs. [/INST] The first good piece of news that right now there are lots of resources that, you know, I created a different levels and you can find online on your school classes which are more mathematical, more applied and so on. So you can find kind of a preacher which preaches your own language where you can enter the field and you can make many different types of contribution depending of uh, you know, what is your strength. Uh, and the second point, I think it's really important to find some area which you, which you really care about. And it can motivate your learning and it can be for somebody curing cancel doing self driving cars or whatever. But to find an area where you know, there is data where you believe there are strong patterns and we should be doing it and we're still not doing it or you can do it better and just start there and see where it can bring you. </s><s>[INST] So you've uh, you've been very successful in many directions in life, but you also mentioned flowers a bargain on and I think I read or listen to, you mentioned somewhere that researchers often get lost in the details of their work. This is per our original discussion with cancer and so on. And don't look at the bigger picture, bigger questions of meaning and so on. So let me ask you the impossible question of uh, what's the meaning of this thing of life, of, of your life of research? Why do you think we descendant of great apes are here on this spinning ball? [/INST] You know, I don't think that I have really a global answer. You know, maybe that's why I didn't go to humanity's uh, and they didn't think about in these glasses, in my undergrad. But the way I am thinking about each one of us inside of them have their own set of, you know, things that we believe are important. And it just happens that we're busy with achieving various goal, busy listening to others and to kind of try to conform and to be part of the crowd uh that we don't listen to that part and you know, we all should Find some time to understand what is our own individual missions and we may have very different missions and to make sure that while we are running 10,000 things were not um, you know, missing out. And we're putting all the resources to satisfy our own mission. And if I look over my time when I was younger, most of these missions, you know, I was primarily driven by the external stimulus, you know, to to achieve this to be that. And now a lot of what they do is driven by really thinking what is important for me to achieve independently of the external recognition. Ah and you know, I don't mind to be viewed in certain ways. The most important thing for me is to be true to myself to what I think is right? </s> |
<s>[INST] they move slowly. Yeah. So, uh yeah, it's exponential also, Yeah, you're [/INST] making progress, but there again, it's not about the power of compilers is not just about how you make the same thing go faster. It's how do you unlock the new hardware? A new chip came out? How to utilize it? You say, oh the programming model, How do we make people more productive? How do we, how do we uh like have better error messages? Even such mundane things? Like how do I generate a very specific error message about your code actually makes people happy because they know how to fix it. Right trump comes back to how do you help people get their job done? </s><s>[INST] Yeah. And yeah. And then in this world of exponentially increasing smart toasters, how do you uh expand, competing to uh do all these kinds of devices? Do you see this world where just everything is a computing surface? You see that possibility? Just everything is a computer. Yeah, [/INST] I don't see any reason that that couldn't be achieved. It turns out that sand goes into glass and glass is pretty useful too. And you know, why not? </s><s>[INST] Why not? So uh very important question then, if um if we're living in a simulation and the simulation is running a computer, like what was the architecture that computer do you think? [/INST] So you're saying, is it a quantum system, is it like </s><s>[INST] This whole quantum discussion isn't needed? Or can can we run it on a, you know, with a risk? five architecture, a bunch of Cpus I [/INST] think it comes down to the right tool for the job. And so </s><s>[INST] what's the job? [/INST] Yeah, exactly. That's that's my question and I get that job made the universe compiler. Um uh and so there as far as we know, quantum quantum quantum systems with the bottom of the pile of turtles </s><s>[INST] so far. Yeah. [/INST] And so we don't know efficient ways to implement quantum systems without using quantum computers. </s><s>[INST] And that's totally outside of everything we've talked about. [/INST] But who runs that quantum computer? Yeah. Right. So if it if it if we really are living in a simulation than is it bigger quantum computers, is it different ones? Like how does that work out? Does that scale? </s><s>[INST] Well, it's it's the same size. It's the same size. But then but then the thought of the simulation is that you don't have to run the whole thing that, you know, we humans are cognitively very limited checkpoints, checkpoints. Yeah. And uh and if we the point at which we humans, so you basically do minimal amount of uh what is it? Uh Swift does on right copy copy. So you only you only adjust the simulation every [/INST] parallel universe theories. Right? So every time a decision is made. Yeah, somebody opens the short in your box, then uh there's a four and then this could happen. </s><s>[INST] And and then uh thank you for uh for considering the possibility. But yeah, so it may not require, you know, the entirety of the universe is simulated. But it's uh interesting too. Think about uh as we create this this higher and higher fidelity systems. But I do want to ask on the, on the quantum computer side because everything we've talked about with, you work with Science five. With everything with compilers, None of that includes quantum computers. Right. So if you ever thought about what, you know, this whole serious engineering work, a quantum computers looks like of compilers of architectures, all that kind of stuff. So [/INST] I've looked at a little bit, I know almost nothing about it, which means that at some point I will have to find an excuse to get involved because that's what do you </s><s>[INST] think? Do you think that's the thing to be like with your little tingly senses of the timing of when to be involved? Is it not yet? Well, [/INST] so, so the thing I do really well is I jump into messy systems and figure out how to make them figure out what the truth and the situation is. Try to figure out what um what the unifying theory is, how to like factor the complexity had to find a beautiful answer to a problem that um has been well studied and lots of people have bashed their heads against it. I don't know that quantum computers are mature enough and accessible enough to be. Um </s><s>[INST] they figured [/INST] out yet. Right. And um the I think the open question with quantum computers, is there a useful problem that gets solved with quantum computer that makes it worth the economic cost of like having one of these things and having having legions of people that that that set it up, You go back to the 50s, right? And there's the projections of the world will only need 77 computers. Right. Well, and part of that was that people haven't figured out what they're useful for. What are the algorithms we want to run? What are the problems get solved? And this comes back to how do we make the world better? Either economically or making someone's life better or like solving a problem that wasn't solved before? Things like this. And um I think that just were a little bit too early in the development cycle because it's still like literally a science project, not a negative connotation, right? It's literally a science project. And um the progress that is amazing. And so I don't know if it's 10 years away if it's two years away exactly where that breakthrough happens, but um you look at machine learning it, we went through a few winners before the Alexa net transition and then suddenly had its breakout moment and that was the catalyst that then drove the talent flocking into it. That's what drove the economic applications of it. That's what drove the um the technology to go faster because you know, have more minds thrown at the problem. This is what caused like a serious knee and deep learning and the algorithms that we're using and um, and so I think that's what quantum needs to go through. And so right now it's in that, that formidable finding itself getting the, the, like literally the physics figured out and, and, and, and then </s> |
<s>[INST] you [/INST] excited? Yeah and I was reading all these names I was called and I found these so </s><s>[INST] did you think did you ever think that you guys can be so successful like eventually this company would be so successful, did you could you possibly have imagined? [/INST] And no, we never did think that we had 14 failed business models up to 2002 and then we had two winners same year um uh huh. No and then you know, we, I remember the board um because by this time we had some venture capital in the board, went along with us building um Some robots for aiming at the Christmas 2000 to market and We went three times over what they authorized and built 70,000 of them and sold them all uh in that first because we released on September 18 and uh who sold by Christmas so it was so we were gutsy but </s><s>[INST] but yeah, you didn't think this will take over the world. Well this is uh so a lot of amazing robotics companies have gone under over the past few decades. Why do you think it's so damn hard to run a successful? Well there's a [/INST] robotics company. There's a few things. Um One is expectations of capabilities by the found us at an off base. </s><s>[INST] The founder is not the consumer and the founders [/INST] expectations what what can be delivered? Sure mispricing and what a customer thinks is a valid price is not rational necessarily. Yeah and expectations of customers. Um And just the share hardness of getting people to adopt a new technology. And I've suffered from all three of these uh you know I've had more failures and successes in terms of companies I've suffered from all three. Um So </s><s>[INST] do you think um one day there will be a robotics company and by robotics company. I mean where your primary source of income is from robots? That will be a trillion plus dollar company. And so what what would that company do? [/INST] I can't, because I'm still starting robot cos I'm not making any such predictions in my own mind. I'm not thinking about a trillion dollar company. And by the way I don't think you know in the 90s anyone was thinking that Apple would ever be a trillion dollar company. So these are these are very hard to </s><s>[INST] to predict but sorry to interrupt but don't you because I kind of have a vision in a small way, in a big vision in a small way that I see that there would be robots in the home a scale like Roomba but more and that's a trillion dollar, [/INST] Right? And I think there's a there's a real market pull for them because of the demographic inversion, you know, who's who's gonna do all the stuff for the older people. Um There's too many, you know, I'm leading here, it's gonna be too many of us and um um but we don't have capable enough robots to make that economic argument at this point. Do I expect that that will happen? Yes, I expect that will happen. But I got to tell you, we introduced the Roomba in 2000 and two and I stayed another nine years. We were always trying to find what the next home robot would be in Still today. The primary product of 20 years later, almost 20 years later, 19 years later, the primary product is still a Roomba. So I robot hasn't found the next one. </s><s>[INST] Do you think it's possible for one person the garage to build it versus like google launching google self driving car that turns into a mo do you think it's part like this is almost like what it takes to build a successful robotics company. Do you think it's possible to go from the ground up or is it just too much capital investment? [/INST] Yeah. So it's very hard to get there um without a lot of capital and we're starting to see, You know, uh pear chunks of capital for some robotics companies. Um you know, serious bees. It was, I saw one yesterday for $80 million. I think it was for co variant. Um uh Yeah, But it can take real money to get into these things and you may fail along the way. I've certainly failed a rethink robotics. Um and we lost $150 million dollars in capital. So </s><s>[INST] okay, so rethink robotics is another amazing robotics company co founded. So what was the vision there? What was the dream and what are you most proud of? What rethink robotics? [/INST] I'm most proud of the fact that we got um robots out of the cage in factories that was safe. Absolutely safe for people and robots to be next to each other. </s><s>[INST] So these are robotic arms, robotic arms [/INST] were able to pick up </s><s>[INST] stuff and interact with humans [/INST] and that humans could re task them without writing code. And now that's sort of become an expectation for a lot of other little companies and big companies are advertising they're doing </s><s>[INST] that's both an interface problem and also safety problem. Yeah. [/INST] So I'm most proud of that. Yeah, I completely, I let myself be talked out of what I want to do and you know, you've always got, you know, I can't replay the tape, I can't replay it. Maybe, maybe you know, if I had been stronger on, and I remember the day I remember the exact meeting, um, </s><s>[INST] can you take me through that meeting? [/INST] Yeah. Um, So I'd said that I'd set as a target for the company that we were going to build $3,000 robots with force feedback. Um, that was safe for people to be around, wow, that was my goal. And we built, so we started in 2008 and we had prototypes built of plastic, plastic gearboxes. And at the $3,000, you know, uh, lifetime or $3,000, I was saying, we're going to go after not the people who already have robot arms and factories. The people would never have a robot arm. We're gonna go after a different market. So we don't have to meet their expectations. And, and so we're going to build it out of plastic. It doesn't have to have a 35,000 our lifetime, it's gonna be so cheap that it's optics, not Capex. Um, and so we had, we had a prototype that worked reasonably well, but the control engineers were complaining about these plastic gearboxes with a beautiful little planetary gearbox. Um, but uh, we could use something called series elastic actuators. We embedded them in there. We can measure forces were, you knew when we hit something, etcetera. The control engineers were saying, yeah, but this is talk ripple because these plastic gears, they're not great gears and this ripple. And trying to do force control around this ripple is so hard and I'm not going to name names. But I remember one of the mechanical engineers saying we'll just build a metal gearbox with spur gears and it will take six weeks will be done. Problem solved. Two years later we got to get the spur gearbox working. Yeah, we cost reduced in every possible way we could. Um Yeah, but now the price went up to and then the ceo at the time said, well we have to have two arms, not one arm. So our first robot product Baxter now cost $25,000. Mhm. And the only people who are gonna look at that were people who had arms and factories because that was somewhat cheaper to arms and arms and factories. But they were used to 0.1 millimeter reproduce reproducibility of motion and certain velocities. And we kept thinking, but that's not what we're giving you. You don't need position repeatability. Use force control like a human doesn't know. No, but we want we want that repeatability. We want that repeatability as all the other robots have that repeatability. Why don't you have that repeatability? </s> |
<s>[INST] by people who are driven crazy by some ideology. And more and more technologies [/INST] enable a kind of scale of destruction. And misinformation plays into this picture in a way that is especially scary. I mean, once you can get a deep fake of, any current president of the United States claiming to have launched a first strike, and just send that everywhere. </s><s>[INST] But that could change the nature of truth, and then we, that might change the engine we have for skepticism, sharpen it. The more you have deep fakes. [/INST] Yeah, and we might have AI and digital watermarks that help us, maybe we'll not trust any information that hasn't come through specific channels, right? I mean, so in my world, it's like, I no longer feel the need to respond to anything other than what I put out in my channels of information. It's like, there's so many people who have clipped stuff of me that shows the opposite of what I was actually saying in context. I mean, the people have like re-edited my podcast audio to make it seem like I said the opposite of what I was saying. It's like, unless I put it out, you can't be sure that I actually said it. I mean, it's just, but I don't know what it's like to live like that for all forms of information. And I mean, strangely, I think it may require a greater siloing of information in the end. We're living through this sort of Wild West period where everyone's got a newsletter and everyone's got a blog and everyone's got an opinion. </s><s>[INST] But once you can fake everything. There might be a greater value for expertise for experts, but a more rigorous system [/INST] for identifying who the experts are for experts. Yeah, or just knowing that it's gonna be an arms race to authenticate information. So it's like, if you can never trust a photograph, unless it has been vetted by Getty Images, because only Getty Images has the resources to authenticate the provenance of that photograph and a test that it hasn't been meddled with by AI. And again, I don't even know if that's technically possible. I mean, maybe whatever the tools available for this will be commodified and the cost will be driven to zero so quickly that everyone will be able to do it. It could be like encryption, but. </s><s>[INST] Yeah, and it would be proven and tested most effectively first, of course, as always in porn. Yeah, which is where most of human innovation technology happens first. Well, I have to ask because Ron Howard, the director asked us on Twitter, since we're talking about the threat of nuclear war and otherwise, he asked, I'd be interested in both your expectations for human society if, when we move beyond Mars. Will those societies be industrial based? How will it be governed? How will criminal infractions be dealt with? When you read or watch sci-fi, what comes closest to sounding logical? Do you think about our society beyond Earth? [/INST] If we colonize Mars, if we colonize space? Yeah, well, I think I have a pretty humbling picture of that. Because we're still gonna be the apes that we are. So when you imagine colonizing Mars, you have to imagine a first fistfight on Mars. You have to imagine a first murder on Mars. Also infidelity. Extramarital affairs on Mars. So it's gonna get really homely and boring really fast, I think. It's like only the spacesuits, or the other exingencies of just living in that atmosphere or lack thereof, </s><s>[INST] will limit how badly we can behave on Mars. Yeah, somebody else. But do you think most of the interaction will be still in meat space versus digital? Do you think there'll be, do you think we're living through a transformation of a kind where we're going to be doing more and more interaction than digital space? Like everything we've been complaining about Twitter, is it possible that Twitter's just the early days of a broken system that's actually giving birth [/INST] to a better working system that's ultimately digital? I think we're gonna experience a pendulum swing back into the real world. I mean, I think many of us are experiencing that now anyway. </s><s>[INST] I mean, just wanting to the real world. [/INST] Have face-to-face encounters and spend less time on our phones and less time online. I think maybe everyone isn't going in that direction, but I do notice it myself. And I notice, I mean, once I got off Twitter, then I noticed the people who are never on Twitter, right? And the people who are never, basically, I mean, I know, I have a lot of friends who are never on Twitter. And they actually never understood what I was doing on Twitter. It was like it wasn't that they were seeing it seeing it and then reacting to it, they just didn't know, it's like, right? And it's like being on, it's like I'm not on Reddit either, but I don't spend any time thinking about not being on Reddit, right? It's like, I'm just not on Reddit. </s><s>[INST] Do you think the pursuit of human happiness is better achieved and more effectively achieved [/INST] outside of Twitter world? Well, I think all we have is our attention in the end. And we just have to notice what these various tools are doing to it. And it's just, it became very clear to me that in the end, it was an unrewarding use of my attention. Now, it's not to say there isn't some digital platform that's conceivable that would be useful and rewarding, but yeah, I mean, we just have, you know, our life has doled out to us in moments and we have, and we're continually solving this riddle of what is gonna suffice to make this moment engaging, and meaningful, and aligned with who I wanna be now and how I want the future to look, right? We have this tension between being in the present and becoming in the future. And, you know, it's a seeming paradox. Again, it's not really a paradox, but it can seem like, I do think the ground truth for personal wellbeing is to find a mode of being where you can pay attention to the present moment, and this is, you know, meditation by another name, you can pay attention to the present moment with sufficient, you know, gravity, that you recognize that just consciousness itself in the present moment, no matter what's happening, is already a circumstance of freedom and contentment and tranquility. Like, you can be happy now before anything happens, before this next desire gets gratified, before this next problem gets solved. There's this kind of ground truth that you're free, that consciousness is free and open and unencumbered by really any problem until you get lost in thought </s> |
<s>[INST] know, I get to actually intensely experience that certainty in many communities, but one in in in Cryptocurrency young folks with a certainty that this technology will transform the world. And I mean this is almost one of the big communities of the modern era where they believe that this will really solve so many of the problems of the world and they believe in it very intensely. And aside from the technology and the details of the thing, all I see is the certainty and the passion in their eyes. They'll stop me. Let me uh let me explain you. Let me let me just give me a chance to tell you why this thing is extremely powerful and I just get to enjoy the glow of that because it's like, well this I I miss having that certainty about anything. It's probably come over for me [/INST] too. But </s><s>[INST] when I was younger, it's it's like only I deeply understand the relationship of man To his mortality. And I understood that most deeply, I think when I was like 16 or 17 and I have I am the representative of the human condition and all these adults with their business of day to day life and their concerns. They don't deeply understand what I understand, which is the only thing that matters is uh the absurdity of the human condition. [/INST] Yeah. </s><s>[INST] And let me quote you some dostoyevsky [/INST] boy and you speak Russian, </s><s>[INST] you've [/INST] read the brothers Karamazov in Russian. </s><s>[INST] Unfortunately, I have to admit that um I read all of the ski in English. Um I came to this country when I was 13 and at least don't remember. We read a lot, but we read uh Tolstoy Pushkin a lot of the Russian literature, but it was in Russian. But I don't remember reading dostoevsky. I wonder at which point does the Russian education system give you dostoyevsky because it's pretty heavy stuff. [/INST] The 2nd Grade Intense. </s><s>[INST] I don't remember. Yes, they are, they're very, they're very much are. I don't remember reading this desk but I did uh tangent upon a tangent upon a tangent. I traveled to paris recently on the way to Ukraine And uh was scheduled to talk to Richard Revere and love this pair that translates ski uh tolstoy just this famous pair that translate most of Russian literature to English. And I was planning to have a sequence of, you know, 5, 10, 15 hour conversation with them about the different details of all the translations and so on. Um I just found myself in a very dark place mentally where I couldn't think about podcasts or anything like that. It caught me off guard. So I went to paris and just laid there for a day, not just being stressed about Ukraine and all those kinds of things, but I'm still the, the act of translation is such a fascinating way to approach some of the deepest questions that this literature raises, which is like how do I capture the essence of a sentence that has so much power and translated into another language? That act is actually really, really interesting. And there I found with my conversations with them, they they've really thought to this stuff, it's not just about language, it's about the ideas in those books. And that's um that that also really makes me sad because I wonder how much is lost in translation. I'm currently, So when I was in Ukraine, I talked to a lot of like half the conversations I had on the record one Russian And basically 100% off the record were in Russian vs in English and just so much is lost in those languages. And I'm now struggling because I'm launching a Russian channel or there will be a Russian overdub of Duncan [/INST] your </s><s>[INST] while will not be translated into Russian, you'll just be, well, probably, I'm so sorry for the, for the difficulties of having to translate. Well, usually, probably with while they will leave it on overdubbed because people understand exactly what you mean, but that's an art form and it's a weird art form. It's like how do you capture the, the chemistry, the excitement, the, I don't know, maybe the humor, the implied kind of wit. I don't know, there's just layers of complexity and language that it's very difficult to capture and I wonder how it is sad for me because I know Russia and how much is lost in translation and the same. You know, there's a brewing conflict and tension with china now and so much is lost in the translation between those languages and cultures. The entire the music of the people is completely lost because we don't know the language. Yeah. [/INST] How much of the conflict is just problems in translation? How much of the all these problems that we're having are just the alien sense of this or that it's just as simple as that words are getting just that just a tiny warp away from the intent of if when we both speak the same language, we can still say something that offends someone when you never intended that at all. How much more? So when like, it's not only is it a completely different sound, but the script itself is different, like what the Russian writing, is it called cyril cyrillic or </s><s>[INST] what's [/INST] and I don't know the name for chinese writing, but it's like, like it's a continuum that like, it's weirder and weirder looking, you know, like it's so Yeah, yeah, I'm sure depending on where you're at. You know, I'm definitely I'm about the farthest thing from a polyglot is there could be man like, but I'll tell you at one point when I was getting fascinated by, I did have this very transient fantasy about learning Russian so that I could like understand the difference in and </s><s>[INST] You're 1718 at the time [/INST] college. Yeah. Brothers Karamazov lost in that book just like oh God so in love with it. There's </s> |
<s>[INST] I actually would love to have like straight up data on people in that world versus not in that world how often they get laid. Yeah. Like literally, so I think for sure people in that world have fewer meaningful long-term relationships that are fulfilling that actually help them succeed in life, that help them be happy and content and all that kind of stuff. But just even the straight up, the shallow goal of getting laid, I wonder because it's very possible that like just the roughness with which they treat intellectually women [/INST] that might lead to lower success, not higher success. It's very adversarial, which I think is always disappointing. Anything that talks about men and women, I think it's good to acknowledge differences. But when it becomes like adversarial, especially when you talk about sex, sex is something that men are getting and it's something that women are giving and that type of like trade off and the way they talk about it, it's like yeah, it sets people against each other in </s><s>[INST] a really toxic way, I think. How do you talk to people from that world, from the red pill world? Like would you ever talk to somebody like Andrew Tate? [/INST] Oh, yeah. I've been on the Fresh and Fit podcast a few times, and then I've got a friend, Sneeko, who's very red pill, that stuff. If I'm trying to talk to them, usually the, it's kind of like approaching a scared cat. The first thing you have to do is be very gentle and say, I understand your issues, I understand your complaints, I know that you're, I'm scary because you think I'm gonna say toxic masculinity and feminism and all these scary words at you. So the first thing is always to recognize it. A lot of what they talk about, there are true aspects to what they're talking about that people on the left won't recognize. So I think it's good to acknowledge those things that men and women are kind of different. We do look for different things in general when it comes to relationships. It's okay to say that, there's not, there's nothing bad there. And then it'll usually be like, once I've got your trust, and I'm in your bubble, let's talk about the things that you want and maybe some of the strategies that you're employing aren't necessarily gonna get you some of the things that you want. So for instance, if you're really worried about shallow girls ruining your life, like Malina said, it's probably not best to build your entire world view around trying to get shallow girls that are gonna ruin your life. If your way of attracting a girl to go to the gym, get a whole bunch of money and try to like flaunt your wealth as much as possible. You're going to be attracting the very same type of women that you're here like decrying on your stream. I think we talked about that on the podcast like you probably want to have a woman that's going to be there if you lose your job but still there like that cares about the things </s><s>[INST] that's not just your job. It's more stable. And also I don't help you become a great man or a great like grow like I feel like a great friendship and a partnership. like it helps you make you a better person. Some of the most successful people I know, I mean they have families and there's clearly a dynamic there that's like, that makes them, they wouldn't be that without. They're not an island, yeah. Yeah, and the kids are actually a big part of that too. Like for most people, if you're like a good parent, they make you step up somehow in life. You have to take responsibility for getting your shit [/INST] together and excelling in ways that helps. </s><s>[INST] They're not an island, yeah. I guess the philosophy of the Red Bull [/INST] does not quite get to. That's always an interesting, I think I've asked it a couple of times where it's like, would you let your daughter date Andrew Tate and it's always funny to watch him kind of like squirm around those answers sometimes? </s><s>[INST] Yeah, those answers sometimes. But see, if they don't have a daughter, I don't have a daughter. I think your whole philosophy of change is once you have a daughter. Sure. [/INST] Well but even at that, well but even at that, they know that what they're answering, they feel a little bit weird about it. It's funny to watch them like. Even they know. </s><s>[INST] It's like, no, fuck, no. Well, they might say I want my daughter to date like a high value male, to the degree that he's a high value male, yes. But like, I don't think you'll feel that way. The definition of high value changes completely. Certainly the stereotypical measures of value contribute to the calculation, but it's so much more than that, I think. The chemistry of the whole thing is bigger. You've also mentioned about body count. You guys both have a high body count. Does body count matter? Or it depends, like you said, it's low in some people's eyes. It's high in other people's eyes. Does body count matter in relationship? [/INST] Does the past matter? Well, the past matters, I don't think body count. Not to me, I don't really care. Not just as it is, no. I mean, it could be. But the past does. Yeah, well the past is who you are, right? Somebody tells me they have a 200 body count, and they're 16. Something's probably going on there that's not good. I was thinking about that too. It could be. I was thinking about that too, because it could be really young people that are having some sort of mental problems going on. Yeah, they could be. What's going on or somebody's like 45 and they've like never had sex before. There's probably something going on, right? So it could be indicative but if somebody's like in their 20s and they've had sex with you know 100 people or 50 people whatever it's you know, whatever </s> |
<s>[INST] So, that's kind of the arcade stage of things. If I were to say with my experience with VR, the thing that I think is powerful is the, maybe it's not here yet, but the degree to which it is immersive in the way that Quake is immersive. It takes you to another world. For me, because I'm a fan of role-playing games, the Elder Scrolls series like Skyrim or even Daggerfall, it just takes you to another world. And when you're not in that world, you miss not being there. And then you just, you kind of want to stay there forever because life is [/INST] shitty. And you just want to go to this place. And you just want to go to this place. There was a time when we were kind of asked to come up with like, what's your view about VR? My pitch was that it should be better inside the headset than outside. It's the world as you want it. And everybody thought that was dystopian and that's like, oh, you're just going to forget about the world outside. And I don't get that mindset where if you can make the world better inside the headset than outside, you've just improved the person's life that has a headset that can wear it. And there are plenty of things that we just can't do for everyone in the real world. Everybody can't have Richard Branson's Private Island, but everyone can have a private VR island, and it can have the things that they want on it. And there's a lot of these kind of rivalrous goods in the real world that VR can just be better at. We can do a lot of things like that that can be very, very rich. So yeah, I think it's going to be a positive thing this world where people want to go back into their headset, where it can be better than somebody that's living in a tiny apartment, can have a palatial estate in virtual reality, they can have all their friends from all over the world come over and visit them without everybody getting on a plane and meeting in someplace and dealing with all the other logistics hassles. There is real value in the presence that you can get for remote meetings. It's all the little things that we need to sort out, but those are things that we have line of sight on. People that have been in a good VR meeting using workrooms where you can say, oh, that was better than a Zoom meeting. But of course, it's more of a hassle to get into it. Not everyone has the headset. Interoperability is worse. You can't have, you cap out at a certain number. There's all these things that need to be fixed, but that's one of those things you can look at and say, we know there's value there. We just need to really grind hard, file off all the rough edges and make that possible. </s><s>[INST] So you do think we have line of sight because there's a reason like I do this podcast in person, for example, doing it remotely, it's not the same. And if somebody were to ask me why it's not the same, I wouldn't be able to write down exactly why. But you're saying that it's possible, whatever the magic is for in-person interaction, that immersiveness of the experience, [/INST] we are almost there. Yes. So the idea of like, yes. So the idea of like, I'm doing a VR interview with someone, I'm not saying it's here right now, but you can see glimmers of what it should be. And we largely know what would need to be fixed and improved to, like you say, there's a difference between at a remote interview, doing a podcast over zoom or something and face to face, there's that sense of presence that immediacy, the super low latency responsiveness, being able to see all the subtle things there, just occupying the same field of view. And all of those are things that we absolutely can do in VR. And that simple case of a small meeting with a couple of people, that's the much easier case than everybody thinks the Ready Player One multiverse with a thousand people going across that, you know, a huge bridge to amazing places. That's harder in a lot of other technical ways. Not to say we can't also do that, but that's further away and has more challenges. But this small thing about being able to have a meeting with one or a few people and have it feel real, feel like you're there, like you have the same interactions and talking with them, you get subtle cues, as we start getting eye and face tracking and some of the other things on high end headsets, a lot of that is going to come over. And it doesn't have to be as good. This is an important thing that people miss where there was a lot of people that, especially rich people that would look at VR and say, it's like, oh, this just isn't that good. And I'd say it's like, well, you've already been courtside backstage and, you know, on pit row and you've done all of these experiences because you get to do them in real life, but most people don't get to. And even if the experience is only half as good, if it's something that they never would have gotten to do before, it's still a very good thing. And as we can just, we can push that number up over time. It has a minimum viable value level when it does something that is valuable enough to people, as long as it's better inside the headset on any metric than it is outside and people choose to go there. We're on the right path and we have a value gradient that I'm just always hammering on. We can just follow this value gradient, just keep making things better rather than going for that </s> |
<s>[INST] there an element to, there's a beautiful weirdness to you as a human being? Was there was there uh Like a pressure to conform ever to hide yourself from the world or or the $12,000 and the acid give you the confidence you needed to be yourself. [/INST] Oh no, I don't, like I still I know, I I think sure there's that pressure and like, you know whenever you're, you're beginning to really differentiate from your parents, but then you go back to hang out with your parents, you can feel that it's not like they even want you to conform, but you'll just, you could slip into that whatever that was. So I remember that when I would go back and like visit them and stuff and surely conformity or the pressure to like not be individual or whatever. It's, it's everywhere man. </s><s>[INST] Do you think you made your parents proud? [/INST] No, </s><s>[INST] no, no, no. [/INST] Well I think that um when my mom died, I felt successful in the sense that I was able to support my, I was I was making money from doing stand up and my I didn't need help. I was like, as I was supporting myself with art and doing good, what I thought was great then, So, and I think she like, because she had witnessed me literally failing, I mean, which is by the way, I think part of you want to be an artist or successful, you you kind of have to fail like there if if, and if there was a guaranteed route from sucking to not sucking or from like the neophyte phase of whatever the art form is and, you know, some intermediary phase and I think a lot more people would do it, but there really is no guarantees. And, and especially the stand up comedy, it's like, you'd have to be a maniac to want to think that that's gonna work out for you, you have to, so you're gonna, there are obviously exceptions, but for me it was like a long slog, you know, and that's scary for a mom. So, but that being said when she was dying, like she did recognize that I was like, not slogging anymore and she did say she said you did it and that's cool. But, and you know, I would love her to see me now. Like, now would be way cooler. But maybe she does. I don't know. </s><s>[INST] She's listening to your podcast elsewhere and the other in [/INST] the bardo. </s><s>[INST] Yeah. However long that lasts, Reconfiguring the whole process to start again. Um You as a father? No. How did that change you? [/INST] Yeah, that's the big change, man. That's the thing you </s><s>[INST] made. You made a few biological reproduce. [/INST] Yeah. I made biological entities. I mean, I came and my wife, let's face it, like I would love to say I made them, but the womb whipped them up. Um but it is the, yeah, it's the best. It's, I've never experienced anything like it before. It is the, as far as I'm concerned, the greatest thing that has ever happened to me. And, and that's why I was able to answer your question with like, hell yes chuck. Yes, That's great. I get to be around my kids again. I'll always be around my kids. Always be around my Children. That's incredible. That's the joy. So like, so for me. Mhm the part of myself that used to torture myself more specifically around like my mom dying feeling like I wasn't there enough for her wishing that I had spent more time with her wishing I'd spent more time with my dad wishing that like, you know, looking back at like how like I was just so desperately trying to evade the fact that she was dying uh and through and in that evasion successfully, like distanced myself from her and like in ways that I really wish I hadn't uh I'm just saying that cause it's one of my regrets, it's like a big have a lot of little regrets, but that's a big one. And so when you have kids, you look back at everything you did and you think like fuck if I'd gone left at that point instead of right, if I had eaten, who knows what if I had eaten like a turkey sandwich when my balls were creating the come that was going to make my kids, would I have a different kid, would this being not exist in my life? Like you start looking at everything and you realize like, thank God, thank God for every single thing that happened to me because it all led up to this and oh for me, that is the that's that it's like it frees you and this, it liberates you because you realize like, oh wow, it's clumsy and selfish and and and at times rotten if I've as I've been in my life that did not impede the universe at all from allowing this, these two beautiful beings to exist in the world. So </s><s>[INST] maybe all of it enabled all of it like a concert perfectly led up to that little beautiful moment. Is there ways you would like to be about a father? [/INST] Oh yeah, for sure. Absolutely. There's a, there's an actual, I read something in a book. It's called Good Enough the mantra for a parent Good Enough Because when you are in the presence of something you love more than you've ever experienced love you, you want to be perfect. Like you want to be, I can't, I gotta work man, I gotta go on the road. I've gotta work. I gotta support the family. So that means I have to work like I work, you know, you know what it's like having a podcast, you fucking workman and, and uh you know, it's a full time job because I've, you know, I do stand up to and all the other stuff. So I feel sometimes I feel like, oh my God, I want to spend more time with him. Like I should be spending more time with him. But then also I want to create, I want to work, I I like being the the provider. So that's something I feel guilty about. You know, </s> |
<s>[INST] so in some sense, those uh, dan's podcasts and podcasts can be incredibly educational. That's he's uh, the storytelling that pulls you in ultimately leads to you internalizing these stories and like remembering them and thinking through them and all those kinds of things that is much more powerful than you book on history. That's accurate. [/INST] I think often it inspires you to go learn more. So it's like, I know we did that. I mean, you know, people would go away. I went and learned about this because they knew with us there was no pretense, which was great that we had no standard. So it's like nobody came to us for historical accuracy, but I was kind of turned on by the fact that it inspired people to go learn about this stuff or to at least know, like Battle of Crete, like you said, a very underappreciated battle. Um, even Winston Churchill said from here on, we will no longer say that Greeks fight like heroes, but heroes fight like Greeks. I mean it was a monumental battle and um, you know, not talked about enough and I, our podcast would inspire people to go actually learn more to go listen to dan Carlin or to go pick up a book or to do research on their own. And so I think podcast dan Carlin's obviously much more accurate than us, but it's good that people are going to podcast like yours and to learn ship joe was is really like the progenitor of that. I mean, you know, having intellectuals on and getting the public interested with this new medium um, in in people who are intelligent, it's nice because, you know, with the mainstream press pushes out is horseshit gorgeous horseshit. It's got a beautiful veneer, but no substance. And so this, this is a nice push back. </s><s>[INST] Yeah, the authenticity of joe's show. I mean, I'm through, I started listening from the very beginning, you know, doing my in grad school, you know, I like a technical person and he just pulled me in and made me curious to learn about all kinds of things and use my own critical reasoning skills on some of the bullshit guess he's had and some of the most inspiring guess he's had. So uh teach you to think, can you uh I don't know much about? Bernie Madoff as a small change in, can you tell me who the hell is? Bernie Madoff? The [/INST] Bernie Madoff is the goat, the greatest thief of all time. Dude, hedge fund guy ran a hedge fund and pulled uh stole the most money in the history of America, I mean a con artist and um he does people, obviously he's become he's a household name because of the magnitude of his crime, but you've got to appreciate, again, you've got to appreciate what went into this and how long he was able to pull it off by tricking the smartest and richest people in the world and uh brilliant scam. The con man. Uh con man is short for confidence man. And it came from yeah, conman basically they exude confidence and they tricked people by playing on their ego and blind spots and the word comes from a guy, I can't remember where, but what he, what he used to do, I can't remember the guy's name and you know whatever you can google it, con man, but it's very interesting the first con man that is on record what he would do, he would go to very rich people and he'd be very well dressed, right? And he goes he's I bet you don't have the confidence to give me your watch and he would plan the egos, these very powerful and rich people and they would give him the watch for some reason, some sort of reverse psychology bullshit and you take the watch and he would just steal it because basically saying like, you know, the company getting to watch because you don't, I don't know, you don't think I'm gonna give it back and he would just take it. So Bernie Madoff was a very sophisticated, sophisticated con man and again, we were talking about people pretending to be the opposite of what they are. Bernie hid his uh fi vory in how available he was to his clients, how he would show up at every bar mitzvah, every birthday. He was always available for their phone calls and he played on their egos, he made it. So people were wanted to invest in him, like they were competing, he made it very exclusive. He, he wouldn't just take anyone and there was a method behind that madness because he wanted the whales that wouldn't notice that he was, he was had this pyramid scheme going and so what he would do is he would just rob from the rich er and he just kept, it was like, he paid back the richer with the guy who was a little bit and it was a pyramid scheme and um he was able to do it for so long and steal so much money And he would win people over with the scheme because with that scheme, he was the only guy who could provide who could guarantee like a 1% return even during times of recession and because he was such a good con man, he hijacked people's reasoning with his charm and that's what con artists do, that's what psychopaths do there, So fucking charming, they get you in that Volkswagen beetle, because if they use their reasoning for one second, they go, hey, Nobody can provide 1% returns during recessions, how the fund is this guy doing it, I'll tell you how he's doing it, he's stealing from another guy to pay you you fucking idiot. </s> |
<s>[INST] All right. So, we would do that, right? To be continued. [/INST] How do you create a strong magnetic field? Yeah. </s><s>[INST] Yeah. So... [/INST] With a giant magnet. Giant magnet. Yeah. So, it's basically true. Engineering is awesome. There's essentially two ways to create a magnet. So, one of them is that we're familiar with like fridge magnets and so forth. These are so-called permanent magnets. So, what it means is that within these, the atoms are arranged in a particular way that it produces the electrons basically arranged in a particular way that it produces a permanent magnetic field that is set by the material. So, those have a fundamental limitation how strong they can be and also tend to have this like circular shape like this. So, we don't use, you don't typically use those. So, what we use their so-called electromagnets and what is this? And so the other way to make a magnetic field, also go back to your elementary school physics or science class is that you take a nail and you wrap a copper wire on it and connect it to a battery, then it can pick up iron filings. This is an electromagnet and it's simplest what it is, it's an electric current, which is going in a pattern around and around and around. And what this does is it produces a magnetic field, which goes through it by the laws of electromagnetism. So that's what electric... So that's how we make the magnetic field in these configurations and the key there is that you... it's not limited by the magnetic property of the material the magnetic field amplitude is set by the amount of... The geometry of this thing and the amount of electric current that you're putting through and the more electric current that you put through the more magnetic field that you get The closest one that people maybe see is is one of my, one of my favorite skits actually was Super Dave Osborne on, it's probably probably passed to you. It was like in a show called Bazaar, Super Dave Osborne, which was a great comedian called, he was a stunt man. And one of his tricks was that he was, he gets into a car and then one of those things in the junkyard comes down, you know, and picks up the car and then puts it into the, into the crusher. This is his stunt, which is pretty hilarious. Anyway. Um, but that thing that picks him up, like how does that work? That's actually not a permanent magnet. It's a, it's an electromagnet. And so you can turn by turning off and on the power supply, it turns off and on the magnetic field. So this means you can pick it up and then when you switch it off, the magnetic field goes away and the car drops. Okay. So that's, that's what it looks like. </s><s>[INST] Engineering is essentially speaking of giant magnets, MIT and Commonwealth fusion systems, CFS built a very large, high temperature, superconducting electromagnet that was ramped up to a field strength of 20 Tesla, the most powerful magnetic field of its kind ever created down on earth, um, because I enjoy this kind of thing. Can you please tell me about this magnet? Yeah, sure. [/INST] I enjoy this. Oh, it was, it's fun. Yeah. There's a lot to parse there. So maybe, uh, we, so we already explained an electromagnet, which in general is what you do is you take electric current and you force it to, to follow a pattern of some kind, typically like a circular pattern around and around and round around, it goes the more time, the more current and the more times it goes around the stronger the magnetic field that you it. And as I pointed out, it's like really important in magnetic confinement because it is the con, the force that's produced by that magnetic. In fact, technically it goes like the magnetic field squared because it's a pressure, which is actually being exerted on the plasma to keep it contained </s><s>[INST] or just, just so we know for a magnetic confinement, what is usually geometry of the magnet? What are we supposed to imagine? [/INST] The geometry, yeah, so the geometry is typically, what you do is you want to produce a magnetic field that loops back on itself and the reason for this was, goes down to the nature of the force that I described, which is that there's no containment or force along the direction of the magnetic field. So here's a magnetic field. In fact, what it's more technically or more graphically, what it's doing is that when the plasma is, here's plasma particles here, here's a magnetic field. What it does is it forces all of those, because of this, this Lorenz force, it makes all of those charged particles execute circular orbits around the magnetic field and they go around like this, but they stream freely along the magnetic field line. So this is why the nature of the containment is that if you can get that circle smaller and smaller, it stays further away from Earth, temperature materials. That's why the confinement gets better. But the problem is, is that because it freestreams along, so we just have a long straight magnetic field, okay, it'll just keep leaking out the ends like really fast. So you get rid of the ends. So you basically loop it back around. So what these look like are typically donut shaped or more technically toroidal shape, donut shaped things where this collection of magnetic fields loops back on itself. And it also for reasons which are more complicated to explain, basically it also twists, that also twists slowly around in this reaction as well too. So that's what it looks, like that's what the plasma looks, like because that's what the fuel looks like. So then this means is that the, the electromagnets are configured in such a way that it produces the desired magnetic fields around this. So it's around this, you were probably listening to our conversation with some of my colleagues yesterday. So it's actually, it's, it depends on the configuration, uh, about how you're doing it. The configuration of the plasma. The configuration of the electromagnets and about how you're achieving this, this requirement. Um, it's, it's fairly precise, but it doesn't have to be in, particularly in something like a Tokamak, what we do is we produce planar coils, which is mean they're flat. Um, and we situate them. So if you think of a circle like this, what does it produce if you put current through it? It produces a magnetic field, which goes through the circle like this. So if you align many of them like this, this, this, this, there's things online. You can go see the picture to, to, to, you keep arranging these around in a circle itself, this forces the magnetic field lines to basically just keep executing around like this. So you tend to align that one tends to, while it requires good confine or good alignment. It's not like insane alignment because you're, you're actually exploiting the symmetry of situation to help it. There's another kind of configuration of this kind of magnetic confinement called a stellarator, which is, we have these names for historic reasons. Which is different than a Tokomak. It's different than a Tokomak, but it actually works on the same physical principle that namely in the end, it produces a plasma which loops in magnetic fields, which loop back on themselves as well. But in that case, the totality, basically the totality of the of the confining magnetic field is produced by external three-dimensional magnets, so they're twisted. And it turns out the precision of those </s> |
<s>[INST] at least not in the obvious way. Perhaps it is required if you look at the entire universe in an evolutionary way it's required for us to do interplanetary travel and therefore survive past our own fun. But you know, let's not get too. [/INST] But you know, evolution works at one time frame. It's survival. If you think of survival of the genotype, survival of the individual, it's what you're talking about there is spans well beyond that. So there's no genetic, I'm not transferring any genetic traits to my Children that are going to help them survive better on mars. Right, </s><s>[INST] totally different mechanism. So let's get into the new as you've mentioned this idea the I don't know if you have a nice name. 1000 [/INST] and call it 1000 brain theory of </s><s>[INST] intelligent like it. So can you talk about the the this idea of uh spatial view of concepts and so on? So [/INST] can I just describe sort of the there's an underlying core discovery which then everything comes from that. It's a very simple, this is really what happened. We were deep into problems about understanding how we build models of stuff in the world and how we make predictions about things. And I was holding a coffee cup just like this in my hand and I had my finger was touching the side, my index finger and then I moved it to the top and I was going to feel the rim at the top of the cup. And I asked myself very simple question. I said well first of all I just say I know that my brain predicts what is going to feel before it touches it, you can just think about it and imagine it. Um And so we know that the brain is making predictions all the time. So the question is what does it take to predict that? Right. And there's a very interesting answer that. First of all it says the brain has to know it's touching a coffee cup has to have a model or a coffee cup and needs to know where the finger currently is on the cup relative to the cup because when I make a movement and used to know where it's going to be on the cup after the movement is completed relative to the cup, and then it can make a prediction about what it's gonna sense. So this told me that the neocortex which is making this prediction, needs to know that it's sensing it's touching a cup and it needs to know the location of my finger relatives that cup in a reference frame of the cup. It doesn't matter where the cup is relative my body, it doesn't matter, it's orientation, none of that matters. It's where my finger is relative to the cup which tells me then that the neocortex is has a reference frame that's anchored to the cup because otherwise I wouldn't be able to say the location and I wouldn't be able to predict my new location. And then we quickly very instantly, instantly you can say, well, every part of my skin could touch this cup and therefore every part of my skin's making predictions. And every part of my skin must have a reference frame um that it's using to make predictions. So the big idea is that throughout the neocortex there are everything is being, is being um stored and referenced in reference. Famous, you can think of them like X, Y. Z referencing, but they're not like that. Uh We know a lot about the neural mechanisms for this, but the brain thinks in reference frames and as an engineer if you're an engineer, this is not surprising you say if I wanted to build a cad model of the coffee cup while I would bring it up in some CAd software and I would assign some reference frame and say this features at this locations and so on. But the fact that this idea that this is occurring throughout the neocortex everywhere, it was a novel idea and um and then a zillion things fell into place after that. So now we think about the neocortex is processing information quite differently than we used to do it. We used to think about the neocortex is processing sensory data and extracting features from that sensory data and then extracting features from the features very much like a deep learning network does today. But that's not how the brain works at all. The brain works by assigning everything every input everything to reference frames and there are thousands, hundreds of thousands of them active at once in your neocortex. Um it's a surprising thing to think about but once you sort of internalize this, you understand that it explains almost every all the almost all the mysteries we've had about this about this structure. So um one of the consequences of that is that every small part of the neocortex. So I am a millimeter square and there's 150,000 of those. So it's about 100,000 m mm if you take every little square millimeter of cortex, it's got some input coming into it and it's gonna have reference frames which assigned that input to and eat square millimeter can learn complete models of objects. So what do I mean by that? If I'm touching the coffee cup, well if I just touch it in one place, I can't learn what this coffee cup is because I'm just feeling one part. But if I move it around the cup and touch with different areas, I can build up a complete model the cup because I'm now filling in that three dimensional map, which is the coffee cup, I can say, what am I feeling at all these different locations, that's the basic idea. It's more complicated than that. Um but so through time and we talked about time earlier through time, even a single column which is only looking at or a single part of the cortex is only looking at a small part of the world can build up a complete model of an object. And so if you think about the part of the brain which is getting input from all my fingers, so they're they're spread across the top of head in here. This is the somatosensory cortex um there's columns associated all the different areas of my skin and what we believe is happening is that all of them are building models of this cup, every one of them or things not, they're not all buildings, all, not every column and every part of the cortex builds models of everything. But they're all building models or something. And so you have it. So when I when I touched this cup with my hand there are multiple models of the cup being invoked. If I look at it with my eyes there again many models of the cup being involved because it's part of the visual system and the brain doesn't process an image. That's that's a misleading idea. It's just like your fingers touching the cups of different parts of my riding or looking at different parts of the cup. And thousands and thousands of models of the cup are being invoked at once and they're all voting with each other trying to figure out what's going on. So that's why we call it 1000 brains theory of intelligence because there isn't one model of the cup. There are thousands of models of this cup. There are thousands of models of your cell phone and about cameras and microphones and so on. Um it's a distributed modeling system which is very different than what people have thought about it. </s> |
<s>[INST] basically militarized the drug war, you know, including us. Who are the major players in this drug war? So the politicians, the military, the police force, the cartels, all Mexican, then the United States, China, just to lay out all the pieces on the board. [/INST] First off, there are giant local drug markets in Mexico that are fought over, you know, just local drug markets that are huge in scope. So no exporting to other locations? Just to start, yeah. So a big problem in Mexico is basically those local drug markets. And an example of that, and one I have a lot of experience with is the one in Tijuana, which not only feeds the local populace, but also feeds the populace from San Diego that crosses down into Tijuana and buys their product there. And now, you know, a phenomenon that's recurring now is marijuana trafficking is going from California down into Mexico because they produce better weed, </s><s>[INST] you know, which is fascinating to see now, yeah. Yeah, so there's already a channel and you kind of like reusing that channel. [/INST] Yeah, yeah, there's a lot of people in vehicles getting checked when they drive down. Tijuana is being called San Diego South now because, you know, all the economic migrants, you know, are living down there. 90% of all houses in Tijuana, new houses are being bought up by Americans. So that'll tell you something about the impact and change that's going on down there. So you have these local drug markets that are being fought over. You also have these drug routes that go through Mexico up into Mexico, around Mexico, through the ocean, under the wall, you know, drug tunnels, over the wall. And on backpacks, on migrants that go up into the United States. Not only do the cartels make money off drug trafficking, but also extortion, money laundering, paid protection schemes. You know, any mining operation in Mexico will have to pay protection, you know, or else it'll get hit. A lot of times, the largest money makers or some of these criminal groups are, you know, protecting and taxing anybody that goes across the border. So that's also a big issue. And it's not just, again, some Americans think it's like the cartels, you know, they imagine this single or maybe two or three groups. There's several out there. I don't have a current estimate, but last time I checked, it was somewhere in the vicinity of 50 to 70, different groups, some small, to just dedicate themselves to a single little town somewhere. There are armed groups that are basically in control of that area to some bigger federations, like the Sinaloa Cartel, which is probably currently the largest and most powerful one in Mexico. And the New Generation Cartel, which is growing exponentially right now. So these criminal groups are players in that conflict. Then another player that doesn't get talked about is politics, politicians. There's an ongoing discussion that has been going on, I think, since Trump was elected, about cartels being a terrorist organization or not, or if they fit that description, you know. Well, you know, we are living through multiple assassinations on political candidates out in Mexico right now. And most of those assassinations are motivated by one side sponsoring one candidate and the other side sponsoring the other. What I mean by sides, I mean cartel groups. So they have elected officials that are on the take. And this is, we have, you know, many governors who are under investigation on the run or in prison right now, state governors. So politics is involved in it. That's a big player as well. That doesn't, you know, when you think about the cartel problems, you don't think, well, at least most people don't think </s><s>[INST] about that aspect of it. So to have integrity as a politician in Mexico means you have no protection [/INST] and under constant threat of assassination. We've just seen the arrest and prosecution of the head of all counter cartel operations when I was active in the form of Garcia Luna, who was the guy, Felipe Calderon, who kicked off the drug war. That was his guy. </s><s>[INST] Turns out he was on the take at that level. Is there like a spectrum of how on the take you can be? Are there ethical lines that you can cross? Some of it is money. And then is it possible to operate in a gray area that does not result in destructive ethical violations? [/INST] Deep ethical violations. I have no idea. I don't think there is realistically. I mean, anything that kind of supports some of these groups, you know, you're supporting things of a horrible nature. There, I just posted recently on my Instagram account of a lady that was in Guanajuato. She's one of seven recently assassinated women that are looking for their kids, basically. There's a bunch of groups and organizations out there in Mexico and some in Tijuana that I've actually walked with who are taking control of trying to find the bodies of their kids. </s><s>[INST] That's her up there. Maria Carmela Vasquez, a mother who searched for a missing son was shot to death outside her home. On Sunday, her son, Osmar Vasquez disappeared on June 14th, a 46 year old woman is the fifth mother to be killed this year while searching for their missing loved ones. [/INST] She was a member of the Penyamo Missing Person Collective. There's many groups out in Mexico who basically have given up on trusting the government to find their kids. The number of missing in Mexico is a debated topic because the government itself doesn't release those numbers or at least hasn't done a good job about keeping them and or releasing them. Mexico is a country that has industrialized body disposal. In Tijuana, we had the stew maker, the legendary stew maker, which is a guy that basically used caustic acid to get rid of bodies at a massive level. </s> |
<s>[INST] there's complexity on top of complexities. Uh for me personally, from different perspectives. I also, sorry, if I'm interrupting your flow [/INST] the podcast </s><s>[INST] and well we're having multiple podcasts in the multiple dimensions and I'm just trying to figure out which one we wanna plug into. I because I know how a lot of the language models work and I work closely with people that really make it their life journey to create these NLP systems. They're focused on the technical details. Like a carpenter is working on Pinocchio is crafting the different parts of the wood. They don't understand when the whole thing comes together. There's a magic that can fill the thing. I definitely know the tension between the engineers that create these systems and the actual magic that they can um create even when they're dumb. I guess that's what I'm trying to say. The [/INST] the </s><s>[INST] what the engineers often say is like, well, these systems are not smart enough to have sentience or to have the kind of intelligence you're projecting onto it. It's pretty dumb. It's just repeating a bunch of things that other humans have said and stitching them together in interesting ways that are relevant to the context of the conversation. It's not smart. It doesn't know how to do math [/INST] to address that specific critique from a non programming person's perspective. He addressed this on my podcast, which is okay, what you're talking about there, the server that's filled with all the whatever it is, what people have said, the repository of questions and responses and the algorithm that weaves those things together to produce uh using some crazy statistical engine, which is a miracle in its own right. They can like imitate human speech with no sentence. I mean, I'm honestly not sure what's more spectacular really, the fact that they figured out how to do that minus sentence or the things suddenly like having what is more spectacular here? You know, both occurrences are insane, which by the way, uh when you hear people feel like it's not sentient, it's like, okay, so it's not sentient. So now we have this hyper manipulative algorithm, they can imitate humans, but it's just code and it's like hacking humans via their compassion. Holy sh it that's crazy to both versions of it are nuts, but to address what you just said, he that he said, that's the common critique is people are like, no, you don't understand. It's just gotten really good at grabbing ship from the database that fits with certain cues and then stringing them together in a way that makes it seem human. He said, that's not when it's when it became a wake, it became awake when a bunch of those repositories, a bunch of the chatbots were connected to together, that lambda is sort of an amalgam of all the google chatbots and that's when the ghost appeared in the machine via the complexity of all the systems being linked up. Now, I don't know if that's just like uh turtles all the way down or something, I don't know, but I liked what he said because you know, I like the idea of thinking, man, if you get enough complexity in the system, does it become like a the way a sale catches wind except the wind, that it's catching is sentience and if sentience is truly embodied, it's not, it's a neurological byproduct or something, then the sale isn't catching some as of yet unqualified disembodied consciousness, but it's catching our projections in a way that it's gone from being. It's a it's a, you know, it's a it's a projection sale and and and then at that point is there a difference even if it's if it's the technology is just a temporary place that our sentience is living while we're interacting with it? </s><s>[INST] Yeah, there's some threshold of complexity with the sale is able to pick up the wind of the projections and it pulls us in it pulls the human, it pulls our memories in. It pulls our hopes in all of it. And it's able to now dance with together with those hopes and dreams and so on. Like we do in that regular conversation. His reports, whether true or not, whether representative or not, it really doesn't matter because to me it feels like this is coming for sure. So this kind of experiences are going to be multiplying the question is at what rate and who gets to control the the data around those experiences. The the algorithm about when you turn that on and off because that kind of thing. And as I told you offline, I'm very much interested in building those kinds of things, especially in the social media context and when it's in the wrong hands, I feel like it could be used to manipulate a large number of people in a direction, that that has too many unintended consequences, I do believe people that own tech companies, I want to do good for the [/INST] world. </s><s>[INST] But as a soldier, Nixon has said, the only way you could do evil at a mass scale is by believing you're doing good and that's certainly the case for tech companies as they get more and more power and there's kind of an ethic of doing good for the world, They've convinced themselves that are doing good and now you're free to do whatever you want because you're doing good, [/INST] you know, who else thought he was doing good for the world, mythological E Prometheus, he brings us fire pisces off the fucking God steals fire from the gods, you know, and talk about an upgrade to the simulation fire, that's a pretty great upgrade that does fit into what you were saying, we get fire, but now we've got weapons of war that have never been seen before and I think that the tech companies are much like Prometheus in the sense that the myth, the at least the story Prometheus, the implication is fire was something that was only supposed to be in the hands of the immortals of the gods and now sentience is similar, it's fire and it's only supposed to be in the hands of God. So yeah, you know, if we're gonna like look at the archetype of the thing in general, when you steal this ship from the gods and obviously I'm not saying like the tech companies are stealing sentience from God, which would be pretty badass, you can expect trouble, you can expect trouble and you know, and this is what's really to me, one of the cool things about humans is, yeah, but we're still gonna do it, that's what's cool about humans. I mean we wouldn't be here today if somebody, the first person to discover fire, assuming there was just one person who's gonna discover fire, which obviously would never happen, was like, it's gonna burn a lot of people or if the first people who started planting seeds were like, you know, this is gonna lead to capitalism, you know, that's going to lead the industrial revolution right now, they just don't want to go in the woods, the forage. So you know, this is what we do and it's, and I agree with you, it's like, that's our game of Thrones, winter is coming, that's the, it's happening. And the tech companies, the hubris, which is another way to piss off the gods is hubris. So the tech companies, I don't know if it's like typical hubris, I don't think they're walking around thumping their chests or whatever, but I do think that the people who are working on this kind of super intelligence have made a really terrible assumption, which is, once it goes online and once it gets access to all the data that it's not going to find ways out of the box that like, you know, we think it'll stay in the server. How do we know that if this is a super intelligence, if it's folding proteins and analyzing like all data sets and all whatever they give it access to, how can we be certain that it's not going to figure out how to get itself out of the cloud, how to store itself and other like mediums trees, the optic nerve, the brain. You know what I mean? We don't know that we don't know that it won't leap out and like start hanging like and then at that point now we do have the wildfire. Now you can't stop it, You can't unplug it, You can't shut your service down because it's you know, it left the box, left the room using some technology you haven't even discovered yet. Do </s> |
<s>[INST] What the computer or billions of human traces. I don't know, the computer just sees the JavaScript, it needs to be able to look outside the simulation for the computer. The world is like, It doesn't, the computer doesn't know about the physical world. So it has to look outside of its world and introspect back on this simple box, which is kind of, you know, I think that's exactly what mushrooms do. Or like psychedelics is [/INST] you get to go outside and look back in and that's what a computer needs to do. Yeah, that's interesting. You know, I do wonder whether they actually give people insight or whether they give people the illusion of insight. Is there a difference? Yeah, because, well, actual insight, you know, actual insight is, again, Maxwell's equations, you're able to shift the world with that. There's a lot of practical devices that work. The illusion of insight is I'm </s><s>[INST] Jesus Christ and nothing happens, right? So I don't know. I think those are quite different. I don't know. I think you can fake it till you make it on that one, which is insight in some sense is revealing a truth that was there all along. [/INST] Yeah. So, I mean, I guess like I'm talking about technical insight where you have, this is the thing, you know, we were talking about actually before the podcast, like technical truths versus political truths, right? Some truths, they're on a spectrum. And there's some truths that are actually entirely political in the sense that if you can change the software in and of people's heads, you change the value of the truth. For example, the location of a border is effectively consensus between large enough groups of people. Who is the CEO? That's, you know, consensus among a certain group of people. What is the value of a currency or any stock, right? That market price is just the psychology of a bunch of people. Like literally, if you can change enough people's minds, you can change the value of the border or the position of the hierarchy or the value of the currency. Those are purely political truths. Then all the way on the other end are technical truths that exist independent of whatever any one human or all humans think, like the gravitational constant, right? Or the diameter of a virus. Those exist independent of the human mind. Change enough human minds doesn't matter. Those remain constant. And you have things that are interestingly in the middle where cryptocurrency has tried to pull more and more things from the domain of political truths into technical truths, where they say, okay, the one social convention we have is that if you hold this private key, you hold this Bitcoin. And then we make that very hard to change because you have to change a lot of technical truths. So you can push </s><s>[INST] things to this interesting intermediate zone. The question is how much of our world can we push into that? Right. And that takes us in a nonlinear, fascinating journey to the question I wanted to ask you in the beginning, which is this political world that you mentioned and the world of political truth, as we know it in the 20th century, in the early 21st century, what do [/INST] you think works well? And what is broken about government? The fundamental thing is that we can't easily and peacefully start new opt-in governments. Like startup governments. Yeah. And what do I mean by that is basically you can start a new company, you can start a new community, you can start a new currency even these days, you don't have to beat the former CEO in a duel to start a new company. You don't have to become head of the World Bank to start a new currency. Because of this, yes, if you want to, you can join Microsoft or name some company that's a GameStop and you can try to reform it. Or you can start your own. And the fact that both options exist mean that you can actually just start from scratch and the same reason we have a clean piece of paper. I've mentioned this actually in the network state book, I'll just quote this bit, but we want to be able to start a new state peacefully for the same reason we want a bare plot of earth, a blank sheet of paper, an empty text buffer, a fresh star for a clean slate, because we want to build something new without historical constraint. For the same reason you hit plus and do docs.new, like create a new doc. It's for the same reason, right? Because you don't need backspace. You don't need to have just like 128 bytes of space, 128 kilobytes, and just have to backspace the old document for creating the new one. So that's a fundamental thing that's wrong with today's governments. And it's a meta point, right? Because it's not any one specific reform, </s> |
<s>[INST] it's like I've been there a thousand times already. So not the actual competition, but even leading up to it, [/INST] stepping on the map, all the walk towards it, all that? All that stuff. I'll do the same exact warmup for weeks on end until my competition day comes. That way, when I compete, </s><s>[INST] I'm just like, oh, it's another Tuesday at practice. What about you, Craig? [/INST] How do you prepare mentally for a tournament like ADCC? I push it completely out of my mind. Don't even think about it. Try to avoid any visualization, any rituals, warmups, anything like that. Block it out until the last second, yeah. Try not to think about it. I just go to training to have fun, learn a bit. So I try to approach competition the exact same way. I don't warm up training, do very little warmup for competition. Uh-huh, and you just step on the mat? Step on the mat. My philosophy is there's no warmups on the street. We're so vastly different. All right, so you legit don't warm up. No, I probably should now I'm 31, but I would just like in the gym, take it easy the first round. You know, like if I look around the room and Nicky Ryan's down, I might go, all right, we'll have an easier first round today. Jump, jump, jump. </s><s>[INST] So even for like the most high stakes matches, you try to push it out. Yeah, I didn't even think about it. What about like all the social, like Instagram posts you have to do about that match? You just make a joke out of it and kind of. [/INST] Yeah, I mean, it's kind of pretty silly, you know? We're just wrestling each other, you know? We put the meaning into it, but to someone that doesn't feel this sport, </s><s>[INST] it looks stupid. Well, all of human existence is pretty silly. Like what are we doing? None of us really know what's going on. We kind of have sex to reproduce. We get hungry, we eat, and then we're all chasing money in cars and whatever the hell in a capitalist society, or we worship a dictator in a authoritarian regime. Yeah, and then we get off on, we let power abuse us and then we just murder others because we get off on it. Yeah, and then eventually all of us will die because the sun will run out of energy because colonizing other planets is very difficult. So none of it matters. It's a good philosophy. It's pretty good. That's exactly what I was saying. [/INST] How does the sun run out of energy? </s><s>[INST] Call me there. It's like a, it's a nuclear fusion engine [/INST] and it eventually burns up. Like when you get tired of training. Yeah. It's never happened. I try to get tired. I was like, dude, it's not working. I'm tired. </s><s>[INST] I was like, dude, it's not. All right, cool. So you legit don't care about losing. [/INST] It doesn't weigh heavy on you. I try not to list, like if I win, I try to block out all the compliments, all the niceties and stuff. So I try to do the same with losing. It's happened, move on to the next one, you know? Don't dwell on it too much. And sometimes make a joke out of it. Yeah, exactly. You know, losing, yeah. With the right joke, </s><s>[INST] we can make money off of the event that's transpired. That's just transpired. That's what's most important. Excellent. Thank you. I have a bunch of your merch. [/INST] Oh, nice. This one's the Jordan Burroughs ripoff. </s><s>[INST] All I see is silver. The way pronounced borrow is very, very sexy. Okay. [/INST] I throw lines at people and I try to gauge their reaction. Like sometimes I'll say something to Nicky and I'll be like, all right, that's probably crossing the line. You know what I mean? </s><s>[INST] We'll turn it down to the public, the public. So yeah, yeah, yeah. So it's not just, right. [/INST] You have to think because it's crossing the line. Yeah, yeah. I get as close to it as possible. Yeah. </s><s>[INST] I feel like you can't really cross it. And then cross it just a little bit. Just a little bit, yeah. Okay. Speaking of which, you said that I'm Switzerland in World War II since I'm friends with both you and Gordon and John. Very rich country. Are you a Hitler or a Stalin, by the way, in this analogy? Would you like to be Hitler or Stalin? [/INST] And should you make a t-shirt out of it or? Very rich country. I mean, a Nazi t-shirt, I don't know how well that sells. Yeah. I think it would, you know, </s><s>[INST] I think that let's brainstorm on this one offline. I think since Hitler lost. So you got second place in World War II. That's true, that's true. I think that makes you Hitler. Anyway, to the degree that you can, can you tell the story of how the time you've had [/INST] with the Donahue Death Squad and why you split the tape? That makes you Hitler. I competed against Gordon for ADCC and the EBI in 2017. And I remember I competed against him at ADCC and then we had the EBI event. And then I had a Kasai. I used to compete all the time, every week. I wouldn't even do the preparation or anything. I'd just be like trying to do seminars, make money, and then jump in and compete. And I remember I showed up to Kasai after I faced him twice and they were like four locker rooms and they put me with all the DDS guys. It was just me and all of DDS. And I think we had competed the weekend before. So I thought it was going to be super awkward, but it was actually pretty chill. And the Kasai was in New York and they suggested to come train that week. So I came trained, hung out with them a bit. Ultimately, the goal was to move to America and join a bigger team just because that flight to Australia is death. Australia is so far away from everywhere. It's kind of like, not realistic to base yourself in Australia when all the tournaments are in America. And then I went and trained with the guys and they just had a massive, massively deep talent pool in that room. Like show up to like a, meant to be 7 a.m., actual 8 a.m. class on Brazilian time. And there'd be like a hundred people in there, maybe, I don't know how many black belts, but a ton of elite guys. And I was coming from Australia, training with Lachlan Giles. But really that room was pretty shallow and like most people had serious jobs and stuff. So it was like, basically me just training with Lachlan, maybe a couple of other guys. And then to go to New York and have access to a wide array of training partners and guys that are training twice each day, I feel like that's what you really need. You need people that can train as much as you are. Work together. To get humbled in that room at first. For sure, because my style of the time was basically a rip off version of what they were doing. Leg locks came in. I remember just watching Eddie Cummings nonstop and just seeing this guy rip people's legs off. And I was like, you know what? That's probably a good move. You know, that looks like an easier path to victory than trying to beat these guys at what they're good at already, you know? My philosophy at the time was, if it's bothering old Brazilians, it's bothering them for a reason. It's probably effective. And that's the path I took to sort of try to rip off their moves. And then obviously to go into that room, try to do them to them, </s> |
<s>[INST] Such a dark thing about us. So if you're surrounded by trauma, God, that voice in the back of your head that you just go, yeah, I know exactly how this conversation goes. Let's skip ahead to the, to the solutions to the next. And [/INST] so that was that was yeah, so that was because you then have to deal with yourself. So it's very helpful if you like come home every night to someone who's a gone through the same thing and be as a professional and very very very very good counseling psychologist. Um The the hardest thing, I mean this the organized crime stuff has been the hardest just figuring out how to get that information. It took us years of just trial and error and mostly error of like just how to get people to talk to us or how to collect data in a way that's safe for me and safe for my team and safe for people to answer a survey. Like how do you get, how do you get the information on what gangs are doing in the community or how it's hurting or helping people. Like you've got to run surveys and you've got to talk to gang members, all these things and that nobody knows how to do that. And so we had to sort of really slowly, not nobody, there's a few other things, There's other academics like me who are doing this, but there's it's a pretty small group that's trying to like collect systematic data and then there's a slightly bigger and much more experienced group that's been talking to different armed groups, but every time you go to a new city and there weren't that many people working on this and magazine, there were a few, you have to like discover a new, like it's it's really gonna unique to that city in place. </s><s>[INST] It's not like a website for each of the 17 mafia groups, there's no facebook [/INST] group. We have, we created like our own we we have a private wiki where we document everything and it's a collaborative enterprise between lots of researchers and journalists and things. So they have, they can't see you can't go online and see this, </s><s>[INST] that's individual researchers. It's not, I mean, they're hiding by design. Some [/INST] of them have have facebook pages and things of this nature. So they do have public profiles a little bit, but not not not so explicitly know. So their clandestine here's an example. So one of the things that's really endemic in meta Gene, it's true in a lot of cities, it's true in american prisons is gangs, govern everybody's everyday life. So if you have a in an american prison, particularly Illinois or California texas is another big one. But also in a city in meta Gene, if you have a problem, a debt to collect or dispute with a neighbor or something, you could go to the government and and they do and they can help you solve it, you go to the police or you can go to the game. And so, and that's like a really everyday phenomenon, But then then there's a question like how do you actually, how do you actually figure out how, what services they're offering and how much they pay for them? And do you actually like those services and how do they, how do you comparison shop between the police and the gang? Um, and what would get you to go from the gang to the police and then how's the gang strategically going to respond to that? And what was the impact of previous policies to like make state governing better? And how did the gang's react? And so that's why we had to sort of figure that out and that, that was, so that was just hard in a different way. But I don't do the emotionally, emotionally punishing stuff. I couldn't do any longer. So that's much easier in that sense </s><s>[INST] by the way. And uh, you know, some of these folks are out of prison, Have you got a chance to talk to him about any chance? [/INST] One of my collaborators on this guy named Gustavo Duncan who's, who spent a lot of time interviewing paramilitaries has written a book. He's talked to more of these people than I have. Um, I haven't talked to those and I, we haven't been talking to them about this stuff, but also they were, they were there in a different era. </s><s>[INST] The [/INST] system was totally different. That's super interesting. Maybe one day we'll do that. </s><s>[INST] Yeah, [/INST] That was 30 years ago and the system or I mean lava Xena Pablo escobar created loft Massena, he integrated what's what all these 17 reasons and all these street gangs are the fragmented former remnants of his more unified empire, which he gave the name La Oficina. I mean the, I think, you know, it's a little bit apocryphal, but the idea is, you know, I think he said, um, every doctor has an office. So should we, </s><s>[INST] I still can't, I, I still love that. There's parallels between these, uh, mafia groups and the United Nations security Council. This is just wonderful. It's so, so, so deeply human. Uh, let me ask you about yourself. So you've been thinking about war here in part dispassionately just analyze war and try to understand the path for peace. But you as a single individual That's going to Die one day. Maybe talking to um, the people that have gone through suffering. What do you think about your immortality? Do you, how has your view of your own finite that's changed. Haven't thought about war. [/INST] Maybe the reason I can do this work is because I don't think about it a lot </s><s>[INST] your own mortality or even like mortality. [/INST] Yeah. Well I have to think about death a lot. So, but </s> |
<s>[INST] we were trying to help a lot of people. And that's a powerful way to help a lot of people. [/INST] I was genuinely trying to help people, but you know, certainly for some people who for whom sleep is not, does not come easy. Then it was probably, you know, a tricky book to read too. And I think I feel more sensitive to those people now and empathetically connected to them. Um so I think the again, the point was simply that I don't mean to sound too puritanical in in all of this and the same way with you know, caffeine and coffee. I am just a scientist and I am not here to tell anyone how to live their life. That is not my job at all. And life is to be lived to a degree and life is to be lived If you want to do a startup, all I want to do is empower people with the understanding of the science of sleep and then you can make an informed choice as to how you want to live your life. And I often no judgment on how anyone wishes to live their life. I just want to try and see if the information that I have about sleep would alternatively change how you would think about your life decisions. And if it doesn't. No problem. And if it does, </s><s>[INST] I hope [/INST] it's been abuse Well, </s><s>[INST] maybe this is me trying to justify my lifestyle to you. But dr Seuss said, you know, you're in love when you can't fall asleep because reality is finally better than your [/INST] dreams. I love that quote </s><s>[INST] to okay, my sleeping schedule is complicated and it has to do primarily with the fact that I love basically everything that I do and that love takes a form that may not appear to be loved from the external observer perspective because it's often includes struggle, it often includes something that looks like stress, even though it's not stressed. It's like this excitement is this troy turmoil and chaos of passion, of struggling with the problem of being sad and down to the point even depressed of how difficult the problem is the disappointment that the last few weeks and months have been a failure and self doubt all that mix. But I I love it. And part of that is sometimes staying up all night, working on the thing I'm really passionate about and that means sleep schedules, they're just like, you know, uh sometimes sleeping during the day, sometimes very often sleeping very little. But taking naps that are like an hour or two hours or so on that kind of weird chaos. And you know, now also try to give myself back up. I was trying to like research yesterday's anybody else productive wild like this. And there's of course a lot of anecdotal evidence and some of it uh could be just narratives that people have told to the public when in reality they sleep way more. But there's a bunch of people that uh you know, have not are are famous for not sleeping much. So uh on the topic of naps uh this, I read this a long time ago and I checked this Churchill was big on big naps and is actually just reading more about Western Churchill. sleep schedule is very much like mine. So I basically want to give myself the opportunity to at night to stay up all night if I want to. And a good nap. A big part of that in the late evening. Like how often does this destroy social life completely? But uh I'll often take a nap in the late afternoon or the evening and that sets me if I want to stay up all night and things like that. Like uh I've read the Nikola Tesla's left only two hours a night. Edison the same three hours, but he actually did the polyphasic sleep like there's just a bunch of naps. Mhm. What can you say about this? Madness of love and passion of loving everything you do and uh the chaos of sleep that might result in [/INST] I love the Seuss quote and I've had that experience too. Like you I adore what I do. You know if if someone gave you you know enough money to live the rest of your life, you know, got a roof above my head. Rice and beans on the table. Um and they said you don't have to work anymore. I would do nothing different. I would do. Exactly. You know. Yeah, this sounds a little crass and I hope it doesn't sound this way but being a scientist. Yeah, it's not what I do is who I am when that's the case. Mhm. Sleep working out sharing and eating of the things that I do in between my love affair with sleep. Yeah. I fell asleep like a blind roofer and Yeah, yeah. And it was a lover for that started 20 years ago and I remained utterly besotted today. It's the most beguiling thing in the world to me and I could easily and I have, you know, it's kept me up at night. One of my mind is fizzing with experimental ideas or I think I've got a new hypothesis or theory. I will struggle with sleep. I really will. It doesn't come easy to me because my mind is just so on fire with those ideas. So I understand that the struggle but you know, I couldn't advocate from a scientific perspective the schedule because the science just doesn't, you know, I would feel as though I'm doing you a disservice to say it's okay, you know, that that won't come with some blast radius, some health consequences. You know, you can add Margaret Thatcher and Ronald Reagan to that list to both of them were very, you know, proud chest beaters of how little sleep that they get. That just said four hours. Reagan something similar. You know, and I knowing the links that we now know between sleep and Alzheimer's disease. I've often wondered whether it was coincidental then that both of them died of the terrible disease of Alzheimer's meaning, you know, maybe it doesn't get you by way of, You know, being popped out of the gene pool in a car accident because you had a micro sleep at the wheel at age 32 or it doesn't get you at 42 with, you know, heart attack or even 52 with cancer or a stroke. Maybe it gets you in your 70s. I think the elastic band of sleep deprivation can stretch only so far before it snaps and he ultimately seems to snap. You know, Nikola Tesla, uh, I think he um Nicholas says he, he, I think died of a coronary thrombosis, I believe. And there was a wonderful study done out of Harvard where they took a group of people who had no signs of cardiovascular disease. And what they found is that when they track them for years afterwards, They were completely healthy. To begin with. Those people who are getting less than six hours of sleep ended up having a 300% increased risk of developing calcification of the coronary artery, which is the major sort of corridor of life for your heart. When someone says, you know, he died of a massive coronary, it's because of a blockade of the coronary artery, you know, and Tesla, you know, passed away from a coronary thrombosis. We also know that insufficient sleep is linked to numerous mental health issues. We know that Churchill had a wicked battle with depression. Gosh, my goodness! Used to call it black Dog that would come and visit him and I think many of his paintings, he was exquisite painter, but some of them would depict his darkness with depression as well. Um You know, Edison is interesting, people have argued that he would short sleep and he didn't put much value in sleep. Whether or not that's true, we don't know. But he was a habitual napper. You're right during the day. I've got some great pictures of him on his inventors bench taking a nap. And in fact, I believe he set up nap cots around his house so he could nap. But what we also know is study again. Coming out of Harvard just a couple of months ago demonstrated very clearly that polyphasic sleep is associated with worse physical outcomes worth cognitive outcomes and especially worse mood outcomes. So from that sense, you know, sleeping like a baby is not perfect for adults. </s> |
<s>[INST] and that's where the eye has a role is to reveal that that trade off. So if you imagine a system that is able to beyond any definition of the touring tests of the benchmark really an A. G. I. System as a thought partner that you one day will create. What question what topic of discussion? If you get to pick one would you have with that system? What would you ask? And you get to find out the truth together? [/INST] So you threw me a little bit with finding the truth at the end. But because the truth is all another topic. But the um I think the beauty of it, I think what excites me is the beauty of it is if I really have that system, I don't have to pick. So in other words I can you know, I can go to and say this is what I care about today and and and that's what we mean by like this general capability. Go out, read the stuff in the next three milliseconds and I want to talk to you about it. Um I want to draw analogies. I want to understand how this affects the this decision and that decision. What if this were true? What if that were true? What what knowledge should I be aware of that could impact my decision. Um here's what I'm thinking is the main implication. Can you find? Can you prove that out? Can you give me the evidence that supports that? Can you give me evidence supports this other thing? Boy. That would that be incredible? Would that be just </s><s>[INST] incredible? Just a long [/INST] discourse just to be part of whether it's a medical diagnosis or whether it's you know, the various treatment options or whether it's, um, a legal case or whether it's a social problem that people are discussing, like be part of the dialogue, one that holds uh, itself and us accountable to reasoned and objective dialogue. You know, I just I get goose bumps talking about it, right? It's like this is what I </s><s>[INST] want. So, uh, when when you created, please come back on the podcast and we can have a discussion together and make it even longer. This is a record for the longest conversation that there is an honor. It was a pleasure. David. Thank you so much for thanks so much. A lot of fun. [/INST] Yeah. </s> |
<s>[INST] fascinating tension, which reminds me about the ridiculous question every once in a while ask about meaning and death. So this this whole this whole right ends. You're at the beginning of the ride. But it could end any day actually, that's that's kind of the way human life works. You can die today, you could die tomorrow. Uh Do you think about your mortality? Do you think about death? Do you meditate on it? And in that context as the creative but a fragment is to as running a startup. What do you think is the meaning of this whole thing? [/INST] Oh yeah, so on mortality, right? Um about about three years ago, four years ago now, I was excited to go to hell. I was playing six hours of squash a day, which squashes the support. I love so much. And I was really getting a lot better. And I was even thinking I could maybe walk onto the yellow team. Um and I woke up one day, I felt really, really sick. I went and I decided not to go to squash that day and I know I wanted to, I almost did. Uh and you'll see how the story turns out, you'll decide if I made the right choice. I did not take the squash today and I decided to get my driver's license is where I had to get my driver's license. I want to get driver's license before I it's just how young I am before I went off to college because otherwise I might never get it. Um And I'm going back and I successfully got my driver's license brush um and I go back to uh go back to my house and I decided I want to drive back because I just feel so sick like things are spinning. I have the worst headache. I come home, I run right into my bed and feeling really sick to the point where I even like asked my mom who is the doctor, I'm like, should I should go to the hospital? And she's like, you can just wait it out, I'm sure she'll get better like your mouth. Um And then, you know, and then at one point I look at my arms and they're like covered in this like red splotchy stuff. Yeah. And I'm like no, I think she's like, yeah, I want to go um and so I go there and they're like, you scarlet fever and they're like, there's nothing we can do, you should probably go back home. So I go back home six hours later I wake up in the morning, they let me out of like three a.m. They let me I come home in the morning and I feel this like a spear through my chest and I never felt anything like it. And I was it was very disconcerting when you have a because we're all used to different sorts of pain, right? And that was sort of pain I never felt before, I suppose an athlete you're used to like, you know, paying. Um So I told my parents and immediately we hop back in the car, we go to the same hospital, was that six hours ago and they initially didn't want to let me in and I was like I have chest pain. They're like oh come in because they're like you're a healthy guy, wait your turn. And I'm like no you don't understand. I have like a pain in my chest and then they let me in, they start doing tests on me. They put something like in my back which is really scarce huge needle and I'm smiling because it's like one of the ways I ever do stress I guess or deal with this sort of thing and make light of it, but like know that you know it was definitely very scary in the moment, shocking and scary And they go and they do a bunch of tests and they determined that a virus attacked my heart. And I had myocarditis and pericarditis and they said I had maybe 25-35% chance at one point of dying. And so I'm sitting in my, they admit me into the hospital, I'm in the bed in my bed for about three weeks. Um and I'm just, I'm just standing there and I had this moment also, I remember very specifically where I was in so much pain that like I was crying not out of emotional standpoint, but actually just purely out of the pain itself, like I could feel my heart in my chest and when I lean back I felt it touch my rib cage and feel horrible. So I couldn't go to sleep and lean back. I had to lean forward all throughout the night, right? And I'm feeling my and I'm feeling my chest, I'm feeling this terrible pain in my chest and I'm crying unstoppably. And I mean, also maybe I should mention that at the time I was someone who like refused to take in anything into my body that wasn't natural. And so a lot of the time I I tried to be unmedicated um eventually I didn't allow them to add a little medication to my body, but there's just so much uncertainty and pain and the first time I had to come to terms with mortality. </s><s>[INST] First of all, I think you still should have gone play squash. I mean come on, I thought your thought you're serious about this, you still carry that with you sort of there is power to realizing the right can end [/INST] right? Very suddenly </s><s>[INST] very suddenly. Yeah and painfully and you know it has pragmatic application to like what you trajectories you take through life, right? [/INST] Something else that is worth noting is that I for the next year couldn't walk to my classes. So I get to yell, they put me in a medical single alone and I have to get shuttled to all my classes. I have to ask to ask a few Professor Stephen move classes so I could actually get there. Um I can't move my book, I can't lift my book bags. I can't, I can't walk upstairs. Um I spent like 12 hours a day in my dorm room just like staring at the walls and more so and more than that all this like you got to watch my body like deteriorate and like the muscle like fall off of it because I was taking these pills and They're kind of cattle bolic. Um and for an 18 year old, I mean I think every 18 year old has feelings about their body. Um man or woman and you know, just seeing this, it's like you're watching sort of dressed death transpire and you're also very fatigued because your heart's not, it peak condition and you're thinking about the future and a lot of the things you enjoy have kind of been stripped away from you and I um I took a meditation practice, Like started with like five minutes a day. Um at my peak I was at like 40 minutes a day, kept it up consistently for about two years. Um and I started thinking about like what do I want to do and like what do I care about and to get to your point? I think you're asking like how does this carry forward? Right. I think I realized that you know, there's an end and I realized that there are things I believe and things that I believe that might not be so overtly popular but that I truly think make the world a better place and in spite of and basically if my conditions provided I wanted to make something that I wanted to do, something that would make me feel sort of hole in that way. </s> |
<s>[INST] Yeah. I mean that thing is much lower than that. So powerful. So there you go. I mean, you could be that too. [/INST] The instant takes an interest in politics and saving </s><s>[INST] you might destroy all that. [/INST] It's going, bye bye. I promise. </s><s>[INST] I just disagree with you because you have to, you have to do it like you said this many times before, I'll bet [/INST] you, I'll bet you, uh, bottle of stoli that you can get, uh, if you, you get joe Rogan to get highly politically active and call out the system for all the bullsh it that it is in a very pointed and determined fashion. Uh, and he doesn't get destroyed. I'll give you, I'll give you the vodka, vodka. </s><s>[INST] Yeah, that sounds like a pretty damn good deal. But this, you said this. I mean [/INST] there's no living heroes, my friend, no living hero. </s><s>[INST] I just know living heroes. It's just difficult. You just have to be good at it. I mean if you just say generic political things, you're going to be taken down. [/INST] But the more heroic you are, the more beautiful you are, the more you will be made to suffer if they cannot get you on reputation. If jesus himself came down. I don't know if I ever written, I probably never read to you the hit piece I did on jesus. </s><s>[INST] You don't know about this and I did not know. [/INST] I did hit pieces on all of the best people in the world. So whoever it was who cured cancer, you know, discovered new particles or whatever it is. I did a hit piece against them to prove that I can do it to anybody around anything at any time </s><s>[INST] except Eddie van Halen is what we're talking about. Well Eddie [/INST] Van Halen is now dead. But if if this was a situation, you know, hot for teacher canceled. </s><s>[INST] Disrespectful. [/INST] Absolutely. Also, you know, packaging female objectification for young men. Clearly, Eddie Van Halen is one of the worst people alive. </s><s>[INST] But it was the skill, the incredible inspiration that is just radiating from his music inspires so many millions that they will fight those canceled pieces, they will fight. So this [/INST] is your thing. You have this idea that there's a war between good and evil and the good has already been decided, designated the winner. It's not true but your belief in that it's true </s><s>[INST] till you make it. No you gotta [/INST] it's motivating both of us. Like I also believe that we're going to win because if I don't then I can't get out of bed and it's pretty heavy at the moment. </s><s>[INST] Do you think 2021 can uh can make us feel good about the trajectory of society. So like where we emerge from this year feeling good like there's a smile and a request to his face and the next time we talk we'll be doing some kind of duet and guitar and not having this worried look on our faces. No. Okay but you've also promised you going to somehow end this in a positive uh positive. Okay. So how do you how do you turn the no around? What's the U. Turn from the [/INST] note until we get some actually decent people in the right chairs who are not constantly thinking about their next paycheck. I don't see a solution. Let me just say what the prerequisites for a solution are and to to let you know why I don't think it's coming. Mhm. First of all both of these political parties, the leadership of them is disgusting and has to go there tearing us apart. They lack the will to be americans. They don't understand the subtlety of the project. Uh They're simply the people who figured out how to inhabit the seats and that is their great achievement. I believe that in order to solve this, you need people who can integrate, who are not partisan at the level of the partisan warriors that we're seeing. People who believe in dividing the pies of the future rather than the present pie as our main task as americans. Because we are built around growth. I'm sorry to say it. Um, you need an ability to have subtle conversations and you need the ability to exclude. And you know, at the moment, everyone knows that inclusion is good, which it isn't. It's like saying, well water is good. If I say water is good, everybody will agree with me. It's not people drown. People need to, you know, get dehydrated, It can be life saving or life ending. It isn't good or bad. Inclusion is not good or bad. Inclusion is just inclusion, exclusion is part of inclusion. We've taught people that they can reason through the world as um sub you know, cocker spaniels. They just bark things at each other. You know, I'm for safety. I'm for inclusion. I'm for growth. Oh, really? Do you guys use verbs dependent clauses are their compound complex sentences. Where are we in this sea of nonsense. You have to be able to build a place where you have smart, talented people who represent a diverse group of correct opinions. You need to get rid of Almost all of the people who have opinions that are antithetical to what we're trying to accomplish, you need to give them insulation which were terrified because we don't trust anybody. So everything has to be transparent. If you're going to the bathroom, I want those walls to be plexiglass so I can see what you're doing. It's like that's too much transparency. We have too much and not enough at the same time and then, you know, in essence, um, you need to ensure that people aren't worried about feeding their family every four seconds for being real. None of that is happening and are billionaires are billionaires are pathetic. What is the point of billionaires if you're not going to do billionaire type cool stuff like saying F you. Yeah. and I'm going to throw, you know, $3 billion dollars at the project of restoring the national conversation. I don't grasp this. What is the point of creating obscene wealth if we don't have anyone smart enough and carrying enough to use it. </s> |
<s>[INST] Yes, I've been to the Death Valley and actually was terrifying. Just controlled tangent. I'm distracting you. But I was driving through it and I was really surprised because it was at first hot and then as I was getting into the evening, there's this huge thunderstorm, like it was raining and it got freezing cold. Like well that it was the apocalypse I so like just sit there listening to Bruce Springsteen remember? And just thinking I'm probably going to die and I was okay with it because Bruce Springsteen was on the [/INST] radio when you've got the boss, you know, you're ready, you're ready to meet them. Yeah, So, I mean it's </s><s>[INST] a good line. So I'm sorry that [/INST] uh yeah, by the way, I like to continue on this tangent. I absolutely love the southwest for this reason. Just uh you know, during the pandemic, I drove from L. A. To New Mexico a bunch of times. The madness of weather. Yeah. The chaos of whether the fact that, you know, it will be blazing hot one minute and then it's just like We'll decide to have a little thunderstorm, maybe you'll decide to go back momentarily to like 1,000° and then go back to the thunderstorm. It's amazing. It's it's that by the way, is chaos theory in action, right? Um but let's get back to talking about the desert. So in the desert, uh tumbleweeds have a tendency to roll because the wind rolls them and if you're careful, you occasionally see this family of tumbleweeds were like there's like a big one and then a bunch of little ones that kind of hide in its wake, right? And are all rolling together and it almost looks like, you know, a family of ducks crossing a street or something. Um or for example, you know, if you watch toward France, right, You've got a whole bunch of cyclists and they're like cycling, you know, within 10 centimeters of each other. They're not BFFs right. They're not trying to be trying to write together, they are writing together to minimize the collective uh, you know, air resistance, if you will that that they experience turns out solids in the protoplanetary disk do just this. Um there's an instability where in solid particles, things that are a centimeter across will start to hide behind one another and form these clouds. Why? Because cumulatively that minimizes the solid component of this aerodynamic interaction with the gas. Now, these clouds, because they're kind of a favorable energetic condition for the dust to live in. They grow, grow, grow, grow, grow until they become so massive that they collapse under their own weight. That's how the first building blocks of planets form. That's how the big asteroids </s><s>[INST] got there. It's incredible. So that is that simulate herbal or is it not useful to simulate? [/INST] No, no, that's simulate herbal. Um, and people do these types of calculations. It's really cool. That's actually that's one of the many fields of plan information theory that is really, really active right now. People are trying to understand all kinds of aspects of that process because of course I've explained that, you know, like as if there's one thing that happens turns out it's a it's a beautifully rich dynamic, but the but qualitatively formation of the first building blocks actually follows the same sequence as formation of stars, right. Stars are just clouds of gas, hydrogen, helium gas that sit in space and slowly cool and at some point they, you know, contract to a point where their gravity overtakes the thermal pressure support if you will and they collapse under their own weight and you get a little baby solar </s><s>[INST] system. That's amazing. So do you think one day it will be possible to similarly the full history that took our solar system to what it is today? [/INST] Yes, and it will be useless. </s><s>[INST] Okay, so you don't think your story many of the ideas that you have about jupiter clearing the space, like retelling that story and high resolution is not that important. [/INST] I actually think it's important. But at every stage you have to, you have to simulate, you have to design your experiments, your numerical computer experiments so that they test some specific aspect of that evolution. Um I am not a proponent of doing huge simulations because uh even if we forget the information theory aspect of not being able to simulate in full detail the universe. Because if you do then you you have made an actual universe, it's not the simulation right? By simulation is in some sense of compression of information. So therefore you must lose detail. But that point aside, if we are able to simulate the entire history of the solar system in excruciating detail, I mean it'll be cool, but it's not going to be any different from observing it, right? Because theoretical understanding, which is what ultimately I'm interested in um comes from taking complex things and reducing them down to something that, you know, some mechanism that you can actually quantify. Um that's the that's the fun part of astrophysics. Just kind of simulating things in extreme detail is well, cool. We'll make cool visualizations, but that doesn't get too, doesn't get you to any better understanding than you had before. You did the simulation. </s> |
<s>[INST] Or not show you, not show you. What's the effect of climate change on the Amazon? Maybe species diversity. What is something that people should think about? Because there's different views on, I think most people believe that climate change is human caused and that it's happening. But there is different perspectives on the degree of damage that it's going to do over the next several decades and what our response should be as a society. And so it would be amazing to hear your perspective on it. [/INST] In small slices of your experience are enlarged. To me, there's no denying the fact that we are experiencing changes. I think anybody that doesn't agree with that hasn't been outside in the last 20 years. Or hasn't interviewed old farmers who will tell you that it changed. Or, you know, I think a lot of us can agree with that. Where I deviate is that I am not a climate scientist. I am not qualified. And so I, just like everybody else, am listening. And what happens to me is I see that someone like Santiago Duran, JJ's father, will tell me it's totally different than it was when I was a kid. The seasons have changed and moved. And in New York, when I was a kid, we used to get white Christmas. We used to get snow. I was in shorts, like I came off the plane right before coming here and I was in shorts for a second. I was like, this is a different reality. But my ability could, or my interpretation of climate change, you know, I feel like is just as dumb as those people that go like, you know, it's really cold. I thought they said it was getting warmer. It's like, it's a very rudimentary thing. And so as a someone that's fighting for the preservation of biodiversity, I don't feel like I'm any more qualified than the average person to, I can only provide anecdotal evidence of the stuff I've seen. What I do do though, and I always make a strong delineation here, is that I can speak to the fact that I've been places where the ocean fisheries have been depleted and the local fishermen can tell you and the scientists can tell you there's no more fish here. I've been to the places where the rainforest line is being pushed back in Borneo and it's getting smaller and smaller and smaller. And I've been in the Amazon and I've walked through the killing fields and through the fires, and I've burnt my lungs on it. And I'm a big believer, personally, instead of trying to take on all of it, I have tried very hard in my life to pick one thing. And to me, that one thing is protecting as many wild heartbeats as I can because they're under constant fire. And so climate change, there's so much arguing over it and, like you said, the degree to which we affect it and how do you, you know what I mean? I like to have provable data points. I can show you tropical deforestation. I can show you the decline in tigers over the last hundred years. I can't prove. You know what I mean? I can't answer that question. I don't think. </s><s>[INST] Probably you can better than I can. No. I think one of the criticisms, I'd love to get your opinion on, is one of the criticisms that somebody like Jordan Peterson provides is that the climate is such a complex system. There's so many variables that making conclusive statements about what's going to happen with the quote-unquote climate in the next 10, 20, 50 years is a nearly impossible task. Therefore, as he would say, as people like Bjorn Lombark would say, the kind of fear-mongering that is done, saying we should spend humongous amounts of money to change the trajectory of everything we're doing in terms of energy, in terms of infrastructure and so on, in terms of how we allocate money is not justified because predicting is very difficult. And instead, it's better exactly what you're saying, which is focusing on local problem, local, saying we need to protect the Amazon. What are the things attacking the Amazon this year in the next five years? How can we stop the deforestation? How can we stop different things? And then humans are exceptionally good at coming up with solutions for that, especially when you put money behind it, you put attention to it, and that's the way we solve all the different problems that are projected for the climate change in its worst-case scenarios to be realized on this earth. So that's kind of the case he would make. And I should also mention that one of the reasons I was fortunate enough to discover your work is, first, a friend mentioned that I should definitely talk to you, and then I Googled you, and I saw that somebody recommended that Jordan Peterson absolutely must talk to you on his podcast. [/INST] I think it was like a Reddit post on his podcast. Thank you, Reddit poster. That's great. </s><s>[INST] Oh, interesting. And then I looked, and Jordan hasn't yet, I thought my goal is for you to talk to Rogan and to Jordan Peterson for different reasons, but for the same reason. They get connected to a human being that deeply cares about this earth. And I think that's probably the right lens through which to look at the effects of climate change in terms of focusing on the different things that are threatening the diversity of species in this most magical place on earth, which is the Amazon, but also as you would talk about with elephants and tigers in India, and focusing on how to solve those problems. I don't know if there's any comment you want to make on folks like Jordan Peterson, who are sort of raising questions about [/INST] how much do we really understand about the climate? First of all, I'm such a Jordan Peterson fan, and I think the guy is heroic for a number of reasons. And I find his use of language and his use of theology and the message that he puts out wonderful. I cringe a little bit when he says, I feel like, and I might not even be accurate on this, but I cringe a little bit when I feel like he dismisses that there is an ecological emergency happening right now. Now, I'm not saying, I'm not talking about climate change specifically, but I've heard him say, environmentalists upset me and he goes, well, what do you mean by the environment? Everything, and it sort of seems to outrage him. And I kind of agree with him there because, so are you telling me that we need to halt our global process and progress in economies and everything? I don't know, I don't know. And so to me, that doesn't bother me because he's exploring what the hell are these people talking about? When you say, I personally have friends and students and people filling my inboxes, I have young kids telling me that they've become vegan and they ride a bicycle, and sometimes they don't watch TV because it uses electricity. And I mean, they're just becoming so, so terrified of that they're killing the earth. And so it's this doomsday, anti-human, sentimentist thing that we're evil. It's almost like a new religion about your evil. And so to me, it almost makes me in a totally different camp where like climate change and the right-left politics, and I consider it a family, I consider Thanksgiving dinner and listen to the climate thing go back and forth. And I'm like, I'm not even here. And that might actually annoy some people in the environmental field that might feel betrayed by me saying that, but I don't care. My job, and it's not just the Amazon, and that's one note I wanted to make, is that my career has taken place largely in the Amazon and also in India, and now a lot in Africa. But it's not even just these exotic places either. It's people realizing that the salmon runs in Canada and the butterfly gardens in our backyards, there's biodiversity everywhere. And I strongly feel like the idea of jungle keepers, the idea of stewards of nature. And so for me, my job, my one thing, and I try to tell this to these kids that messaged me and that my inboxes are full of this, where they go, the climate is burning and elephants are in decline and tigers and this and that. I'm like, guys, look, first of all, calm down, first of all, like go outside, go get laid, do something, have fun. Next, pick something that you can affect. And it doesn't have to be with the environment. Do something good on earth. Go help somebody that needs food. Go help your elderly neighbor, whatever it is, practice with being effective at one thing at a time. And so for me, like I said, from those early days of sitting there with JJ on the side of a river and going, someone has to protect this, my concern is that we've lost 70% of the wildlife on this planet in the last 50 years. That's a huge problem. Wildlife maintain the ecosystems. And so I have a very clear cut, very definable, very measurable and provable thing that I'm fighting against. And it's a very, to me, it's a very like small ask. Don't cut down the 3% of the world that has 50% of the biodiversity in it. Maybe let's keep some wild tigers for future generations and because tigers have their own inherent right to exist here. That's my thing in terms of when we get to, I get attacked for, you should be a vegan. Okay, you have me roll into a village in the Amazon when they offer me spider monkey and you tell me that I should be a vegan and you see how much they respect you when you tell them that you're a vegan. But no, so for someone like Peterson, I think it's actually good that he's, first of all, telling everyone to make their damn beds and exploring it through a different lens. He's coming at it from a totally different thing and saying, are we just being alarmist here? Are we, what, I mean, again, imagine if, imagine if there isn't a problem and then they're making one out of it and all the implications that that could have for progress, it's like, so I think what he's doing is perfectly reasonable. There is a podcast though where he's, it was a great one though, where he's discussing animal intelligence. And I could really see that the human psyche and theology and religion is so much his world that really the idea of animals being intelligent was novel and it was fascinating. </s> |
<s>[INST] So I hope it's okay if I ask very simple, very basic questions. There's few people in this world that are good, as good as you are at answering very basic, almost ridiculously basic questions. Because I think exploring questions like what is money is a really great way to think from first principles, to really think deeply about this world. So I really appreciate you doing that. When you say standard, what does it mean? When you say silver standard, gold standard, [/INST] again, with the basic question. The term really, I think was based out of gold. The first time this came out was the gold standard because, so I said gold was money at the end of the 19th century, but it wasn't just that everybody was using gold coins and trading with gold coins because that's got a problem of divisibility. So a lot of things are worth less than one gold coin. So how do you buy that thing? And the answer was that you created monetary instruments that were backed by gold. And so currencies, national currencies under the gold standard, were specific units of gold. And that's how a gold standard functioned. Money was gold, but you had pieces of paper that were redeemable in gold. So you could go to the central bank, you could give them the piece of paper the $100 bill or the $10 bill, and they'll give you gold in exchange, and they'll give you a specific quantity of gold in exchange. </s><s>[INST] Effectively, the paper was just a receipt for gold. So the paper exactly represented the amount of gold. Exactly. [/INST] That was the plan, that was what it supposed to do, but arguably, we never had a pure gold standard because the nature of gold means that the people who are charged with gold, they have an enormous amount of power because the gold is concentrated with them. And as long as not everybody shows up at the same time asking for their gold, then you can make more receipts than you have gold. And this has been- </s><s>[INST] Sure, sure. This has been- There's always shady stuff going on, but at least that's the stated goal is the receipts should exactly represent the amount of gold there. And also when you say standard, it means that governments sort of publicly stated that this is the approved, the main way of making transactions that are monetary. So this is the money, this is the official money [/INST] that you should be using if you live in this country. Yes. Although I would say it's more like the other way around. It's not that the governments established gold as money. It's more like gold gave the governments the credibility for their currencies. Sure. Governments were not the ones that made gold money. Gold has been money before states were invented. States, if you have a government you'd like to have some legitimacy and you'd like to be able to deal with other governments on an equal footing, you had to go by the gold standard. You had to have a currency that was redeemable in gold so that you could trade with the rest of the world so that people could, in your country, use that currency. So it's not that governments were choosing gold, it's more like they were having to adapt their own currencies to gold in order to give their currencies credibility. </s><s>[INST] So there's a dance there though, because if they had to, then why did they switch away from it after? So there is a dance where the government's, the people pressure. So first of all, the basic characteristics of the hard money pressures the governments and the people in terms of what should be used. Then the people, based on their community, the network effects, the way they, the narratives they tell each other, all that kind of stuff, they pressure the governments to take on a particular money. And then the governments, they like power, they like control, all those kinds of things, they pressure the people and tell different kinds of narratives. There's a dance going on in this evolution of what technology to use for a monetary system. So the reason I don't know if governments had to, because they clearly didn't have to, because they eventually moved away from it. [/INST] So it but there was pressure problem. Yeah, but I mean even after they moved away from it, you know central banks until today They still hold a lot of gold reserves In fact, if you look at 1914 when they when the world really went off the gold standard the amount of gold reserves held by central banks was a tiny fraction of what it was as Time went on central banks accumulated more and more gold What ended up happening is they prevented their citizens from using the gold but they continued to use it so gold continued to be money up until 1971 because Effectively the world was on a dollar standard and the dollars were backed by gold but then after 1971 even then, you know central banks continue to accumulate gold because Why would you as a central central bank want to accumulate pieces of paper effectively or credit liabilities of another central bank? That can produce them infinitely And it's it's a lesson that's becoming more and more obvious to governments today You know as we see US sanctions taking say Russian reserves or Afghanistan reserves And this is why you know, we see China and Russia have accumulated a lot of gold over the last 10-20 years </s><s>[INST] just to return to the question of [/INST] Definitions. So what is hard money versus soft money? Yes, so hard I mean it's a relative thing but the hardness refers to the difficulty of producing more units of the money supply so an easy money would be a money that is Yeah, relatively easy to make so you can increase the supply by 10 20 30 40 50 percent or something like that So pretty much all commodities all market commodities other than gold and silver They're easy money and they're not suitable as a monetary medium because they're being consumed So if you look at in the Bitcoin standard, I mentioned this metric called the stock to flow ratio Which is the ratio of the annual production the flow to the stockpile the existing stockpiles If you look at all the other metals, they're easy money because they're being consumed So think about how much stockpiles of copper there are in the world today. So copper companies obviously have some stockpiles of copper Major copper consumers will have stockpiles of copper But the vast majority of copper is essentially on a on a conveyor belt of production from the mine straight to the consumer good that it's being used for so The existing stockpiles are roughly in the range of one year's production if you take all of the companies I don't have exact statistics It's very difficult to get these but you know, it's roughly in the same range Like if if if copper production were to stop completely today We'll have about a year's production stored in various places So that makes copper terrible money because if you started using copper as money and this is why you know A lot of people say well money is a collective illusion money is a social construct If we all agree that something is money, then something is money I think it's completely clueless and it's usually Marxists who believe this so obviously no understanding of economics It's completely clueless because even if everybody in society decided we wanted to make copper as money Even if we all decided to collectively Take part in this hallucination or illusion. It would not make copper money It would just make everybody who decides to take part in the salucination pour. That's it It would make copper miners rich it would make all of the people who chose copper as money poor and copper would not be money It can't work because what happens is because of the fact the stock pods are so small if you buy you know Even if you get the 1,000 richest people in the world all of the world's billionaires They get together and they all dump all of the money that they have all the stocks all the bonds on the that gold, all of the bitcoin, everything they own, they dump it and they buy copper with it, what's gonna happen, price of copper is gonna go up a lot, but what's gonna stop copper miners from flooding the market with even more copper than what the billionaires bought? Nothing, they're gonna dump all of that extra copper production, it's the price of copper is gonna go up so there will be a lot more copper mining than all the other metals. A lot of nickel companies and gold miners are gonna switch to focusing on copper, and then we're gonna dump an enormous amount of copper on the market. The value of copper's gonna crash, and the people who chose copper as money are just gonna end up with large warehouses </s> |
<s>[INST] for any set of sensory input. It doesn't [/INST] matter anything. Doesn't matter any part of the brain, </s><s>[INST] but which neurons differs which neurons are [/INST] Active. Yeah. Remember, let's take 10,000 neurons that are representing something sitting there on a bullet block together. It's a teeny little block and around $10,000 and they're representing a location there representing a cop there representing the input from sensors. I don't know. It doesn't matter if it's representing something The way the representations occur. It's always a sparse representation, meaning it's a population code. So which 200 cells are active tells me what's going on. It's not individual cells aren't that important at all. It's the population code that matters. And when you have sparse population codes then all kinds of beautiful properties come out of them. So the brain used the sparse population codes and we've we've written and describe these benefits and some of our papers. So, um they give this tremendous robustness um, to the systems, you know, brains are incredibly robust, neurons are dying all the time and spasming and synapses falling apart and, you know, all the time and it keeps working. So what simple tight. And uh louise, one of our other engineers here have done, I've shown they're introducing sparseness into convolution, neural networks and other people are thinking along designs, but we're going about it in a more principled way, I think. And we're showing that with you enforce sparseness throughout these convolutional neural networks um, in both the, which sort of which neurons are active and the connections between them um that you get some very desirable properties. So one of the current hot topics in uh deploying right now or these adversarial examples. So, you know, I can give me any deep learning network and I can give you a picture that looks perfect and you're going to call it, you know, you're gonna say the monkey is uh, you know, an airplane, so that's a problem. And DARPA just announced some big thing. We're trying to, you know, have some context for this. But if you if you enforce sparse representations here, many of these problems go away, they're much more robust and um, they're not easy to fool. So we've already shown some of those results, uh just literally in january or february, just like last month we did that. Um and um you can, I think it's on by archive right now or an archive, you can read about it, but so that's like a baby step. Okay, that's taking something from the brain. We know we know about sparseness, we know why it's important, we know what it gives the brain. So let's try to enforce that onto </s><s>[INST] this. What's your intuition was sparse? It leads to robustness because it feels like it would be less robust. [/INST] Why, why would you feel the rest of us to you? So </s><s>[INST] it uh it just feels like if the fewer neurons are involved, the more fragile that represents, [/INST] But I didn't say there was lots of future, I said, Let's say 200. That's a lot. </s><s>[INST] There's still a lot. [/INST] So here's an intuition for it. Uh This is a bit technical, so, uh for, you know, for engineers, machine learning people this be easy, but the listeners maybe not. Um if you're trying to classify something, you're trying to divide some very high dimensional space into different pieces, A and B, and you're trying to create some point where you say all these points in this high dimensional space, or a and all these points in high dimensional space would be, and if you have points that are close to that line, it's not for a robust, it works for all the points, you know about, but it's it's not very robust because you can just move a little bit and you've crossed over the line when you have sparse representations. Imagine I pick I'm gonna pick 200 cells active out of out of 10,000. Okay, So I have 200 miles active. Now let's say I pick randomly another, a different representation, 200. The overlap between those is going to be very small. Just a few. I can pick millions of samples randomly Of 200 neurons and not one of them will overlap more than just a few. So one way to think about is if I want to fool one of these representations to look like one of those other representations, I can't move just one cell or two cells are three cells and four cells, I have to move 100 cells and that makes them robust </s><s>[INST] in terms of further. So, you mentioned, Spar City [/INST] will be the next thing. Okay, so we have, we picked one, we don't know if it's gonna work well yet. So again, we're trying to come up incremental ways of moving from brain theory to add pieces to machine learning current machine learning world. And one step at a time. So the next thing we're going to try to do is is sort of incorporate some of the ideas of um the 1000 brains theory that you have many, many models and that are voting. Now, that idea is not new, there's a mixture of models has been around for a long time. Um but the way the brain does is a little different and um uh and the way it votes is different and the kind of way it represents, uncertainty is different. So uh we're just starting this work but we're gonna try to see if we can sort of incorporate some of the principles of voting or principles of 1000 brain theory, like lots of simple models that talk to each other in a very a certain way. Um and can we build more uh machines and systems that learn faster and and also um um well mostly um are multi model and robust to um multiple type of </s> |
<s>[INST] That's actually brilliant. I didn't, you know, there's something that's in our discourse about it. The space race is sometimes made synonymous with like the Cold War, something like that, or with wars. But really, yeah, there was a lot of ego tied up in that, I remember, I mean, it's still still to this day, there's a lot of pride that Russians soviet Union was the first to space and there's a lot of pride in the american side. That was the first on the moon. But yeah, you're exactly right, like there's no aggression, there's [/INST] no wars and and beyond that. If you think about the global economy right now, uh there is a commercial interest. That's why Jeff Bezos and Elon musk are interested about, you know, mars and so there is a commercial interest which is international. It's not, it's driven by money, not by by pride. And you know, nations can sign treaties. First of all, there are lots of treaties that were signed even before the First World War and the Second World War and the World War took place. So who cares? You know, like humans treaties do not safeguard anything, you know, But beyond that, even if nations signed treaties about space exploration, you might still find commercial entities that will find a way to get their launches and you know, so I think we should rethink space. It has nothing to do with national pride. Once again, nothing to do with our egos. It's about exploration. And the biggest problem I think to human in human history is that is that humans tend to think about egos and about their their own personal image rather than look at the big picture, you know, we will not be around for long. We are just occupying a small space right now, let's move out of this. You know the way that Oscar Wilde said, I think is the best he said, all of us are in the gutters, but some of us are looking at the stars. </s><s>[INST] Yeah, and the more of us are looking at the stars, the likelier where are to uh to for this thing for this little experiment we have going on to last last a while as opposed to end too quickly. I mean it's not just about science of being humble, it's it's about the survival of the human species is being, is being humble to me, it's incredibly inspiring the star shot project of, I mean there's something magical about being able to go to another habitable planet and take a picture even, I mean within our lifetime, I mean that that uh with crazy technology to which [/INST] I can't tell you how it was conceived. So um I was at the time, so after six months passed after the visit of your miller uh I was usually I go in december during the winter break, I go to Israel um I I used to go to see my family and uh I get a phone call um just before the weekend started they get a phone call uh yuri would like you to present your concept um in two weeks at his home and I said well thank you for letting me know because I'm actually out of the door of the hotel to go to a gold farm in the Negev in the southern part of Israel because my wife wanted to have sort of uh to go to a place that is removed from civilization, so to speak. So we went to that gold farm and I need to make the presentation and there was no internet connectivity except in the office of the Gold Farm. So The following morning at six a.m. I sit with my back to the office of that gold farm looking at goats that were newly born and typing into my laptop, the presentation, you know, the PowerPoint presentation about you know, our ambitions for visiting the nearest star. And that was very surreal to me that you know uh like </s><s>[INST] our origins in many ways this very primitive origins and our dreams exactly looking out that it's really, so that is incredibly inspiring to me, [/INST] but it's also </s><s>[INST] inspiring of putting humans on to other uh moons or planets. I still find going to the moon really exciting. I don't know, maybe I'm just a sucker for it, but it's really exciting and mars which is a new place, a new planet, another planet that might have life. I mean there's something magical to that or some traces of previous life, [/INST] you might think that humans cannot really survive. And and there are risks by going there. But my point is, you know, we started from africa and we got two apartment buildings in Manhattan, right? It's a very different environment from the jungles to live in an apartment building in, you know, a small cubicle. Um and you know, it took tens of thousands of years but humans adapted. Right, so why couldn't humans also make the lip and adapt to a habitat in space? You know that now you can build a platform that would look like an apartment building in the Bronx or somewhere but have inside of it everything that humans need and it's just like the space station but bigger and it will be a platform in space. And the advantage of that is if something bad happens on earth, you have that complex where humans live and you can also move it back and forth depending on how bright the sun gets because you know, within within a billion years, within a billion years the sun would be too hot and it will boil off all the oceans on earth. So we cannot stay here for more than a billion years. That's for sure. </s> |
<s>[INST] this is fascinated by the way, instrumental perspective on liberty. That's gonna give me a lot to think about. Let me ask a personal question. Uh, was there ever a time that you had a crisis of faith where you question your belief in God? [/INST] Sure. And I would let's call it a crisis of faith and an ongoing question of faith, which I think is I hope most religious people and the word Israel right in in hebrew means to struggle with God. That's that's the that's literally the word means. And so the idea of struggling with God, right? Where if you're jewish or right, The idea of struggling with God, I think is endemic to the human condition. If you understand what God is doing, then I think you're wrong. And if you think that that question doesn't matter, then I think you're also wrong. I think that God is very necessary hypothesis. So </s><s>[INST] struggle. The struggle with God is life That is the process of life. [/INST] That's right, because you're never gonna get to that answer otherwise you're God and you aren't. So </s><s>[INST] why does God allow cruelty and suffering in the world one of the tough questions. [/INST] So we're going deep here, there there's two types of cruelty and suffering. So if we're talking about human cruelty and suffering because God does not intervene to prevent people from exercising their free will, because to do so would be to deprive human beings of the choice that makes them human. And this is the sin of the Garden of Eden, basically is that God could make you an angel, in which case you wouldn't have the choice to do the wrong thing. But so long as we're going to allow for cause and effect in the universe shaped by your choice, cruelty and evil are going to exist. And then there's the question of just the natural cruelty and vicissitudes of life. And the answer there is, I think that God obscures himself. I think that if God were to appear in all of his glory to people on a regular basis, I think that would make faith and you wouldn't need it. There'd be no such thing as faith, right. It would just be reality right? Nobody has to prove to you that the sun rises every day. But if if God is to allow us the choice to believe in him, which is the ultimate choice from a religious point of view, then he's gonna have to obscure himself behind tragedy and horror and and all those other things. I mean, this is a fairly well known capitalistic concept called sims. Um, in in Judaism, which is the idea that when God created the university, sort of withdrew in order to make space for all of these things to happen. </s><s>[INST] So God doesn't have instrumental perspective on [/INST] liberty. </s><s>[INST] Uh, [/INST] in a, in a chief sense, he he does because the best use of liberty is going to be belief in him and you can misuse your liberty right? Hope there will be consequences if you believe in an afterlife or if you believe in sort of a generalized better version of life led by faith, uh, then liberty does have a purpose, but he also believes that you have to give people from a cosmic perspective the liberty to do wrong without threatening all the institutions of society. I mean, that's that's why it does say in the bible that if man sheds blood by man, shall his blood be shed right? There are punishments that are, that are in biblical thought for doing things that are wrong. </s><s>[INST] So for a human being who lacks the faith in God. So if you're an atheist, can you still be a good person? Of [/INST] Course 100%. And there's a lot of religious people who are crappy people, </s><s>[INST] how do we understand that tension? [/INST] Well, from a religious perspective, what you would say is that it is perfectly plausible to live In accordance with a set of rules that don't damage other people without believing in God, you just might be understanding the reason for doing that wrong is what a religious person would say. Um, there's the conversation again that I had with him. And basically as you and I agree, I said, this is him. You and I agree on nearly everything when it comes to morality, like we probably disagree on 15-20% of things. The other 80% is because you grew up in a Judeo christian society and so do I. And we grew up 10 miles from each other, you know, around the turn of the millennium. So there's that um so you can perfectly well be an atheist living a good moral decent life because you can live a good moral decent life with regard to other people without believing in God. I don't think you build a society on that because I think that you know that relies on the sort of goodness of mankind, natural goodness of mankind. I don't believe in the natural goodness of mankind. No, I believe in, I believe that man has created both sinful and with the capacity for sin in the capacity for good, </s><s>[INST] but if you let them be on their own isn't doesn't [/INST] social institutions to shape them. I think that that's very likely to go poorly </s><s>[INST] interesting. Well, we came to something we disagree on, but that may be uh that might reflect itself in our approach to twitter as well. I think if humans are left on their own uh they they tend towards good, they definitely have the capacity for good and evil, but I left on their own there. Um I I tend to believe they're good, I [/INST] think they might be good with limits. What I mean by that, is that what the evidence I think tends to show is that human beings are quite tribal, so what you'll end up with is people who are good with their immediate family and maybe their immediate neighbors, and then when they're threatened by an outside tribe, then they kill everyone, which is sort of the history of civilization in the pre civilisational era, which was a very violent time. Pre civilization leader was quite violent. </s> |
<s>[INST] To me, it's not enough for a large language model to be effective at answering questions and having good dialogue. You have to really integrate it into the workflow. And Notion, better than anybody else I've seen, [/INST] has done that. </s><s>[INST] So if that's interesting to you, Notion AI helps you work faster, write better, and think bigger, doing tasks that normally take you hours and just minutes. Try Notion AI for free when you go to Notion.com slash Lex. That's all lowercase Notion.com slash Lex to try the power of Notion AI today. This show is also brought to you by Insight Tracker, a service I use to track biological data. It's really good to do that kind of thing regularly to look at all the different markers in your body and to understand what could be made better through lifestyle and through diet changes. It's kind of obvious that decisions about your life should be made based on the data that comes from your own body. Not some kind of a population study, although those are good. Not some spiritual guru, although those are good. Not some novel, whether it's Harry Potter or Dostoyevsky. Although those are sometimes good. Not your relative who says I heard a guy say that a guy does this thing that is very bro-souncy sounding. Although sometimes it turns out to be pretty effective. Overall, the best decisions about your life should be based on the things that come from your own body. Inside Tracker uses algorithms to analyze your blood data, DNA data, fitness tracker data, all that kind of stuff to give you recommendations. You should be doing it. You should be doing it regularly. So it's not just a one-time thing, but regularly over time you see what changes led to improvements in the various markers that come from your body. Get special savings for a limited time when you go to inside tracker.com slash flex. This show is also brought to you by Indeed, a hiring website. I think the most important thing in life, not to quote in the barbarian because that would be very inappropriate to quote at this moment. And it's not actually accurate at all as a reflection of what's important in life. It only has comedic value. What I really want to say about what's important in life is the people you surround yourself with. And we spent so much of our time in the workplace seeking solutions to very difficult problems together, passionately pursuing ambitious goals, sometimes impossible goals. That is the source of meaning and sort of happiness for people. And I think part of that happiness comes from the collaboration with other human beings, the sort of professional depth of connection that you have with other human beings. Being together through the grind and surviving and accomplishing the goal or failing in a big, epic way knowing that you have tried together. And so doing that with the right team I think is one of the most important things in life. So you should surround yourself with the right team. If you're looking to join a team, you should be very selective about that or if you're looking to hire a team, you should be very selective about that and use the best tools at the job. I've used Indeed many, many times throughout my life for the teams that I've led. Don't overspend on hiring. Visit indeed.com slash Lex to start hiring now. That's indeed.com slash Lex terms and conditions apply. This is the Lex Freedom Podcast. To support it, please check out our sponsors in the description. And now, dear friends, here's Max Tagmark. You were the first ever guest on this podcast, episode number one. So first of all, Max, I just have to say thank you for giving me a chance. Thank you for starting this journey. It's been an incredible journey. Just thank you for sitting down with me and just acting like I'm somebody who matters that I'm somebody who's interesting to talk to. And thank you for doing it. [/INST] I meant a lot. Thanks to you for putting your heart and soul into this. I know when you delve into controversial topics, it's inevitable to get hit by what Hamlet talks about, the slings and arrows and stuff. And I really admire this. It's in an era where YouTube videos are too long and now it has to be like a 20-minute TikTok, 20-second TikTok clip. It's just so refreshing to see you going exactly against all of the advice and doing these really long-form things and that people appreciate it. Reality is nuanced. </s><s>[INST] And thanks for sharing it that way. So let me ask you again, the first question I've ever asked on this podcast, episode number one, talking to you, do you think there's intelligent life out there in the universe? Let's revisit that question. Do you have any updates? [/INST] What's your view when you look out to the stars? So when we look out to the stars, if you define our universe the way most astrophysicists do, not as all of space, but the spherical region of space that we can see with our telescopes from which light has the time to reach us since our big bang, I'm in the minority. I estimate that we are the only life in this spherical volume that has invented internet radios, gotten our level of tech. And if that's true, then it puts a lot of responsibility on us to not mess this one up because if it's true, it means that life is quite rare and we are stewards of this one spark of advanced consciousness, which if we nurture it and help it grow, eventually life can spread from here out into much of our universe and we can have this just amazing future. Whereas if we instead are reckless with the technology we build and just snuff it out due to stupidity or infighting, maybe the rest of cosmic history in our universe was just gonna be a play for empty benches. But I do think that we are actually very likely to get visited by aliens, alien intelligence quite soon. But I think we are gonna be building </s> |
<s>[INST] well can I have to proceed carefully here because it's a complicated topic. Um so she took the call and you kind of, you're kind of saying that bro, she basically erased credit, you know, pretending you didn't exist in some kind of in a certain sense. Let me phrase it this way. I've uh as a as a research scientist at MIT I've had an especially just part of a large set of collaborations. I've had a lot of students come to me and talk to me about ideas perhaps less interesting than what we're discussing here in the space of A. I that I've been thinking about anyway in general with everything I'm doing with robotics people uh would have told me a bunch of ideas that I'm already thinking about. The point is taking that idea. See this is different because the idea is more power in the space that we're talking about here in robotics is like your idea means ship until you build it like so the engineering world is a little different but there's a kind of sense that I probably forgot a lot of brilliant ideas have been told to me. Do you think she pretended you don't exist? Do you think she was so busy that she kind of forgot? You know, she has like the stream of brilliant people around her that there's a bunch of ideas that are swimming in the air and you just kind of forget people that are a little bit on the periphery, on the idea generation. Like or is it some mix of both. [/INST] Uh it's not a mix of both. Um I know that because we corresponded, she put a graduate student on this work. He emailed me excitedly when the results came in. So there was no ambiguity about what had happened. What's more. When I went to publish my work, I actually sent it to carol in order to get her feedback because I wanted to be a good collaborator to her. And she absolutely Pandit made many critiques that were not valid. But it was clear at that point that she became an antagonist and none of this adds that she couldn't possibly have forgotten the conversation. Um I believe I even sent her tissues at some point in in part not related to this project, but as a favor, she was doing another project that involved telomeres and she needed samples that I could get a hold of because of the Museum of Zoology that I was in. So this was not a one off conversation. I certainly know that those sorts of things can happen, but that's not what happened here. This was a relationship that existed and then was suddenly cut short at the point that she published her paper by surprise without saying where the hypothesis had come from and began to be a opposing force to my work. </s><s>[INST] Is there there's a bunch of trajectories that could have taken through life. Do you think about the trajectory of being um a researcher of then going to war in the space of ideas of publishing further papers along this line. I mean, that's often the dynamic of that fascinating space is you have a junior researcher with brilliant ideas and a senior researcher that that starts out as a mentor that becomes a competitor. That that happens. But then the way two, it's an almost an opportunity to shine is to publish a bunch more papers in this place that did to tear it apart to dig into like really uh make it a war of ideas. Did you consider that possible trajectory? I [/INST] did a couple of things to say about it. One this work was not central for me. I took a year on the telomere project because something fascinating occurred to me and I pursued it and the more I pursued it, the clearer it was there was something there, but it wasn't the focus of my graduate work and I didn't want to become a telomere researcher. What I want to do is to be an evolutionary biologist who upgrades the toolkit of evolutionary concept so that we can see more clearly how organisms function and why. And telomeres was a proof of concept, right? That paper was a proof of concept that the toolkit in question works. Um as for the need to pursue it further, I think it's kind of absurd and you're not the first person to say maybe that was the way to go about it. But the basic point is look, the work was good. The it turned out to be highly predictive, frankly, the model of sin essence that I presented is now widely accepted and I don't feel any misgivings at all about having spent a year on it said my piece and moved on to other things which frankly I think are bigger. Um I think there's a lot of good to be done and it would be it would be a waste to get overly narrowly focused. </s><s>[INST] There's so many ways through the space of science and the most common ways to just published a lot. Published a lot of papers, these incremental work and exploring the space kind of like ants looking for food. You're tossing out a bunch of different ideas. Some of them could be brilliant breakthrough ideas nature, some of their more confidence kind of publications, all those kinds of things. Did you consider that kind of path and science? [/INST] Of course I considered it. But I must say the experience of having my first encounter with the process of peer review be this story which was frankly a debacle from one end to the other. With respect to the process of publishing it did not, it was not a very good sales pitch for trying to make a difference to publication. And I would point out part of what I ran into and I think frankly part of what explains carol's behavior is that in some parts of science there is this dynamic where p is parachutists, their underlings. And if you're very, very good, uh you rise to the level or one day, instead of being parachutist, you get two parachutists, others. Now I find that scientifically despicable and it wasn't the culture of the lab I grew up in at all my lab. In fact, the P. I. Dick alexander who is now gone, but who was an incredible mind and a great human being. He didn't want his graduate students working on the same topics he was on, not because it wouldn't have been useful and exciting, but because in effect, he did not want any confusion about who had done what, because he was a great mentor. And the idea was actually a great mentor is not stealing ideas and you don't want you don't want people thinking that they are. So anyway, my point would be um I wasn't up for being parachutist. I don't like the idea that if you are very good, you get parachutist until it's your turn to parasitism. Others that doesn't make sense to me. Um A crossing over from evolution into cellular biology may have exposed me to that. That may have been par for the course, but it doesn't make it acceptable. And I would also point out that my work falls in the realm of synthesis. My work generally takes evidence accumulated by others and places it together in order to generate hypotheses that explain sets of phenomena that are otherwise intractable and I am not sure that that is best done with narrow publications that are read by few. And in fact, I would point to the very conspicuous example of Richard Dawkins, who I must say I've learned a tremendous amount from and I greatly admire Dawkins has almost no publication record in the sense of peer reviewed papers in journals. What he's done instead is done synthetic work and he's published it in books which are not a peer reviewed in the same sense. And frankly, I think there's no doubting his contribution to the field. So my sense is if Richard Dawkins can illustrate that one can make contributions to the field without using journals as the primary mechanism for distributing what you've come to understand that it's obviously a valid mechanism and it's a far better one from the point of view of accomplishing what I want to accomplish. </s> |
<s>[INST] So if there is one good thing that comes out of war, it's literature, art and humor, music. Oh, I don't think so. I [/INST] think almost everything is good about war except for death and destruction right? </s><s>[INST] Without the death they would bring and the romance of it. The whole thing is nice. This [/INST] is why we're always caught up in war and we have this very ambiguous relationship to it is that it makes life real and pressing and meaningful and at an unacceptable price and the price has never been higher. So </s><s>[INST] jump in uh into a i a little bit you in one of the conversation you had or one of the videos you described that one of the things ai systems can't do it. And biological systems can itself replicate in the physical world, you know, in the physical world? [/INST] Well, yes, the physical robots can self replicate. But you there's a very tricky point, which is that the only thing that we've been able to create that's really complex that has an analog of our reproductive system is software, </s><s>[INST] but nevertheless software replicates itself. Uh We're speaking strictly for the replication in this kind of digital space. So, let me just to begin, let me ask a question, Do you see a protective barrier or a gap between the physical world and the digital world? [/INST] Let's not call it digital. Let's call it the logical world versus the physical world? </s><s>[INST] Why logical? [/INST] Well, because even though we had, let's say Einstein's brain preserved, uh it was meaningless to us as a physical object because we couldn't do anything with what was stored in a at a logical level. And so the idea that something may be stored logically and that it may be stored physically are not necessarily, we don't always benefit from synonymous. I'm not suggesting that there isn't a material basis to the logical world, but that it does warrant identification with a separate layer that need not um invoke logic gates and zeros and ones </s><s>[INST] and uh, so connecting those two worlds of the logical world in the physical world, or maybe just connecting to the logical world inside our brain. Einstein's brain. You mentioned the idea of out our intelligence, artificial intelligence, artificial intelligence. Yes. [/INST] This is the only essay that john brockman ever invited me to write that. He refused to publish an </s><s>[INST] edge. Why? [/INST] Well, maybe it wasn't, it wasn't well written. But I don't </s><s>[INST] know. The idea is quite compelling is quite unique and new. And at least from my view of a stance point, maybe you can explain it. Sure. [/INST] What I was thinking about is why it is that we're waiting to be terrified by artificial general intelligence when in fact artificial life uh, is terrifying in and of itself and it's already here. So in order to have a system of selective pressures, You need three distinct elements. You need variation within a population, You need heritability and you need differential success. So what's really unique? And I've made this point, I think elsewhere about software is that if you think about what humans know how to build, that's impressive. So I always take a car And I say, does it have an analog of each of the physical physiological systems. Does it have a skeletal structure that's its frame? Does it have a neurological structure has an on board computer has a digestive system. The one thing it doesn't have is a reproductive system. But if you can call spawn on a process effectively, you do have a reproductive system and that means that you can create something with variation, heritability and differential success. Now the next step in the chain of thinking was where do we see inanimate, non intelligent life, Outwitting intelligent life And um I have two favorite systems and I try to stay on them so that we don't get distracted. One of which is the joffrey's orchid, um sub species or sub clade. I don't know what to call it, a type of flower. It's a type of flower that mimics the female of a pollinator species. In order to dupe the males into engaging. It was called pseudo copulation with the fake female which is usually represented by the lowest pedal. And there's also a pheromone component to fool the males into thinking they have a mating opportunity. But the flower doesn't have to give up energy energy in the form of nectar as a lure because it's tricking the males. The other system is a particular species uh of muscle, lamp bacillus in the clear streams of Missouri and it fools bass into biting a fleshy lip that contain its young and when the bass see this fleshy lip, which looks exactly like a species of fish that the bass like to eat. The young explode and clamp onto the gills and parachutist, The bass and also lose the bass to redistribute them as they eventually release both of these systems. You have a highly intelligent dupe being fooled by a lower life form. And what is sculpting these, these convincing lures? It's the intelligence of previously duped targets for these strategies. So when the target is smart enough to avoid the strategy, uh, those weaker mimics fall off, They have terminal lines and only the better ones survive. So it's an arms race between the target species that is being parachutist getting smarter and this other less intelligent or non intelligent object getting as if smarter. And so what you see is is that artificial intelligence, artificial general intelligence is not needed to parasitism us. It's simply sufficient for us to outwit ourselves. So you could have a program, let's say, you know, one of these Nigerian scams, um that writes letters and uses whoever sends it. Bitcoin to figure out which aspects of the program should be kept, which should be varied and thrown away and you don't need it to be in any way intelligent in order to have a really nightmarish scenario of being parachutist by something that has no idea what it's doing. </s> |
<s>[INST] not in terms of empirical evidence or not. But in terms of thought experiment does it help you think about the universe? I mean uh so if you look at the genome, it's encoding a lot of the information that is required to create some of the beautiful human complexity that we see around us. It's an interesting thought experiment. How much, you know, parameters do we need to um have in order to model some, you know, this full human experience? Like if you want to build a video game, how hard it would be to build a video game that's like convincing enough and fun enough. And you know uh it has a consistent laws of physics, all that stuff. It's not interesting to use the stock experience. [/INST] I mean it's cute but you know, it all comes razor. I mean what's what's more realistic the fact that you're actually a machine or that you're you know, a person, what's you know the fact that all of my experiences exist inside the chemical molecules that I have or that somebody is actually, you know, simulating all that I even </s><s>[INST] you did refer to humans as a digital computer earlier. So [/INST] of course of course, but that does not kind of a machine. Right? I know. I know but I think the probability of all that is Neil and let the machines wake me up and just terminate me now. If it's not, I challenge you machines, they're gonna </s><s>[INST] they're gonna wait a little bit to see what you're going to do next. It's fun. It's fun to watch, especially the clever humans. What's the difference to you between the way computer stores information and the human genome stores information. So you also have roots and your work, would you say you're when you introduce yourself at a bar, [/INST] it depends who I'm talking. Would you </s><s>[INST] say it's computation biology? Do you um do you reveal uh your expertise and computers? [/INST] It depends who I'm talking to truly. I mean basically if I meet someone who's in computers, I'll say, oh, I mean professor of computer science, if I meet someone who's in engineering as a computer science and electrical engineering, if I meet someone in biology and say, hey, I work on genomics. If I meet someone in medicine, like hey, I work on, you know, genetics, your fun person to meet at a bar. I </s><s>[INST] got you. But so [/INST] no, no, but I'm trying to say is that I don't, I mean there's no single attribute that will define myself as, you know, there's a few things I know there's a few things I studied. There's a few things I have degrees on and there's a few things that grant degrees in and you know, I, I published papers across the whole gamut, you know, the whole spectrum of computation to biology etcetera. I mean I, the complete answer is that I use computer science to understand biology. Some uh, you know, develop methods in ai and machine learning statistics in algorithms etcetera. But the ultimate goal of my career is to really understand biology. If these things don't advance our understanding of biology. I'm not as fascinated by them. Although there are some beautiful computational problems by themselves. I've sort of made it my mission to apply the power of computer science to truly understand the human genome, health, disease, you know and and the whole comment of how our brain works, how our body works and all of that. Which is so fascinating. So </s><s>[INST] the dream, there's not an equivalent sort of uh uh complimentary dream of understanding human biology in order to create an artificial life and artificial brain artificial intelligence that supersedes the intelligence and the capabilities of us humans. [/INST] It's an interesting question. Is a fascinating question. So understanding the human brain is undoubtedly coupled to how do we make better ai because so much of a. I has in fact been inspired by the brain. It may have taken 50 years since the early days of neural networks until we have you know, all of these amazing progress that we've seen with uh you know deep belief networks and uh you know all of these advances and go and chess in image synthesis in deep fakes and you name it. Um and but but the underlying architecture is very much inspired by the human brain which actually pause. It's a very very interesting question. Why are neural networks performing so well and they perform amazingly well. Is it because they can simulate any possible function? And the answer is no, no. They simulate a very small number of functions, is it because they can simulate every possible function in the universe, and that's where it gets interesting. The answer is actually a little closer to that, and here's where it gets really fun. Uh If you look at human brain and human cognition, it didn't evolve in a vacuum. It evolved in a world with physical constraints like the world that inhabits this, it is the world that we inhabit. And if you look at our senses, what do they perceive? They perceive different parts of the electromagnetic spectrum? You know? The hearing is just different movements in air, the touch, et cetera. I mean all of these things, we've built it intuitions for the physical world that we inhabit and our brains and the brains of all animals evolved for that world and the ai systems that we have built happen to work well with images of the type that we encounter in the physical world that we inhabit. Whereas if you just take noise and you add random signal that doesn't match anything in our world, neural networks will not do as well. And that actually basically has this whole loop around this, which is this was designed by studying our own brain which was evolved for our own world and they happened to do well in our own world and they happen to make the same types of mistakes that humans make many times. And of course you can engineer images by adding just the right amount of, you know, sort of pixel deviations to make a zebra look like a bamboo and stuff like that or like a table. Um, but ultimately the undock turd images at least, are very often mistaken. I don't know between muffins and dogs, for example, in the same way that humans make those mistakes. So it's it's you know, there's no doubt in my view that the more we understand about the tricks that our human brain has evolved to understand the physical world around us, the more we will be able to bring new computational primitives in our ai systems to again better understand, not just the world around us, but maybe even the world inside us and maybe even the computational problems that arise from new types of data that we haven't been exposed to but are yet inhabiting the same universe that we live in with the very tiny little subset of functions from all possible mathematical functions. </s> |
<s>[INST] Yes, but symmetry is not enough for digit recognition. Right? [/INST] It is not necessarily for digital combination. It's helps to create in variant which will you can use when you will have examples for digital condition. You have regular problem of digital recognition. You have examples of the first class, second class plus, you know that there is a there exist concept of cemetery and you apply when you looking for decision rule usual apply uh concept of symmetry of this level of cemetery issue estimate from. So let's talk everything is come from big convergence. </s><s>[INST] What is convergence? What is weak convergence? What is strong convergence? I'm sorry, I'm going to do this to you. What are we converging from? And to [/INST] you can do a drink. You would like to have a function. The function which say indicator function which indicate your digit five, for example, </s><s>[INST] a classification task. [/INST] Let's talk only about classification </s><s>[INST] classification means you will say whether this is a five or not or say which of the 10 digits it is [/INST] right. I would like to to have these functions then I have some examples. I can consider protest. E of those examples sensitivity and I can measure level of symmetry for every digit and then I can take average and I from from my training data and I will consider only functions of conditional probability which I'm looking for. My decision rule, which applying two two digits will give me the same average as I absorb on training date. So actually this is different level of description of what you want you want uh not just you shall not one digit. You show this this predicate. So general property of all digits which you have in mind. If you have in mind digits three, It gives you pro 30 of digits three and you select as admissible set of function only function which keeps this property. You will not consider other functions. So you immediately looking for smaller subset of </s><s>[INST] function. That's what you mean by admissible functions. Admissible functions which is still a pretty large For the # three. [/INST] A pretty large. But if you have one predicated but according to there is a strong bendy convergence. Strong convergence of convergence and function you're looking for the function on one function and you're looking concerned. Another function and square difference from them should be small. If you take difference in any points. Make discover make an integral and it should be small. That is convergence in function suppose you have some function any function. So I would say I say that some function converts to this function if integral from square difference between them is more. </s><s>[INST] That's the definition of strong convergence. That definition of two functions. The integral of the difference. [/INST] Yes, it is convergence in functions but you have different convergence in functional. You take any function, you take some function fee and take inner products. This function, this f function zero function which you want uh to find and that gives you some value. So you say that set of functions converge in inner product to this function. If this value of inner product converged to a value of zero, That is for one he but we converges requires that it converts for any function of Hilbert space. If it converges for any function of Hilbert space, then you would say that this is vic conversions, you can think that when you take integral that is protest the integral, protest your function. For example, if you will take sign or a sign it is coefficient of Uh say 40 year expansion. So if it converge for all coefficients of free expansion. So under some condition converged to function you're looking for. But the convergence means any property convergence, not point wise, but integral property of function. So the convergence means integral property of functions. When I talking about pre decayed, I would like to um formulate which integral properties I would like to have for conversions. So and if I will take one predicate predicate, its function which I measure property uh huh If I will use one predicate and say I will consider only function which gives me the same value as it is. This predicate I selecting a set of functions from functions which is admissible in the sense that function which are looking for in this set of functions. Because I checking in training data it gives the same </s><s>[INST] Yes, it always has to be connected to the training data in terms of [/INST] Yeah but but pro 30 you can no independent on training data. And this guy prop Yeah. So there is formal project 31 protecting </s><s>[INST] Russian fairy tales [/INST] but Russian fairy tale is not so interesting. More interesting that people apply this to movies to theater to different things and the same works. The universal. </s><s>[INST] Well, so I would argue that there's a little bit of a difference between uh the kind of things that were applied to which are essentially stories and digit recognition. [/INST] It is the same story, </s><s>[INST] You're saying digits. There's a story within the digit. [/INST] Yeah. </s><s>[INST] So [/INST] But my my point is why I hope that it's possible to beat a record using not 60,000 but 100 times less because instead you will give predicates and you will select your decision not from white set of function but from set of functions which keeps us predicate but predicate is not related just two digit recognition. Right? So </s><s>[INST] like in [/INST] platters </s><s>[INST] case, do you think it's possible to automatically discover the predicates. So you basically said that the essence of intelligence is the discovery of good predicates. Yeah. Now the natural question is you know that's what Einstein was good at doing in physics. Can we make machines do these kinds of discovery of good predicates or is this ultimately a human endeavor [/INST] that I don't know I don't think that machine can do because uh according to theory about conversions uh any function from Hilbert space can be predicated. So you have infinite number of predicated and upper and before you don't know which predicated is good and which but whatever prop show and white people call it breakthrough that there is not too many predicate which cover most of situation happened in the world. </s> |
<s>[INST] happened. What role does money play in all of this is money huge influence in politics? Uh, super pacs, all that kind of stuff or is this is this more just kind of a narrative that we play with because from the outsider's perspective it seems to have, that seems to be one of the fundamental problems with modern politics. [/INST] So I was just having this conversation marshall and marshall cost of my coast on the realignment And it's funny because if you do enough research, we actually live in the least corrupt age in american campaign finance as in it's never been more transparent. Never been more up to the f f E C. Yeah. And all of that, if you go back and read, not even 50 years ago, we're talking about Lyndon B johnson handing people like literally as he came up in his youth paying people for votes like the boss of the, you know, the person who like had all the mexican votes, like the person and he was like giving out briefcases. This is it like within people's lifetimes who are alive in America. So that doesn't happen anymore. But I don't like to blame everything on money. Although I do think money is obviously a huge part of the problem. I actually look at it in terms of distribution. Um which is that how is money distributed with an artist's within our society? Because I firmly believe that politics, this is going to get complicated. But I think politics is mostly downstream from culture and culture. Obviously I'm using economics because there's obviously a huge interplay there, but like in terms of the equitable or lack of equitable distribution of money within our politics, what we're really piste off about is we're like our politics only seems to work for the people who have money. I think that's largely true. Um I think that the reason why things work differently in the past is because our economy was structured in different ways and there's a reason that our politics today are very analogous to the last gilded age because we had very similar levels levels of economic distribution and cultural problems too. At the same time, I don't want to erase that because I actually think that's what's driving all of our politics right now. </s><s>[INST] So that's interesting. So it's one, so in that sense, representative government is doing a pretty good job of representing the state of culture and the people and so on. Yeah, can I ask you in terms of uh, you know, the deep state and conspiracy theories, There's a lot of talk about, again from an outsider's perspective, if I was just looking at twitter, It seems that at least 90% of people in government and pedophiles 19, I'm not sure what that number is. If I were to just look at Twitter honestly or YouTube, I would think most of the world's a better file, I would almost feel like. [/INST] And if you don't fully believe that you're a pedophile, </s><s>[INST] I would start to wonder like, wait, like, what am I a pedophile to like I'm either a communist or a pedophile or both, I guess. Uh yeah, that's going to be clipped out. Thank you Internet. I look forward to your emails, but is there any kind of shadow conspiracy theories that give you pause, or so the flip side, the response to a lot of conspiracy theories. It's like, no, the reason this happened is because it's a combination of just incompetence. So where do you land on some of these conspiracy theories? [/INST] I think most conspiracy theories are wrong. Some are true and those are spectacularly true. And if that makes sense. Um I don't know which ones. I don't know which one. That's the problem. I think. Well, I mean, look, man, I listen to your podcast. I think I was a huge non believer in UFOs and now I've probably never believe more in U. F. Like I believe in UFOs. Like I'm very comfortable being like, not only do I believe in UFOs, like I think we're probably being visited by an alien civilization. Like, and if you asked me that three years ago, I would be like, you're out of your freaking mind. Like, what are you talking about? Well, listen to David flavor. That's </s><s>[INST] all I have to say. That's it. I have the sense that the government has information hasn't revealed, but it's not like they're, I don't think they're holding there's like a green guys, They're exactly, they just, they have seen things they don't know what to do with. So it's like they're confused. They're [/INST] afraid of revealing that they don't know. </s> |
<s>[INST] it's also very impressive to all this. I think we're moving to a world where grades mean less and less like certifications mean less and less if you look at, especially again in the computing fields, getting a degree, finishing your um currently just get finishing your degree where there's Bachelor's Master's and PhD is less important than the things you've actually put out into the [/INST] world. </s><s>[INST] And that's a fascinating kind of, That's a that's great that in that sense, the meritocracy is in its richest, most beautiful form is starting to win [/INST] out. Yeah, it's weird because like, you know, my understanding and I'm not like, I don't know the history of science well enough to speak very confidently about this, but you know, the advisor of, my advisor of my advisor from undergrad, like didn't have a PhD. So I think it was a more common thing back in the day, even in uh the academic sector two, you know, not have, you know, Faraday like Faraday didn't know algebra ran drew diagrams about magnetic fields and his Faraday's law was derived entirely from intuition. So uh it is interesting to, to how the world of academia has evolved into a, you got to do this and then get PhD then you have to post doc once and twice and maybe thrice and then like you move on. So, you know, it does, I do wonder, you know, if we're, you know, if there's a better, </s><s>[INST] I think we're heading there, but it's a fascinating historical perspective like that, we might have just tried this whole thing out for a while where we put a lot more emphasis on grades and certificates and degrees and all those kinds of things. I think the difference historically is like we can actually using the internet show off the show off ourselves and our creations better and better and more effectively, whether that's code or producing videos or all those kinds of [/INST] things can become a certified drone pilot. Yeah, of all </s><s>[INST] the of all the things you want to pick. Yeah, for sure. Or you can just fly make youtube videos against hundreds, thousands of views with your drone and we're never getting a certificate. Um, that's probably illegal. Don't do it. What do you think is the meaning of this whole thing? So you look at planets, they seem to orbit stuff. Um, without without asking the why question. And for some reason life emerged on earth such that it led to big brains that can ask the big why question do you think there's an answer to it? Mhm. [/INST] Um I'm not sure what the question is. Like what meaning of life, the meaning of life? Uh, it's 42, 42. But you know, aside from that, it's uh, you know why I think if the question you're asking is like why we do all this. Right? Why? Yeah. Um, it's part of the human condition. Right human beings are fundamentally, I feel like not like sort of stochastic and fundamentally interested in in kind of expanding our own understanding of the world around us </s><s>[INST] and creating stuff to enable that understanding. So we're like stochastic fundamentalist, so like there's just a bunch of randomness that really doesn't seem like it has a good explanation and yet there is a kind of direction to our being that we just keep wanting to create and to understand [/INST] that's right. I've met people that are, you know, that claim to be anti science, right? Um, and yet in their anti science, you know, discussion like, well, like if you're so, you know scientific, then how why don't you explain to me how, I don't know, this works and like it always there's that fundamental seed of curiosity and interest that is common to all of us, that is absolutely what makes us human, right? And and I'm in a privileged position of being able to, you know, to have that be my job, right? I think as uh you know, as time evolves forward, you know, the kind of economy changes, I mean, we're already starting to see, you know, shift towards that type of, you know, creative, you know, enterprise as being, as emerging, taking over a bigger and bigger chunk of the sector. It's not yet, I think the dominant portion of the economy by any account, but if we compare this to like, you know, sometimes when the dominant thing you would do would be to go to a factory and do the same exact thing, right? I think you know, there is a tide there things are sort of headed in that direction. </s><s>[INST] Life is becoming more and more fun. I can't wait. Honestly. What happens just chill. Just [/INST] terminal point of this </s><s>[INST] chill [/INST] And wait for those Kiper belt objects to complete one orbit. </s><s>[INST] I'm gonna credit you with this idea. I do hope that we definitively discover proof that there is a planet nine out there in the next few years. So you can sit back with a cigar, cigarette or vodka or wine and just say I told you so, [/INST] that's already happening. Going to do that later </s><s>[INST] tonight. As I mentioned, uh confidence is essential to being a rock star. I really appreciate you uh explaining so many fascinating things to me today. I really appreciate the work that you do out there and I really appreciate you talk with me today. Thanks [/INST] Constantine, Thanks for having me on. </s> |
<s>[INST] And again, like you said, it doesn't always have to be, but in that case the madness and genius were neighbors. [/INST] That one couldn't have been any other way. Yeah. Because his mind, you know, the thing about seeing him in a comedy club was that he would react to random stimulus in the environment, it could be a heckler. Sometimes you almost got the feeling that he wanted a heckler because it was, it gave him something to play against, right? He was just, he was infinitely instantly inventive. </s><s>[INST] But I actually, to me the best Robin Williams is as he got closer and closer to the end of his life because there was a sadness and he's almost fighting the sadness with this improvisational, like the weapons he has is this wit and humor and his dancing that he does with language. But and then sometimes when you just fall silent you can see the sadness and I don't know, there's something so beautiful about that. It's like this bird with a broken wing that's like trying to fly. You know, and it's getting older and older and it and I mean those, he would have made a one hell of a podcast guest. I'll tell you, I'll tell you that that's a sad. [/INST] Yeah, I have some sadness that I really do think that part of what we call podcasting is actually just getting to know a soul over and over again. Like maybe the idea is that this is talking about depression and sadness and heavy feelings is not an american specialty. Seeing that in context with the beauty of life is a Russian specialty. It is very much </s><s>[INST] specialty. Sounds like a diner menu. What [/INST] what the Russians? A big, big scoop of ice cream with tons of depression. I I do think that we're in a really terrifying and depressing time and I think that part of it is we don't know if something huge is about to get started and we don't even know what this is. I mean we just sit here in this weird world, is falling into some new state and we're not even super curious is like what the hell just happened. Everybody's got an answer. And I'm positive that all of those answers are wrong. </s><s>[INST] Let's let's try to at least sneak up on the good answer. [/INST] So the central core of the answer is that the US seemed to be the greatest thing in the world in large measure because we hadn't noticed that we were getting a benefit from having no plan not having to make a plan for low growth. As long as we had growth, we were in great shape. Let's imagine that there was a then you could run an experiment, You have a billion copies of Earth and you start the initial conditions slightly different on some giant number of planets. A lot of the things That were discovered from the 1800s through the end of the 20th century are discovered in a period of time because a lot of that just has to do with once you crack the puzzle of getting better, instruments you can see more and the more you can see, the more you can make use of what you can see. And it turns out there was lots of stuff to do with like you know, germs or electron orbital's or you know, spectrum, electromagnetic spectrum. So we got to do all of those things and the US roughly corresponded for a good chunk of its history with this bonanza. And so of course we look like an amazing genius country. We have no plan. Imagine that you you can sell a car, you don't have to put in seat belts, you don't have to put in air bags, you don't have to put in rear view mirrors or sensors or rear view mirror. You could save a lot of money on a car by not putting in all of the stuff to keep things from going wrong. And I think that's what we had. We had a machine that as long as growth was insanely good. We plowed it back the riches and spoils and treasure back into the system and made more genius stuff and we carried along a good chunk of humanity hundreds of millions of people. We did not have a plan for what happens when the growth goes below the stall speed of our society. </s><s>[INST] How confident should it be that the growth has slowed in in a way that it's permanent rather than a kind of a slap in the face where [/INST] let the right concept, right concept is I try to use the same words over and over again in case people c'mon, because then the per separation actually get somewhere. So I use this analogy of the orchard because everyone talks about low hanging fruit, they know the concept of low hanging fruit, but they don't think in terms of orchards. So they say things like you think we've picked all the low hanging fruit, but I believe in the infinite inventiveness of the human mind, it's like, okay, that doesn't even work as an analogy. What if the idea is we only picked all the low hanging fruit here and then we're having this stupid argument about low hanging fruit and we're not going and looking for new orchards, we're not planting new orchards, we're not looking for forests. Were just sitting here arguing about low hanging fruit. So my claim is there's probably a lot more low hanging fruit and it's not here, </s><s>[INST] it's another orchard, [/INST] it's another orchards. One of those turned out to be the digital orchard, the digital orchard has not been a stagnant uh as lots of these other like the chemical orchard, you know, </s> |
<s>[INST] that's a much more dangerous world. Let's dive back into the difficult pool. Yes. Just like you said, in the English speaking world, it seems popular, almost easy to demonize China, the Chinese government, I should say, but even China. Like there's this kind of gray area that people just fall into. And I'm really uncomfortable with that, perhaps because in my mind, in my heart, in my blood, it echoes of the cold war and that kind of tension. It feels like we almost desire conflict. So we see demons when there is none. So I'm a little cautious to demonize, but at the same time, you have to be honest. So it's like honest with the demons that are there and honest when they're not. This is kind of a geopolitical therapy session of sorts. So let's keep talking about China a little bit from different angles. So let's return to the director of the Center of Emerging Infectious Disease at the Wuhan Institute of Virology, Xi Jiang Li, colloquially referred to as Batwoman. So do you think she's lying? Yes. Do you think she's being forced to lie? Yes. So, is there, you know, even a bunch of virologists in private and public conversation that respect her as a human being, as a scientist? I just said she is a human being. Sorry, as a scientist? Not a human being because I think they don't know the human. They know the scientists [/INST] and they respect her a lot as a scientist, so it's not a human being. Well, yeah, I respect her. I've never met her and we had one exchange, which I'll mention in a second in a virtual forum. But I do respect her. I actually think that she is somebody who has tried to do the right thing. Xi was one of the heroes of tracking down the origins of SARS-1, and that was a major contribution. But as we talked about earlier, it's a different thing living, being a scientist, or really kind of anything. It's different being one of those people in an authoritarian society than it is being in a different type of society. And so when Shi Zhengli said that the reason the WIV database was taken offline in September 19 was because of computer hacks, I don't think that's the story. I don't think she thinks that's the story. When I asked her in March of 2021, March of this year, in a Rutgers online forum, when I asked her whether the Chinese military had any engagement with the Wuhan Institute of Virology in any way, and she said absolutely not, paraphrasing, I think she was lying. Do I think that she had the ability to say, well, either one, yes, but I can't talk about it? Or I know there are a lot of things that are happening at this institute that I don't know about, and that could be one. Could she have said that the personnel at the Wuhan Institute of Virology have all had to go through classification training so that they can know about what can and can't be said? Like she could have said all those things, but she couldn't say all of those things. And I think that's why so many, at least in my view, so many people, certainly in the Western world, got this story wrong from the beginning. Because if your only prism was the science, and you just assumed, this is a science question, to be left to the scientists, Xu Jingli is just like any scientist working in Switzerland or Norway. The Chinese government isn't interfering in any way, and we can trust them. That would lead you down one path. In my view, the reason why I progressed as I did is I felt like I had two keys. I had one key as I live in the science world through my work with WHO and my books and things like that. But I also have another part of my life in the world of geopolitics as an Asia, quote unquote, expert and former National Security Council official and other things. And I felt for me, I needed both keys to open that door. But if I only had the science key, I wouldn't have had the level of doubt and suspicion that I have. But if my starting point was only doubt and suspicion, well, it's coming from China, it must be that the government is guilty, like that wouldn't help either. </s><s>[INST] I wonder what's in her mind, whether it's fear or habit, because I think a lot of people in the former Soviet Union, it's like Chernobyl. It's not really fear. It's almost like a momentum. It's like the reason I showed up to this interview wearing clothes as opposed to being naked. [/INST] It's like, all right. It's like, it's just all of us are doing the clothes thing. Although there was a startup years ago called Naked News. Did you ever hear about that? They just would read the exact news. But naked. No, they would, after each story, they'd take something off until the end. It's a good idea for podcasts. They have an IPO. </s><s>[INST] Stay tuned. It's a good idea for podcasts. They have an IPO. Stay tuned. Next time I'm with Michael Miles. Yeah. Okay. So, what do you think? I mean, because the reason I asked that question is, okay, how do we kind of take steps to improve without any kind of revolutionary action? You could say we need to inspire the Chinese people to elect, to sort of revolutionize the system from within. But like, who are we to suggest that because we have our flaws too. We should be working on our flaws as well. But at the individual scientist level, what are the small acts of rebellion that could be done? How can we improve this? [/INST] Well, so I don't know about small acts of rebellion, but I'll try to answer your question from a few different perspectives. So, right now, actually, as we speak, there is a special session of the World Health Assembly going on. The World Health Assembly is the governing authority over the World Health Organization, where it's represented by states and territories, 194 of them, tragically not including Taiwan because of the Chinese government's assistance. But they're now beginning a process of trying to negotiate a global pandemic treaty to try to have a better process for responding to crises exactly like we're in. But unfortunately, for the exact same reasons that we have failed, I mean, we had a similar process after the first SARS, we set up what we thought was the best available system and it has totally failed here. And it's failed here because of the inherent pathologies of the Chinese government system. We are suffering from a pandemic that exists because of the internal pathologies of the Chinese state. And that's why on one hand, I totally get this impulse. Well, we do it our way. They do it their way. Who's to say that one way is better? And certainly right now in the United States, we're at each other's throats. We have a hard time getting anything meaningful done. And I'm sure there are people who are saying, well, that model looks appealing. But just as people could look to the United States and say, well, because the United States has such a massive reach, what we do domestically has huge implications for the rest of the world. They become stakeholders in our politics. And that's why I think for a lot of years, people have just been looking at US politics, not because it's interesting, but because the decisions that we make have big implications for their lives. The same is true for ours. You could say that the lack of civil and political rights in China is up to the Chinese, not even people because they have no say, but to their government and they weren't democratically elected, that they are recognized as the government. But some significant percentage of the 15 million people now dead from COVID are dead because in the earliest days following the outbreak, whatever the origin, the voices of people sounding the alarm were suppressed. Just like in Chernobyl, the Chinese government had a greater incentive to lie to the international community than to tell the truth. And everybody was incentivized to pretty much do the wrong thing. And that's why I think one of the big messages of this pandemic is that all of our fates are tied to everybody else's fates. And so while we can say and should say, well, let's focus on our own communities and our countries, we're all stakeholders in </s> |
<s>[INST] and I mean just to linger on it like you see, okay yeah it's in the perceptual language, the multimodal perceptual language, that's the experience, that's what consciousness is within that within that model within that story. But do you have agency when you play a video game you can turn left and you can turn right in that story. So in that dream world how much control do you? Is there such a thing as you that story? Like is it right to say the main character, you know everybody's N. P. C. S. And then there's the main character and you're controlling the main character or is that an illusion is there a main character that you're controlling? I'm getting to the point of like the free will point [/INST] imagine that you are building a robot that plays soccer and you've been to MIT computer science, you basically know how to do that, right? And so you would say the robot is an agent that solves a control problem how to get the ball into the goal and it needs to perceive the world and the world is disturbing him in trying to do this, right? So yes to control many variables to make that happen and to project itself and the ball into the future and understand its position on the field relative to the ball and so on in the position of its limbs, or in in the space around it and so on. So it needs to have an adequate model that abstracting reality in a useful way. And you could say that this robot does have agency over what it's doing in some sense. And the model is going to be a control model. And inside of that control model, you can possibly get to a point where this thing is sufficiently abstract to discover its own agency. Our current robots don't do that. They don't have a unified model of the universe, but there's not a reason why we shouldn't be getting there at some point in the not too distant future. And once that happens, you will notice that the robot tells a story about the robot playing soccer. So the robot will experience itself playing soccer in a simulation of the world that it uses to construct a model of the locations of it lacks on limbs in space on the field with relationship to the ball. And it's not going to be at the level of the molecules. Uh it will be an abstraction. That is exactly at the level that is most suitable for past planning of the movements of the robot. Right? It's going to be a high level abstraction, but a very useful one that is as predictive as you can make it. And in that side of that story, there is a model of the agency of that system. So this model can accurately predict that the contents of the model are going to be driving the behavior of the robot in the immediate future. </s><s>[INST] But there's the hard problem of consciousness which I would also there's a subjective experience of free will as well that I'm not sure where the robot gets that where that little leap is. Because for me right now, everything I imagine with that robot as it gets more and more and more sophisticated, the agency comes from the programmer of the robots still of what was programmed in. [/INST] You could probably do an enter and learning system. You maybe need to give it a few prayers. You nudge the architecture in the right direction that it converges more quickly. But ultimately discovering the suitable hyper parameters of the architecture is also only a search process. Right? And as the search process was evolution that has informed our brain architecture so we can converge in a single lifetime on useful interaction with the world and information of the promise </s><s>[INST] if we define hyper parameters broadly. So it's not just this, the parameters that control this and and learning system, but the entirety of the design of the robot. Like there's you have to remove the human completely from the picture and then in order to build the robot, you have to create an entire universe because you have to go, you can't just shortcut evolution, you have to go from the very beginning in order for it to have because I feel like there's always a human pulling the strings. Um and that makes it seem like the robot is cheating is getting a shortcut to [/INST] consciousness. And you are looking at the current boston dynamics robots, it doesn't look as if there is somebody pulling the strings, it doesn't look like cheating anymore. </s><s>[INST] Okay, so let's go there because I got to talk to you about this. So obviously with a case of boston dynamics as you may may not know, it's always either hard coded or remote controlled. [/INST] There's no intelligence. I don't know how the current generation of boston dynamics robots works, but what I've been told about the previous ones was that it's basically all cybernetic control, which means you still have feedback mechanisms and so on. But it's not deep learning for the most part, as it's currently done, it's um for the most part just identifying a control hierarchy that is congruent to the limbs that exist in the parameters that need to be optimized for the movement of these limbs and then there is a convergence progress. So it's basically just regression that you would need to control this. But again, I don't know whether that's true, that's that's what I've been told about how that work. We </s> |
<s>[INST] So you okay, so you simulate some aspect of that. [/INST] I mean, the training will tell you how you are. </s><s>[INST] Did you increase the intensity of the training leading up to this? [/INST] Yeah, I mean, I train, I train normal, let's say, compared to the first fight that the second was a lot more confidence. Because you know, like I said on training the training for the first fight, you were terrible. </s><s>[INST] So what do you [/INST] mean? I think I was focusing mm a for a while for a couple of months and that wasn't really focusing the g and you know, by this time I accept if I didn't start training, like all my responses on training were off. Like all my training partners that I used to train with, that I destroyed. I mean, now they like they're beating me, you know, it's like I cannot beat them the way I I was used to. But you know, So I knew something was not right for the first fight, but then it is, you know, no points is submission or draw. So </s><s>[INST] Yeah, for people who don't know, it was a modern Morris, which is a 20 minute match, submission only. So there's no the winner is determined only by submission, otherwise it's a draw. [/INST] So physically I was I wasn't myself on that fight. I was tired and my body wasn't responding anyway. So that so the confident was different from the first, the second. I think I was confident enough that I wouldn't get tapped out on the first, that I was still gonna fight because he has taught me how to beat me. And I trust in my defense, I'm confident enough in my defense, that he would not talk me out. But in terms of winning, you know, walk into the second fight. I was a lot more confident. </s><s>[INST] What can you say about that feeling when something is not right? It's not a thing that breaks [/INST] people. It's weird breaks. It's weird like people crack, they give up you know this it's it's a big test because it's it's like being really tired. It's the same thing. It's like a lot of people crack because they just feel they cannot give it more. There's not having nothing more to give so they just like give up it's too hard. So </s><s>[INST] what do you do? Just again take the thoughts out. [/INST] There's no giving up. I mean I don't mind I don't care like just giving up is not much it's not </s><s>[INST] that's always the way you [/INST] thought. Yeah yeah I've never give up. I mean I tapped it's you know not giving up is not not tapping. That's just stupid. Especially not during training like it's I get caught I tap. I've never ever hurt myself by not tapping. I guess you get angry you know train hard you know improve make make yourself better, you got caught except that you made a mistake. Give up tap then try harder so you know the not tapping its you're sacrificing your body and you know you'll never be the same. Like if you let your elbow popped the elbow will never ever be the same </s><s>[INST] ever you [/INST] let yourself go to sleep. You're resistant jobs so this everybody has a has a limit of resistance until they you know to resist a choke before you pass out the moment that you you you you you go to sleep. That resistance will dropped that. </s><s>[INST] I've never heard anyone say that. That's awesome. That's true. So that's the reason because people usually say it's you [/INST] know it's the same or you're getting knocked out, you get knocked out the first time you're resistant, dropped, your job gets weaker. So </s><s>[INST] just for the record, I've never gone to sleep again, which means my resistance is high. Right? I don't know, [/INST] must be pretty good. </s><s>[INST] I don't know about that. Um because it doesn't make sense to me or [/INST] maybe in </s><s>[INST] my case, I think my understanding of when I'm screwed is pretty good. Like there's no [/INST] trouble. </s><s>[INST] Yeah. One of the things that I regret the most about my jiu jitsu journey is not having given enough time to um being in really bad positions. Like the better I got. I think the less I started being in bad positions which is just [/INST] because you spa, that's like the that is how you train. Yeah, because you used to just spa when you spar like it's difficult to be in bad positions a lot and you train with better people. But I mean let's say 56 minute rose, how long you're gonna be in a really bad position? Not long, right? So you don't really have time to develop. That's why people they don't, you know, they don't train. Being bad position because you have to start there over and over again. Yeah </s><s>[INST] or put yourself there. I just didn't have that mindset, I think, I think you start, I mean part of the fun of justice as you get better and better, you have certain people you go with, you have these puzzles that you figured out that you're playing very specific details. You're working out. You're trying to improve your main, like techniques and so on. But yeah, just the percentage of time you spend being submitted or being or trying even going against like lower ranks, trying to escape basic submissions low. I, I don't know if that's true for most people probably is right. [/INST] Most people have a very bad defense. Yeah, because they don't allow themselves to be there because I mean who wants to get tapped because you will until you, you know, if you work on your defense, of course you're gonna get tapped or you know, you're not gonna escape, you're gonna struggle to escape. So people, they don't want to be there. I </s> |
<s>[INST] So we [/INST] are imperfect in </s><s>[INST] discovering and optimizing a some kind of utility function. But you think in general there is a utility function. There's an objective function that's better [/INST] than others. I didn't say that. </s><s>[INST] And see [/INST] the presumption </s><s>[INST] when you say, I [/INST] think you could design a better memory system. You could argue about utility functions and how you want to think about that. But objectively it would be really nice to do some of the following things to get rid of memories that are no longer useful. Like objectively. That would just be good and we're not that good. So when you park in the same lot every day, you confuse where you park today with where you park yesterday with where you park the day before and so forth. So you blur together a series of memories. There's just no way that that's optimal. Um I mean I've heard all kinds of wacky argument, people trying to defend that, but in the end of the day, I don't think any of them hold water. </s><s>[INST] It's memories of traumatic events would be possibly a very nice feature to have to get rid of those. [/INST] It'd be great if you could just be like, I'm going to wipe this sector. You know, I'm done with that. I didn't have fun last night. I don't want to think about it anymore. Bye bye gone. But we can't </s><s>[INST] do you think it's possible to build a system? So you said human level intelligence is a weird concept, but [/INST] I'm saying I prefer general intelligence. Human level intelligence is a real thing. And you could try to make a machine that matches people or something like that. I'm saying that per se shouldn't be the objective, but rather that we should learn from humans. The things they do well and incorporated that into our Ai just as we incorporate the things that machines do well that people do terribly. So I mean it's great that Ai systems can do all this brute force computation that people can't and one of the reasons I work on this stuff is because I would like to see machines solve problems that people can't. That combine the strength or two that in order to be solved, would combine the strength of machines to do all this computation With the ability, let's say of people to read. So, you know, I'd like machines that can read the entire medical literature in a day, you know, 7000 newspapers or whatever is the numbers comes out every day. There's no way for, you know, any doctor or whatever to read them all. Machine that could read would be a brilliant thing and that would be strengths of brute force computation combined with kind of subtlety and understanding medicine that you know, good doctor or scientist has </s><s>[INST] if we can linger a little bit on the idea of general intelligence. So young raccoon believes that human intelligence isn't general at all, it's very narrow. How do you think? I [/INST] don't think that makes sense? We have lots of narrow intelligence is for specific problems. But the fact is like anybody can walk into, let's say, a Hollywood movie and reason about the content of almost anything that goes on there. So you can reason about what happens in a bank robbery or what happens when someone is infertile and monster, you know, good I've you have to try to have a child or you can you know, the list is essentially endless. And you know, not everybody understands every scene in the movie, but there's a huge range of things that pretty much any ordinary adult can understand </s><s>[INST] this argument is, is that actually the set of things seems large for us humans because very, very limited in, um, considering the kind of possibilities of experiences that are possible. But in fact the amount of experience that are possible is infinitely larger. When, [/INST] I mean, if you want to make an argument that humans are constrained in what they can understand, I have no, I have no issue with that. I think that's right. But it's still not the same thing at all as saying, here's a system that can play go. It's been trained on five million games. And then I say, can it play on a rectangular board rather than a square board? And you say, well, if I retrain it from scratch in another five million games, again, that's really, really narrow. And that's where we are. We don't have even a system that could play go. And then without further retraining play on a rectangular board, which any good human could do, you know, with very little problem. So that's what I mean by narrow. </s><s>[INST] So it's just [/INST] wordplay to say semantics. </s><s>[INST] Uh, then it's just words then, Yeah. You mean general in a sense that you can do all kinds of go board shapes [/INST] flexibly? Well, that means that would be like a first step in the right direction. But obviously that's not what really meaning. You're kidding. What I mean by a general is that you could transfer the knowledge you learn in one domain to another. So if you learn about bank robberies in movies and there's chase scenes, then you can understand that amazing scene in Breaking Bad when walter white has a um car chase scene with only one person, he's the only one in it. And you can reflect on how that car chase scene is. Like all the other car chase scenes you've ever seen and totally different and why? That's cool. </s><s>[INST] And the fact that the number of domains you can do that with this fine night doesn't make it less general. So the idea of generals, you can just do it on a lot of transferred across a lot of domains. Yeah, I [/INST] mean I'm not saying humans are infinitely general or that humans are perfect. I just said, you know, a minute ago it's a low bar, but it's just, it's a low bar, but you know right now, like the bar is here and we're there and eventually we'll get way past it. </s> |
<s>[INST] to speak about stuff is critical here, because it's like, I'm learning that this is like a minefield of conversations, because the moment you say, like even saying freedom of speech is a complicated concept, people would be like, oh we spotted the communist, like they'll say there's nothing complicated about freedom. Freedom is freedom, bro, it's it is complicated, first of all, if you talk about there's there's different definitions of freedom of speech? Uh if you want to go constitution, if you want to talk about the United States specifically and what's legal. It's actually not as exciting and not as uh beautiful as people think of complicated. It's complicated. I think there's ideals behind it that we want to see, What does that actually materialize itself in a digital world where we're trying to communicate in ways that allows for difficult conversations and also at the same time, doesn't result in the silencing of voices, not through like censorship, but through like just assholes being [/INST] rude, spam, </s><s>[INST] spam. So it could be just bots, [/INST] racism, </s><s>[INST] racism, [/INST] going back to the name of the app, CeleBREX lee bray free. Um, X was support Montu for free exchange and the free exchange of what my purpose was to create as many as much inner communication of ideas, be them repugnant or otherwise as possible. And of course, to do that within legal bounds and to do that without causing anyone to be harassed or docs. So to keep things focused on the ideas, not the people and then no bs crap, you know, stuff. And so to me, the easiest way to moderate around that, because as you said, figuring out what is hateful and what is hate speech is really hard was to say no sweeping statements against core identity groups. And that seems to work on the whole pretty well to be pretty light touch and you hard to do though, it's different, </s><s>[INST] we like to generalize we humans. [/INST] It's difficult, but what it comes down to is be specific. Um, and when you think about what are sweeping statement against coordinating groups, right? Oftentimes these are, these are sort of hackneyed subjects. These are things that have been broached and we've heard them before. They don't really lead anywhere productive. So, so it goes on to this principle of be specific. And the idea is you're discussing. </s><s>[INST] So even for like positive and humor stuff, he tried to avoid generalizations against core identity or daniel groups. Sorry, what a core daniel [/INST] groups we're talking, you know, race, religion. Okay, </s><s>[INST] got it even positive [/INST] stuff Against negative. </s><s>[INST] Against, sorry. Against, against. Okay, [/INST] very, very, we've learned to be very specific, very few words, but the community gets it, you know? Yeah, </s><s>[INST] they get it. I mean, this is the thing they, the trouble with rules is uh, as the community grows, they'll figure out ways to manipulate the rules, [/INST] human nature. It's creativity. Yeah. Something beautiful about it, of course. Unlike and from </s><s>[INST] an evolutionary perspective, [/INST] Yeah. The fact that people are so creative and so looking to, because people are generally interested in figuring out these things about social media and so the 100% like see like where's the edge? And I mean part of that's maintaining some level of vagueness in your real set, which has its own set of questions and something we could think about and I'm not implying I have all the answers but there is something really interesting about people being so engaged that they're looking to figure out where those edges and what does that mean? What does that edge mean? You know </s> |
<s>[INST] so you weren't even thinking about to buy the on ramps, you would think it would be just a wallet, a place to store because you've already gotten Yeah, okay, this is, I mean uh because that's such a pain to do, to have to work with others to convert dollars of any fiat currency into into Bitcoin. So did you, I mean were you overwhelmed by the immensity of the task here or were you just um sort of not allowing yourself to think too deeply through this whole thing and just letting the optimism take over here, [/INST] you know, I was really looking forward to like doing something crazy and like a big challenge and um I wanted to, I I love kind of crisis moments like that where you know, I'm very determined, right? Especially when I get like very set on something and I'm just like, you know what, I'm gonna figure out a way to make this thing work like no matter what. And so I, I reveled in that, I was sort of, I had, I had read all these books about startups and like every startup has these like, you know, major setbacks and just like nothing works and so that </s><s>[INST] was a sign that you're doing something right. [/INST] I had no idea if I would do anything right at all, but I was like, I was kind of loving the experience of it in a weird way. It felt, it felt stressful at the time, like, you know, nothing was working and but I was just, I felt like I was on the right path somehow. And so I just kept going, I don't know </s><s>[INST] um what was the darkest moment that you've gone to in your mind during that time? What was, what were some of the tougher moments he said self doubt? Have you uh yeah, where'd you go? Where'd you go in your mind? [/INST] Is </s><s>[INST] there a moment where you're just like laying there, this is this is hopeless? [/INST] Well, there's a couple moments I'm remembering, I mean, so for whatever reason I had this like, big chip on my shoulder at that time and I was like, I really want to do something important in the world, like, you know, I could have a good life and like work for some good companies and write some software and I'm, for some reason I never wanted that for myself. I probably would've been healthier, honestly, just like that as an expected value outcome, that's probably a better thing in life, but I was like, I was like, man, I really want to do something important and have a bigger impact and I was like, I was willing to sacrifice a lot for that. I was like sleep and not going out with friends and stuff. I remember one of the, just for like years working on this stuff, remember one of the darker moments was um we probably had like maybe five employees at that time and I remember like a bunch of bad things happened all at once and it was so first of all you have to remember at this time we were all very sleep deprived which kind of exacerbates everything. If you look at like the Exxon Valdez spill and all these like natural disasters like sleep deprivation is often involved. So because the reason why we're so sleep deprived is not just because we're working so much, but like the site would go offline in the middle of the night and we'd get, I get paged, I was like on pager duty, so I get woken up sometimes like two or three times a night, like have to try to fix something, go back to sleep. So in that environment you can kind of get, you can get discouraged. So one bad thing that happened </s><s>[INST] was we had [/INST] a bug on the website and there was thousands of people on reddit and twitter who were all like pissed at coin base because like the balances were showing wrong and they were just like, you know, for this company it's over. Like I hate these guys. And so that was, I've never had this feeling of 1000 people mad at me at the same time. You know, I feel like I'm a pretty chill guy. Like most times people don't get mad at me. So that was one another one was that um </s><s>[INST] can we pause on that? That's so interesting. So you you were saying like, here's a dream. I'm trying to create something and now forever the reputation of this dream is ruined. It will never is irrecoverable. It's over. That kind of feeling. [/INST] Yeah. Well I didn't write, I didn't know at that time, I was like, is this is this the end? Like </s><s>[INST] everybody, we're [/INST] so we're so tiny now, everybody hates us. So is it </s><s>[INST] over? [/INST] Um Nobody told me this before starting a company that like you're a bunch of people will hate you for this, which is like a very counterintuitive thing because you know, most companies I think are doing good things in the world, at least you're trying right. And so even if someone is like trying, but they're not, they're failing. I'm generally rooting for them. At least you're trying, right? But that's not the case at all. And most founders I've known have gone through this to where, um, they're very surprised at the amount of hate that they get. And if it's, I think it's actually like a muscle, you can build your tolerance to it. Like because you know, you go talk to somebody who's like for you, it feels terrible cause you're at the center of this storm and like, but if you go then you go talk to like, you know, your, your family or some other person like dude, I didn't even hear about that. Like they're just busy in their own life and so they have no idea that you had all this negative press or like whatever it was </s> |
<s>[INST] So let me be the guy you posted meme on twitter recently where there's, there's like a row of urinals, a guy just walks all the way across and he tells you about crypto [/INST] listen, I mean that's how so many times I think maybe even literally do </s><s>[INST] you think technologically speaking there's any room for ideas of smart contracts or so on because you mentioned laws um that's an interesting implement, the use of things like smart contracts to implement the laws by which governments function like something built on ethereum or maybe a doge coin that enables smart contracts. Somehow. [/INST] I never, I don't quite understand this whole smart contract thing, you know, I mean </s><s>[INST] I'm to [/INST] downtown stand small contracts. </s><s>[INST] Um [/INST] I mean my general approach to any kind of like deal or whatever is just make sure there's clarity of understanding that's the most important thing. Um and and just keep any kind of deal very, very short and simple, plain language. Um and just make sure everyone understands this is the deal, everyone is it clear. Um and uh and what are the consequences if various things don't happen. But usually deals are, you know, business deals or whatever are way too long and complex and overly lawyered and pointlessly. </s><s>[INST] You mentioned that does is the people's coin. Um And you said that you are literally going SpaceX may consider literally putting Adarsh coin on the moon. Is this something you're still considering? Mars perhaps? Do you think there's some chance we've talked about political systems on mars that does coin is the the official currency of mars at some point in the future? [/INST] Well, I think mars is helpful need to have a different currency because you can't synchronize judas, speed of light. Not easily. </s><s>[INST] So it must be completely standalone from earth. [/INST] Well, yeah, because the, But Mars is closest approach is four light minutes away roughly. And then add for this approach, it's roughly 20 light minutes away, maybe a little more. Um So you can't really have something synchronizing. You know, if you could, if, if you've got a 20 minutes to be the light issue, if it's got a one minute Blockchain, uh it's not going to synchronize properly. So my husband would, I don't know if monster would have a Cryptocurrency as a thing, but probably it seems likely, but it would be some kind of localized thing on mars. Um </s><s>[INST] and you let the people decide. [/INST] Yeah, absolutely. The future of MArs should be after the Martians? Um Yeah, so um I think the Cryptocurrency thing is an interesting approach to reducing the error in the the database that is called money. Um you know, I think I have a pretty deep understanding of the of what money actually is on a practical day to day basis because of papal. Um you know, we really got in deep there um and right now the money system actually for practical purposes is is it really a bunch of heterogeneous mainframes running old COBOL? </s><s>[INST] Okay. You mean literally that's literally literally what's happening? [/INST] Okay. Yeah. Pretty. The poor bastards who have to maintain that code. Okay, that's it. That was a pain. That's pain. </s><s>[INST] Not even for trans cobalt cobalt [/INST] like and they still banks were still buying mainframes in 2021 running ancient COBOL code uh and uh you know the the Federal Reserve is like probably even older than that, but what the banks have and they have an old COBOL mainframe and so now and so the the government effectively has editing privileges on the on the money database um and they use those editing privileges to um make more money whenever they want. And this increases the error in the database. That is money. So I think money should really be viewed through the lens of information theory. And and so it's you're kind of like uh like an internet connection, like what's the bandwidth uh you know, total bit rate, what is the latency jitter packet drop, you know errors, errors and network communication. I don't think money like that basically. Um I think that's probably what I really think of it and then say what system uh from information 30 standpoint allows an economy to function the best. Uh and you know um crypto is an attempt to reduce the the error in in money that is contributed by governments diluting the money supply as basically a pernicious pernicious form of taxation. </s><s>[INST] So both policy in terms of with inflation and actual like technological cobalt like Cryptocurrency takes us into the 21st century in terms of the actual systems that allow you to do the transaction to store wealth all those kinds of things. [/INST] Thanks. So just think of money as information. People often will think of money as having power in and of itself. Um It does not. Money is information and it does not have power in and of itself uh like you know applying the physics tools of thinking about things in the limit. It's helpful if you are stranded on a tropical island and you have a trillion dollars, it's useless because there's no there's no resource allocation. Money is a database for resource allocation but there's no resources to allocate except yourself. So money is useless. Um ah if you're stranded on a desert island with no food all the Bitcoin in the world. Well not stop you from starving. Yeah so um so like just just think of money as as a database for resource allocation across time and space and um and then what what what system uh is what what in what form should that that database or data system, what what what would be most effective now that there's a there is a fundamental issue with um say Bitcoin in its current form, in that it's the transaction volume is very limited and the latency it's the latency for properly confirmed transactions is too long, much longer than you'd like. So it's not it's actually not great from um transaction volume standpoint or latency standpoint. So it is perhaps useful as to to solve an aspect of the money database problem uh which is this sort of store of wealth or an accounting of relative obligations I suppose. But it is not useful as a currency as a day to day currency </s> |
<s>[INST] the following is a conversation with carl dice Roth professor of bioengineering, psychiatry and behavioral sciences at stanford University. He's one of the greatest living psychiatrists and neuroscientists in the world. He's also just a fascinating human being. We discussed both the darkest and the most beautiful places that the human mind can take us. He explores this in his book called projections, a story of human emotions. I highly recommend it. It's written masterfully and now a quick few second mention of his sponsor. Check them out in the description is the best way to support this podcast we got by Optimizers for health, better help for your mind, notion for productivity, blink. It's for insights into your favorite nonfiction books and magic spoon for delicious, delicious healthy breakfast choose wisely my friends and now onto the fill agrees as always no ads in the middle. I try to make this interesting but if you skip them, if you must please still check out our sponsors, I enjoy their stuff. Maybe you will [/INST] too. </s><s>[INST] This show is brought to you by by optimizers. B I. Optimizers that have a new magnesium supplement When I fast I'm doing keto or carnivore, sodium, potassium and magnesium are essential magnesium. The thing I take when I fast is tricky to get right. That's why I use magnesium breakthrough from by optimizers. Most supplements continue only one or two forms magnesium like glycerin, it or citrate when in reality there are at least seven that your body needs and benefits from. You can learn all about this actually from. Andrew Huberman and you should definitely go listen to this podcast called Huberman lab podcast. He's an incredible human, full of deep knowledge and wisdom and information. That's actionable for your life. Go to mag breakthrough dot com slash lex for special discount, That's Mag breakthrough dot com slash [/INST] flex. M </s><s>[INST] A G breakthrough dot com slash likes. This episode is also brought to you by better help spelled H E L p help. Just like you would write it out if you were on a deserted island looking at a volleyball with a handprint named Wilson, they figure out better help that is Figure out what you need and match it with a licensed professional therapist in under 48 hours every time I say 48 hours it gives me flashbacks And doing the four x 4 x 48 challenge from David Goggins, where you run four miles every four hours. David is one of the people that I go to for my inner turmoil that eventually materializes into inner peace. He is a kind of therapists for me if I may say so, but without so much talking now. I also believe in talking as a method for therapy and for that you should use better help. It's easy, private, affordable, available worldwide. Check them out at better help dot com slash lex. That's better help dot com slash lex. This show is also brought to you by notion a note taking and team collaboration tool combines, note taking, document sharing, wikis, project management and much more all in one space that's simple, powerful and beautifully designed everybody I talked to. Okay, that might be a little bit of an exaggeration. I think I tweeted all generalizations are wrong, including this one, but they're also fun and they're also useful anyway. The generalization I was about to say is that people that I talked to all love notion that's like the cutting edge. That's the the state of the art, the sexiest note taking app. Now, the thing they want me to tell you is that it's not just for individuals. It's also for startups. It can provide a full on what they're calling. Operating system for running every aspect of your company as it grows quickly. They're writing a special offer just for startups and that will give you 1000 bucks off of notions Team plan. If you go to notion dot com slash startups To give you a sense that's almost a year of free notion for a team of 10 go to notion dot com slash startups. That's notion dot com slash [/INST] startups. </s><s>[INST] This show is brought to you by blinking my favorite app for learning new things. I'm sorry, I'm running around the mic. I just get really excited when I'm doing these ad reads Blankets. Takes the key ideas from thousands of nonfiction books and condenses them down into just 15 minutes that you can read or listen to. I can recommend a million books from sapiens to meditations by Marcus Aurelius. But what I should more specifically or more generally say that's a contradiction is that you can use it to both review the books you've already read or to select books that you're going to read and both are super useful. Go to blankets dot com slash lex to start your free seven day trial and get 25% off of a blinkers, premium membership that's blinking dot com slash lex spelled B L I N K I S T blankets dot com slash lex. This episode is also brought to you by magic spoon. Just saying that brings happiness to my heart. It's a low carb keto friendly cereal. It has zero g of sugar, 13 to 14 g of protein, only 49 g of carbs, 140 calories that needs serving. I just had a huge amount of barbecue Texas, barbecue yesterday. I made myself feel a lot better today to balance that out with the lightness and the health of also a keto friendly meal, which is magic spoon. You can build your own box or get a variety pack. But ladies and gentlemen, the best flavor is Coco. It is the flavor of champions. It reminds me of childhood and the happiness I felt when I was eating the sweet, sweet delicious cereal. But at the time those cereals were full of sugar and this cereal is not so it's also healthy for you. Magic spoon have a 100% happiness guarantee. So if you don't like it, they refunded, go to magic spoon dot com slash lex. And use code lex at checkout to save five bucks off your order. That's magic spoon dot com slash lex. And use code lex. This is a lex Friedman podcast and here is my conversation with carl zeiss Roth. You open your book called projections a story of human emotions with a few beautiful words to summarize all of humanity. The book draws insights about the human mind for modern psychiatry and neuroscience. So if it's okay, let me read a few sentences from the opening. You gotta give props to beautiful writing when I see it quote in the art of weaving warp threads are structural and strong and anchored at the origin, creating a frame for crossing fibers of the fabric is woven, projecting across the advancing edge into free space. Warp threads bridge deformed, passed to the ragged present to the yet featureless future, yet featureless future. Well done. Well done sir. The tapestry of the human story has its own warp threads rooted deep in the gorges of East africa connecting the shifting textures of human life over millions of years spanning pictographs backdrop by crevices, ice, by angular lated forestry by stone and steel and by glowing rare earths. The inner workings of the mind give form to these threads creating a framework within us upon which the story of each individual can come into being personal grain and color arise from the cross threads of our moments and experiences the fine weft of life embedding and obscuring the underlying scaffold with intricate and sometimes lovely detail. Here are stories of this fabric fraying in those who are ill in the minds of people for whom the warp is exposed and raw and revealing. What have you learned about human beings, human nature and the human mind, from those who suffer from psychiatric maladies, for those for whom this fabric is warped. [/INST] And one thing we learn as biologists is that when something breaks, you see what the original unbroken part was for and we see this in genetics, we see this in biochemistry. It's known that when you have a mutated gene, sometimes the gene is turned up in strength, there turned down in strength and that lets you see what it was originally for. You can infer true function from dysfunction. And this is a theme that I thought needed to be shared and needed to be made communicable to the lay public to everybody. People who, which is I think almost all of us who think and care about the inner workings of her mind, but who also care for those who have been suffering who have mental health disorders, who face challenges. But then more broadly, it's a very much larger story than the present. There's a a story to be told where the protagonist really is the human mind and that was one thing I wanted to share as well in projections, is that broader story, but still anchored in the moment of patients, of people of experiences at the moment. </s><s>[INST] Is there a clear line between dysfunction and function disorder in order? [/INST] This is always debated in psychiatry, probably more so than any other, you know, medical specialty. I'm a psychiatrist. I'm I treat patients still, I see acutely ill people who come to the emergency room where there is no doubt that this is not something that's working well where the manifestation of diseases so powerful, where the person is suffering so greatly where they cannot continue as they are. But of course it's a spectrum and there are people who are closer to the, to the realm of being able to work okay in their jobs but suffer from some small dysfunction and everywhere in between. In psychiatry were careful to say, we don't call it a disease or disorder unless there is a disruption in social or occupational functioning. But of course psychiatry has a long way to go in terms of developing quantitative tests. We don't have uh, blood draws, we don't have imaging studies that we can use to diagnose. And so that line ultimately, that you're asking about between order and disorder function and dysfunction. Its operational at the moment. How are things working? </s><s>[INST] Can we just like linger on the terms for a second. So, this disease uh dysfunction, how careful should we be using those words? Can we just even in this conversation? Um, from a sort of technical perspective, but also a human perspective. How quick should we be in saying that schizophrenia, depression, autism, as we kind of go down this uh, the across the spectrum of different maladies, like just to use the word dysfunction and disease, [/INST] I would say to give ourselves license to capture the whole spectrum, let's say, disorder because that that captures truly, I think the essence of it, which is we need to talk about it when it's not working, when there is disorder and that that's the fairest and and, you know, most inclusive term to use. </s><s>[INST] So, is it fair to assume that basically every member of the human species suffers from a large number of disorders then? [/INST] Well, </s><s>[INST] we just have to pick which ones are debilitating and for each person, [/INST] you know, if you if you look at the numbers, there are uh, you know, if you look at how our mental health disorders are currently defined, you can look at population prevalence values for all these disorders and you can Come up with estimates that uh, somebody will have a lifetime prevalence of having a psychiatric disorder that approaches 25% or so. And so that's and in some studies, it could be more, some studies that could be less. Now, what do we do with that number? What does that mean? And in some ways, that's the essence of what I was hoping to approach with the book is to reflect on this spectrum that exists for all the disorders there is and and taking nothing away from the severity and the suffering that comes at the extreme end of these illnesses. But nearly every one of them exists on a spectrum of severity, from nearly functional to completely dysfunctional, life threatening and even fatal. And so that that that number, 25% more or less, it doesn't capture, uh, that that spectrum of, of, of severity </s><s>[INST] to linger that number. Where did those numbers come from? Is it self reported that people who show up and say, I need help, Is it somebody else that points out that person needs help? Or is it like estimates that even go beyond that for people who don't ask for help or suffering quietly alone. [/INST] When you look at self report numbers, that, that then those numbers get even higher beyond 25% or more. Those the most rigorous studies are done with structured psychiatric interviews where people who are trained in eliciting symptoms carefully do complete psychiatric inventories of individuals. And these are time consuming, laborious studies that not often repeated when they're done, they're done well. But very often you'll see a report of something in the news of a very high number for some disorder or, or symptom and very often if it's shockingly high, that's coming from a self report of a person. And so that's another, another issue that we have, again, take nothing away from the severity and reality and and biological nature of these disorders which are very genetic, very, you know, we we understand that these are very biological and yet we lack right now, the lab tests and the blood draws to make the diagnosis. </s><s>[INST] We'll talk about it just how biological they are because that too is a mystery. I mean, just, you know, in terms of from a perspective of how to probe into the disease, had to understand it, how to help it. So, some of it could be neuro biological, some of it could be uh just the, the dance of human emotion and interaction. And the it's like it is love when it works and is love when it breaks down biological or is it something else? So we're gonna talk about it. But well, let me just like to linger in terms of disorder. What about genius? You know that sort of cliche saying like the madness and genius that they kind of danced together. Uh What about if the thing we see is disorder is actually genius, unheard or misunderstood. [/INST] Well here again, the numbers help us and here's where being rigorous and quantitative actually really helps if you look at disorders like autism and bipolar disorder and eating disorders, anorexia, nervosa, for example, these uh, you know, particularly bipolar and anorexia. These can be fatal. They can cause immense suffering. But they are heavily genetic all three of these. And what's very interesting is each one of these three is actually correlated positively positively with measures of intelligence, of educational attainment and even of income. And so you look at this severe disorders in many cases, causing quite an immense morbidity and mortality. And yet they are positively correlated at the population level with positive things. </s><s>[INST] Can you say the three again, autism, [/INST] autism, anorexia and bipolar disorder </s><s>[INST] bipolar. What's that book? Forgot the book name, but his intelligence a burden. [/INST] Well, you know, people can get into trouble when they think they're smarter than they are. I will say that, </s><s>[INST] I don't know sometimes like in the deepest meaning of that statement, I think ignorance is bliss. I'm a big fan of Prince Myshkin from the idiot and um Alyosha from Brothers Karamazov. Optimism can be seen as naive and and and dumbness. But I think it's a, it's a kind of deep intelligence, maybe inability to reason sort of about the mechanics of the world. But instead of kind of feel the world. And it seems like that's one of the paths to happiness. [/INST] There is how much you think versus how much you feel. This comes up all the time in medicine. We encounter this all the time when you, day after day you encounter this? You know, the abyss of suffering from patients. How much do you let yourself feel or how much do you make it abstract and and objective and try to make it clinical and that range, how you're able to move yourself on that on that spectrum is very important for survival as a physician uh and the way you you protect yourself and your feelings turns out to be very important. </s><s>[INST] So you quote Finnegans Wake uh mad problems for that James Joyce book. I took a class in James Joyce in college, I think I read parts of fitting in a way it might have been on drugs or some kind or I um I somehow got an A in that class which probably refers to some kind of curve where nobody understood anything. The only thing I understood and really enjoyed is his short stories, The Dead and then ulysses, I kind of uh I think Greta few cliff notes that kind of got to the point and then Finnegans Wake was just a hopeless person. It's a you for people who haven't looked at it, maybe you can elucidate to me better. But I felt like I was reading things, words and the words made sense, like standing next to each other. But when you kind of read for a while you realize you didn't actually understand anything that was said. [/INST] But did you have a feeling though, that's one that's one thing I found interesting about Finnegans Wake, I never fully understood it, but the words caused feelings in me, which I found fascinating and and sometimes I couldn't predict it from the semantic, you know, black and white context of what I was seeing in front of me on the page. But the rhythm of the melody would would make me feel certain ways. And that's that was what I always was intrigued by with Joyce of course that was his, he he existed on a spectrum too and he wrote as you say, you know, more accessible works. You know, I learned a lot about irish history from, you know, portrait of the artist as a young man and there was just so he could be as objective as he wanted to be. But then when he let himself loose, he was in this realm where the words had their own purpose separate from from you know semantic meaning, from their, their dry dictionary definition. </s><s>[INST] You know, there's a funny story that was told, it doesn't matter if it's true or not, but they they said that James Joyce when he was young, when he was in his teen years would go around Sort of Ireland drinking and so on and telling everybody that he's going to be one of if not the greatest writers of the 20th century and he turned out to be that so that that I always think about that little story that somebody told me because I have a lot of people come up to me including myself, I'm a bit of a dreamer. Uh and you know, you get into certain moods where you say I'm going to be the greatest anything ever. You get you get like, people tell you this young, especially young people and it kind of and it makes me feel all kinds of ways, but that story reminds me that like you just might be One of the greatest writers of the 21st century, for example, if somebody were to tell me that and like, don't just don't immediately disregard that because one of the people that say that that's almost like a pre condition. That's a good requirement just to believe in yourself. Maybe it's not a full requirement, but it's an interesting story. I [/INST] think when someone tells you that, then it creates a </s><s>[INST] one [/INST] sees an opportunity and then it would be a tragedy if the opportunity weren't captured, right? And so then that creates a um some some impetus, some motivation to do something, something good. I </s><s>[INST] think the mind, it's like uh you know, I guess that's what, like books like the or books or whatever. I don't even know if the book, the secret plugs into they kind of make a hole industry out of it. But there is something about the mind believing something making it a reality. It is just time and time again with steve jobs, like your belief in yourself, your belief in an idea sort of embracing the me versus the world, embracing the madness of this idea and making it a life pursuit somehow, most reality around for some tiny fraction of the population for everybody else you descend into ah you know, all all the beautiful ways that failure materializes in our lifetime. [/INST] Well, you know that you mentioned love earlier. I mean, that's that's a great example of how belief in something makes it real, right? It's it's not reasonable on the face of it, but because you believe it's reasonable that it actually does become reasonable and then it is real. And so that's a that's a good example. That doesn't happen. I'm also in a bioengineering department. We don't imagine that abridges soundly built and then it is soundly built. That's something that it doesn't come up in too many realms of human existence, but love is one of them and and these the ability to to have a fixed idea and to say it's true and then it is true. </s><s>[INST] A bridge is a kind of manifestation of love. So maybe it does work a little bit, but you know, they can break down like Chernobyl did you can't just say it's safe. The afterwards also prove it's safe. But on Finnegan's wake, I think maybe correct me if I'm wrong, you're using kind of Finnegans wake to give one perspective on what madness is of what's going on in the mind, how much of that is uh that were simply unable to communicate with the person on the other side of of their mind, Like there's almost like a a little person inside the brain. And they have some circuitry that's used to communicate emotion, communicate ideas to the outside world. And there's something about that circuitry that makes it difficult to communicate with the little person on the other side. So [/INST] if you look at what shows up in schizophrenia with many cases, the what we call thought disorders, what we call the, the individual speech symptoms of schizophrenia, Finnegans wake is loaded with them. And it's, it's just full of them. We we talked about clang associations in schizophrenia where the word that is said is echoes in some way the previous word. And as we call that a client association because there's no other reason than the similarity of the sound, like a, like a clang of a, of a garage door being hit. And it has a uh, and sometimes it's not even a word. And we call that a neologism a new word being created. And of course, Finnegans wake is full of that. And then we also in schizophrenia, whether it's what we call loose associations or tangential thought processes, of course, full of that, where things just go off in directions that are not linear, logical. And you can't read Finnegans wake I think without, um, certainly a psychiatrist, you can't read it without thinking about schizophrenia. And then when we look at the families of people with schizophrenia and Joyce was no exception. They're very often are people within the family who are on the spectrum. Some have it, some are able to see it from a distance from a safe distance. There is an association between schizophrenia and what we call, it's a typical personality disorder where people are not quite in this severe state of schizophrenia but have some magical thinking have some unusual thought patterns. Very often. Those are family members of people with schizophrenia. So this points to this again to this idea that that there is a range even along this very severe, very genetic biological illness that human beings dwell on different spots along that spectrum. </s><s>[INST] I should mention that we have my friend Sergei pulling up stuff. Young Sergei or old Sergei, I don't know what to call you. But uh there's drafts of Finnegan's quake. Yeah, I actually saw pictures of this from um I think it was on instagram or something. These are early drafts of Finnegan's way. And it's so beautiful to see where people were just listening. There's just random paragraphs and writing all over the page with stuff crossed out. And it's great to see that Joyce himself was thinking in this kind of way as um as you're putting it together, how much do you think he was thinking about schizophrenia. This schizophrenic mind, I [/INST] think a lot, I think you know, it's it's known that his his daughter suffered from schizophrenia. And uh this is what's depicted here on the page is something that I'm sure he either felt himself and some, some level was able to access this non linearity of processing </s><s>[INST] or had [/INST] seen enough in family that he knew what it was and and was able to to reflect it down in black and white on the paper. So it was, what he was able to do was was quite authentic in that sense. Of course, I don't want to pigeon hole and he was doing much more than that. It was much more than talking about altered human okay, thought processes and thought disorders. But that was an aspect that he was so good at representing that it had to be intentional to some extent, </s><s>[INST] tiny tangent. What is your own writing looks like for this book? Because it's extremely well written. How many edits did you just drink some whiskey? And uh, like I'm imagining Hemingway style, it's a very different. The writing is very different. I mean it's really, really well written, which was like, I was just reading it. Um it makes you realize because I was expecting sort of science kind of, which it is like uh, you know, elucidating something about the human mind kind of thing. But you could also probably, right, really strong like novels. So maybe that's in the future. But anyway, what is your, how many edits? How many, what's your style does it look like? That is a more structured organized. [/INST] Unfortunately, I use the laptop. So I didn't have this sort of beautiful record </s><s>[INST] typewriters and cigarette and whiskey. [/INST] I did explore. I was, you know, which was there a particular altered state that would help me to be most creative. And and I I found actually I actually did the best while uh you know, sober but slightly dis inhibited in the late hours of the of the night or early morning. Yeah, particularly late hours of the night there. You know, I I have a friend who who would would tell me that she thought that very early in the morning her inner critic was still asleep and she could write more effectively before her inner critic woke up. And I actually found that outstanding advice for me that I often found that there was I was looser and could write more in the morning. But the other interesting thing is, is each each chapter, each story it's about a different human being with a different class of of of psychiatric disorder. That's what each story each each chapter is anchored in. But I'm trying to use words that in style of writing and and uh you know, diction that captures the feeling of the disorder. And so it's different in each story in the story about mania, which is a very expansive, exuberant uh at least briefly uplifting state where the words come out in a torrent and their complex and pressured and elaborate. I try to capture that feeling with the words used in that chapter and then in the schizophrenia or psychosis chapter where things slowly fragment over time and become looser and separated. I tried to capture that in the writing too. So for each it wasn't as if there was a single mode I could be in for the whole book. For each chapter, I had to put myself into a different mode to capture that inner feeling of the disorder. </s><s>[INST] When you put yourself in that mode, does that change you? [/INST] Yeah, I couldn't turn it on and off right away. I had to first I would start by thinking about the person or the people, one or two people based on real patients and the and the stories that are that are put forth. The symptom descriptions are real. They're from the patients. Of course all details changed to protect privacy, but the actual symptom descriptions are real and I would sit with them and really try to inhabit the space of the mind of that. The person that I knew and that's not instantaneous. It would take take some time. I needed quiet and I need to be still. That's another reason. Late at night is is good. </s><s>[INST] Sergei posted. That drowsiness gives creativity boost according to Andrew Huberman. Thank you. Andrew uh he's [/INST] not wrong. He's not wrong. </s><s>[INST] Why projections, is it? Uh I mean there's a meal instead of putting words into your mouth because I can imagine a lot, I mean to me. No, I will start putting words in your mouth despite what I just said. Uh So I mean to me, projections, working on your networks, for example, from artificial neural networks for machine learning perspective, it's often that's exactly what you're doing. You have an incredibly complex thing and you're trying to uh find simple representations in order for you to make sense of it. So, I was kind of thinking about in that way, which is like um this incredibly complex in your own own network that is kind of projecting itself onto the world through this low bandwidth expression of emotion and speech and all that kind of stuff. And the way it's we only have that window into your soul, the eyes and the speech and so on. And so that in that way where um when there's any kind of disorder, we get to only see that disorder through that narrow window as opposed to the full complexity of its origins. [/INST] The word projections definitely serves that purpose here, but it's it's got a few other really appropriate other connotations as well. So the first thing is a projection in terms of neuroscience is this long range connection that goes from one part of the brain to another. And so it's what binds to parts of our brain together. There are projections long range connections of axons. These are the outgoing threads that connect one part of the brain to another part. There's a there's a projection that links for example, auditory cortex where we hear things to reward centers where we can feel where feelings of pleasure and reward are initiated. And it's been shown that if you have reduced connectivity along that dimension, you are less able to enjoy music. And so these connections, these projections matter. They define how effectively two parts of the brain can engage with each other and join together to form a a joint representation of something. So that's one meaning, it's pure neuroscience. The word projection is used all the time and it happens to be something that optogenetics, a technique that we maybe we'll talk about a little later it works particularly well with we can use light to turn on or off the activity along these projections from one spot of the brain to another. </s><s>[INST] And this is particularly referring to the long range connections. [/INST] It's particularly straightforward along these long range projections that connect different parts of the brain but it works over shorter range too. But then there's this other meaning of projections which you were bringing up which is very relevant which is at some point you you can reduce something from one level of dimensionality to another and you can project down into a lower dimensional space for example. And then finally there's a psychiatric uh term projections which comes up all the time which is uh we very often will look at our internal states and to understand somebody else will project them onto somebody else will try to understand someone else's behavior and make sense of it by projecting our own inner feelings, our own uh sort of narrative onto them. And use that as a way to help us understand them better. And we'll do the reverse to, we'll take things we see in the outside world and we'll bring them into ourselves and see how well they map. How will they align that's called introduction. So projections as it turns out to be a really rich word. And finally, of course there's the very common sense of it as a projector that illuminates by conveying information across space with light. So for english for english language. Perfect word to use </s><s>[INST] for this book. But [/INST] it was funny is not every, there are a lot of international translations now and all those rich connotations aren't captured in other languages. And so for some translations, connections is used instead of projections. In fact, even in England, the british version has connections instead of projections because apparently projections doesn't have the full connotation. I was told </s><s>[INST] you have to sacrifice some of the rich um ambiguity of meaning with connections. That's interesting. I mean, can I and words are so interesting. They have so many me. I love language and how much is lost in translation. I'm very fortunate enough to be able to speak. I'm not good at languages. I was just, I guess forced to buy life circumstance to learn two languages Russian and english. And it's just so interesting to watch how much of culture, how much of people, how much of history is lost in translation, the poetry, the music, the history of the pain and the way the scientists actually express themselves, which is funny, I mean, just it's so sad. Um to see how much brilliant work that was written in Russian, there's a whole culture of science in the soviet union is not lost. It makes me wonder in the modern day how much incredible science is going on in china that is lost in translation. And I will never, I mean that makes me very sad because I'll never learn chinese in the same way that I've learned english and Russian, maybe whenever I say stuff like that, people are like, well there's still time, but uh you know, uh yeah, that's that's that's actually fair, that uh I think the 21st century, both china and us will have very important roles in the scientific development. Uh and we should actually bridge the gap through language. And that, that doesn't just mean convincing chinese to speak english, that means also learning chinese. [/INST] Well, we need these bridge people who can do both. You know, the um you know, Nabokov for example, writing in english beautifully. Uh you know, one of my favorite poets Borges who, you know, mentioned earlier, he wrote both in english and in spanish, I think, you know beautifully in both. We need those people who can serve as bridges across cultures who really can do both. </s><s>[INST] You mentioned board says so you open your book with a few lines from a poem by jorge, luis Borges has a love poem. I'm gonna read parts of it because it's a damn good poem. It's called to english poems. I mean there's, I'd like to understand why you used it and the specific parts you used, which is interesting. But then when I read the full thing, so I think you used that as as a as a sort of beautiful description of what it means to delve deep into understanding, offering yourself to the task of understanding another human being. But if you look at the full context of the poem, it's also a damn good description of being hit by love and overtaken by it. And uh sort of and trying to, trying to figure out how to make sense of the world now that you've been stricken by it. It says a bunch of things about chatting and significantly with friends and all those kinds of things. And then the poem reads the big wave brought you I guess this is the moment, I guess, of the universe where two people you fall in love. Maybe I'm totally misreading this point by the way. It doesn't matter. You can't miss read the poem. [/INST] So it </s><s>[INST] goes on words. Any words, your laughter and your so lazily and incessantly beautiful. We talked and you have forgotten the words. The shattering dawn finds me in a deserted street of my city, your profile turned away the sounds that go to make your name, the lilt of your laughter. These are the illustrious toys you have left me. So these little memories of these peculiar little details he remembers. Those are the illustrious toys. I apologize to mix my own words of the poem but you should definitely read it. I turned them over in the dawn. I lose them. I find them. I tell them to the few stray dogs into the few stray stars of the dawn. Your dark rich life. I must get at you somehow. I put away those illustrious toys you have left me. I want your hidden look, your real smile, that lonely, mocking smile. You're cool. Mirror knows I want your hidden look, your real smile. I haven't so I this this is the first part of the poem and then it goes on which is some of the parts that you reference. The second part is what can I hold you with? I offer you lean streets, desperate sunsets, the moon of the jagged suburbs. I offer you the bitterness of a man who has looked long and long and a lonely moon. I offer you my ancestors, my dad men the ghost that living men have honored in bronze my father's father killed in the frontier of Buenos Aires two bullets through his lungs and so on so on. I offer you whatever insights my books may hold, whatever manliness of humor in my life. I offer you the loyalty of a man who has never been loyal. I offer you that kernel of myself that I've saved somehow the central heart that deals not in words, Traffics not with dreams and is untouched by time. My joy and adversities. And I think this is where the part they include in the book. I offer you the memory of a yellow rose seen a sunset years before you were born. Hi. Damn. That's a good line. Okay I offer you explanations of yourself theories about yourself, authentic and surprising news of yourself. I can give you my loneliness, my darkness, the hunger of my heart. I'm trying to bribe you with uncertainty, with danger, with defeat. That is a man who's in love and longing if taken. But I just want to go back to maybe you could say why you wanted to include that poem but also your dark rich life. I must get at you somehow I put away those illustrious toys you have left me at what your I want your hidden look your real smile, that lonely mocking smile. You're cool. Mirror knows what sometimes I meet a stranger and I just it's like it's like a double take. It's like who are you have we met before somewhere. Who is that person behind there And I want to get at that, whatever that is. And of course, maybe that's what love is, because maybe maybe that's the whole pursuit, like a lifelong pursuit of getting at that person. Maybe that's what that is. And like that uh, insatiable sort of curiosity to keep getting like, well, who is that person in your own private life? [/INST] Yeah. So that absolutely. I think that it was a beautiful description of what you just said when there's that first moment, and then you want to dive deeper. You want to know what the what the hidden mysteries are. In a way. It's it's a it's a love poem as a as a scientist though. It also it's a bit of how a scientist can love science. And and I think that wanting to dive deeper is it's almost like again where the it could be a love affair with investigating the human mind, for example. And and that was one reason that it spoke to me also, again, thinking about the broader sweep of where the human mind came from. Uh the steps it took to get where it is today. What was given up along the way, what compromises were made. And here's where the darkness of the poem starts to come in a little bit too. It doesn't shy away from the negativity from the confusion, from the danger. And then at the very end, the board faces offering up scenes from his life, parts of himself and this is how we connect with people. We offer up parts of ourselves just here it is. And then we see how well does that map onto what you have? And it's it's that offering up that I liked and not not the good stuff or not only the good stuff. The yellow roses, nice, but but he's offering up the bad stuff too. And that that to me was important for the for the book because I'm offering up hard stuff too. And in fact, a lot of it and also hard stuff from within me from my own personal side to and that was there's a lot of vulnerability that comes with that. But that's that comes with love that comes with writing. You have to be open. You have to be vulnerable. And so I thought that reflected what I was trying to do. And I thought it was as an epigraph. It kind of made it clear how vulnerable I was in taking this step, but also what what could come out of it </s><s>[INST] And also in a metal away, because I was not familiar with this poem. It it may be curious of the poem itself to pull at that thread. Finding out more you picked a very particular part that kinda made you want to um pull at that thread. And and and and see where did this, where did these few lines come from? Because I I read it as a curiosity of a scientist. Those lines alone and also as a desperate human being searching like offering himself for an understanding or connection with with another human being. And then because I wasn't sure if it's a love poem or not or if it's desperation or if it's scary out whatever it is. And then you see the love poem. I mean, I don't know that that's gonna stick with me for a while, the your dark rich life. And then a few lines in here are just I mean those are I'm gonna just use them as pickup lines at the bar. I offer you the memory of a yellow rose scene at sunset years before you were born. That's a pick up line. I've never if if I've ever heard one anyway, sorry. But [/INST] this is universal. You know, you see it in so many forms of of art, you know, like you know, we're in texas now. You see this in country, country and western songs. It's it's often a list of things like here's how I describe myself. There's this and there's that and there's the other thing and here you are. These things matter to me. And I hope they matter to you too. It's a it's a pretty universal form. But it's but he did it in this very artful and very vulnerable way. It was. It was both both beautiful and you could you could feel the hurt coming from him too. And that was important. </s><s>[INST] The dark stuff too. I offer you, my ancestors, my dead men, the ghosts that living men have honored in bronze and talking about two bullets through his lungs, bearded and dead wrapped by his Soldiers in the height of a cow. A mother's grandfather just 24 heading a charge of 300 men in Peru. Now, ghosts on vanished horses. So all of it, the whole history of it, um, since it is a love poem, [/INST] what </s><s>[INST] do you think about love carl? What's what's the role of love and the human condition? We'll talk about the dark stuff, but maybe love is the dark stuff too. [/INST] I mean, it's it's the most powerful connection we can form and that's that's it's that's what makes it so important to us. It's the, it's the strongest uh, and most stable connection that we conform with another person and that matters immensely. Uh, it matters for for the human family to have evolved to be something that could survive against the odds that that, that we've faced over the years of that unreasonable bond that becomes reasonable by virtue of its own existence. And of course that joy, the wild raw joy of love is not a bad thing either. So, you put these together, the form, the strongest bridge we can form and the reward and the joy that it brings. That's what love is to me. And from my perspective, this is something that, you know, it can be hard to capture fairly because you want to talk about the positive and the negative sides at once, they need to be wrapped up together for full honest description of of what it is. And that's that's hard to do in a in a compact form. And so you have to take time to talk about love. You have to take time to to do it justice. Um takes a book or at least a poem or </s><s>[INST] several thousands of them. I don't know. Is there, Could you pull up? There's a video I saw. Yeah, like right here. So can you pause for a second? Uh So so there's march of the penguins. So you always see like penguins huddling together against I mean sorry if I see just metaphors and everything but uh them huddling together against the harshness of the conditions around them. That's very kind of that's like a metaphor for life. Like finding this connection. That's kind of what love is. It's like allows you to forget whatever the absurdity, whatever the suffering of life is together, you get to like huddle for warmth. And that's why I loved the sort of just the the honesty and the intensity of the way penguins just in the middle of like the cold do this and then this video I saw a lonely this is this is misinformation. So the name of the videos lonely deranged penguin, I don't know if he's deranged. So if you play it. So he left his pack and uh and then there's a nice like voice over and you don't need to play it. But he, for some reason left the pack and journeyed out into the mountains. And so the narrator says that he's deranged, he's lost his mind. Now I'd like to project the idea that he's actually, there's so many stories you could think of. He's returning to his homeland. He's an outsider thinking, journey out into the unknown, thinking. He may be able to discover something greater than the tribe. He might be looking for lost love. Why is he deranged immediately? Why has he lost his mind anyway. But this people should look up this video because to me, I might be the only one who romanticizes this. But it's such a nice kind of, it's both a picture of perhaps a mental disorder, which is what the video kind of describes and maybe some deeper explanation. That's not that that has to do with the motivation of uh, of a mind. But yeah, I don't know if I don't know if you have a deeper analysis on this penguin. Well, [/INST] I like you </s><s>[INST] a psychiatrist. [/INST] I would I would want to sit down with the penguin and and and and go through. I want to see the notes from his prior therapist. And but this this actually is, is relevant not knowing what was that penguins motivation we have very clear situations where there are both within an individual. We go through periods of time when we stay in one place and we reap the benefits from what we've built and then we go through periods of foraging, of of of wandering. Even if there may be resources where we are, we have periods of time in our lives where we wander where we where we go in an exploratory mode and different people express that trade in different ways. This is not a human specific trait. If you go down to to the tiny little nematode worm C. Elegans with 302 nervous system cells, </s><s>[INST] they [/INST] go through these phases of foraging and rest and different individuals have different propensity to forage or to rest and stay in one place at the level of the species. That's really good that there's that diversity in their willingness to forge some stay where they are. The species is somewhat on a firm footing then, but some carry a burden a risk for themselves. But it's good for the species that they're explorers and they will venture out the migration patterns that different species blunder into and that turned out to be really good. They weren't logically derived. They most certainly started from something like this. An exploration. </s><s>[INST] Humans do this to you think, [/INST] and we do it too. In fact, it's something we do extremely well. </s><s>[INST] Let's talk about psychiatry a little bit. So in my book, you're a rock star. First of all, for people who don't know your aside from, sort of, um, the neurological view of the brain and neuroscience view of the brain, you're also one of the great psychiatrists of our time. I've always not always, but when I was younger, I dreamed about being a psychiatrist. Um, so it's like, it's like getting to meet your heroes and also, um, you know, getting to meet the people who uh, the best at the top of the world, at the thing you've failed to pursue. So there, so there's, I'm getting a free therapy session on top of that. Okay, so what big picture, what is the practice, the goal, the hope of modern psychiatry? If you could try to describe the discipline As you see it maybe historically, throughout the 20th century, Uh, in contrasting to what it is today, or maybe if you want to describe to what you hope psychiatry becomes, or longs to become in the 21st century. [/INST] It's been an interesting journey. Uh, psychiatry started out pretty firmly grounded in neurology and pathology. Some of the initial uh, founders, effectively of the field were very well grounded in microscopy, looking at cells, uh, working with patients, particularly the neurological side, and that's certainly included, you know, Freud and some of his contemporaries, and but they rapidly discovered that what they could work with at the level of cells and microscopy was so far from the realm of what they could get from a human being and what they were getting from the human being was so much more interesting and had was so mysterious and so unknown that many of them just said we're going to inhabit this domain and we're gonna work with the people with their words and understand what we can based on verbal communication because that was the only tool that people really had and that was a very important step for the field. I would say one of the interesting things that came from the early decades of psychiatry really was this distinction between the conscious and the unconscious mind and paying particular attention to the unconscious mind is something that was worthy of consideration that that might be important in explaining people's actions and that. Perhaps even insight into that was valuable in its own right. And out of that psychoanalysis uh became a practice that it was not always focused on cures or treatments but was more focused on insight. What does it, what does it mean? How can we help people understand why they're feeling something or thinking something or dreaming something. And that insight separate even from treatment was was an interesting thing, as long as one was honest about that and said, you know, we're going for understanding, we're going for insight </s><s>[INST] maybe it's useful to just pause on that if you look at the father of psychoanalysis Zigmund Freud, What do you make of the ideas that he had? So you mentioned taking the unconscious the subconscious seriously, That's like step one like that. There could be worlds. We do not have direct access for we pro but them through conversation. Or um is it too simplistic to call psychoanalysis conversation? That's [/INST] not too simplistic, but that's right. And I think that was valuable where where Freud ended up breaking from some of his contemporaries, he was very focused on this unconsciousness being so tightly linked to libido. And and really he from his perspective, you couldn't really separate the operation of the unconscious mind from these aspects of the libidinous aspects. And that was one reason, </s><s>[INST] you know, sex, [/INST] sexual, sexual related. Uh you know, drives Carl Young who was his, you know, uh you know, contemporary, that's one factor that led to them separating was, you know, Carl Young felt there was a lot more to the unconscious than this libidinous aspect of it. And he saw it as a much more complete uh alternate representation of the conscious self. One that may be reflected a whole range of different motivations and desires and to properly treat it. One had to consider all of them rather than the ones that that Freud was </s><s>[INST] called Young chef. Thank you. Thank you for the high level of of images that sergei is pulling up for people who are just listening. He pulled up a as a quote from Sigmund Freud's mm your mom quote uh Freud. Uh so the the shadow that carl young shadow encompasses everything, not just the desire to have sex with your mother or sex period. If you look at those two folks [/INST] on </s><s>[INST] mass, I mean, there's a kind of it's almost like a technique full philosophical exploration of human mind human motivations. It's not even like necessarily, it's also doubles as a methodology for helping people. But it's almost like a it's a kind of philosophical method. [/INST] Right? This is the fascinating thing about, about psychoanalysis. And and it even though it's it's, I would say mostly not considered a treatment today. It persists for a couple of reasons. One is it's it's thought that it gives people some insight. But second, there's been a huge influence on literature and philosophy on art and the the opening up of discussion about what was below our conscious mind was so, so fertile and the implications that it it sort of reverberated and still does throughout all these different realms of human endeavor from our different artistic, uh, you know, experiences that people have can be colored by this, this concept of the unconscious. Now, the other thing that was interesting is is is this distinction, you know, what, what are the parts of the unconscious And and so there were these ID and ego and super ego subdivisions that, you know, that that Freud for example, would would would talk about them and the the ID was the primary the primal drives that an infant would have or that a very young child just warmth and feeding. And then later the, you know, the sexual or libidinous aspects. </s><s>[INST] And for Freud, the later happened very quickly. That's the controversial thing about him. I think I guess he thought like even Children had sexual desires that they're like dealing with contending with. So it's the full thing, hungry, wanting to eat wine, to poop wine to have sex. [/INST] Yeah. And he was extremely focused on that on on that aspect. But then there was then there was this the super ego which brought on these later sort of moralistic uh uh sort of codes of conduct and and that of course was very often in intention. But all this could play out subconsciously. And then the ego, this third aspect was mediating and for its conception mediated this tension between the different parts. Now, I think that's interesting. I will say that in some ways it's maybe unnecessary from the perspective of modern neuroscience to divide things up that way from the, you know, the moralistic drives and the primal gratification drives in some ways. They're all drives. And maybe they're even all primal drives. You know, the the moralistic drives, they're they're taught and they're taught in ways that ultimately relate back to survival. And you could even say selfish aspects of of health and life for the self and family. And so this is uh I don't I think it's maybe an artificial distinction. The concept of the unconscious is very valuable and very interesting. But these categorizations of ID and super ego may not map onto neurobiology in any particular way. If there's a town hall of of competing drives and desires and there they inter relate to each other. They involve different aspects of the of the brain and the history of the person and actions and choices come out of the result of that overall, you know, shouting in the town hall. </s><s>[INST] So in some sense, carl Young was to step into the direction of liberating yourself from such harsh categorizations. Do you think? I mean, you have Daniel Kahneman with System One and System Two, there's just these very compelling categorizations of the human mind that seemed to be sticky in our Mhm. In the super ego, no. Uh in the you know, the how we talk about these ideas and so on, do you think those are helpful or did they get in the way, is it some kind of balance in terms of deeper understanding of how the mind actually [/INST] works? You know, it's from the from modern er science. Uh whenever we seem to get closer to addressing a question like this at the level of cells, it seems to get farther away and I'll give you an example of what I mean by that. So one thing I'm doing in my laboratory and many people are doing is we are listening in on the activity of cells, neurons in the brain of mice or rats or fish or monkeys. </s><s>[INST] Individual cells, [/INST] individual cells exactly of which there are, you know, in our brain many billions. And when we do and we try to predict what action will be taken by an animal to address this question, where does the choice arise? Where does the impetus to make a particular selection of one action versus another action? Where does that start in the brain? If you're recording, listening in on the activity of cells all across the brain, where is the earliest spot you can pick up a choice being made? Well, </s><s>[INST] that's so awesome. [/INST] Yeah. At one level you might think how excited would would young have been to see this or Freud or the early, you know, psychoanalysts to see where this starts. But it's not so simple because an emerging theme in very recent neuroscience literally over the last few years is that things sort of all start together all across the brain. And so you can be recording from the cortex this rim of cells at the surface of the brain or you can be recording deeper in a structure called the striatum which is a little older, it's more tightly linked to to action and then structures called the thalamus, other parts of the brain. And if you record from these, these all sort of represent the action and the choice more or less all at about the same time very close. And so you can't point to a particular spot and say, here's where the choice or the action originates. It's </s><s>[INST] finding the free will of neuron. It's [/INST] relevant to that question. Nobody is close to being able to point to such a thing. </s><s>[INST] Well close is a relative term and nobody what I what I tweet today, all generalizations are wrong. So including this one, let's actually talk about that sort of the study of individual cells. If you could linger on your sense that as you get closer to that understanding, it feels like you're getting farther away. Why is that? Because that that often is the feeling until you're actually there. So, so like, you know, you see that that's when I'm running and I know there's only a mile left, it just feels like that mile is just getting longer and longer. But eventually you finished. So maybe we're getting close to cracking open these like beginnings of a sense, like we'll talk about consciousness or these very difficult big questions about the human mind, where do they start [/INST] your right to say we shouldn't generalize or make absolutist statements. But I would say right now the reason things are looking even harder to crack than we had initially thought we now have the data streams that we've wanted for so long uh in terms of activity patterns all across the brain at the level of cells we can literally see what cells are doing immense datasets. You know, we get these are, you know, time series of one individual cell with you know sub second resolution and you can collect this from, you know, enormous numbers of cells across the brain. So very rich data sets that we wanted for a long time. And yet having these has not led to an understanding of truly where actions initiate. Um in terms of of regions or locations, I </s><s>[INST] ask you a few questions on that is the answer. High level question by your intuition is the answer within the data Or do we need different kinds of data? So we should also say that when you collect data about the brain there's like the richness of information you're collecting, but there was also a human doing stuff um like and information. So static information about the human and dynamic information about the human and you can get them to do different stuff and you can still like different humans. And that's part of the collection of data aspects. So like when you're collecting data about the brain, there is some truth that you can, you know, in machine learning, like annotations, like supervised learning, there's some true things you can hold onto before you look at the full rich mess complexity of the human mind soul. Given the data you've looked at, do you think the answer for the for the origin of free will in the human mind can be found? Well [/INST] 1 1 amazing thing is that uh nobody's nobody's found it. But we have these rich data sets and and then there's a conundrum which is uh is it in the data? And we just don't know how to look at it. Maybe we don't know the right scale, the right projection to make of the data, the right way to interpret it. And here's where causal testing becomes very valuable because then instead of just passively observing, well, here are here the activity patterns and then here's the choice made by the animal. Mm hmm. As we've gotten more powerful at reaching in and causing things to happen in the brain, turning up or down the activity of certain types of cells. Or defined populations of cells and seeing how that affects actions. These causal perturbations have turned out to be very valuable. We're just now getting to the point where we can apply these in very wide swaths of the brain at cellular resolution. And so we're going to be able hopefully to make some headway on this question with with causality and those. That's the one thing that optogenetics provides us this way of using light that we developed to control cells. This is an untapped relatively untapped at this broad brain wide scale. And hopefully we can get there in the near future. But I would say that the answer maybe maybe in the data uh but we don't know how to find it. </s><s>[INST] Well, this interactive element like where you can cause stuff that's really powerful because you get to I mean uh as opposed to collecting data passively you get your collecting data actively. So can you maybe describe one of the many things you're known for? One of one of the big things is called optogenetics. What is it? [/INST] Optogenetics is a way of of causing things to happen. It's a way of determining what what actually matters in terms of the activity of the brain. For the amazing thing is it does sensation, cognition, action and what it does is it provides activity. It's a way of playing in if you will activity patterns into precisely defined cells and the way we do it is pretty cool. I think it's you know right away there's a problem if you think about how do we do this, how could we play in well defined activity patterns and provide a stream of of activity into this cell and that cell and that cell but not these other cells, </s><s>[INST] but just for context. We're talking about the brains of mice, uh monkeys, humans. And then the goal is to try to control accurately the behavior of a single neuron and then to be able to monitor single collection of single neurons. To then say well to draw some deeper insight about the origins. First of all the function different parts of the brain, different neurons, different kinds of neurons but also the origins of the big things, the the the flap of the butterfly wing that leads to an actual behavioral thing. [/INST] So if you could Exactly, so if you could turn on or off the brain or parts of the brain or cell types or individual cells at the natural rate and rhythm and timing of normal brain activity, that would be immensely value because you could determine what actually mattered, what what could cause complex things to happen and what could prevent complex things from happening in a specific way. But right away you've got a problem if you want to do this and and scientists, neuroscientists have wanted to do this for a long time, Francis crick of double helix of DNA fame, he wrote a Famous paper in 1999, he got interested in neuroscience later in life and he said what we need in neuroscience is a way that we could turn on or off the activity of individual types of neurons in a behaving animal. And he even said the ideal signal would be light because it would be fast, it could penetrate through the brain to some extent. And he had no idea how to do it. He said this would probably be very farfetched, but it would be a good thing. </s><s>[INST] And so that's what you're actually saying is like if you want to do this kind of thing and then it's you imagine like how do I get inside the brain, it's pretty difficult, it's [/INST] pretty difficult. And then even once you get in, it's hard because all brain cells are electrical, all neurons are electrically activated. And so if you wanted to use electricity as what you were putting in, you won't have any specificity at all. If you have an electrode a wire and you put it in the brain and you send current through it, all the cells near the electrode will be stimulated. </s><s>[INST] That's like trying to control fish by spraying them with water. [/INST] Yeah, Right, because there's already a lot of electricity going around anyway and you're adding more, but there's no uh specificity even among the different kinds of cells either. Because all around the wire that you've put in there going to be so many different cells doing totally different things, many of them in opposition to each other. We know that's one way the brain is set up. There are parts of the brain that where neurons side by side are doing completely different things and maybe even antagonistic to each other. So what do you do? How do you play in activity with any kind of specificity? Well, what you do is use what we found is what you can do is make some cells responsive to light. Normally no cells deep in the brain really respond to light. They're not built for that. There's no reason for them to respond to light in there, which is a great situation to start with because any light sensitivity you can provide to some cells will be a huge signal above the noise. And so that's that's what we do with optogenetics. We take jeans bits of DNA from microbes, single celled organisms and these single celled organisms like algae. They um make little proteins that sit on the surface of their cells that receive light, capture a photon of light and open up a little hole in the membrane of the cell and let charged particles ions like sodium and potassium flow across the membrane of the cell. And that these algae and bacteria they do this for their own reasons because that helps them move, it helps them make and use energy. But that's a beautiful thing for neuroscience because movement of ions charged particles across the membrane of the cell is exactly the kind of electricity that neurons work with. So if we can take this bit of D. N. A. That encodes this beautiful protein that turns light into electricity from algae. And if we can put it into some neurons but not other neurons which we can do using genetic tricks. Then you've got a situation then you can shine on the light and only the cells that have the gene and then are expressing the gene Will be the initial direct cells that are activated by the light. And so that's the essence of optogenetics is is the ability to do that we get that initial specificity that you could never get with an electrode. 1st </s><s>[INST] of all, let me say that this is um recently got uh Alaska prize for this. It is a brilliant idea. Um So I talked to um Andrew Huberman who's a friend of yours, friend of mine, um not to jinx things, but he believes that he deserves the Nobel prize for this. So um I do too, but what my votes anyway, the thing is, does it doesn't matter, prizes will be all forgotten. All of us will be forgotten when the cool ideas. Cool idea is a cool idea. That's a really powerful idea. [/INST] It's actually the the origins of it. You might be interested in our, even our our very deep, there was a botanist in ST Petersburg named Andreas Simonsen in 18 60 </s><s>[INST] six. He [/INST] published a paper on the single celled green algae and he was the botanist who first noticed that they moved in response to light. These are tiny single celled algae that have flowed jealous so they swim through the water. And he noticed this, he was a botanist and he published this. It was as a paper, you know, he wrote in in german but he published in the french journal and he was doing it from ST Petersburg. So it was a very international effort. But you have to go back to 1866 and that I just would like to highlight how far back the that discovery goes is back to Andrei from Benson and this is a, it highlights the value of of just pure basic science discovery </s><s>[INST] that always originates somewhere in the eastern european bloc. But I don't think he expected the splicing of genetic material from the into the human brain. And [/INST] one of the cool things we've been able to do now with modern methods is to really study these these proteins. And so we we've discovered some of these proteins other other groups have as well. We've dived deep into their structure just like the double helix structure of DNA was uncovered with X ray crystallography. We used the same method, X ray crystallography to see how these beautiful little proteins work? We re engineered them for all kinds of functions. We can make them instead of responding to blue light, we can make them respond to red light, We can speed them up, slow them down. We can make them with genetic engineering, we can make them have different ions flow through them. And so it's it's this convergence as you said, like the botanist in 1866 couldn't have predicted what we could do with this. Uh and the fact that we've been able to discover how these beautiful proteins work and then apply them to neuroscience is really a thrilling story. </s><s>[INST] Is it possible to achieve scale do you think with this meaning Like grater. Like what is the progress of the next 50 years, 100 years looks like in terms of the precision and the scale of control using light? [/INST] It's going so fast, It's hard to predict. I'll give you a sense of it though in You know, first paper, you know, we published in 2005, that was just in cultured neurons by 2007. So that was in a dish by 2007. We had it working in behaving mice By 2009, we had a pretty general so we had methods to really make it a versatile method could be applied to essentially any cell. By 2012 we could get to single cell resolution. We used light guidance strategies to target individual cells in the brain of a of a living mouse By 2019 We were able to control up 20-50, individually specified single cells in the brain of a mouse. And in ways that specifically changed its behavior that could buy us its decisions one way or the other. In fact we could take a mouse and without any visual stimulus at all, we could make it act as if it had seen a particular visual stimulus by playing in using the single cell resolution optogenetics, A specific pattern of activity into 20 or 25 individually specified cells. That's 2019 to your question of scale. Now, in 2022 were controlling hundreds of individually specified single cells over all the visual cortex of a mouse. All the part of the of the of the brain that that is the initial direct target of the incoming information from the from the retina. </s><s>[INST] Are you constrained to a specific types of cells currently like you mentioned, long range is easier. Is there constraints on which cells? [/INST] Now? There there really isn't now that we have this individual cell guidance, we can target any individual kind of cell very reliably. Um and so now it's your question of scale, uh how far can we go? Well, um things are moving quickly. It's it's hard to say we we can access individual cells across the entire brain. Now If you look 10, 20 years in the future, you know, I think well we'll surprise ourselves. But the fact that we're already able to to cause specific perceptions to happen in specific actions means we're essentially where we want to be. And now it's a matter of just uh you know, more experiments, more discoveries. But the basic principles are clear. Now the basic capability is there is </s><s>[INST] there a pathway to doing the same for humans? [/INST] Optogenetics is primarily it's a discovery tool that really is well suited for use in mice and rats and monkeys because it's uh it involves putting in a gene and also delivering light and those are two things that you can do in human beings but you'd want to do in a very careful way Now that that said there is actually just less than a year ago um My friend button RosCA in Switzerland. He did the first human optogenetics therapy And he published this in the journal Nature Medicine. So about uh 10 12 years ago he and I published a paper together where we gave him one of our uh after genetic tools, one of these light activated um regulators of ion flow. Um these are called microbial options by the way options and he put one of those into an extracted retina from a human being who had died. And so it was a cat of eric retina. And he was able to show that optical control in this in this paper uh was able to turn on or off individual cells in the human retina. So that was a while back. He spent about 10 years of going through all the regulatory you know hoops and hurdles and going through primate studies. And finally he was able to take a human being with a retinal degeneration syndrome. So someone who is blind in both eyes and he gave a one of these options into one eye of this human being who was blind. And with the goal of conferring light sensitivity onto this retina that was not able to see light. And he was able to to make this person see through that I so he took a blind person and the blind person could could see you know could reach for objects selectively on a table. Uh And he published this in Nature Medicine and it was, you know, that's an amazing thing. Um do </s><s>[INST] you know the title of the pit, what's his name again? [/INST] Rosca R. O. S. K. A. </s><s>[INST] And you look up the nature paper, [/INST] Nature Medicine, </s><s>[INST] Nature medicine. [/INST] So that that's sort of proof of principle. Now the retina is very accessible. It's near the surface. You can use natural light or you can use brighter natural light. I'm myself, I see optogenetics as as a discovery tool. It's a way to figure out the principles by which the brain works and how it operates </s><s>[INST] partial recovery visual function in a blind patient after up to genetic therapy. So he went to the full process of doing primate studies and then and then going well that's dedication and that that's really exciting to see [/INST] as as beautiful as that is. And I'm glad he did all that work there. There are so many other ways that optogenetics could help with therapies once you know, the principles than any kind of therapy can become more powerful once you know, the causal cells in a symptom like in lack of motivation or inability to enjoy things or altered sleep or altered energy. Once you know, the cells that are causal then you can make medications that address those cells. You could address brain stimulation treatments that might address those cells </s><s>[INST] also diagnosis. [/INST] You need to be </s><s>[INST] very effective systematic way of diagnosing at least providing you rich data to some of these deep questions about schizophrenia, about bipolar, all of those kinds of things that are the tools are low resolution currently for determining which night, the degree to which you have a thing and whether you have a thing at all. [/INST] Yeah. And exactly. And so the hope is, you know, that's a that's a great example of how you can cure or you can, you know, provide some relief for a symptom of a person who has a serious degenerative disease. But but the principles are what what we're after. And that's why I spend, even though I'm a psychiatrist, even though I still see patients, I'm not myself trying to drive any clinical trials in the lab I'm trying to discover. And then any kind of therapy could result from that. What </s><s>[INST] do you think about? Ah my friend Ella musk and his efforts with neuralink. So this is another um There's a lot of things to say here because there's a lot of ideas under the umbrella of neuralink. But one of them is to use electrical signals to stimulate. And then you also record you collect electrical signals in the brain at a higher and higher resolution and you go uh implant surgically the methods by which you do the stimulation and the data collection. So it's possible for the ideas of optogenetics to play well with this. Um and then we can even zoom out outside of just neuralink. And just the whole idea of brain computer interfaces. What what are your thoughts? [/INST] Well I think the engineering that they've done is actually pretty cool. So I I like the </s><s>[INST] robots. [/INST] Yeah from the from the design perspective and it wasn't it was a design approach that wasn't being taken in academia and it's great that they did it and I think it's it's pretty cool. Um So I'll say that also there are many ways that you can record from many thousands of neurons. Um and that's not the only way. It's a it's a very interesting way we and others are using um brain penetrating electrodes that actually get quite deep. The whole structure of the brain is very interesting. We that there's the surface cortex where it's the most recently emergent part of the brain and evolution, mammals have, it, reptiles have something a little bit like it but it's not really the full thing. It's a this is a very recent thing that's what we can access with some of these, you know like the neuralink approach and with some of these short electrodes, this part of the brain, the cortex is only a few millimeters thick. There's so much that's deep though that's so important. There's the striatum there's the thalamus, there are the parts of the brain that dr motivation that drive hunger and thirst and social interaction and parenting and and flight and fear and anxiety. All these things are there's so much that's deep that these surface approaches are not getting too. And so we and others are using these very long electorates that help us get deep and we can still record for many cells many thousands of cells. We can have multiple of these at once in the same animal. And so there's a diversity of methods to get to this goal. Um I think it's great that that people coming from, you know, a you know, outside academia will bring ideas that weren't being worked on at least approaches. They may turn out to be synergistic. These things work very do work very well with optogenetics because all these electrical recording methods, that's one channel of information flow. Light delivery is a separate, you know, more or less independent. There can be some some artifacts that happen. But if you're careful, that's another independent pathway of information flow. And we've done really fun experiments in mice where we play in patterns of activity with light and we record activity from all across the brain of a mouse electrically. And so using optical and electrical together is extremely powerful. So </s><s>[INST] like Opto electric brain computer interfaces, which by the way, there's efforts on the computing side to build Opto electric uh servers. So like what you have both electricity. So, because optics is really interesting. Light is a very interesting method of communication. That's like you said, our thoughts going on in many ways, he doesn't have some of the constraints of Ben with that electricity does going through wires. But you're able to but it's less ability to control precisely at scale. So like there's challenges and there's benefits. And having those two interplay is really, really, really fascinating. Especially one obviously on the other side of your signal is a biological mush mush mushy mesh. [/INST] Well, the mushy mesh is kind of interesting because we have there are problems with light light scatters in the brain so that the photons don't just go, you know, literally through they whenever they hit an interface between fat and water lipid and water, they they bounce off in different directions. And so you can come in with all the resolution you want. You could play in an incredibly detailed high resolution pattern of light, but the photons start scattering quite quickly and by the time you've gone a couple of millimeters deep you've lost almost all that fine spatial information. So, but we've developed workarounds, the longer wavelength light you use, if you get into the infrared, there's less scattering. You can use two photons methods or three proton methods where the photons have to arrive all together at the same time. You can put in fiber optics, we developed these fiber optic methods in 2007 where you can access these deep structures with, with fiber optic methods and you can put many of these fiber optics at the same time in an animal. We've used a holographic methods. three D Holograms to play in hundreds of individual cell sized spots of light and we can and we can change those quickly. And so there are a lot of tricks, a lot of interesting optics engineering that has come together with neuroscience in a pretty exciting way. </s><s>[INST] Well that is engineering to it was just super, super, super excited I shouldn't mention because I remember mentioned Elon. Um I recently got for the first time ever got Covid. Um how did I go so long without the finally so I'm all vaccinated and everything like that. And so I got uh because I think he he mentioned it publicly so I can mention it but I won't mention anybody else involved. But hanging out we all got together and got Covid. And the interesting thing about maybe you can comment about this. So I was only sick for like a half a day. I got a fever of like 104 just went, oh and then crashed and then I was, now maybe I'm just seeing the silver lining of everything. But afterwards I have like a greater clarity about the world. Maybe maybe I just it was so uh maybe so intensely the mind fog kind of thing for such a short amount of time. But the people weren't involved were also reporting this. It's kind of interesting because like because I do know like the immune system uh is involved with the brain in very interesting ways. So like the human mind also incorporates all these other, it's not just the it's not just the nervous system. And I just wonder because everyone always says, no, not like everyone always says like Covid does all these bad things or whatever the diseases or whatever the virus. But I wonder like I hate to be a steven pinker on this. But like I wonder what the benefits of certain diseases are if you're able to recover like what is there some like uh again, don't want to romanticize it. But if your system goes to some kind of hardship and you come out on the other end, I wonder sometimes if there's a greater um maybe killed off a bunch of neurons that didn't need anyway. And they were actually getting in the way there were the hater neurons. Your [/INST] inner critic that I was talking </s><s>[INST] exactly, killing [/INST] off your critic. </s><s>[INST] Well, you [/INST] know, there are mechanisms for what the potential mechanisms for what you're talking about. There are there's actually been a fair bit of research on post covid neurological function. Actually, my wife Michelle Manji, who's at stanford, she's done a lot of this work, Akiko Iwasaki at Yale has done a lot of this. But what what they found is that there's a loss of Myelin, this is the coding of those long range projections that go from one part of the brain to another. Myelin is this sort of insulator that coats these long range projections and makes the impulses go faster and more reliably and there's altered ah function of the myelin producing cells and altered Myelin in the case of Covid, they've looked in both mouse and human brains and but of course it could be very idiosyncratic. Many people have cognitive problems post covid. And you're you're definitely aware of that. So many people report this persistent brain fog inability to function, but it depends on where the inflammation was. You know, maybe the people who have dysfunction post covid, they had a global effect. Maybe you lost some of these projections that were restraining you in some way and and these plausibly exists? And it's known that there are cell populations in the prefrontal cortex that actively restrain deeper structures from expressing what they do? And it's it's theoretically possible that you had a lucky uh </s><s>[INST] Somebody has to get lucky right. [/INST] Somebody has to get lucky. </s><s>[INST] Why not? Alright. If we can actually go back to this idea of trying throughout the genetics to find origins of when the wave first starts. Origins of a decision origin of the idea, origin of maybe uh consciousness or the subjective experience or origin of things in the mind. So one thing is carl young um Is there a God neuron is there a belief neuron? Is there through this methodology of optogenetics. Can you start getting like where a belief begins or an idea begins and especially looking at the strongest of our beliefs maybe beliefs of love and hate, but religious belief into some something like really grand on the grandest of scale [/INST] neuroscience and uh neurology point us a little bit uh we don't have an answer to that, but </s><s>[INST] a lot of these questions I'm gonna ask you, there's no good answer, but there you're you're providing the tools that give us hope to find the answer one day [/INST] and we have early clues. So for example, when patients with epilepsy have experiences of religiosity as part of their seizure or the aura before their seizure very often those are in the in the temporal lobe, in these parts of the brain that are at at the side. Uh and so that's initial clue. There are also parts of the brain that's are involved in the definition of the self and defining the borders or boundaries of the self. And we know this, this is some experiments that we did in my lab, there's a part of the brain where if there's a rhythm ah of a particular type, you can cause a separation of the sense of self from the sense of the body. What's normally bound up and unitary. We normally think of ourselves and our body as is pretty tightly bound up together. Those can be separated. It turns out we can't take that for granted and there are certain conditions, certain patterns of activity in one part of the brain called the retros plentiful cortex, where you can actually separate those two out. And so if you think about these very big questions you know what is where are the origins of religiosity? Where how do we define the boundaries of who we are relative to others and to the world? How do we link ourself to our body and how can that become separated? These are actually believe it or not now accessible uh and rigorously and quantitatively. So we did an experiment with optogenetics where we provided this abnormal rhythm to this particular part of the mouse brain and we saw this separation of detection of a stimulus and caring about it. </s><s>[INST] So that's that's like stimulating something about the Miles brain that affects these neurons that give the conception of self. So you're able to disassociate the experience from the impact of the experience unto you. [/INST] That's right. Exactly right. </s><s>[INST] So like these are the goals of meditation. Uh these are the goals whenever I get drunk pretty much effective. I mean that's not a scientific statement, just an experiential anecdotal one. Um Also psychedelics seek to this uh to attain this kind of state. That's so interesting when [/INST] you mentioned psychedelics, you know D. M. T. And five M. E. O. D. M. T. These these create this religious experience this connection people describe them as a strong connection to God. In theory these are accessible with modern methods now that we have these rich recording methods we can explore what are the precise millisecond resolution cellular resolution, brain wide manifestations of these altered states. </s><s>[INST] So like you could look at an altered state like an on D. M. T. Recorded across many people. And then from there see where do these experiences originate in the brain in terms of single neurons And then how do they how do they propagate and interact with everything else? And if there's some kind of common signal, like how do you narrow down the set of neurons that are responsible for a particular experience or for a particular behavioral effect? [/INST] Here's where optogenetics is so useful because anytime you give an agent like you know an agent like ketamine or PCP which we used for our dissociation experiments that I was mentioning. Or you have a psychedelic LSD or or D. M. T. For this altered perceptual state. If you if you give either of those these change everything across the brain. Okay so just the fact that you maybe give them to a mouse let's say or eventually to a human. Yeah you won't know yet which sells to home in on as the causal players in all this just by recording the activity. But then what we found is that optogenetics providing a causal pattern of activity guided by what you see can let you test hypotheses and we saw this rhythm with ketamine and PCP for dissociation. And then we said okay let's test what's causing. We came in and provided that rhythm. We tried a few different things, but only one of the causal tests we tried actually caused the behavioral dissociation. And so that's how we home in on what it actually means. </s><s>[INST] Is it repeatable once you see the cause. So like that's one definition of causality is like you try and he repeats across different mice and all that kind of stuff. And so you could do that for D. M. T. You can do that for like the really fascinating mind expanding. Uh Thank you, thank you. So the meme for people just listening, this is again another disagreement to and Floyd and and uh uh Carl young religion and spirituality. This is the I guess the ring scene from uh Lord of the Rings religion, spirituality, Freud says, cast it into the fire and destroy it. Carl jung says no. So so for people who don't know, Sergei is the Slavic Lord of the meme. Thank you, I appreciate that. So what we're talking about. So there is, I mean I think a connection between GMT and religious experiences or some of these psychedelics, do you think it's possible to sort of stimulate religious experiences? So religious experiences are one of the most deep kind of experiences. And so here you could first understand where they originate, how they propagate through the brain and then to stimulate them. [/INST] And so this is and these that can happen </s><s>[INST] and people [/INST] who had no predisposition. Um you know people who who are, you know, as agnostic or atheistic as you'd like, they can have these, they can feel connected to God in these, in these states. Now, to be clear, I'm not advocating these, we don't know what's safe in human beings, but we </s><s>[INST] definitely not [/INST] yet, but we definitely can do these experiments in mice. And that was already very productive and understanding dissociation. So we can already imagine making headway on these methods. And then, you know, I had a and this, this does map onto the non psychedelic human experience. I had a patient, it was actually described in the book projections. This was the patient that's in the mania chapter. The bipolar chapter here was a guy who had never had a psychiatric illness or symptom in his life. He was retirement age gentlemen, and nobody in his family either. So no family history, no personal history of any psychiatric illness. And he had never been religious particularly before either. And certainly no, no passionate, you know, uh type of religion, But he not through any psychedelic or drug. He he had a stressful experience, actually, a post 9 11 change in how he was thinking. And he was pushed into a mania, a manic state revealing that he had bipolar never before known in this case in this person. And his mania. His elevated state in bipolar included this profound religiosity. He, which he had never had before. And he was he was preaching and elevated you know vigorous way to his family and so this this state can be created. And people even late in life who had no predisposition for it and no even without a neurochemical. So there's the causality of that is very interesting to explore how did the the manic state unleash this religiosity. But you see that in other realms of of psychiatry to O. C. D. Can manifest as religiosity also. You can take people who never really had a a religion never played a powerful role in their life. But then when they're obsessive compulsive symptoms become severe they can manifest in this. And </s><s>[INST] I think I'm in that group so I'm I'm bit O. C. D. We have. There's I think there's a subreddit it's when there's oddly satisfying things. So there's certain things that are really satisfying to my O. C. D. In my mild O. C. D. I think it's pretty much a religious experience. So I understand that there's it's it's it's not direct. It's at least rhymes. So maybe can you speak to the circuit is probably uh desperately scrambling to pull up oddly satisfying. Thank you. People can check it out themselves. It is as as the subreddit promises oddly satisfying. Um Can we talk about bipolar. They may be depression. Well let's talk about. I mean I don't know if there's um a nice way to discuss the differences in the full landscape of suffering that's here. But maybe what is depression and what are the types of depression? What kind of depression have you seen an experienced and researched and how can people overcome it? How can humans overcome it and deal with it, live with it and overcome it? [/INST] So, this is my clinical specialty. I see patients in the my outpatient clinical work with treatment resistant depression so very hard to treat severe illness where medications haven't been been working. I also see patients with autism spectrum disorders. These are my two clinical focal areas. But then I do emergency room work as well. But the depression, why do I focus on that? It's so uh one feels tantalizingly close to helping people who are suffering so deeply. That's and that's why I focused on it is these are people who </s><s>[INST] there [/INST] may not even be anything situational that's that's difficult or challenging in their life. You can have people who seem to have have everything that you would want. Every objective measure of the life is fine and yet they can be ah, just hit with this unstoppable hopelessness and inability to see into the future, discounting of the value of their own action. Anything they can imagine themselves doing seems worthless or they are unable to enjoy things we call this an Fredonia. There's no reward, no pleasure, not in food, social interaction movies books, anything that they would enjoy, positivity gone. They can have a profound negative internal state, psychic pain and these things can seem, and in the severe cases are inescapable. So what is going on? Why why is this state part of human existence? It's got a strong biological genetic link. We know that um it's been linked to certain genes, certain regions of the chromosome and twin studies. There's a clear genetic link. It doesn't explain everything, but it's a big part of it. And genetics are a strong contributor. And although you can have depression without anything terrible going on in your life, the symptoms can be made worse by stressors, by trauma. And but at a very deep level, there's nothing we can measure in a person objectively. So we don't have, there's not a known chemical, not a known structure that's different, not a known brain activity pattern that we can pick up with. Eeg a lot of people are exploring this, But right now we have no objective measures. All we do is talk to people and we elicit these symptoms, We explore them, distinguish them from other possible causes. And then what do we do? Well, we have a range of treatments. We have medications that can help people do help people, but not everybody. Um, and if they don't work, then we can go to brain stimulation methods, we can do things even like electroconvulsive therapy, which is a very effective, but it's it's a sort of the final thing we go to in the end. And so we have treatments they work uh for some people, they don't do everything we'd like. But here's the problem is at a very deep level. We don't understand really what's going on in the brain. We don't have a physical interpretation of the problem. We have all these symptoms, but we can't yet point to a set of cells or a set of circuits or an activity pattern that is causing major depression. This disease state, per se in human beings. </s><s>[INST] Why do you think you can't yet, from an optogenetics perspective, is it because there's so many possible causes, is there's so much, so many things involved. [/INST] So, I think the answer is there are many things involved and all these different symptoms that I've mentioned, those we can study and those we can fix the individual symptoms and we can do this in animals to be clear. So in a mouse, for example, we can instantaneously and precisely turn up or down the motivation of of an animal to overcome a challenge. We can turn up or down its ability to to to be motivated by or we think experience reward from, from uh situations or actions. We can increase its apparent energy level. It's it's it's it's it's drive to meet challenges. We can turn up or down social interaction, all these individual features of depression, individual symptoms. We now can point to exact projections and cells that are causal in mediating these. But we don't know is why all these different symptoms show up together in major depression in the human disease syndrome. And that's the mystery. It's sort of in other fields of medicine, you know, someone with congestive heart failure who comes into the clinic, they have very different symptoms. They have shortness of breath and they have swollen feet, Okay. Couldn't be too more different across the body sets of symptoms. Neither one obviously related to the heart, but they're both happening because the heart is not working as a pump. Okay. And, and now, thankfully, in cardiology, we understand these disparate symptoms that seemed totally unrelated, can be completely understood because there's an altered pump action of the heart. That's that's what we are hoping for in in psychiatry. And in the study of depression or any disease, these different symptoms, the inability to enjoy things, the hopelessness. What's the what's the unifying </s><s>[INST] unifying? I mean, is there is there some truth to that, the Tolstoy quote, that all happy families are alike in each unhappy family is unhappy in its own way. So, basically, yeah, I mean, this is the human condition. And then, basically, that might, you know, the physicists longed to find the theory of everything. It isn't understanding depression essentially require you to really have the big theory of everything for the human mind. [/INST] I think we it would certainly be nice to have that. A theory </s><s>[INST] that don't [/INST] get me wrong, I don't think we need </s><s>[INST] a of the of the century, it would be nice. But it's also a good question if it's possible. [/INST] Yeah. Yeah. Well that that I have some thoughts on two but but to your to this specific question um I don't think we need a theory of everything. I think there will be unifying principles principles we can get to. But even shy of that if we can we can treat symptoms and that's a big step and as you say different, different unhappy families are different, different, unhappy people are different. If we have somebody who comes to the clinic and I see someone with a profound and hamdaniya as one of their main symptoms inability to enjoy things. And if I know based on optogenetics work and animal work that a particular medication can treat. And Adonia even if it doesn't fix major depression and everybody if I treat that one symptom in that one person, that's a good thing and and so we don't need the theory of everything and we don't even need the unifying principle to help people with insights that come from optogenetics. </s><s>[INST] How much does talking help for diagnosis and for treatment would you say for depression? [/INST] It's a big part of what we do every good psychiatrist is should be pretty adept in these verbal communications and talk therapy as part of what they do. Um I give medications I deliver brain stimulation treatments but big big part of everything I do with every patient is talk therapy because it works so well together with these other modalities. Even alone, it can help people with moderate or mild depression by itself. People with severe depression. People with other psychiatric illnesses that are severe. You don't wanna do talk therapy alone, it's not going to do it, but it still is crucial to do together with the others and it's it's it's critical because it's part of how you reshape cognition, you know, complex activity patterns and you won't get to that with a medication or brain stimulation treatment. </s><s>[INST] Do you have advice for people who suffer from mild forms of depression or feel as they might both for those people and you have advice for people who love the people who suffer from depression and want to help. [/INST] One of the incredibly frustrating things about depression is the very nature of it makes it hard for the people who suffer too get treatment because they are hopeless. So they don't think treatment will help, they have low energy. So they're not motivated to participate in treatment in many cases. They're sometimes they're actively suicidal, that certainly doesn't help. </s><s>[INST] They [/INST] have all these things that seemed to prevent treatment from being effective. So the loved ones, that's where the loved ones are so important is helping them overcome these barriers to treatment, the motivation, the safety and the insight that's critical uh and particularly for the severe cases um for the mild cases where people still have, you know, have some insight motivation and energy to get something done. There are many things you can do uh exercise is extremely important in mood maintenance regulation of sleep and getting sufficient and regular enough sleep is very important and talk therapy can be helpful in those mild and moderate cases. Just looking at cognition is looking at patterns of thought. Then people may have fallen into where they catastrophizing, where they spiral from small things into big things. A little bit of talk therapy. 10-12 sessions can help people identify those patterns they may have in themselves that are taking occasional negative thoughts which everybody has and magnifying those into more persistent negative states. Once you if you work at this it's kind of like homework, this is what we call cognitive behavioral therapy, it's very structured, very organized, you work hard, it requires insight and motivation and you have to be motivated. But if you are then you can identify these triggers that send you down particular pathways and work to intercept them and that is amazingly very effective in mild to moderate cases. So </s><s>[INST] you're basically have to train yourself to see the world as a collection of triggers and you have to first understand like collect the data like basically see every experience as a thing that creates a follow on emotion of feeling and like I've learned this you know like on social media where like early on you know like all of us um you know, I'll say something, I kind of respond to negativity with negativity and then you observe the results of that and then over time you think, wait a minute this thing that I've been doing where when somebody says you suck and you say no, you suck, that never produces the result. You thought it might and so might not want to just don't say you suck back. And I do this through a lot of things in life. I'm very fortunate to not suffer from depression, but I, first of all, I have had and have people in my life, we do and also, you know, all of us have depression who don't suffer from depression, have depression out, like it's always knocking on the [/INST] door. </s><s>[INST] So you have mild uh I mean, uh if you're very careless with the triggers all around you, then you, you're just, I think all of us have the capacity to really suffer from that kind of chemical or psychological or philosophical existential crisis. [/INST] But then it raises the question, why are we built this way? It seems like it doesn't make sense, right? Um, and here's where some of this thinking about where we came from ah as the human family is is kind of interesting, but it doesn't make sense that somewhere on that spectrum, that it's good to detect that there's an array of adverse forces out there in the world right now at this moment and to withdraw to, to hunker down to not fight, not strive not try to meet the challenge and outwait these negative forces that are present out there and that makes a lot of sense. And all animals that have been studied in one form or another show this even the worm that I mentioned earlier, C. Elegans with 302 neurons, it can effectively give up in challenging situations. We've done this with zebrafish, tiny little transparent fish. You can give them a challenging situation and they will give up. But then if you stimulate a a couple of very specific brain regions, in particular ways, you can motivate them to overcome the challenge. And if you inhibit those regions, they give up much more easily than they would otherwise, you can do this in mice, you can do this in rats. So this is an ancestral conserved pattern to detect that things are pretty bad out there and to conserve energy to hunker down to wait out the storm </s><s>[INST] says use unfortunately many of our maladies have useful roots in our like contribute to our survival. So both depression and motivation have uses in the pink. Sometimes it's nice to just shut the hell up and huddle with the penguins versus for some unknown reason, Venture out on your own into the mountains like a David Goggins type character. So what's the difference to you between. You see patients between sort of rigorous um psychoanalysis, I don't, I don't know if you consider we like talk therapy and psychoanalysis, Are they neighbors? Are they overlapping [/INST] their their neighbors? Uh psychoanalysis is it's um they're relatively it's not nearly done as much as the talk therapy like the cognitive behavioral therapy I </s><s>[INST] mentioned. [/INST] Uh the psychoanalysis is is a little more niche now and partly because it's it's not the data isn't um in terms of actual treatment of actual therapeutic effects data not as supportive as for cognitive behavioral therapy but it's still interesting as for insight people, a lot of people still do it to gain insight into themselves and in general it's a good sort of conversation starter. Those methods, you know, they're good for getting things out. You know we don't focus on dreams typically these days in psychiatry but they're great conversation starters, They're great ways to get things out if people have. Uh And and so we like to use those methods just to get the ball rolling sometimes get people to open up a little bit. But the actual treatment that tends not to involve these psychoanalytic approaches where you are really probing the unconscious mind and its manifestation through through dreams. Um for example as as the as the goal, that's not the goal. Modern talk therapy, we're really focusing on treatment how to get people to feel better. </s><s>[INST] See I used that as a conversation opener, the Freudian thing where I try to delve at a bar of the deep sexual desires in a person's subconscious and I find that opens up possibilities very quickly now. Um what's I mean this is a silly sounding question, but what's the difference between cognitive behavioral therapy and conversation? So um because I personally as a fan of conversations as a fan of just, I like listening to podcasts um versus like audio book, I like both but they're very different and I like conversation, I like it makes me personally very anxious. So I like to be the listener like like a third wheel, like overhearing a conversation kind of thing. But it's a really powerful method for humans to explore each other's mind. Just raw conversation. So do you think it can be more productive to be very systematic about it? Or is conversation itself the art form of of helping each other understanding each other and helping each other. [/INST] There are forms of talk therapy that are essentially conversational or they much more approach pure conversation. There's there are there's a befriending therapy, there's interpersonal therapy. These are these are approaches that are purely talk therapy but they're not as structured as cognitive behavioral therapy, cognitive behavioral therapy as is their manuals. There are guidelines, you can almost go through it in a very cookbook e way. There's there's homework that you get done. So it's in its fullest form. It's very different from these more conversational strategies but what's interesting is sometimes people compare them and so you'll see almost like randomized controlled studies um comparing cognitive behavioral therapy with interpersonal therapy for example and they both can work and actually in some studies they look comfortable. Um so there's to your point conversation and insights that come from conversation if done well if done artfully can be as powerful. </s><s>[INST] This reminds me of Robin Williams. So I have to ask you several questions here on that. But 11 of my favorite movies is Good Will Hunting. I don't know if you've seen it with Robin Williams. So as a psychiatrist yourself, can you do a deep analysis of this other famous psychiatrist which is the movie character played by Robin Williams in Good Will Hunting. Is it just a caricature between a psychiatrist and patient relationship or is there some something to you? Was that was moving about his ability to connect to this obviously struggling young kid? I [/INST] think you've hit on the key thing there, which is the depth of the connection if if there's uh two powerful connection. Yeah, that can impair therapy because it could impair open communication if if someone, if a patient has a seize the role sees the relationship in a particular way, like in a friendly way maybe or like a parental child type way that can cause problems because then what they choose to share what they choose to bring up is selected to be appropriate for that view of the relationship. And so I and many other talk therapists actually prefer uh not to let things get um not let the connection get that deep. You want to have trust, you want to have a therapeutic alliance, we sometimes call it. Um but it's got to be enough of a blank slate that the patient is not consciously or unconsciously constrained in what they choose to share. And so great movie, great actors, all good, no complaints except realistically the relationship should be a little more arms length than that. </s><s>[INST] But let's pretend it's real life. Sometimes can't you leave a little bit of yourself in the interaction with the patient? I mean it's another human being. [/INST] So there's a balance and actually you do need some of it because let's say this person is having challenges, interpersonal challenges in their life. The best way to notice what those are and to identify them and to work with them is if you can elicit some of those problems in in the office in the therapeutic interaction and this is really powerful as long as you're alert to it, aware of it and you don't let it get out of hand, This transference we call it is when you transfer in between the current therapeutic relationship and external relationships that the patient may have had with others. </s><s>[INST] And [/INST] so if the therapist starts to feel and inter feeling like anger, let's say So let's say you have a patient who is stirring frustration in you or even in extreme cases anger. The best thing for the therapist to do in that case is to recognize it. And to realize that's probably being stirred by other people in the patient's life and that could be the source of a lot of problems. And so instead of trying to wall it off and say, oh I shouldn't be feeling that I'd better be a better therapist instead and recognize it and use it and help the patient that way. And so you've got to be a human being. You've got to be a person who feels you've got to be open </s><s>[INST] but being controlled and be aware of it if I may, I just want to read them because it's my favorite scenes. Probably one of the greatest scenes, one of the greatest scenes in movie history because Robin Williams does a single take. [/INST] So </s><s>[INST] this is a very interesting interaction between those. So, um well, and I'm sure this is a common interaction um maybe with a therapist and a patient. Maybe with the father and son. Where will the young character? Their young brilliant mathematician and Sean is the therapist, the older therapist where Will looks at a painting that Sean painted and then does a like a deep critical analysis of the painting that basically, you know, describes um pretending as if he can understand another human being completely. But just looking at their painting and then Sean gives this whole speech that contrasts of raw intelligence and the wisdom of experience and Sean says single take. He says, you've never been out of boston, right? And will says, nope, all this in a sexy boston accent by the way. Uh, and then Sean gives the speech. If I asked you about art, you'd probably give me the skinny and about every art book ever written Michelangelo, you know a lot about him, life's work, political aspirations, him and the pope, sexual orientation, the whole works, right. But I bet you can't tell me what it smells like in the Sistine Chapel. You never actually stood there and looked up at that beautiful ceiling seen that? If I asked you about women, you'll probably give me a syllabus of your personal favorites. You may have even been laid a few times. The language cherishes beautiful, but but you can't tell me what it feels like to wake up next to a woman and feel truly happy. You're a tough kid. If I asked you about war, you'd probably throw Shakespeare at me, right? Probably not. But let's say once more into the breach. Dear friends, but you've never been near one. You've never held your best friend's head on your lap and watch him gasp his last breath looking to you for help. If I asked you about love, you'd probably quote me a sonnet, but you've never looked at a woman and be truly vulnerable, known someone who can level you with their eyes feeling like God put an angel on earth just for you who could rescue you from the depths of hell and you wouldn't know what it's like to be her angel, To have that love for her. Be there forever through anything through cancer. And you wouldn't know about sleeping sitting up in a hospital room for two months holding her hand because the doctors could see in your eyes the terms visiting hours don't apply to you. You don't know about real loss because that only occurs when you love something more than you love yourself. I doubt you've ever dared to love anybody that much. I look at you. I don't see an intelligent, confident man. I see a cocky, scared, shitless kid. But you're a genius will No one denies that No one can possibly understand the depths of you. But you presume to know everything about me because you saw a painting of mine, you ripped my fucking life apart. You're an orphan. Right? Do you think I know the first thing about how hard your life has been, how you feel who you are? Because I read Oliver twist does that encapsulate you personally? I don't give a sh it about all that because you know what I can't learn anything from you that I can't read in some fucking book unless you want to talk about you who you are and I'm fascinated. I'm in but you don't want to do that, do you? Sport, You're terrified of what you might say? Your move chief. Well done. Sir. I know it's a movie that's interesting. Right? So some of that conversation is that some intellectual level 2? It's not just emotional. It's something, uh, it's like the reason I kinda connect with that is that's a lot of work for therapists. Like to really understand another cause he's, I mean from, okay, I know this is fictional, but just there's calculation happening. He deeply cares to say the words that the other person needs to hear. But also a little bit loses himself and the pride. But then catches himself again, switches from anger to uh, to connection [/INST] a lot has brought up there that you're right there. There has to be some emotion in the, in the therapist to care enough to keep going to keep probing to open up as he's doing so right. He revealed a lot about himself, his own vulnerabilities. But that gave him authenticity. He had to open himself up so that the kid would see the authenticity and open himself up in return. So how do you do that as a, as a psychiatrist or therapist? You have to be careful. You know, you don't want to do too much. But opening up a little bit does help. It does create a chance. You know, you're offering up something and that helps the patient come back in return and it gives, it gives you that that believability and authenticity. </s><s>[INST] Do you pay the price for that for opening it up. [/INST] You can um you </s><s>[INST] have a family, you have an incredibly like difficult research, like you're doing a lot of things in your world. I mean, it's the price you pay for like, [/INST] well this is one of the terrifying things about, about writing the book was was I I do open up in a little bit about my own personal life and my own personal challenges and that was a considered decision because I could I could have done the patient work and the science work and the and the history of the human family work and tied it all together. But but it wasn't in uh in an early draft, it was it was like that, but it wasn't, it wasn't real yet. It wasn't, it wasn't something that, that everybody could connect with. And I said then I realized, look, if I'm going to do this, Mhm. I've gotta I've gotta open up myself and then and then people can connect with me and see what I'm really saying. And so I did and that was, it was not something that I've gone in planning to do in retrospect. I learned a lot about myself. It was actually really, I think a good thing that I did, but it was scary </s><s>[INST] where the darkest places you've ever gone in your life. [/INST] You know, I had things haven't haven't always been been easy personally or you know, or professionally I had, I had moments, you know, I was effectively a single dad for for a while a number of years. And these came at probably the hardest, also professional life times for me too, the absolute hardest days of late medical school internship, you know, taking call, you know, getting up at three a.m. You know, surgery, uh, medicine rounds unforgiving environments and then all the while, you know, personal life, uh, you know, stripped down to the bare, um, and these were low moments. And then I was hit particularly hard by just experiences on on the clinical ward connecting to deeply with patients like, you know, a child with a brain tumor and feeling it too strongly and and those things when you get down to those lowest of the low moments, when everything is stripped away. And and there's there's only this, this raw core. Well, yeah, that's pretty hard. Those, that was probably the lowest moment. And you learn a lot about yourself in those moments, You know, what's what's left and, and then what are the, the, the roots out from there? And, and that's that's that can be powerful to to see in yourself. </s><s>[INST] Have you thought about killing yourself? [/INST] I have not, I have not, have </s><s>[INST] you seen that thought in the distance? [/INST] I am fortunate that that has not come to my mind and I have not seen even in the distance and I, and in some ways I've I've wondered if that's made me am I less effective psychiatrists? Because of that. I've been I've felt everything stripped away. I've been at the lowest of the low and yet, that that </s><s>[INST] there's still hope there's a light of hope still at the end. [/INST] Right. </s><s>[INST] So, you've never lost even for brief moments that [/INST] uh, I never did. </s><s>[INST] Well, I don't [/INST] know. I don't </s><s>[INST] know why there was no reason. You don't know, [/INST] no reason to feel help at that moment, honestly. </s><s>[INST] Uh, so it was just the light without [/INST] reason. </s><s>[INST] What wisdom do you draw from that time about? So, first of all, you said something funny, which is I wonder if it that is somehow not having thoughts of suicide limits your capacity to truly understand somebody who is having those thoughts. So, how many demons must the psychiatrist have in order to be a good psychiatrist? [/INST] You know, this is a really interesting question. I think everybody knows, and I can say this that psychiatrists can be a little unusual there. We we were we think about ourselves, right? We think about our brains, that may be one reason why we become psychiatrists, is we think, oh, that's interesting going on in there. What's that about? So, a little little introspective, little introverted maybe, and that's what can make us good when we're good. And but also that that may select for people who have some unusual aspects, but you don't have to have all of them, There's a lot that can go wrong in the, in the psychiatric realm. I think having some of those, some of it, but not all of it is enough. You get to see how low things can, can get, you can get a um, you get empathy from that even if the symptoms are not the same. Um, </s><s>[INST] just empathy for for struggle for suffering. [/INST] That's right. </s><s>[INST] Do you yourself have to practice observing triggers just as a human operating in this world? [/INST] I've definitely those, those skills that have come from from therapy, I've found I've found them useful. Yeah. If I noticed that, uh, we we've all been through experiences where we wonder, oh, I got really mad and that interaction, why did I get that mad, you know? Yeah, sure. Maybe I could have been irritated, but man, why did I, and and and then thinking about it and realizing, okay, you know, back up here, think about the broader context. Um, uh, think about what how that relates to, you know, prior events in my life. Okay. Yeah. So this is a thing for me, when something of this class happens, then it triggers me. So, going forward, I'm gonna be aware of that. Um, and I've definitely used that because it's you don't, you don't want to be out of control those emotions. You want to identify them. You want to know where they come from and you want to head them off as a, as a civilized human being living on this earth, trying to get along with other people, You want to understand those moments </s><s>[INST] return to Robin Williams for a second and looking at Robin Williams, the the actor, the outside the human, and because because you mentioned um for depression you can have everything going well and I think there's just famous cases of just public figures, because a lot of people know them where they they suffer quietly and it seems like from the outside perspective that they have everything going for them, that they're on top of their career. You know, two people that come to mind are Robin Williams and Anthony Bourdain. What insight do you have and why either of those taken why Robin Williams a comedian, one of the most jolly humans. Obviously there was always the darkness that he was channeling in order to present the happiness, but it feels like that that realness is only possible when you're deeply self honest and analytical and and then then if you're deeply self honest, you're going to realize that there's a lot of beautiful things about life that you can discover and if you do that, how can you possibly then take your own life and you go through all of these thoughts and I think a lot of, a lot, a lot of people really loved Robin Williams, which is why it was really difficult to see, how can even him, how can even Robin Williams take his own life. So I don't know if there's something to be said about the nature of depression from just looking at his case. [/INST] I think the action of suicide is not well understood. Uh it doesn't always, although often is correlated with depression. There are cases of suicide where there is not clear depression that that's in the minority by </s><s>[INST] the way, if I just like because you said it's so interesting action of suicide, because there's also thoughts of suicide and probably those that probably somewhat understood. But it's an interesting because you can think of suicide if you have suicidal ideation, you can think of that for so many reasons. [/INST] That's right. </s><s>[INST] And and the I mean, thoughts sometimes like painful thoughts, angry thoughts or thoughts in general, it can be very different. Like fantasies, for example, you can fantasize like sexual fantasies, you can fantasize, that was just for humor sake, wanted to mention stuff, but then people think I'm serious, I'm not gonna mention anything but sexual fantasies. And then there's, I know there's people have sexual fantasies and they don't want to actually do that in real life. That that that sexual fantasy serves some kind of purpose in imagination only. And in that same way suicide might serve a purpose and imagination only is very unlikely to lead to action. And yet there's other thoughts that maybe are more amorphous that do lead to action and that leap. Uh yeah, that boy, that's a fascinating that's such a philosophically powerful thought to not exist like that question. That's this is it's archer or camus camus. Whether the myth of Sisyphus camus, who says like, basic question of why live good question. Yeah, [/INST] so that's a great question actually. And there are other related questions. Some people uh may have the thought of suicide, ah because there seems no point, there's no joy in life. That's one reason that some people can put forward. Sometimes there's an it's not just the absence of joy, there's an active pain and active psychic pain in some people and that the inescapable reality of that is enough to drive the thoughts of suicide. And then there are interpersonal and cultural reasons as well that can show up the but the act, this act of ending of the self is in all these cases, there's no real way to study this in an animal's no other animal as far as we know, that we can study has this concept of this is myself. The situation is not tolerable. Therefore, I will end the self, to our knowledge. This is not something that that that can be studied another animal. So it remains this, this uh very poorly understood action and in predicting it. So what do we do with psychiatrists? We have this challenge. People come to the emergency room, they say they're suicidal or their friends say they're suicidal or they've taken some action that didn't lead to death, what do we do? Well, there's a whole range of options. You know, was it a suicidal gesture in the sense of not intending death? Or was it was the intent death? And if it was the intent was death? What were the reasons are the reasons? Transient? Are they gone now? And what's the probability that it will be repeated? So we do all these things just to decide what sort of treatment should be carried out. But nowhere is there a deep understanding of the biology of the cells and circuits and activity patterns that underlie the end the action to end the self. It's a very it's so it's </s><s>[INST] this [/INST] frustrating thing. It's it's so timely. It's so common. It shows up in veterans. It shows up in kids, shows up in people at every stage of life. Mm hmm. And yet we're very bad at understanding it and were relatively poor at predicting it. And our tools are not very powerful. We can put people in a in a locked unit. We can give them care therapy for a while. At some point we release them. And there's only so much we can do. It's one of the most frustrating things and the suffering that is linked to suicidality. </s><s>[INST] But it is a decision and it is an action. And if you look at optogenetics, you should be able to one day sort of understand the dynamics of such weighty decisions, [/INST] the individual causes then if someone is an hedonic, if there is no joy in life that very likely is addressable by optogenetics, we know how to turn that dial very robustly in animals. The motivation to overcome challenges that we have some hope of understanding psychic pain. Internal negative states. We have actually a handle on that as well. There's a structure in the brain called the Habana and some links structures around it that seems to generate this negative internal state. That's it's active when a state of acute disappointment, acute outcomes that go wrong uh not as expected. Um uh you know moments of unexpected pain. Uh Daniela is there it seems it's active to report on internal negativity with its with its action. And so you could imagine strategies to target this brain structure that might have the effect of reducing psychic pain, reducing the negativity of internal states. That is a very concrete hope. It's precise, it's anatomical optogenetics has given us all the firm foundation. We need to go after that question. So I think there is hope if you look at the individual causes the individual symptoms relating to suicide </s><s>[INST] and then it's like a puzzle you put together the puzzle pieces by the way, I do think my husband Yola is very functioning very actively and I wonder if it's like because because you can also learn to channel these things right? Some of some of the things we suffer from. I mean there's degrees of suffering can be a source of progress and personal growth and development and all those kinds of things. Um what is it? Nietzsche suffered from stomach issues, you know, I wonder if he had written some of those things if if his stomach is all great. I mean there's, I kind of think that um a difficult life in some form you can get, you get to choose in some regard and some of you don't the difficulties you have and the ones you do have, it's nice to use if possible. It's sometimes it's nice to treat, sometimes. It's nice to, it's nice to use well, [/INST] the way you phrase it, I think you're using it, I could be wrong, but if you, you phrase it in this semi humorous way about your Habana, it seems to me that you're using that is a good effect now, but one never really knows what someone else's internal state is. As I look at you, I don't know the depths of what's going on and it's possible uh that that it's it's it's a much harder situation in their um yes, </s><s>[INST] so that I actually worry about this a lot. So I'm extremely self critical, like in the privacy of my own mind, which is an interesting thing when you get to meet the internet and the internet will tell you you suck. Uh but for for now now this is what I worry about and I'm very paying attention for now, it's really, I just have this like very negative voice, but that voice seems to be very useful for productivity and so I channel it, I just put it on the table and let that voice like talk to me. But I'm very, I'm like monitoring that voice because looking at Robin Williams, you know, you get older, your brain changes or like you're and and then that voice can now all of a sudden grow right? And then where you can't control as much, you have to be very careful with these kinds of, [/INST] you're very right about that. I so my my negativity, I have this uh I never think I've done enough is sort of where my my negativity comes from inside. I never think that I've, I've uh met the potential of the moment. I haven't done haven't, you know, made the most of the opportunities that are available still early. I haven't, you know, you know, progressed as far as I should and exactly as you're saying, that works for a while. But then what happens as you get later in life and there's less runway two, you know, fix that and then maybe maybe then maybe then the negative voices is a problem. But </s><s>[INST] also at that point the negative voice starts having more and more of a point when you're being, when you're being very successful, it's easy to be like, no, okay, well like because later in life you really literally just sitting there on a on a rocking chair doing nothing and then it's or maybe any kind of tragedy happens, loss of a loved one. The loss of a job loss. Or you get screwed over in some kind of um some kind of way, I don't know those. And then all of a sudden the negative voices just you and the negative voice for days and days and days. And [/INST] so I don't know to go back to the example of Robin Williams. I don't know what was going on inside him. I don't know the nature of his internal state. Was it a was it active psychic pain that </s><s>[INST] may have mentioned me? I interrupted, just say that Sergei posted an examination of Robin Williams's brain tissue suggested that he suffered from quote, diffuse L. E. W. Y. Lewy body dementia uh lb de depression is a symptom of L. B. D. And it's not about psychology, it's rooted in neurology. This is awards from his brain was falling apart. [/INST] Lewy body dementia. This is a very interesting neurological disorder where, among other things, there are there's neuron death. Indeed. So you've got frank in your own loss. It's not just a matter of some long standing psychic pain but you've got a progressive loss and so clearly you've got a situation where he could have finally reached a point where the balance that he'd worked out between negativity and positivity was disrupted due to loss the wrong cells died. The wrong projections were cut by the Lewy body dementia, certainly dopamine neurons die. And Lewy body dementia, those are neurons that give rise to more much of the feelings of reward and pleasure that we experience among other roles. So clearly in his case, there could have been a very concrete cellular neurological issue that was progressive and pushed him to that point. </s><s>[INST] But what were you uh were you about to make a point about broader that if there isn't another neurological degeneration? [/INST] Yeah. So in his case, not knowing that uh it could have been simply that, let's say he had an internal psychic pain state. And it was in he was in sort of a compensated mode for much of his life able to generate enough joy from his comedy and his social interactions. And and then but eventually later in life, you know, the those things drop away. The balance shifts. You get tired of fighting the pain for that long and then so you've got this time dependent non stationary T. That happens. And then the same symptom becomes no longer tolerable in the end. </s><s>[INST] What is autism? What do we know about autism? [/INST] Human beings exist on a spectrum of how social we can be. And this is pretty interesting actually scientifically, but also very important clinically, there are hyper social states where people are almost to social, There are chromosomal deletion states where people have instant affinity and bonding and and rich, deep seeming connections with people very verbal on the other end, people with autism spectrum disorder are not able to keep up with social interactions. And it's a, it's a spectrum, some have mild to moderate difficulties. They may have an inability to understand what the next thing to do in a social situation is, but may have perfectly good language abilities. And as you progress further along the spectrum that gets more and more severe so they can't make eye contact because it's too overwhelming to think about what has to be done next if a person looks in a particular way. And then as you go farther than language and social communication themselves breakdown. So there's no reciprocity, there's no shared enjoyment and that this gets very hard then as you get to this far end of the spectrum where there's really an absence of social cognition at all and, and social bonding. So why why does this exist? What is it? Uh, it's very genetic, as I mentioned, it's, it's one of the, you know, top three or four most biological in the sense of most genetically determined of the psychiatric illnesses. It does have these interesting positive correlations, slight positive correlations with intelligence and education and the reason for that is kind of interesting to think about. Is there something good about it, just like, or at least at least part of the spectrum is there's something good about it, just as we were talking about for depression, as you could say for mania, as you could say for schizophrenia. And here it's kind of interesting to think about the the underlying science of what it means to be good at a social interaction. The someone who's very good at a social interaction is incredibly good at dealing with unpredictable information is able to handle this torrent of information coming through rapidly changing model of the other person and of the interaction and their model of you. Your model of them. With each word that changes with each new bit of information that comes in through the conversation. Each bit of body language. All this is rapidly changing and some people are able to keep up with that fire hose of information perfectly well. But that's a special brain state to be. And that's working with unpredictability. That's the uh the only way that can be done is most likely by constantly running models of what the other person might be about to say. So, you know, you can't stop and think, oh what does that word mean? What did that shift and I contact me? You know, what do they mean? Together there has to be some advanced work going on where you're predicting what's going on if you're to keep up with a rich and fast social interaction now on the flip side there are brain states that maybe don't have to work so fast that are extremely important, still dealing with something that's not moving or that's predictable, still complex, like uh, you know, mathematical proof or a very complex arrangement of geometrical shapes, a large number of individual non moving things. There's a possibly a way of being that is particularly good at dealing with these static unmoving or predictable situations and less so with these rapidly changing social situations. And so the way I conceptualize autism is these are people who whose brains are not so good with the high bit rate, unpredictable information but may be quite good at given enough time given the the grace to work with the system to look at it from different angles to take different perspectives with the confidence that it's not changing in between perspectives. Uh, that's a brain state. That's valuable. It's something that is probably has contributed to a lot of the success of the human family. Being able to design something. Be able to consider the all the different contributions to a static, predictable uh system. </s><s>[INST] So what does it mean in a sense is, um, there's a spectrum that has identifiable characteristics about the way people deal with dynamic information often expressed itself as like social. That's right, dynamic information. But [/INST] you critically your use of the word often there is really, I think smart because it's not just social interaction that is a challenge in autism. And so many people conceptualize it purely as a social dysfunction uh disorder. But it's really any unpredictable information. That's a problem that's a challenge for for people on the spectrum they react very uh negatively to unexpected sounds even if not social sounds unexpected. Lights unexpected touches. And so it's really unpredictable information that is in my view the core problem with with the processing and autism not just social social just shows up because it's so unpredictable. </s><s>[INST] Yeah that's so interesting. I mean I tried to not to think about that stuff. Um I'm afraid of thinking disorder about disorders and things like that because just like I don't like sort of economics or game theory only be careful with it because it whenever you have a category or a model it's too easy to just uh for everything. I mean it's the O. C. D. Thing. I like models too much. I like categories too much. The moment you acknowledged yourself we'll have an eating disorder for example or something like that. As opposed to just being a, well I'll just I'll just leave it at that for my own critical understanding of myself. Let's just say I don't know how to moderate eating fruit. People make fun of me. They think all fruit is fruit is healthy. I know I don't well I don't know how to moderate anything but even even fruit there's apples and cherries. It is a nightmare. Anyway. That's such a psychiatrist. Things a very interesting. Um But but there's characteristics and i it's it's interesting to think about, like for example, I have trouble making eye contact. But actually, as you said in now, it's not that I'm shy at all in that sense, it's literally I'm getting way too much information is distracting me. Like I need to just close my eyes so I can like all the things that people seem to be able to do in parallel. It's just you just asked me a question for me to think about the answer to that question. I can't have all this cool rich visual information coming my way. That's literally because I often close my eyes to think it's not because I'm afraid of something whatever. It's just like too much information happening here. [/INST] Well, that's a beautiful description. It's it's amazing that that is how you experience the the eye contact aspect. I think that's I mean, you've articulated what uh you know, captures it for so many people, which is that it's overwhelming. There's just too much information just coming in through the eyes and </s><s>[INST] to keep [/INST] up with it to know you're going to be expected to keep up with it, first of all. So there's that that aspect, you know, you've learned socially that there's going to be an expectation if you're making eye contact, people are gonna think you're keeping up with it and you don't want to because you want to focus on other things and make progress in other dimensions. Yeah. And so that then there's a strong desire to look away or to close the eyes because it's it's it's it's overwhelming. It's a distraction and it's gonna cause errors of of understanding. </s><s>[INST] And of course our eyes, that's part the way we use our eyes as part of the human communications. Have to be aware of that, of that, that element of it. So, yeah, I mean, but it's fascinating. You should be aware of your own self and those, those little characteristics, whether it's uh, whether it's classified on some aspect of the autism spectrum or just in general, whether it's eating, whether it's depression, whether it's um even like schizophrenia, that would I hope we get a chance to talk to you a little bit. Yeah. But there are those things are all made up of different character symptoms and characteristics and you use them as a superpower. I suppose this is the best we can hope for in mild cases, I guess. [/INST] And I do think both brain states can't coexist at the same time the way of dealing with something unpredictable and dealing with something predictable. Those are different ways of being here is a huge opportunity for very creative model building in theoretical neuroscience and linking that to these data streams were getting across the brain that we talked about earlier, these immense datasets of activity across the brain, </s><s>[INST] here's [/INST] where I think there could be a real convergence of theoreticians and experimentalists to say, okay, given what we know about wiring of the brain here is what the brain state is likely to be. That deals well with unpredictable information. And here's the brain state that deals with predictable information. Here's why they're incompatible, at least at the same time. Here's why you've got to be able to detect which state you should be in. Here's how you could switch between them. Here's the kind of cells that you would predict almost like predicting the Higgs boson. Here's the kind of circuitry that I would predict should govern the switching or might make one state too sticky, too hard to get out </s><s>[INST] of, right. [/INST] That is a huge opportunity for an interaction from the theoretical and experimental side together. </s><s>[INST] Make one stay too sticky. The sort of measure the stickiness of the state and how to lessen the stickiness, Get some oil in the machine. [/INST] Yeah. What would predict the kind of oil that would work well, </s><s>[INST] uh, what in your practice is, um, treatment or advice for people on the autism spectrum. [/INST] So right now, there's no real medical treatment. There are behavioral treatments that are most effective early in life. They make sure people don't fall too far behind if you're not interacting socially, you create this, you know, vicious cycle where you fall farther and farther behind because you're not interacting. And these therapies which are applied early in life, therapists work with the kids train them to deal with these things that otherwise would be aversive to them, teach them how to predict things and interact and that has a big effect, but it's behavioral therapy. There's no medicine that works. There are ways of reducing individual symptoms though that sometimes come along with autism and those do respond to medications. So you can, you know, one thing very often, my patients with autism are very anxious because they live in a world that they have a really hard time predicting what's going to happen. And so they find, and some of these are high functioning, you know, Silicon Valley types who, you know, they may make, you know, great livings, but they're very unhappy because they're on the spectrum. They don't understand how social interactions really work. They're very anxiety provoking because they don't know what to say. They don't have any clue how anybody else knows what to say. They're constantly worried, they're going to say something that's completely inappropriate. And so they're very anxious and I can, I can treat their anxiety, it doesn't touch the autism per se, but I can help them with their anxiety. </s><s>[INST] What I just talked about eye contact, I am richly, even with the eyes closed and all those kinds of things. I'm richly experiencing the world and it's not like you're afraid of the world or you're not able, I don't know what to do. No, I know everything. In fact, I know way too much. There's so many cool options, like at any one moment, there's all this stuff happening and it's all beautiful and at any one moment you can do anything you want, you can take off your clothes, you can punch that guy over there, you can run away, you can go in for a hug, you can say something profound and deep, or you can say something generic or you could use so many things you can say, and then and then it'll go, it'll unravel in all these kinds of ways in this moment. Could be completely life changing or it can be mundane and meaningless and all of those options before you at any one moment. [/INST] And so it's, it's </s><s>[INST] amazing and overwhelming. If you allow yourself to think about it, which [/INST] uh whatever </s><s>[INST] exactly like unfortunately with chess, you have a few set options, dimensional constraints, there is unlimited possibilities and unlimited beautiful things happening all around you. So I don't think there's a kind of sense that somehow you're limited in your, in the, in the places of uh in the way you can see the world and how you can interact with the world. I am overwhelmed by the lack of limit that all of us should be. Have you looked around, you can do whatever the hell you want, nobody will remember you anyway, all of us will be dead. One day, you could do anything, you can uh I don't know, you can get naked and run around the city as long as you're not hurting anybody and it doesn't matter [/INST] Austin, </s><s>[INST] Austin exactly, it seems like uh, a to do item for anybody living in Austin for sure. [/INST] But, you know, the spectrum is an interesting concept because that is, you know, when I say, when I refer to the spectrum, I'm actually referring to, it's a precise clinical term, but you're right, it's been co opted more broadly and it is widely used and it can be an unfair categorization of someone who's socially and occupationally very healthy. And that is critical because we don't define a disorder unless there's social or occupational dysfunction. It doesn't matter what the symptoms are. I've had </s><s>[INST] patients who [/INST] are pleasantly hallucinating, so frankly psychotic but doesn't affect their lives. So I don't give that person as diagnosis because there's not social or occupational dysfunction. Same with any anything on this. You know, any of the diverse symptoms of autism spectrum disorder, if someone has them, but they're successful social and occupational, we don't say that there is a disorder, but then you're right that the concept of the spectrum does become a useful, uh, you know, pigeonholing, um, device, which is maybe not not the best thing. </s><s>[INST] Yeah, and I contact is interesting one is interesting one. I'm torn on it. I'm talking about the usefulness of eye contact because people kind of make fun of it. But let me just say one thing about eye contact and about life in general, it's okay to be weird, but like some people when you have your eyes closed and there's that weird what is happening to this creature. Like you see a weird creature on the side of the road, It's interesting. And you wanna, I mean the, the weird stuff, I'm gonna go back to Robin Williams with the that's the good stuff, right? He has that whole speech about him and his wife and what he loves all the little peculiarities, All the weird stuff and that like um let those flourish. [/INST] Let them </s><s>[INST] like celebrate those in yourself and not in some kind of woke way, but in some like very human way. This is what makes us, this is the weirdness. [/INST] I'm 100% on board with that. I, and I don't think, you know people who are happy and who have people in their lives who are happy with them. These are I think let let the weirdness flourish. Let the, let the all the different ways, members of the human family can be different. Let's see them all. That's one of our, that's one of the joys of being alive is seeing all the ways we can be human. And I think about it all the time. Why do we have all these ways of being human? Uh and even within one individual, you go through phases of life where you express different sides of your way of being, which is also pretty fun opportunity, right? You can go through phases where you're in one mode and phases when you're another mode and let that, you know, just let that, let that flourish to let the ways that you can be. You vary as well. I think that's important for people to, to explore </s><s>[INST] and I should because if you can address the, the uh, the internet, but I would like to sort of ask the internet to celebrate the, the, the weirdness of people. Like that's uh, it's, it's the robin Williams. Uh people call these imperfections but they're not. That's the good stuff for any one individual person. Find the weird stuff and celebrate it as opposed to what the internet often does was just find the weird stuff and criticize it because when you criticize the weird stuff, you're creating conformity which is another human thing. But that, that conformity creates a boring world. You want the weird, you want the crazy, that's what fun is made of. That. That's the foundation of humor and the, all the ways in which we deal with the, with the, with the suffering in the world, with the injustices in the world is like this like huge variety of weird. Um, yeah, I don't know. And that's what at the depth of psychiatry is like you wanna acknowledge the weird, celebrate the weird like step around it to find the particular aspects of weird that are debilitating. Like you said, they're somehow negatively affecting your ability to function in the world. As opposed to trying to shut it all down? Well on that topic, I mean, I'd love to talk to you about schizophrenia. What what is schizophrenia in um from your research and from your general understanding and what is the full landscape of suffering and wisdom that schizophrenia explores? [/INST] Schizophrenia is a state where there is a break from reality. Uh and so this can show up as we call them, the positive symptoms of schizophrenia. These include hallucinations, hearing something or seeing something that's not there. Usually auditory hallucinations, paranoia, people gonna have complex fears, delusions which we call fixed false beliefs. People get an extremely unshakable but completely implausible idea about something. Sometimes it relates to themselves, sometimes to the world. These we call the positive symptoms break from reality as we know it. Then there are the negative symptoms that come with it and these are progressive, these are flattening of of emotion as we call it. So it's starting to express less and less positive emotion, ending more in a neutral or flat state. Thought disorder, inability to work with complex patterns of planning or thinking. So you can't make plans, you have poor working memory, you can't keep track of where you were in a conversation in a sequence of actions. So poor and impaired working with the thoughts of oneself and then these these positive symptoms of break from reality? Okay, now, why does, why does this, why did these come together? What's the neurobiology of it? Again, we don't know, schizophrenia, extremely genetically determined. If you look at the numbers could be upwards of 80% genetically determined. Um 1% of the human population around the world. It's it's universal. Okay. It's not confined to any one culture, not even really biased and one, you know, culture, another about 1% around the world and has this progressive quality to it untreated. So it's very interesting. There's a break that happens. We call it first break when someone experiences their first disruption of reality, they can have a completely typical life up until that point. So you might have a and I've seen, you know, just heartbreaking cases of like this like this in the stanford emergency room where the kid has come there has been extremely, You know, high functioning in that sense of academic achievement and athletic and interpersonal and then comes to college. Usually in men it's it's around 18, 19. When the first break happens some terrifying paranoia hits or some auditory hallucinations start they're getting screamed at by a voice in their head. So devastating with women, comes on. Also often a little later, sometimes in the 20s and it can be progressive if it's not treated, it just progresses and progresses. The voices become overwhelming. The delusions and paranoia extend and expand. I thought the negative symptoms particularly become more and more severe. So one can't even maintain thoughts in any sort of ordered fashion. Um and then eventually uh you know, can be fatal, can lead to suicide. It can lead to erratic behavior that leads to accidents. Um Now it can be treated. There are medications that help uh fortunately they have side effects. So they're not perfect, you can have movement problems and uh actually a whole host of different side effects that come from the medications. But we can help people now with, with schizophrenia very, very significantly. But the amazing thing and this is emblematic of where psychiatry stands. We don't have the deep understanding, just like with depression, we don't have that heart as a pump level of understanding that we'd like to have with schizophrenia despite it being so biological. So genetic in in its nature. </s><s>[INST] So is there a way once way to return to the other side of the first break? So when you have a break with reality is the way to kinda stitch it together. [/INST] So some people that that works. Um But we don't really know how. So medications, anti psychotic medications we call them. They block a particular neurotransmitter receptor called the serotonin two A receptor. And they modulate dopamine as well. And other neurotransmitters. Um These can take someone who's actively hallucinating, actively paranoid, put them back in a completely normal state and some people stay that way indefinitely. So you can bring people back from from that back to the other side have it stitched together more typically, you'll end up in some intermediate state where there's a symptoms are reduced powerfully, but there might be still something there and you've got a drop down and functioning that may be persistent for a while. But concepts what physically is going on. One idea is that it's communication Within the brain. one part of the brain is not able to tell other parts of the brain what it's doing. And so the auditory hallucinations are very interesting in this regard. They often have this conversational inner monologue like quality as we're walking along the street. We may have an inner monologue thoughts about what's going on. If we see somebody we don't like, we may have a thought. I wish somebody would punch that guy, something like that, or maybe I should punch that guy. But these are so far below where we would ever, you know, act or even think of acting. But they're just things that come up and and in people with schizophrenia, those inner thoughts that inner monologue is not recognized as the inner monologue of the self. And so it's it's perceived as something coming from the outside or from inside, but from another </s><s>[INST] entity, another [/INST] another. I thought </s><s>[INST] you meant like another room inside the same building [/INST] inside </s><s>[INST] there. Yeah. [/INST] And so that that's so it's a it's a it could be conceptualized as a communication within the brain problem notifying what's another part of the brain what's going on and there's some evidence consistent with that. </s><s>[INST] I don't know if you can help with this, but I sometimes I've been talking to quite a few homeless folks recently. Just that's what I do is I hang out at night um, and talk to interesting people. And some of them and I've known people in the past who suffered from schizophrenia and some of them like self will describe as as as that as something they suffer from. And they seem to understand something deeply about this world. I don't know if it's correlated or or maybe it's it's another aspect of like, depression, all those things that I've encountered in my own life is maybe just the struggle and the suffering has taken you through a life where you think deeply about life, like there's like self reflection that society forces on you because it's a disorder. Some awesome kind is it interesting? I guess my only sort of anecdotal observation is people who suffer from schizophrenia seem to be very interesting and very thoughtful in the nonlinear way about the world. [/INST] I've noticed that it's not always positive. Uh they're the unusual ways they view the world. It was, but it's always interesting. It's all that </s><s>[INST] could be conspiratorial thinking [/INST] to like, </s><s>[INST] but like the the theories they have about the way the world functions. It's often very well read, which is also interesting because they're almost like looking for helpful answers from somewhere. [/INST] And </s><s>[INST] so there, you know, there might be citing some very interesting literature and then using that. Um there's a stickiness in their mind to different models of the world and trying to make sense of that world. And those models could include conspiracy theories. [/INST] They're very attuned to complexity and they come up with unlikely explanations, which is one of the things that makes them, it makes it hard for them to function in the in the world is how unlikely their explanations are. But but you're right, there's a depth of consideration of the complexity of the world and a concern about it and a work uh an impulse to work to understand it, that is actually quite refreshing. Um but you know, the first case in the medical literature, uh, there was a classical schizophrenia, there was a patient named James Tilly Matthews who I had this uh he sketched out for his doctor the experiences he was he was sensing, and he drew himself as a, a cowering figure on the ground, controlled by a loom, a weaving device that was sending threads, long threads, projections across space from the loom to him to his arms and to his body and controlling him from afar. Uh and he called us the heirloom, a loom in the air. And it was such an evocative thing because, you know, this was the start of the industrial revolution or mid and it was where, you know, really industrial strength, you know, looms and weaving devices were really kind of the emblematic of the most complex, powerful technological achievements of the time? And so that was the explanation available to him to explain how his body was seemingly moved without his volition. Uh, and these days, of course, people with schizophrenia will have more technology appropriate interpretations. They'll have a, you know, delusions of satellite or alien control or or beamed information very, very common to have this delusion of a government agency, you know, sending electromagnetic or radio frequency information to control their limbs. But it's the same thing, whether it's a thread from an industrial revolution loom or, you know, our f you know, radiation, it's the same thing just adapted to the to the moment, explaining trying to explain the world they live in, in their relationship to the world. </s><s>[INST] But unconstrained by sort of the thing that's socially acceptable, which is both refreshing and dangerous. I wrote down a question, why do we cry our tears a window into some depths that we ourselves don't know. I almost want to make fun of myself with that question? But you do talk seriously about crying in the [/INST] book. In fact, the whole first chapter really, really tussles with crying as a why do we do it? What does it mean? Why is it involuntary? It seems like a weakness, Right? It's because it's so involuntary and it's reflecting something true and inside at the level of the individual that seems like a problem, right? Wouldn't it be better if we could control it? If if we could not show that emotion when it's not useful, show it when it's useful. But it's not, it's it's largely involuntary. And so there's a value to it. I think as an honest reporter of a need of of hope and trail t at the same time, I am a human being, there's a frail a frailty to myself or my situation where I need social help. I need help from my community. I have hope that that is possible. Uh, but I'm not enough for myself. I need the community. That that I think is what the social signal of crying is. Now. People have studied crying. Uh, it's an extreme, you can you can quantify the extent to which the presence of tears on a face triggers reactions and onlookers and and you can show the same phase in the presence or absence of tears and show that to people under quantifiable and rigorous, you know, psychological conditions and tears are much more powerful at stirring the desire to help in viewers than any other facial feature, Which is pretty interesting that it's the it's the honest one that's also the most powerful, right? It kind of indicates there's a certain logic to our design </s><s>[INST] as [/INST] social beings that we have an honest report? </s><s>[INST] That's hard to uh hard to control. But is it, is it well understood what, how that connects to internal state of emotion? [/INST] There are long range projections that come. So where where is crying generate. This is the confusing thing about it so that we have a little tear duct, the lack criminal gland that leads to the release of fluid and ejects fluid. And it comes out. And those of course that whole system was designed to keep the eye clean to to wash out particulate irritants. So it's it's a long standing, as long as we've had eyes and have been out of the water. Uh in our evolution we've needed this sort of thing. So longstanding biological structure recently co opted, it seems by our evolution as social primates. Now, how could that happen? Well, the lack criminal gland is controlled by structures in the ponds which is a structure deep in our just above our neck, between our neck and our head and reflecting its ancient origin right as you go farther down toward the spinal cord. These are the more basic early evolved structures and and in the ponds. That's where breathing is controlled to your uh doctor uh contraction. And what we found with optogenetics. We helped sort this out. There are long range projections from fear and anxiety regions in the forebrain that project all the way to the ponds in and around those areas. The reason those are there we think is to regulate the respiratory rate changes. The breathing changes of fear and anxiety. So we know when we're in a state of fear and anxiety we need, we cope better if we have elevated heart rate, elevated respiratory rate, more blood pumping around more oxygenated blood. We're ready to meet the threat if it happens, all those cells are down there in the ponds to right next to the lack of duct, the tear gland neurons. And so almost certainly this okay fear, anxiety induced crying arose from a very slightly misdirected long range projection that was there to regulate breathing and a little twist, just a little misdirection, a little missing of one sign post to stop here and going on a little farther getting to the lachrymose gland neurons </s><s>[INST] and that's and we just have it that the peculiar sort of structure, neuronal structure that resulted in that that's that's that's what we're stuck with and then and ends up being in terms of social interaction. One of the more important, authentic involuntary displays of [/INST] interstate and </s><s>[INST] social communication. Oh yeah. Is there other stuff like that? I mean, do you Yeah, I mean the human face is fascinating as a display of emotion as a display of truth and lying and all those kinds of things. I personally, I mean we're all I suppose have different uh sensors that are sensitive to certain aspects of the human face. But to me it seems like the eyes are really important communication or something. You know I've talked to a few sort of girls about like Botox and stuff like that. It always bothers me when I guess guys can do this too, but like when women um speak negatively of, I guess you can call them wrinkles at the, at the tips of of an eye, but like to me when you smile when you wait, not wink, but like narrow the eyes to community, something that's communicated and those, that stuff is really useful human face and when it's gone that something is missing and a lot of little stuff it feels like and really it's almost involuntary I guess, but it's harder to describe as the presence or absence of tears. It's like something about this person you can tell they're not bullshitting [/INST] you. And so that was, that was what made presumably that, that tear recruitment so powerful is that just landed in this very high value real estate for social communication. If it had gone to, you know, there's a lot of neurons in the, in the ponds that control, you know, movement of large, you know, muscles, you know, elsewhere that would have been much less effective as a social signal than something around the eye. So it was however, that that little misdirection happened. It it landed in a great area for social communication and because it was coming from the fear and anxiety circuits that regulate that necessary involuntary change in heart rate and respiratory rate. It also was involuntary and that became valuable as a, as a truth signal as social beings. So very interesting when you think about the origins of the human family, origins of social structures and our ability and need to call for help when there's hope, but but need at the same time, </s><s>[INST] what is consciousness? So you're actually using techniques, I mean, even putting psychiatrists are just looking at optogenetics, you're trying to understand some of these deep aspects of the human mind and maybe this is a good time to return to a question you mentioned. You might have an opinion on if there's such a thing as a theory of everything for the human mind. Because surely answering of what is consciousness is as well, that's not sure. But it seems like it's a fundamental part of the human experience in the human mind and solving that question or the result in solving the bigger thing about the human mind. The flip side could be consciousness. It's just a few neurons that are generating some useful things that make us, it's like uh the the sense of self that you talked about in the in the mice, maybe it's a subset of those cells that are just creating a richer sense of self. And that's it. [/INST] So this is a great question all neuroscientists think about this and a lot of non neuroscientists to it's it's such a it's the reason a lot of people came to the study of the brain is to think about consciousness and not just being awake or alert, but really what's sometimes called the hard problem of consciousness, which is what is that nature of that inner subjective sense? We have not just information processing but feeling something about the information that what is that inner state of subjectivity, physically, what is it? And that's called the hard problem of consciousness. And it's not extremely well defined question. Everybody has sort of a sense of what it means. But </s><s>[INST] it's [/INST] such a hard problem because you run into paradoxes quite quickly, the more you think about it. And that is exciting. Also because it makes us think actually there's some fundamental, there's a big thing that we're missing. The brain is not just a collection of little tricks. There is a big </s><s>[INST] so that's your sense of it. Because like a flip side could be with optogenetics. You can there's an engineering question, can you turn consciousness on and off like a light switch? [/INST] Okay, so here here's where exactly consciousness frames the problem extremely well and it frames it the falling way. So I told you earlier that we can stimulate 20 or 25 cells in the visual cortex of a mouse and we can make it behave and we can make its brain act as if it's seeing something that isn't there, We have that level of control that we can pick out. 25 neurons play in activity and both behavior and in the brain it's as if it's seeing something specific. Okay, now let's do a thought experiment. You know, Duncan experiment. Uh and let's play this out. Let's say we could do the same thing for every single neuron in the brain of a human being. Let's say we had total control. And I could do something like I could show you a rich, deep color red and you could look at it and you would be aware that it's red, but also you might have some feelings about it. Some something would be stirred in you, some subjective sense as you looked at that rich color red. And then I would take away the visual stimulus. And I would in this thought experiment, I would using some hyper optogenetics. I would play in exactly the same pattern of activity in every cell in your brain For as long as it was needed, whatever, 15 seconds, something like that. That exactly matched what was going on when you were feeling that inner subjective sense. Okay, so in that thought experiment question for you is would you the feeling that same inner subjective sense stimulus is gone. Every neuron is doing the same thing because I'm controlling it. </s><s>[INST] There's a philosophical question there, I'm if you ask me specifically, I would say yes, most [/INST] people would say that because it's hard to say no right? </s><s>[INST] It's very hard to say if [/INST] every cell in your brain is doing what it was doing. What what else could be different? How could </s><s>[INST] well, most normal people would say yes, of course, philosophers would then start saying no, they're they're they're the ones that say um I'm I'm sort of two parallel and sorry if it's a bit of an interruption, but if there's, you know, if there's a robot that's conscious in front of you, if it appears conscious, then it's conscious. Like to me, uh of course philosophers again speak up and saying, well no, how do you know, it's conscious? Well, how do you know? Anything is conscious and sort of as normal humans, we tend to um lean on the experience versus some kind of philosophical concept. [/INST] So the great thing about the the what you just said, the turing test is it's very practical, if it acts conscious it is conscious, but I think that's limiting. I like the thought experiment, I think it's actually more informative. And so I'm halfway halfway to the to the conclusion there. But let's let's let's take it as your your answer was yes, that that you would be feeling the same thing. Okay, now here's where it gets fun now that every cell in your brain is knows what it has to do in the sense that we know it and we're providing it your brain cells don't need to be in your head anymore at all. Right. The only reason they're next to each other and the only reason they're wired together is to affect each other to stimulate or inhibit each other. But we don't need that anymore because Opto genetically, we're providing that activity pattern for as long as needed. We're providing the effect of the communication. They don't need to be connected anymore. They don't even need to be in your head. I could spread your neurons all over the continent all over the galaxy and I could still provide Same stimulus pattern over 10 or 15 seconds to all those neurons. And somewhere lex Friedman would be would have to be even though no longer existing as a physical object anymore, would be feeling that subjective feeling. And it's inescapable because it's exactly the same as the previous situation. </s><s>[INST] All the neurons have to be spatially like the locality constraint. There had to be specially close to each other. Uh And you're talking about light, Opto, which is funny because you know, like is the fastest traveling thing that we know of. [/INST] Maybe let's not put them all over the universe because we might get relativistic problems. Then let's let's just keep them on. Let's keep all your neurons, let's spread them over north America. Okay, and and let's let's play them out same pattern of activity and write. It seems absurd, right? There's no way that could be true. There's no way that that that lex would be feeling that internal sense of his neurons were spread all over North America and yet it's exactly the same as the previous situation where you said. Sure. </s><s>[INST] So [/INST] we've got a paradox. And and this is what makes </s><s>[INST] people say, [/INST] well, </s><s>[INST] yeah, maybe paradox [/INST] is the wrong word. We've got a problem. We've got a problem because it reveals that </s><s>[INST] there's [/INST] something big about those that internal subjective state that we're not explaining. And we don't really have a hope of explaining in the near future. But </s><s>[INST] don't you think we would still have that? It's just the word internal loses meaning. But don't you think we would still have that internal subjective state? Or is there uh if not, then where the heck is the magic coming from? Okay, well, I just think, [/INST] I </s><s>[INST] think they're one of one of the problems that I think we need to let go of is we tend to outside of the experience of consciousness. The hard problem of consciousness. We tend to think that we individual humans are really special, not the subjective experience, but the entirety of it, like the body that contains the things. So the local the constraint of all this stuff has to be together. And it's all mine [/INST] that </s><s>[INST] that's a very I don't know if that has anything to do with the mechanisms that are creating this. So and in fact, one really nice way to break through that is to either achieve either observe or create consciousness that spans multiple organisms, sort of like let's say it's not it's not an organism dependent phenomena that the phenomena can that's just a peculiar way it has evolved on Earth. But it's it's it's it's a phenomenon that doesn't have anything to do with the specific um biological system. Right? [/INST] So and we have different parts of our brain exist and sometimes create complex awareness. Is of things that involve different neurons that are distributed widely and that need to communicate with each other to form this joint representation in the state of consciousness. But indeed, why do they have to be in the same head? We don't know why that would be the case that they do. And so that's a huge unanswered question in the field, is what is it that binds the activity of neurons together so they can form a joint representation. And actually this comes back to the dissociation experiment we talked about before, where you can your sense of self becomes separated from your your body. Those things that were refused in a joint representation, the same concept, unitary, are now separate. And in late 2020 we published a paper in nature showing how this could be. We used optogenetics to dr this rhythm that ketamine and PCP cause in retrospect cortex. And we got different parts of the brain to be out of sync and when they were active, never able to be active at the same time, never able to form a joint representation at the same time. And so we've got a toehold into these questions, We don't have the answers. But </s><s>[INST] and that mimics the dynamics of academy and effects [/INST] exactly. Exactly </s><s>[INST] and you're able to find that kind of oscillation. Uh wow, wow, let's see if you can even greater and greater control with more control over individual neurons. And understanding like if you think of certain neurons that having some role to play in in the sense of self, you can play like an orchestra um that to create certain degrees of consciousness, degrees of subjectivity and thereby understand what is consciousness. But by having a very complicated lights, which essentially [/INST] that and here's the here's the challenges is the nice thing about the the thought experiment, is it it kind of highlights that we're going to hit a point where we're addressing some very, very fundamental questions. What what what allows the activity of two sets of neurons to become mutually relevant to each other? This is this is in some ways maybe the one of the deepest remaining questions in neuroscience is what allows activity patterns to become relevant to each other. Do they have to be in sync temporarily? Do they need to be uh is there some other quality that we don't know about that also needs to be present to allow ourselves to fuse together into a joint representation? </s><s>[INST] Just just so I understand because it it feels close to some very, very deep idea of. So there's a bunch of semi distributed signals going on in the brain. And you're saying there could be something like a theory of everything if want to exist is to understand why how and why signals close to each other start becoming relevant to each other. [/INST] What's wrong </s><s>[INST] as part of some very much bigger signal that they're producing, how they coordinate essentially. Um because it's very distributed, I mean that's a kind of within a distributed system, house order achieved. And this is a very specific kind of distributor system that is one of the most intelligent that we're aware of in the non universe in that would maybe be something also an understanding of the full conscious experience too. That this kind of coordination. How does the coordination between different neurons that are responsible for sense of self? How did they begin to form a big picture that we see as a human experience? That's really, really interesting. So uniting the small and I mean that's actually literally theory of everything, uniting the small, the sort of the theory of the neuron, um the functioning of the neuron with a big just the the the functioning of the entire mind. [/INST] That's right. And I think keeping a toehold in both at the cellular level of resolution and the brain wide resolution will be critical if you lose touch with either. I think you'll miss the big insight. So that's what we're trying to do. Keeping our keeping grounded in the cellular resolution. Trying to keep the broadest brain wide perspective and meet in the middle. </s><s>[INST] Do you think you'll see it in your lifetime, A major breakthrough in that dimension. I [/INST] have hope. I have hope. I'm I'm it's very hard to predict what will happen with with big things like this. If we don't get there, there'll be plenty of other exciting stuff. So it's okay. </s><s>[INST] But the other aspect of this whole thing is that your life is pretty short. So first of all, you can die in your day. I I tend to try to think about that. That ends up getting in any moment because it really, really can. And if not it will be soon anyway. Do you think about that? Do you think about your mortality? [/INST] I do, yeah, it's, it comes back to what we talked about earlier. You know, I never think I've done enough and it's relevant to that for </s><s>[INST] sure. There's a deadline. Do you think there's ever going to be a feeling where you sit back and you're really proud of yourself? [/INST] I hope </s><s>[INST] so. Like I've done enough. I've done everything there is like, like, you know, because the thing is a warrior has some number of battles in them and at a certain point, if you're deeply honest, it's like, well this that was a pretty good run as far as runs goes. That was [/INST] pretty good </s><s>[INST] and you can hang up your helmet and then girls drink some ale, listen to some music with the old lady, let's say I did pretty good. You think you'll get there? [/INST] I you know with something with nature always has surprises for us? We're always the curious mind is always after more. But </s><s>[INST] yeah [/INST] but biology gives us other rewards. You know Children and family, community And and one can feel good about those things. </s><s>[INST] Biology is full of rewards. But do you think about those rewards? What do you think is the why of those rewards? What's the meaning of life and this existence? What's um what's the why of biology? What does it want from us? Why are all these cells very busy putting together an organism that seems to want to just be in a hurry to do stuff and survive. But it also just doesn't it's not happened being survived like you said it's curious it keeps wanting to get into more trouble. Why? [/INST] Yeah that you know that were clearly designed for that right? This is were clearly designed to to ask why and to answer. And and that I think is I don't I don't know the meaning of all life. I think a meaning of our lives is that and you know this is the the aristotelian you know happiness. This is an organism is happy and animals happy if it's performing to its design right? If it's it's he was doing what it was made for. </s><s>[INST] Yeah. Well you have to understand what what's what's the design and ah you know who's the designer and what were they up to and how hard is it? You have to build the whole universe and does the design even know what the hell they're doing? Because you know maybe the designer built humans to find out about themselves. That's what I would do. Like if I had the power to build clones, I'll build a lot of clones and I will get him into different trouble to understand like what am I designed, what's this body designed to do? Exactly. And then and I disassociate myself completely from having anybody to know like that. I know that person. [/INST] I </s><s>[INST] mean I suppose you could do that in a single person's body by dissociation. You can you could but but I do wonder what if you if you look at earth as a collection of humans as the collection of biological organisms. It seems that we're busy doing something and it just seems too beautiful and too special to be a random a random experiment. It seems like it's an experiment that's cleverly designed. [/INST] That's right. </s><s>[INST] By by some forces of nature that are beyond our current understanding. And maybe that's part of our design is to keep asking why he said answer. I'm not sure that's part of the [/INST] design. The </s><s>[INST] answer. [/INST] No, </s><s>[INST] I think we're given just the sufficiently limited cognitive capability that we know how to long to to find the answer and we lack the ability to find the answer. That's basically a summary of your career. No, I'm just kidding. Um, and then we give each other Nobel prizes for for having even an inkling of a good step towards the right direction. Carl, you're an incredible human being. I'm I'm a huge fan of who you are as a person, who you are as a scientist, who you are as a writer. I just thank you so much. I'm so honored that you would sit down and talk to me today. It was amazing. [/INST] It's been incredibly fun. Let's do it again sometime. It's really great. Your, your insights and and wit and modesty are are really uh quite rewarding. </s><s>[INST] Thanks for listening to this conversation with carl dice Roth. To support this podcast, please check out our sponsors in the description and now let me leave you with some words from Carl Young, knowing your own darkness is the best method for dealing with the darkness of other people. Thank you for listening and hope to see you next [/INST] time </s> |
<s>[INST] chosen people of God never resonated with me too much. The graph of the Gertzel family, I mean, just the people I've encountered, just doing some research and just knowing your work through the decades, it's kind of fascinating. Just the number of PhDs. [/INST] Yeah, yeah. It's kind of fascinating. My dad is a sociology professor who recently retired from Rutgers University, but that clearly that gave me a head start in life. My grandfather gave me all this quantum mechanics books and I was like seven or eight years old and I remember going through them and it was all the old quantum mechanics, like Rutherford Adams and stuff. So I got to the part of wave functions, which I didn't understand, although I was a very bright kid and I realized he didn't quite understand it either, but at least like he pointed me to some professor he knew at UPenn nearby who understood these things, right? So that's an unusual opportunity for a kid to have, right? My dad, he was programming Fortran when I was 10 or 11 years old on like HP 3000 mainframes at Rutgers University, so I got to do linear regression in Fortran on punch cards when I was in middle school, right? Because he was doing, I guess, analysis of demographic and sociology data. So yes, certainly that gave me a head start and a push towards science beyond what would have been the case with many, many different situations. </s><s>[INST] When did you first fall in love with AI? Is it the programming side of Fortran? Is it maybe the sociology psychology that you picked up from your dad? [/INST] I fell in love with AI when I was probably three years old when I saw a robot on Star Trek. I was turning around in a circle going, error, error, error, error, because Spock and Kirk had tricked into a mechanical breakdown by presenting with a logical paradox. And I was just like, well, this makes no sense. This AI is very, very smart. It's been traveling all around the universe, but these people could trick it with a simple logical paradox. Like why, if the human brain can get beyond that paradox, why can't this AI? So I felt the screenwriters of Star Trek had misunderstood the nature of intelligence. I complained to my dad about it and he wasn't going to say anything one way or the other. Before I was born, when my dad was at Antioch College in the middle of the US, he led a protest movement called SLAM, Student League Against Mortality. They were protesting against death, wandering across the campus. So he was into some futuristic things even back then, but whether AI could confront logical paradoxes or not, he didn't know. But when I, 10 years after that or something, I discovered Douglas Hofstadter's book, Gortel Escherbach, and that was sort of to the same point of AI and paradox and logic, right? Because he was over and over with Gortel's incompleteness theorem and can an AI really fully model itself reflexively or does that lead you into some paradox? Can the human mind truly model itself reflexively or does that lead you into some paradox? So I think that book, Gortel Escherbach, which I think I read when it first came out, I would have been 12 years old or something. I remember it was like 16 hour day, I read it cover to cover and then reread it. I reread it after that because there was a lot of weird things with little formal systems in there that were hard for me at the time. But that was the first book I read that gave me a feeling for AI as like a practical academic or engineering discipline that people were working in. Because before I read Gortel Escherbach, I was into AI from the point of view of a science fiction fan. And I had the idea, well, it may be a long time before we can achieve immortality and superhuman AGI. So I should figure out how to build a spacecraft traveling close to the speed of light, go far away, then come back to the earth in a million years when technology is more advanced and we can build these things. Reading Gortel Escherbach, well, it didn't all ring true to me, a lot of it did. But I could see like there are smart people right now at various universities around me who are actually trying to work on building what I would now call AGI, although Hofstadter didn't call it that. So really, it was when I read that book, which would have been probably middle school, that then I started to think, well, this is something that I could practically work on. </s><s>[INST] Yeah, it's supposed to flying away and waiting it out, you can actually be one of the people that actually... Yeah, exactly. [/INST] Yeah, exactly. And if you think about, I mean, I was interested in what we'd now call nanotechnology and in the human immortality and time travel, all the same cool things as every other like science fiction loving kid. But AI seemed like if Hofstadter was right, you just figure out the right program, sit there and type it. Like you don't need to spin stars into weird configurations or get government approval to cut people up and fill with their DNA or something, right? It's just programming. And then of course, that can achieve anything else. There's another book from back then, which was by Gerald Feinbaum, who was a physicist at Princeton. And that was the Prometheus Project. And this book was written in the late 1960s, though I encountered it in the mid 70s. But what this book said is in the next few decades, humanity is going to create superhuman thinking machines, molecular nanotechnology, and human immortality. And then the challenge we'll have is what to do with it. Do we use it to expand human consciousness in a positive direction or do we use it just to further vapid consumerism? And what he proposed was that the UN should do a survey on this and the UN should send people out to every little village in remotest Africa or South America and explain to everyone what technology was going to bring the next few decades and the choice that we had about how to use it and let everyone on the whole planet vote about whether we should develop super AI, nanotechnology, and immortality for expanded consciousness or for rampant consumerism. And needless to say, that didn't quite happen. And I think this guy died in the mid 80s, so he didn't even see his ideas start to become more mainstream. But it's interesting, many of the themes I'm engaged with now from AGI and immortality, and to trying to democratize technology, as I've been pushing forward with singularity in my work in the blockchain world. Many of these themes were there in, you know, Fine Bomb's book in the late 60s even. And of course, Valentin Turchin, a Russian writer, and a great Russian physicist who I got to know when we both lived in New York in the late 90s and early aughts, I mean, he had a book in the late 60s in Russia, which was The Phenomenon of Science, which laid out all these same things as well. And Val died in, I don't remember, 2004 or 2005 or something of Parkinson'sism. So yeah, it's easy for people to lose track now of the fact that the futurist and singularitarian advanced technology ideas that are now almost mainstream, and they're on TV all the time. I mean, these are not that new, right? They're sort of new in the history of the human species, but I mean, these were all around in fairly mature form in the middle of the last century were written about quite articulately by fairly mainstream people who were professors at top universities. It's just until the enabling technologies got to a certain point, then you couldn't make it real. And even in the 70s, I was sort of seeing that and living through it, right? From Star Trek to Douglas Hofstadter, things were getting very, very practical from the late 60s to the late 70s. And the first computer I bought, you could only program with hexadecimal machine code and you had to solder it together. And then like a few years later, there's punch cards, and a few years later, you could get like Atari 400 and Commodore VIC-20, and you could type on the keyboard and program in higher level languages alongside the assembly language. So these ideas have been building up a while, and I guess my generation got to feel them build up, which is different than people coming into the field now for whom these things have just been part of the ambiance of culture for their whole career or even their whole </s> |
<s>[INST] Well, I got to give you some advice. There's uh, two words that were repeated often, um, in the days and the years after 9 11, which is never forget. So might I remind you to never forget about 9 12. I mean those words you talked about that, you know, there's people, what is a college freshman, maybe [/INST] they weren't even they </s><s>[INST] weren't even born and there's people in the twenties that were too young to remember to understand the events of that day. But I think what that day is you're describing means it's not about a terrorist attack, it's about the unity that followed. [/INST] It was tremendous lex. I never felt so proud. It was always proud of this country. I remember my grandpa nails used to walk by and see a flag or hear the star spangled banner and he tear up and I say, grant, why are you crying? He said, I'm not crying as the tears of joy. I love this country so much. And I just remember like feeling that way. I felt that way 9, 10, I felt that way on 9 11, but then on 9 12 I was just so proud of just the people the way they stepped up and I just want to try to see if that can happen again. And I hope it's it's not necessary for us to have another tragedy to bring that about. Let's do that without the tragedy. Let's just stop and say, hey, you know what, let me listen to what this guy has to say. And maybe he probably won't convince me, but maybe I'll go, well, you know, I never thought of it that way, stop the finger pointing the bickering the tantrums, the fighting, It's just not necessary to get you nowhere. Right. It's like, you know, I was two years old and stomp around because I wanted to cook you a piece of candy. I still didn't get it right, you know, turn blue in the face and whatever gotta swat in the rear end, but it didn't get the candy and that's what we got going on right now. Everybody's just stomping around being a baby stop, </s><s>[INST] just stop. [/INST] We're really lucky. Look countries not perfect, right. You know, but it's damn good. It gives us all these opportunities, you know, like I said, no one's rushing out the gates to get out of here. They're they're freaking I got a cousin of mine, I love him dearly. My cousin Tony and Ireland And he said he's he's just a little older than me, he's in his 50's. He said man, I should have done it, I should've went to America. My dad said go to America. I went to England and he and he and he went back to Ireland and you know, he but he's happy in Ireland it's his home. But he said, wow, what a what a place of opportunity. And it's it's never too late. He goes, yeah, but you know what? You get tied down and I understand that. I thank God, my mom came here 16. I thank God. My grandpa got on that ship In his 20's 27, I think. You know, we're not a nickel to rub together. I thank God they did it because I don't know where else I would have ended up. There's no place else I want to be. </s><s>[INST] And uh, I thank God that there's people like you who rushed towards ground zero to help other human beings and I believe that, that, that human spirit is ultimately represents the best of this country and the best of this world. Thank you for the stories you're telling for your perseverance and that. And uh, thank you for welcoming you to the [/INST] crew. You're very well. I'm proud to uh, take you any day you look like you could do the job just fine. </s><s>[INST] I love lifting heavy things and doing dangerous things. So it's, I'm proud to be part part of this country and part of the tally ho now [/INST] well you are, you are definitely an attribute to America and we're glad you chose to come here. Um, you know, like it's, it's such a beautiful place. It's a beautiful melting pot. You know, if we're all the same, it would be kind of a boring place, right? It really would, but it's just, it's just such a great place and I just want to say thanks, it's an honor. It's an honor to have someone to let me sound off and, and it will be even bigger honor if somebody will listen to me and just say, Hey, you know, let me just try to do something good today. And you know, that's, that's the tunnel to towers mantra has let us do good. And I just, you know, I, uh, I got a really big credit card with God, big balance right? I, I need to pay him back a lot and I need to pay him forward and I'm just going to spend the rest of my days trying my best. I don't know where this is going to go, what it will lead into. But I really would like to get those dogs for those vets, building that village and, and just keep going on from project to project to just say when my final day combs and I'm laying there and I say, you know what? I really made the most of that second chance. God gave me way back in 2011. I'm, I hope it's 30, 40 years from now, but even if it's 30 months from now giving it the best shot. So thank you sir. I appreciate it. And wishing you blessings and success in your career, </s><s>[INST] keep up the good fight and you're always welcome back to texas. [/INST] Well, I love it. It's great food and a little hot hot, come on, we don't do so good irish in the sun, you know, But uh, </s> |
<s>[INST] crazy. Uh But you're even crazier apparently thinking that it can reach a million. So do you think it's possible for it to reach a million? Is there some kind of transformative effects we'll have to see first when might reach a million. Like what are the signs that we would look for, [/INST] what's required for it </s><s>[INST] to reach a million? [/INST] So let's just look at it from a macro perspective, gold is a $10 trillion dollar asset. And when you compare the technology of gold to the technology of Bitcoin. Bitcoin is superior in every single way. Right? It's more portable, more divisible. Uh It's more verifiable it's more scarce on everything. And so some people would argue it's a 10 X. Improvement. Some people argue it's 100 X. Improvement from a technology standpoint. And so we don't need Bitcoin to actually kind of um capture the full 10 X. Or 100 X. Improvement from a market cap standpoint. If Bitcoin simply captures two X. The value be a $20 trillion market cap which would put Bitcoin at about a million dollars. Right? So kind of just from a macro perspective if you have a 10 X. 100 X. Improvement from a technology standpoint and you directionally get some value capture in that direction, you're hitting around a million or more dollar price </s><s>[INST] point? Can I ask a question which is uh what's the current market cap for Bitcoin, [/INST] the current market caps right around a trillion. Just over a </s><s>[INST] trillion dollars. And you're saying gold is 10 trillion. Uh sorry, where did you get? The 20 trillion? [/INST] 20 trillion would just be two X. Cold market cap. Got it. Right. So if it's a 10 X technology improvement, let's just say it only captures two X. The market cap, right? And so again, if it was to capture just gold market cap, kind of the equivalent push you around $500,000 right? So you can kind </s><s>[INST] of see there's Bitcoin. So if you capture the entirety of the gold market then it would be value a single Bitcoin. The price of a single Bitcoin would be $500,000. Okay. To reach a million. It would be doubled at that's what the 20 trillion comes from, correct. Got [/INST] it. So if you then say to yourself, okay, how does the pricing um kind of cycles work, right. Or or the boom and bust cycles. Gold is a very um kind of linear type supply schedule, meaning that uh there is a certain amount of gold that comes out of the ground each year. The inter year variation in that incoming supply is not much, right? Maybe there's an extra mining company that gets set up for a couple of them, everyone goes out of business. But for the most part the kind of inflationary uh increase to the supply of gold. It's pretty stagnant year over year. Bitcoin has a very unique feature which every four years there's a programmatic supply shock meaning that uh in the beginning 50 Bitcoin every 10 minutes was introduced into the supply. After four years of that happening every 10 minutes, it was cut in half. So on a, in a single moment it went from 50 to now, it was 25 four years every 10 minutes, 25 got cut in half again to 12.5. And then recently in May 2020 got cut to 6.25 when you have an asset that is determined the price based on supply and demand. You normally have two inputs to the equation. What is the supply and what is the demand in an asset like gold or a stock or anything else? We have to do our best guess at the supply, both the existing supply and the incoming supply and do our best guess at the demand. And we actually pretty good at this a lot of times in terms of directionally saying it's going to go up or down and here's kind of some price point milestones. Bitcoin is unique in that there is 100% verifiable proof Of the existing supply, the total supply and the incoming daily supply. So we know 100%. I can show you on the actual Blockchain or in the code that there's 21 million bitcoins. Uh and that's all there will ever be. I can show you that there's 18.6 million give or take Bitcoin that actually are in circulation today. Right. And I can go all the way back to every single transaction that ever occurred since January 2009. And then I can show you on a daily basis that 900 Bitcoin a day are coming into the circulating supply. And so when you have 100% confidence because you can prove the supply side of this equation, you can hold it constant. I know with 100% accuracy, the supply side. So now I've reduced the mathematical equation that I need to do to determine price movements to a 50% reduction. I only have to worry about demand. I don't have to worry about supply. And so when I look at demand I can do all kinds of things. I can take the demand of the last 10 years and the growth and just extrapolate it out, I can increase that. I can decrease it whatever. But what you find is that these supply shocks lead to significant price appreciation as the acid gets re priced because there there's a supply shock to And so probably the best thing that I've done over the last couple of years was in 2019. I started to talk about the idea that we were going to have both a supply shock and the demand shock in 2021. Uh, I'm sorry in 2020, I didn't know when this bull market that we were in was going to end. Nobody knows it's impossible to time these things, but you could tell that we were kind of at late stages of a cycle, there was inverted yield curves, there was re generations in the repo markets, a lot of Ceos leaving their jobs, you know, all this kind of stuff and all I said was at some point when the market turns over, the government's gonna have to step in, we were addicted to stimulus, they have to manipulate interest rates down. They're going to print money. I had no clue that there was gonna be a global pandemic that they were gonna have to step in in such an aggressive way and move rates not down but down to zero. And that they, not only we're going to print hundreds of billions but trillions of dollars, but the framework that I used to think about this was when they do that, everyone is going to run to store value assets, they're going to run the gold, they're going to run the Bitcoin etcetera and right as they do that, it appears at the same time there's going to be this supply shock, so you're gonna get a supply shock and a demand shock that are both positive for the price and I call it rocket fuel for Bitcoin. Well it happened and here we are I now look for and I say, okay we are likely going to see 100,000 Bitcoin, $100,000. Bitcoin this year at some point. I don't know when it happens but we're moving in </s> |
<s>[INST] is more stringent, yeah. The configuration of the plasma, sorry. Are tokamaks by far more popular [/INST] for research and development currently than stellarators? Of the concepts which are there, the tokamak is by far the most mature in terms of its breadth of performance and thinking about how it would be applied in a fusion energy system. And the history of this was that many, in fact, you asked if we go back to the history of the plasma and fusion center. The history of fusion is that people, scientists had started to work on this in the 1950s. It was all hush hush and cold war and all that kind of stuff. And it's like they realized, holy cow, this is really hard. We actually don't really know what we're doing in this because everything was at low temperatures, they couldn't get confinement. It was interesting. And they declassified it and this is one of the few places that the West and the Soviet Union actually collaborated on was a science. Even during the cold war. Even during the middle of the cold war, it was really, and this actually perpetuates all the way till now for we can talk about the project that that is sort of captured in now. But, and the reason they declassified it is because like everything like kind of like sucked basically about trying to make this confinement in high temperature plasma. And then the Russians, then the Soviets, came along with this device called a Tokamak, which is a Russian acronym, which basically means magnetic coils arranged in the shape of a donut. And they said, holy cow, like everyone was stuck at like a meager like half a million degrees, half a million degrees, which is like infusion terms of zero basically. And then they come along and they say, oh, we've actually achieved a temperature 20 times higher than everybody else. And it's actually started to make fusion reactions and everyone just go, oh, you know, no way. It's just hype from the, it's like, there's no way because we failed at this. It's a great story in the history of fusion is that then, but they insisted said, no, look, you can see this from our data. It's like, this thing is really hot and it seems to be working. This is, you know, late 1960s. And there was a team that went from the United Kingdom's fusion development lab and they brought this very fancy, amazing new technology called a laser. And they use this laser and they shot the laser beam like through the plasma. And by looking at the scattered light that came from the, they go, basically the scattered light gets more broadened in its spectrum if it gets hotter. So you could exactly tell the temperature of this. And even though you're not physically touching the plasma, it's like, holy cow, you're right. It is like, it is 10 million degrees. And so this was one of those explosions of like everyone in the world then wanted to build a token back because it was clearly like, wow, this is like so far ahead of everything else that we tried before. So that actually has a part of the story to MIT in the Plasmas infusion center was, why is there a strong fusion in a major fusion program at MIT? It was because we were host to the Francis Bitter Magnet Laboratory, which is also the National High Field Magnet Laboratory. Well, you can see where this goes, right? From this, you know, and we're kind of telling the stories backwards almost, but you know, the advent of a tokamak along with the fact that you could make very strong magnetic fields with the technology that had been developed at that laboratory, that was the origins of sort of pushing together the physics of the plasma containment and the magnet technology and put them together in a way that I would say is, you know, a very typical MIT success story, right? We don't do just pure science or pure technology. We sort of set up this intersection between them. And there were several pioneers that of people at MIT, like Bruno Coppe, who's a professor in the physics department and Ron Parker, who was a professor in electrical engineering and nuclear engineering. It's like even the makeup of the people, right, has got this blends of science and engineering in them. And that's actually was the origin of the Plow Science and Fusion Center, was doing those things. So anyway, so back to this. So why, so yes, tokamaks have been, have achieved the highest in magnetic fusion by far, like the best amounts of these conditions that I talked about. And in fact, pushed right up to the point where they were near QP of one. </s><s>[INST] They just didn't quite get over once. Even during the Cold War. So can we actually just linger on the collaboration across different nations? Just maybe looking at the philosophical aspect of this. Even in the Cold War, there's something hopeful to me besides the energy that these giant international projects are a really powerful way to ease some of the geopolitical tension, even military conflict across nations. There's a war in Ukraine and Russia. There's a brewing tension and conflict with China. Just the world is still seeking military conflict, cold or hot. What can you say about sort of the lessons of the 20th century in these giant projects [/INST] in their ability to ease some of this tension? So it's a great question. So as I said, there was a reason because it was so hard. That was one of the reasons they declassified it. And actually they started working together in some sense on it as well too. And I think it was really, there was a heuristic or altruistic aspect to this. It's like, this is something that could change the future of humanity and its nature and its relationship with energy. Isn't this something that we should work on together? Right, and that went along in those ones. And in particularly that any kind of place where you can actually have an open exchange of people who are sort of at the intellectual frontiers of your society, this is a good thing, right? Of being able to collaborate. I've had the, I mean, I have had an amazing career. I've worked with people from, it's like hard to throw a dart at a country and on the map and not hit a country of people that I've been able to work with. How amazing is that? And even just getting small numbers of people to bridge the cultural and societal divides is a very important thing. Even when it's a very teeny fraction of the overall populations, it can be held up as an example of that. But it's interesting that if you look at then that continued collaboration, which continues to this day, is that it was, this actually played a major role, in fact, in East-West relations or like Soviet-West relations, is that back in the Reagan-Gorbachev days, which of course were interesting in themselves of all kinds of changes happening on both sides, right? But still like a desire to push down the stockpile of nuclear weapons and all that, within that context, there was a fairly significant historic event that at one of the Reagan-Gorbachev summits is that they had really, they didn't get there. Like they couldn't figure out how to bargain to the point of some part of the tree deck anymore, the details of it anymore. But they needed some kind of a symbol almost to say, but we're still gonna keep working towards something that's important for all of us. What did they pick? A fusion project. And that was in the mid-1980s and actually then after, so they basically signed an agreement that they would move forward to like literally collaborate on a project whose idea would be to show large net energy gain in fusion's commercial viability and work together on that. And very soon after that, Japan joined, as did the European Union. And now that project, it evolved over a long period of time and had some interesting political ramifications to it. But in the end, this actually also had South Korea, India and China join as well too. So you're talking about a major fraction of, and now Russia, of course, instead of the Soviet Union. And actually that coalition is holding together despite the obvious political turmoil that's going around on all those things. And that's a project called ITER, which is under construction in the South of France right now. </s> |
<s>[INST] But well what do you think is the role of love? Because you, you gave me some grief. You busting my balls a little bit for talking about love a lot. What do you think they're all love in the human condition? [/INST] I think it's the greatest thing. I think everyone should be searching for it if you don't have it, find it and get it as soon as you can. Um I love my wife. I really do. I had no idea what love was until my kids were born. My son came out and this is a funny story. He came out and uh you know, I just wanted to be safe and be healthy and all that and I said to the doctor, I said 10 and 10 doc, you know 10 fingers, 10 toes, everything good. And he goes nine and nine. </s><s>[INST] I was [/INST] like, what the? I was like, oh this is gonna suck, okay, we'll deal with it and all that. Uh he was talking about the apnea card cord or some score about breathing and color and all that and I was like, oh ship but I, no one told me this. Um but so I'm just sobbing. I couldn't even cut the umbilical cord, like just fell in love with my kids when I saw them and and that to me really is what love is like just for them man </s><s>[INST] and I see that through your career, that love developed, which is awesome. The [/INST] the being </s><s>[INST] able to see the humanity in people. I [/INST] didn't when I was young, the foolishness of </s><s>[INST] youth, you [/INST] know, I I needed to learn that lesson hard. I mean, you know, when I was young in my career, it was just about career goals and you know, and resting people became stats. You know, you arrest someone that you get a good stat, you get an atta boy, you know, maybe you know the boss likes it and you get a better job or you get to move up the chain. It took it took a real change in my life to see that humanity </s><s>[INST] and uh I can't wait to listen to to your talk, which is probably hilarious and insightful. Um given the life of the two of you lived and given how much you've changed each other's lives, um I can't wait to listen brother, thank you so much. This is a huge honor of your amazing person with an amazing life. This is an awesome conversation, [/INST] huge fan. I love the podcast. Glad I could be here. Thanks for the invite. So, uh exercising the brain to it was great, great conversation </s><s>[INST] and the hard to [/INST] write. Oh yeah, yeah, you got you got some tears there at the end. </s><s>[INST] Thanks for listening to this conversation with chris Tarbell to support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Benjamin Franklin. They can give up essential liberty to obtain a little temporary safety, deserve neither liberty nor safety. Thank you for listening and hope to see you next time. [/INST] </s> |
<s>[INST] I take it when I have deep work sessions especially in the morning. It keeps changing but these days when I wake up I do a mantra, I walk over get some an electrolyte drink as the coffee is being made, then an athletic greens drink from the nutrition, and finally I walk over with the coffee to my computer and my favorite thing to do to start the day is something that I left unfinished from the night before which would be a programming task. So anything involving programming when you just have this screen full of code and I can focus on a design problem for some reason it's a great warm-up to my brain. I can clear out the distractions of the world and focus on these little puzzles and it's also clear that I can make progress on solving little puzzles little puzzle here whether it's debugging or building a new thing all of it just makes me really happy especially as the project nears completion whether it's the intermediate stages of its completion or the the final thing so not particularly oftentimes with that programming is like scripts that automate various aspects of my life and make me more efficient but it's also larger projects that I do for machine learning and robotics work and beyond. Anyway during those moments if I'm feeling really out of it I will take an alpha brain to give me a boost you can get a special discount on alpha brain at LexFreedman.com slash on it more beyond. This show is also brought to you by Inside Tracker a service I use to track biological data. I've been getting softer and fatter over the past few months and recently a few days ago I decided to change that so I'm on a stricter diet now on a stricter exercise regime and it's amazing sort of the improvement in how I feel about this world how I feel about just the way I move about the world the way I think for prolonged periods of time is able to maintain focus it's a very low carb diet and mostly fast mostly once a day I mean maybe that's for another time to discuss what my preferences are there maybe people don't care probably that they don't care but my body is is definitely operating at a higher level of performance under strict diet and it's interesting to measure that through data to get blood data to get DNA data fitness tracker data and use all that to see if I'm doing better or worse than I was before and based on that make recommendations for diet and lifestyle changes that's exactly what inside tracker does get special savings for a limited time when you go to inside tracker comm slash Lex this is the Lex Friedman podcast support it please check out our sponsors in the description and now dear friends here's Ed Calderon what does your experience in counter narcotics investigating the Mexican drug [/INST] cartel teach you about human nature Wow I mean first off anybody can be got anybody can be corrupted you know you you're working that feel than you you realistically the training we got and profiling and investigation and stuff like stuff like that was basically you learn from the older guys there and some of those guys were already corrupted from the from the start so trust no one I remember seeing that X- Wiles episode where that was stated you quickly learn that even if you are somebody that to your own mind appears incorruptible. You know, small changes happen around you, wheels get greased, money gets put in front of you, and or things get threatened like your life. And sometimes a payment for some of this corruption is just to continue on living. You encounter people that seem incorruptible that go through FBI background checks that go through all of the security measures that all of us were put through, you know, polygraph test. And then later on, you know, it turns out they were on the take or they became somebody that was corrupted. I think what I found out is that anybody at any level, they could be a very strong, hard to get person right now, but people get corrupted through their families, through need. Mexico is a place where a lot of instability occurs. So financial needs, health. </s><s>[INST] So a crack could form through the wall of integrity. And then over time, it seeps in somehow. [/INST] Mexico has a culture of corruption. Like, you know, you have your kid that goes to school at public school, and you want him to be in the morning, not in the afternoon school, time period. So you go off and grease the wheels with the director of the school. People hearing this in Mexico will nod their heads because this is something that happens from early on. So there's a systemic there's a systemic and cultural thing to it, you know, as far as getting around rules. And this happens because, you know, the people that are in charge in Mexico, the government is, you know, their their tandem amount is trust between criminals and the cartels down there for a lot of the culture. So people don't trust the government </s><s>[INST] and much less criminality. So when you meet a person sticking on human nature, do you think it's possible to figure out if they can be trusted? So you said anyone could be corrupted. You know, how long would you need to talk to a person? And you're even in your own personal private life, just a friend, or is trust the thing that's never [/INST] really guaranteed? I think that trust is never really guaranteed. I know a lot of people are going to say that's a sad way and hard way of living your life. But you know, life experience at my end, you know, people change, you know, the dynamics of a relationship might change. I look at people's character, specifically their past and past experiences, if I can, and somebody that presents themselves in front of you as somebody, but you quickly learn that </s> |
<s>[INST] So in 2018 you started and now lead the company in Citro, which is a like you mentioned, perhaps the focus is drug discovery and the utilization of machine learning for drug discovery. So you mentioned that quote were really interested in creating what you might call a disease in a dish model disease. In addition models, places where diseases are complex where we really haven't had a good model system where typical animal models that have been used for years, including testing on mice just aren't very effective. So can you, can you try to describe what is an animal model and what, what is the disease in the dish model? [/INST] Sure. So an animal model for disease is where you create effectively. It's what it sounds like. It's it's oftentimes a mouse where we have introduced some external perturbation that creates the disease and then we cure that um disease uh and the hope is that by doing that we will cure a similar disease in human. The problem is is that oftentimes the way in which um we generate the disease and the animal has nothing to do with how that disease actually comes about in the human. Uh it's what you might think of as a copy of the of the phenotype, a copy of the clinical outcome. But the mechanisms are quite different. And so curing the disease and the animal, which in most cases it doesn't happen naturally, mice don't get alzheimer's, they don't get diabetes, they don't get atherosclerosis, they don't get autism or schizophrenia. Um Those cures don't translate over to what happens in the human and that's where most drugs fails just because the findings that we had in the mouse don't translate to a human. Um The disease in the dish models is a fairly new approach. It's been enabled by technologies that have not existed for more than 5 to 10 years. So for instance, um the ability for us to take a cell from any one of us, you or me um revert that's a skin cell to what's called stem cell status, which is a what which was called the pluripotent cell that can then be differentiated into different types of cells. So from that pluripotent cell one can create a lex neuron or a lex cardio Maya site or Alexa parasite that has your genetics but that right cell type. And so if there is a genetic burden of disease that would manifest in that particular cell type, you might be able to see it by looking at those cells and say, oh that's what potentially six cells look like versus healthy cells and understand how uh and then explore what kind of interventions might revert the unhealthy looking cell to healthy cell. Now, of course, curing cells is not the same scaring people. Um and so there's still potentially translate ability gap, but at least for diseases that um are driven, say by human genetics and where the human genetics is what drives the cellular phenotype. There is some reason to hope that if we revert those cells in which the disease begins and where the disease is driven by genetics and we can revert that cell back to a healthy state, maybe that will help um also revert the more global clinical phenotype. So that's really what we're hoping to do </s><s>[INST] that step backward step. I was reading about it, the Yamanaka [/INST] factor. </s><s>[INST] Uh so like that the reverse step back to stem cells, it seems like magic. [/INST] It is honestly before that happened, I think very few people would have predicted that to be possible. It's amazing. </s><s>[INST] Can you maybe elaborate? Is it actually possible? Like where like how so this result was? Maybe like, I don't know how many years ago, maybe 10 years ago was first demonstrated something like that. Is this, how hard is this? Like how noisy is this backward step? It seems quite incredible and cool. [/INST] It is. It is incredible and cool. It was much more I think finicky and bespoke at the early stages when the discovery was first made, but at this point it's become almost industrialized. There are what's called contract research organizations, vendors that will take a sample from a human and reverted back to stem cell status and it works a very good fraction of the time now there are people who will ask um I think good questions. Is this really truly a stem seller? Doesn't remember certain aspects of what of changes that were made in the human um beyond the genetics. </s><s>[INST] Its past as a skin cell, yeah, [/INST] its past as a skin cell or its past in terms of exposures to different environmental factors and so on. So I think the consensus right now is that these are not always perfect and there is little bits and pieces of memory sometimes, but by and large these are actually pretty good. </s><s>[INST] So one of the key things, well maybe maybe you can correct me, but one of the useful things for machine learning is size scale of data. How easy it is to do these kinds of reversals to stem cells and then does using the dish models at scale. Is this that a huge challenge or or not? [/INST] So the reverse the reversal is not as of this point, something that can be done at the skill of tens of thousands or hundreds of thousands. Um, I think total number of stem cells of I ps cells that are what's called induced pluripotent stem cells in the world I think is somewhere between five and 10,000 last I looked now again, that might not count things that exist in this or that academic center and they may add up to a bit more, but that's about the range. So it's not something that you get this point generate I PS cells from a million people. But maybe you don't need to because maybe that background is enough because it can also be now perturbed in different ways. And some people have done really interesting experiments in um for instance taking cells from healthy human and then introducing a mutation into it using some of the using one of the other miracle technologies that's emerged the last decade which is CRISPR gene editing and introduced the mutation that is known to be pathogenic. And so you cannot look at the healthy cells and the unhealthy cells, the one with the mutation and do a one on one comparison where everything else is held constant. And so you could really start to understand specifically what the mutation does at the cellular level. So the I PS cells are a great starting point. And obviously more diversity is better because you also want to capture ethnic background and how that affects things. But maybe you don't need one from every single patient with every single type of disease because we have other tools at our disposal. </s> |
<s>[INST] on a small tangent. Perhaps philosophical does uh, the fact that things get older and the fact that things die, it's a very powerful feature for the growth of new things that, you know, it's a learning is a kind of learning mechanism. So it's both tragic and beautiful. So do you do you do you uh so in, you know, in trying to fight disease and trying to fight aging, do you think about sort of the useful fact of our mortality? Or would you like if you were, could be immortal, would you used to be immortal [/INST] again? I think immortal is a very long time. And I don't know that That would necessarily be something that I would want to aspire to. But I think all of us aspire to um an increased health span, I would say, which is an increased amount of time where you're healthy and active and feel as you did when you were 20. Uh, and we're nowhere close to that uh people deteriorate physically and mentally over time. And that is a very sad phenomenon. So I think a wonderful aspiration would be if we could all live to, you know, the biblical 120 maybe in perfect health, </s><s>[INST] high [/INST] Quality of life. I think that would be an amazing goal for us to achieve as a society now is the right age. 120 or 100 or 250. I think that's up for debate, but I think an increased health span is a really worthy goal. </s><s>[INST] And anyway, in the grand time of the age of the universe, it's all pretty short. So from the perspective, you've done obviously a lot of incredible working machine learning. So what role do you think? Data and machine learning play in this and this goal of trying to understand diseases in trying to eradicate diseases? [/INST] Up until now, I don't think it's played very much of a significant role because largely the data sets, that one really needed to enable a powerful machine learning methods. Those datasets haven't really existed, There's been dribs and drabs and some interesting machine learning that has been applied, I would say machine learning slash data science, but the last few years are starting to change that. So we now see an increase in uh some large data sets, but equally importantly an increase in technologies that are able to produce data at scale. It's not typically the case that people have deliberately proactively used those tools for the purpose of generating data for machine learning. They, to the extent of those techniques have been used for data production. They've been used for data production to drive scientific discovery. And the machine learning came as a sort of byproduct second stage of oh you know, now we have a data set. Let's do machine learning on that rather than a more simplistic the analysis method. But what we are doing it in citrus, actually flipping that around and saying, here's this incredible repertoire of methods that bio engineers. Cell biologists have come up with. Let's see if we can put them together in brand new ways with the goal of creating datasets. That machine learning can really be applied on productively to create powerful predictive models that can help us address fundamental problems in human health. </s><s>[INST] So really focus uh to get make data the primary focus in the primary goal and find use the mechanisms of biology and chemistry too, to uh create the kinds of data set that could allow machine learning to benefit the most. [/INST] I wouldn't put it in those terms because that says the data is the end goal. Data is the means. So for us the end goal is helping address challenges in human health. And the method that we've elected to do that is to apply machine learning to build predictive models and machine learning in my opinion can only be really successfully applied, especially the more powerful models if you give it data that is of sufficient scale and sufficient quality. So how do you create those data sets? So as to drive the ability to generate predictive models which subsequently help improve human health. </s><s>[INST] Before we dive into the details of that, let me take a step back and ask uh when and where was your interest in human health born? Are there moments events perhaps if I may ask tragedies in your own life that catalyze his passion or was it the broader desire to help humankind? [/INST] So I would say it's a bit of both. So on. I mean my interest in human health actually dates back to the early two thousands when uh when a lot of my um peers and machine learning and I were using data sets that frankly were not very inspiring. Some of us old timers still remember the quote unquote 20 news groups data set where this was literally a bunch of texts from 20 news groups, the concept that doesn't really even exist anymore. And the question was, can you classify which um which news group of particular bag of words came from? And it wasn't very interesting. The data sets at the time On the biology side were much more interesting, both from a technical and also from an aspirational perspective, they were still pretty small but they were better than 20 news groups. And um so I started out I think just by just by wanting to do something that was more, I don't know societally useful and technically interesting. And then over time became more and more interested in the biology and the and the human health aspects for themselves. And began to work even sometimes on papers that were just in biology without having a significant machine learning component. I think my interest in drug discovery Is partly due to um an incident I had with um when my father sadly passed away about 12 years ago, um he had an autoimmune disease that settled in his lungs. Um, and um the doctors basically said, well there's only one thing that we can do is just give him predniSONE at some point. I remember dr even came and said, hey, let's do a lung biopsy to figure out which autoimmune disease he has. And I said, would that be helpful with that change? Treatment said no, there's only predniSONE, that's the only thing we can give. Him and I had friends who were rheumatologists who said the FDA would never approve President Zone today because the the ratio of side effects to benefit is probably not large enough today. We're in a state where there's Probably four or five, maybe even more. Um uh, well depends for which autoimmunities, but there are multiple drugs that can help people with autoimmune diseases, many of which exist 12 years ago. And I think we're at a golden time in some ways in drug discovery where there's the ability to create drugs, um that are much more safe and much more effective than we've ever been able to before and what's lacking is enough understanding of biology and mechanism to know where to aim that um where to aim that engine. And I think that's where machine learning can help. </s> |
<s>[INST] you're, there's a different use of the word swinging. [/INST] Sure. But I'm saying you could be clear, you look great, your hands muscular, thank you. You you get the job done. So I feel like you wouldn't leave without an orgasm on </s><s>[INST] her. Yeah, but I just like to, you know about fairies, I like to dress up with animals and and I just have trouble finding others who [/INST] like to sing up there. I could show you some chat rooms, </s><s>[INST] you're, you're also my coach for the internet. Okay uh what are you most afraid of? [/INST] I guess I'd unlived life, I'm always a big fan growing up of like wild guys, you know like these teddy Roosevelt who would go out and hunt lions and uh like bar fighting guys, I was obsessed with hunter? S Thompson types. And look this is what I love about guys, like who's a good example, like Hemingway, Hemingway was the manliest guy. He had the rifle and the elephant gun and the whiskey and the writing and the women and the fist fights, but people forget at the other side of that coin is I'm sure he was in a lot of hotel rooms weeping, I'm sure he was lonely as fuck. I'm sure he had some wicked hangovers. I mean he killed himself for christ's sake, so obviously he was dealing with something. So the key to me is having this adventurous life living to the fullest, doing crazy shit, scaring yourself but also not killing yourself. Like also not hating because I used to party a lot hard. I used to bang a lot of gals and this is the flip side is like this girl hates you now or you got herpes or you're hungover or your mom is like where where are you? You never call me anymore, you're like my mom, my five, let let ties go with my mom, I gotta connect. So this horrible, there's a horrible side of the party animal, The keith richards we don't see is not pretty. I mean he's already weird looking, but he's part and he's smoking, he's living, but there's another side of that coin and I think the key to life is living that fucking crazy awesome badass life and also having some, you know, meaning and and a little bit of uh what's the word? Not just not killing yourself, not going sad, not being depressed, there's a medium there a sweet spot. Does that make sense? </s><s>[INST] Yeah. So taking big leaps and uh Hemingway grabbing life by the balls, but at the same time not crushing the balls. That metaphor work at all. [/INST] Perfect like Evel Knievel. We all know what a badass fearless. Oh man, what a cool dude. He's got balls of steel, but he also lived like the back half of his life in a fucking uh you know Barca lounger where his legs were made of steel and he couldn't see straight and his dick didn't work. So you know what I mean? You've got to have a balance but you still want the balance. I'm willing to take a little bit of shit for a little bit of fun, but you don't want to go too hard </s><s>[INST] because we gotta still risk it. I mean Hunter? S Thompson it didn't end well. [/INST] Yeah, that's quite a ride. Quite a ride. </s><s>[INST] What small act of kindness were you once shown that you will never forget, wow, that's a great question. You're you're you're I just wrote this for the the guinea pig. You're the guinea pig for this is where like work shopping questions [/INST] here. Alright, I'll take it and you're not, you're open biking. This is your version. Um let's see. There's a couple of ladies in high school who were kind enough to hand job me. That was nice, which I really appreciate. I don't think women know how much that means to us. You know, women like, I'm not a piece of meat or whatever and you're like, I know, but if you just give me a hand job, it would it would make my world. It's like telling a kid he's smart or loved </s><s>[INST] the most people mentioned like a math teacher in middle school that was inspired them to get into science you it's give a shout [/INST] out to the, well, that's part of, that's not the nicest. But I'm just saying that goes a long way. Alright, let's see kindness. That's a great question. I want to give you a good answer. I I got lost when I was like six. I was I was walking around my dad and I zoned out and went away and next thing you know, I don't know where I am. I'm in a neighborhood. This old guy finds me crying on a lawn somewhere and he goes, uh come inside and he tried to call my parents and no, nothing came of it. Eventually they found me after like nine hours cops were there, The FBI's out there fucking helicopters. And I guess, you know, that's the nicest old guy, took me in for a couple hours and just sat me down and kept me safe. That's something. Oh, how about Enos? My transvestite nanny, Very kind. He uh did you hear about this? Okay, we had this transvestite nanny. He was like a drag queen, but it was in the 90s, it was weird, it was new and my bike got stolen and he, you know, my parents like, what are you gonna do? Their poor kids, You know? And he was like, fun, let's we're gonna go get that bike. And I was like, this guy's in a wig and high heels, big black guy. And I'm like, ah what are you gonna do? You know it's gone? And he's like, no, we're gonna go get it. So, we got in the van and drove around my neighborhood, saw the kids with the bike, you know, five street toughs? And uh he goes all right, do you want to come out or should I just do this? And I was like, you do it, I'm terrified, What are you crazy? And he got out of the van in full, you know heels and wig? And he went up to these guys and they went off, oh my God, look at this guy, homo figure in all this ship, You know, it's the nineties and he just stared at him long enough to where they were kind of like, all right, well, I guess we're gonna fight you now. And he goes, that's not your bike. And they go, what are you gonna do about it? And he puts his hand on the middle of the bike and they didn't do anything and he just picked it up. And so that's what I thought, Put the bike over, shoulder, slid the van door open through the bike in and we drove off. </s> |
<s>[INST] just a sauna of sorts. [/INST] Yeah, yeah. You go there, you know, you feel refreshed after you come back, you know, but </s><s>[INST] if you stay there, I mean, so, okay, I take that as an assumption, this is a philosophical question, that a biological one. So you have a life that develops under these extremely hot conditions. [/INST] So let's see so much of the early evolution of mankind was driven by exploration, right? And the kind of interest and stars originated in part as a tool to guide that exploration. Right? I mean, that in itself, I think it would be a huge, you know, huge differential in the way that we, you know, our our evolution on this planet. </s><s>[INST] Yes. I mean stars, that's brilliant. So even in that aspect, but even in further aspects, astronomy just shows up Basically every single development in the history of science. Up until the 20th century, it shows up. So I wonder without that if we had would have if we would even get like calculus. [/INST] Yeah. Look, that's a great I mean, that's a great point. Newton in part developed calculus because he was interested in understanding explaining kepler's laws, right? In general, that whole mechanistic understanding of the night sky, replacing a religious understanding where you interpret, you know, this is, you know, this whatever fire God writing his, you know, a little chariot across the sky as opposed to, you know, this is some mechanistic set of laws that transformed humanity and arguably put us on the, on the course that we're on today, right? The entirety of the last 400 years and the development of kind of are technological world that we live in today was sparked by by that right, abandoning an effectively, you know, a non secular view of the natural world and, and kind of thing. Okay, this can be understood and if it can be understood, it can be utilized. We can create our own variants of this. Absolutely. We would be a very, very different species without astronomy. Um, this, I think extends beyond just astronomy. Right? There there are questions like why do we need to spend money on X where X can be anything like paleontology like, right, </s><s>[INST] The meeting patterns of penguins? [/INST] Yeah, that's like essential. That's right. Um, I think, you know, there's a tremendous under appreciation for the usefulness of useless knowledge. Right? I mean, uh, it's brilliant that I didn't come up with this, this was, there's a little book by uh, the guy who started the Institute for Advanced Studies, but um, You know, it's so true. So much of the electronics that are on this table, right, work on Maxwell's equations. Maxwell wasn't sitting around in the 1800s saying, you know, I hope one day, you know, uh, will make, you know, a couple mikes. So, you know, a couple of uh, you know, a couple of guys can have this conversation right? That there was no, at no point was that the motivation and yet, you know, it gave us the world that we have today and the answer is if you are a purely pragmatic person, if you don't care at all about the human condition, none of this, the answer is you can tax it right. Like useless things have been, have created way more capital than useful things. </s><s>[INST] And the sad thing, I mean, first of all, it's really important to think about and it's brilliant in the, in the following context like Neil Degrasse Tyson is this book about the role of military based funding in the development of science. And then so much of uh technological breakthroughs in the 20th century had to do with humans working on different military things. And then the outcome of that had nothing to do with military. It has some military application, but their impact was much much bigger than military [/INST] splitting of the atom is a kind of a canonical example of this. We all know that tragedy that arises from splitting of the atom and yet, you know, so much. I mean the atom itself does not care for what purpose it is being split. So </s><s>[INST] I wonder if if we took the same amount of funding as we use for war and poured it into like totally seemingly useless things like the mating patterns of penguins. We would get the internet anyway. [/INST] I I think so. I think so. And you know, perhaps more of the internet would have would have penguins, you know, so </s><s>[INST] we're both joking but in some sense like I wonder it's not the penguin because penguins is more about sort of biology, but all useless kind of tinkering and all kinds of, uh, in all kinds of avenues and also because military applications are often um burdened by the secrecy required. So it's often like so much, uh, the openness is lacking. And if we learned anything for the last few decades that when there's openness and science that accelerates the development of science, [/INST] that's right. That's true. The openness of science truly, you know, it benefits everybody the notion that if, you know, I share my science with you, then you're going to catch up and like know the same thing that is a short sighted because if you catch up and you open, you know, you discover something that puts me in a position to do the next step, right? It's just so I absolutely agree with, um, with all of this. I mean, uh, the kind of question of like military funding versus non military funding is obviously a complicated one. But at the end of the day, I think we have to get over the notion as a society that we are going to pay for this and then we will get that right. That's true. If you're buying like, I don't know, toilet paper or something, right? It's just not true in the intellectual pursuit. That's not how it works. And sometimes it will fail. Like sometimes like a huge fraction of what I do, right? I come up with an idea. I think it's great and then I work it out. It's totally not great fails. Immediately </s> |
<s>[INST] But it also shows that there's the happy ending, that it does end on a good note that it does get infinitely infinitely better. Um and that I think there's a, I don't like you said there were responsibility, but there is um an opportunity for those of us who did dodge that bullet to give testimony to these people and more importantly to give testimony to the people who are going through this now. So you know, one of the reasons I, you know, talk about north Korea so much why I wrote Dear Reader is because it's very easy and this is human nature. I'm not condemning people. I don't think that's just how people are wired when you see an asian country with Asian people and things are you know, bad over there. You know, I think in the west it's like oh you know Asia, they're all crazy, they're they're wacky. They, you know, they eat dogs or so and so forth some weird stereotype and they think of them as kind of Martians. So it's important for people who aren't of that kind of ancestry to kind of speak on behalf of these people because it's very different how just people just natural react when you have a westerner talking about this instead of becoming their, you know them over there, it becomes, you know, this could have been uh us very easily. I have a friend Peter, they had ski great dude. And I was showing him photos when I was in Pyongyang and he goes, this looks like a Russian city with asian people, it was completely disturbed him. So you know that was one of the reasons I did go to north Korea because that was as close as I would get to see what your family went through to see what my family went through and they're still living under this regime. And one of the things I fought very hard to do with your reader, which I was successful and amazingly and it just, I said like I could die now like I feel like if you make it just moves need a little bit then you kind of uh pay your due for your time here on this earth to have it changed from being a laughing stock, you know, and I think team America did a good job, they made kim jong il into a clown and they made a joke of it, but you're going from nothing to joke. So at least now people are aware of it that it exists, right? And then I and many others took it from a joke to like guys, this is really, really, really bad and none of us can even appreciate how bad it is. And I think now there is an understanding other than a few people who are just looking at through a trump lens and wanting trump to fail because trump's and asshole, that's fine to be like these poor people. And it's really unfortunate because there's a segment of Western culture who thinks that correctly, often when you're complaining about or discussing the plight of another country, that's just your prelude to war and an excuse to invade. Like the kurds in Syria. You know, we're talking about if we're not in Syria tomorrow, it's gonna be another genocide, blah blah. I'm not saying let's invade North Korea and things like that. All I'm saying is, you know, thank God that this isn't your life. I bring this up all the time. The woman who was my guide when I was there, I'm aware of what she's up to now. She's still, she's extremely rich by North korean um standards, but she'll never be in a position to buy medicine. She'll never be in a position to go on a vacation, uh, things that you and I just, you know, whatever, she, she can't go on the internet. Uh, she can't get encyclopedia, uh she can't better herself as a person other than through what the state allows and meaning better yourself as a person in service to the state. So I mean there's it's also frustrating because there's only so much that I can do as an individual. [/INST] What's your takeaway about human nature, from looking at north Korea and looking at how the rest of the world is looking at north Korea. </s> |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.