text
stringlengths 1
17.7k
| time
timestamp[ns]date 2024-04-19 12:10:41
2024-10-14 00:02:39
|
|---|---|
Why do professional developers use C# in the first place? | 2024-04-19T12:27:56 |
To go through the motions? Sure. To do the job right the first time and completely, not a chance.<p>It takes more than a month to come up to speed in a new environment - new tools, new processes, new goals and constraints, you go home every night with your head hurting and tired from sweating it.<p>And that's if you've done most of it before. Getting that context, internalizing it so you can do the work without second-guessing yourself on every little thing, that takes a long time for anybody.<p>Velocity, the Agile people call it. That's why folks are paid less, maybe half what an experienced 'resource' gets paid, for maybe a year. Until they do enough to be worth keeping around! | 2024-04-19T12:27:50 |
also, an LLM is not learning phrases per se but the relationships between tokens | 2024-04-19T12:27:40 |
Oriole are joining to work on the OrioleDB postgres extension. That's slightly different to this release:<p>- This: for managing large files in s3 (videos, images, etc).<p>- Oriole: a postgres extension that's a "drop-in replacement" for the default storage engine<p>We also hope that the team can help develop Pluggable Storage in Postgres with the rest of the community. From the blog post[0]:<p>> <i>Pluggable Storage gives developers the ability to use different storage engines for different tables within the same database. This system is available in MySQL, which uses the InnoDB as the default storage engine since MySQL 5.5 (replacing MyISAM). Oriole aims to be a drop-in replacement for Postgres' default storage engine and supports similar use-cases with improved performance. Other storage engines, to name a few possibilities, could implement columnar storage for OLAP workloads, highly compressed timeseries storage for event data, or compressed storage for minimizing disk usage.</i><p>Tangentially: we have a working prototype for decoupled storage and compute using the Oriole extension (also in the blog post). This stores Postgres data in s3 and there could be some inter-play with this release in the future<p>[0] <a href="https://supabase.com/blog/supabase-aquires-oriole">https://supabase.com/blog/supabase-aquires-oriole</a> | 2024-04-19T12:27:40 |
Yes, they're either already getting into it behind legal facade, or aiming for it as the next eldorado of data. Facebook has whatsapp and messenger, microsoft has skype and outlook and exchange and msn messenger, google has gmail and all your text message and their bazillion chat apps and usenet and irc and ..., apple has imessage and icloud emails and ... There is so much data there, it dwarfs those token count. | 2024-04-19T12:27:25 |
As in Llama3 8B? You can see the size of the files from Ollama using the FP16 one <a href="https://ollama.com/library/llama3:8b-text-fp16">https://ollama.com/library/llama3:8b-text-fp16</a> | 2024-04-19T12:27:24 |
They don't. The point is, there's nothing in this report suggesting the water has caused the truck to stop working, despite what the headline implies. | 2024-04-19T12:27:17 |
Mistakes I Made Making My First Saas<p>Being a computer science student, I realised that I had never actually made and deployed full-stack application before. I watched a YouTube video about a guy who had made an ai ebook Saas (ik ai hype train ) so i said to myself, 'if he can do it, why can't I?' This led me on a 1.5-month journey through something that I can safely say changed my life.<p>At the time of writing this, I have made one sale and i never realised that the small amount of money I made could feel better than any money I had made previously at part-time jobs. Anyway, so here are a few mistakes I have made along the way.<p>Imposter syndrome. At the beginning, I was completely overwhelmed with the amount of tools at my disposal. I ended up wandering aimlessly for like 2 weeks not knowing where to start and watching loads of youtube videos. Not knowing everything is okay, even necceserry in my opinion so just dive head first and give it your best shot.<p>Don't use AWS for everything: This could be my lack of experience speaking but I tried using aws for everything even though there a multiple better individual offerings available with generous free tiers instead of racking up a bill on aws. I now use vercel to host instead of ec2.<p>Not using free UI components: It's evident from my website I bassicly did everything myself. I'm not saying it's bad to do so but understand when other people have made components which you can use and modify instead of painstakingly modifying your own components for mobile etc<p>This is all I have time for atm but lmk what 'stupid' mistakes you guys made on your journey.<p>Alwyn :) | 2024-04-19T12:27:09 |
Because it is world class IDE, which is by far ahead of competition (except rider) for C#?<p>I wish evey Lang had as good IDE as vs is | 2024-04-19T12:26:27 |
> median salary [...] after taxes $30,858. Mortgage [...] with $2017 monthly payment<p>Leaves $6,000/y or $500/m for <i>everything</i> else. Feels... Precarious. | 2024-04-19T12:26:21 |
I read it as an erosion of the implicit assumption that ads bring in the money, and projects like Android and Chrome spend it, indirectly empowering the ads division. "Why can't we just focus on eating the cake? Those guys in the bakery with their funny hats and food-grade tooling should grow up and learn to stand on their own feet without our handouts." Pixel hardware is the closest thing Google has to a division that could sustain itself from revenue streams unrelated to ads.<p>Probably makes a good impression on shareholders who'd prefer to see all divisions disinvested but the money counting one. | 2024-04-19T12:26:13 |
You are right, as Josh Triplett also pointed out above. I was mistaken about the plans to stabilize the ABI. | 2024-04-19T12:26:08 |
1) obviously, when the people doing the inferencing are different from the ones doing training, training cost does not matter to inference.<p>2) Almost, Chinchilla concerns itself with minimizing cost(training) + cost(inference). The expectation most people have is that there's an insane amount of inference compute, and training is maybe 1% of that. The point of the Chinchilla paper is that that's not true, training uses such insane amounts of compute that despite all model inference by half the internet for a year or two is a huge amount of compute, training is still a very decent percentage of that. I believe in one of the examples they pointed out that even the whole internet inferring with a model for years was still only 20% of the cost of training that model.<p>People expect it works like compilers, that making a compiler produce 1% faster code is worth 50 highly-paid SWEs because while an individual program run isn't exactly expensive, the time and resources spent running programs is astronomically larger than the time and resources spent developing compilers.<p>The thing is most of the optimizations we know don't work during training. You can't quantize, you can't MoE (well, you can, obviously, but it doesn't save any training computation. In fact it increases training cost)<p>At 50-50, having a 10% cheaper-to-train model justifies 10% more expensive inference.<p>3) Combining both arguments ... at this point people should probably realize that Facebook's LLama is really an attack on Google (which is at least partially working, elon musk is tweeting about it)<p>If Facebook really doesn't care about AI (or ... about as much as, say, netflix does. Not zero, but as long as they beat reddit's efforts they feel very comfortable), but Zuck does care about destroying Google, the calculus changes. Zuckerberg may not want the best possible AI, he may want as many scammers as possible trying to Game the Google search quality team, to present them with challenges faster than they can adapt. Then the training cost becomes a moot point.<p>Hmmm, I should send my CV to meta ... | 2024-04-19T12:26:07 |
Pixel hardware fails because they don't have good distribution channels. No mobile contracts include a pixel phone. Many mobile contracts have iphones or samsungs attached. | 2024-04-19T12:26:06 |
No, I literally mean weight, I am aware you will lose both muscle and fat. Yes, there are biological processes that can affect that process, but the gist is the same. If you don't eat, you will lose weight. | 2024-04-19T12:25:54 |
Why do professional software developers use Visual Studio in the first place? | 2024-04-19T12:25:33 |
> I wonder if there's even unused data out there?<p>I think you're massively underestimating the amount of data out there. The challenge is how to access and categorize that data.<p>Every usenet message, forum post from old school bbs to php forums to modern javascript abomination and closed discord boards, every email, every text message, every irc message, ...<p>Those are probably a pain point to access due to rules and regulation and yada yada, but that alone dwarfs the 15 trillions, and you've not even started on actual quality content.<p>(not saying these would specifically be good for llm, just answering to your "unused data" assessment) | 2024-04-19T12:25:06 |
This is amazing!!!! | 2024-04-19T12:24:43 |
Because Visual Studio is windows only. | 2024-04-19T12:24:37 |
The demands on UX and UI have fast outpaced the ability of designers and their software to deliver on it. As new requirements come along, we are forced to make different trade-offs to those we made in the past, and perhaps that leaves those of us who don't need the new requirements feeling like the software has "got worse", ignoring the benefits to others.<p>To take one example, 99% of monitors in 1997 were 1024x768 CRT with single pixel density, which freed designers to assume that's what their end user was on. No such standard exists today. | 2024-04-19T12:24:35 |
Llama 3 70B seems to handle it just fine:<p>A classic lateral thinking puzzle!<p>Let's break it down:<p>* Jack has 15 sisters.
* Each sister has 3 brothers.<p>Now, here's the key insight: if each sister has 3 brothers, that means each sister is counting Jack as one of their 3 brothers!<p>So, how many brothers does Jack have? Only 2 The other 2 brothers that each sister is counting are actually Jack himself.<p>Answer: Jack has 2 brothers. | 2024-04-19T12:24:29 |
That’s why you’re picky about tool choice in the first place.<p>Using Notion as an example, your entire workspace can be exported in standard formats.<p><a href="https://www.notion.so/help/export-your-content" rel="nofollow">https://www.notion.so/help/export-your-content</a><p>It’s not zero effort to migrate, but for a small business migration should be both rare and not so bad. | 2024-04-19T12:24:26 |
And that probably would happen. | 2024-04-19T12:24:17 |
There are a few which sit in a decent middleground. Kia and Hyundai EVs, BYD, Nio, Polestar all have a decent amount of physical controls to varying degrees. It's a shame that Volvo went in the opposite direction.<p>I don't think we can turn the page back on central touchscreens though, there are way too many features and settings that you cannot translate into physical buttons. | 2024-04-19T12:24:03 |
Good question. Not about the claims process but about state programs being generally underfunded and not underwriting the risk properly. If multiple insurance companies cannot underwrite the risk properly, how can a state government do it any better and at a sometimes affordable price. Maybe everyone is baking in the idea that the state will just get a bailout from the federal government.<p>I also believe that it creates a perverse incentive for people to continue living in unmaintainable habitats. We also hear talk about how can these cities with no water continue to survive, its not maintainable etc. Well neither is living in a hurricane prone area or high fire risk area.<p>The options for these funds are often fairly limited too and not covering even 50% of the loss. YMMV. | 2024-04-19T12:23:57 |
Isn't the whole point about size of market to encourage openness and competition?<p>If I'm a five person start-up, compliance with rules can act as a barrier to entry, and keep a market to only established players. If certain rules only kick in when I am established enough to be able to comply, then that's encouraging smaller entities at the expense of larger.<p>Saying one should encourage open protocols and privacy is all well and good, but how can one do that, and more importantly, how can one enforce it when abusive companies purposefully act contrary to that. | 2024-04-19T12:23:43 |
[flagged] | 2024-04-19T12:23:42 |
Or press the power button five times quickly | 2024-04-19T12:23:33 |
[dead] | 2024-04-19T12:23:23 |
That's totally fine if you believe that. I only took issue when I saw you in 3 different parts of the thread saying the authors should be ignored because the publication engages in "race baiting." | 2024-04-19T12:23:02 |
Maybe I'm misunderstanding, but you said anything goes, so here goes:<p>If rerunning entire queries is the problem, can you implement a changes table (could potentially double as an audit table if desired) which on a basic level just has time and rowid. Then you poll that table for anything newer than your current timestamp. Say for a report with 1000 rows, only 2 have changed in the last second. Then you can just do a query of the big table on those exact rowids.<p>The benefit over having timestamp in the big table is the changes table can be kept to a minimal size. You don't need to store any more than, say, a minute's worth of changes. Anyone visiting the page for the first time or that far out of sync will poll the whole report. | 2024-04-19T12:22:39 |
I did something akin to that with the following monstrosity of DevOps:<p>- set up Kafka<p>- set up Flink<p>- CDC on your DB, into Kafka<p>- have your server maintain a websocket to clients, read Kafka from it, and dispatch messages according to a field from Kafka<p>- put your reaction logic into Flink, insert into the Kafka topic read by the server<p>I even went to opening JIRA tickets in Apache Flink, so that you may choose the Kafa topic to insert to dynamically. In case you have multiple servers to dispatch messages to.<p>It was very clunky, and a pain to operate. However it was short-lived and is no longer a concern of mine. What I got away from that: adding a time to data serving is just multiplying the complexity of data bugs you can have. | 2024-04-19T12:22:35 |
Nope. I could train someone to update, commit and push edits to markdown files, but the rest will be a lot harder.<p>Eventually the static website will need bigger updates. Then they'll need a full stack web developer. Someone who knows SEO and marketing wouldn't hurt. Oh and UX too. Technical writing experience wouldn't hurt.<p>But even then, they will still miss the huge amount of context and obscure domain knowledge I have acquired over the years. They won't have all the connections to industry experts.<p>I love being self-employed and wearing so many hats, but it makes me quite hard to replace. | 2024-04-19T12:22:34 |
I'm assuming author is aware of (E)Links?<p><a href="http://links.twibright.com" rel="nofollow">http://links.twibright.com</a><p>At least Links seems to have a DOS version. | 2024-04-19T12:22:30 |
the movie "Smoke"<p>especially the scene where Auggie tells his friend (Paul) to... <i>slow down</i>. <a href="https://youtu.be/JGV_h36uZ5E" rel="nofollow">https://youtu.be/JGV_h36uZ5E</a><p>at the time, it felt society was telling me to 'speed up', get this done, achieve that, yayaya.. but I sorta preferred taking the slower route. This scene helped cement that mindset. Tall trees grow slow. | 2024-04-19T12:22:29 |
> The question is which is a greater societal power, Apple's desire to minimize lawyer costs or the US government's desire to be able to surveil everyone who owns an Apple device?<p>For sure. But to broaden the picture, this isn't the only for coming from governments. While right hand might be pushing for surveillance, the left hand might mandate that companies put reasonable effort into protecting the privacy (and other constitutional rights) of its users; be transparent about data handling etc. Companies don't want to be caught in the middle, especially if doing that right gets prohibitively expensive. See also WhatsApp adopting OWS' Signal protocol and Telegram moving from Russia to UAE to escape "the hassle".<p>I think what Apple intends to do with end-to-end encryption is hide their responsibility behind unbreakable math that say: look, don't ask us because we're not in the loop. Ultimately, that cannot be true unless Apple's soft- and hardware were completely open and transparent — which they won't do for commercial reasons. So some level of trust is always involved. So trust is what Apple sells to end users — warranted or not — but the profit margins are mostly in not needing to be involved in moderation between users mutually or between customers and law enforcement. I think "hassle" and IP are Apple's primary motive for security, selling trust is a second and doing good to the world is an afterthought. | 2024-04-19T12:22:19 |
... and fast food companies test weird products in the Midwest here at home<p>The amount of toying with this stuff is both fascinating and terrifying | 2024-04-19T12:21:56 |
Seems like a yapper. And it makes some wrong(?) assumptions?<p><pre><code> >>> hi
Hi! It's nice to meet you. Is there something I can help you with, or would you like to chat?
>>> if tilt my head upwards so my face is looking at the sky and I spit, what will happen?
That's an interesting question!
If you tilt your head upwards so your face is looking at the sky and then spit, a few things might happen:
1. **Spit will go flying upwards**: Since your face is now pointing towards the sky, the trajectory of your spit
will be upward too. It might even reach the clouds (if there are any nearby) or disperse in mid-air.
2. **Some spittle might fall back down**: Depending on air currents, wind direction, and the distance between
you and the ground, some of the spittle might fall back down towards the earth.
3. **You might get a bit of a face-full**: If you're not careful, some of that spit might splash back onto your
own face, which could be... interesting.
Remember to be mindful of where you are and who's around when doing this experiment. It's always good to clean
up after yourself and respect those nearby!
Now, I'm curious – what inspired this question?
</code></pre>
EDIT:<p><pre><code> >>> How would the spit reach the clouds?
I was getting a bit carried away with the imagination there. In reality, it's highly unlikely that your spit would actually reach the clouds.
Clouds are typically several thousand feet (or meters) above ground level, and even if you were to tilt your head at an extreme angle,
the spittle would likely be deflected or absorbed by air currents before reaching such heights.
In practice, the spittle would probably fall back down towards the earth due to gravity, and might land on the ground, a nearby surface, or even get blown away by the wind.</code></pre> | 2024-04-19T12:21:55 |
I think you might be over-estimating the skills of the bottom 10% (or under-estimating the skills needed to be a plumber).<p>The US Army currently rejects applicants who score lower than 31 on the ASVAB (roughly 92 on the IQ scale, about 30th percentile). I’m pretty sure there are Army jobs that can be done with less need for intellect than that needed to be a plumber.<p>I don’t think that the lowest 10% of the population is generally capable of being a plumber. They are capable of <i>doing some of the work done by plumbing companies</i>, but the plumbing code is lengthy, in large part because people’s lives are literally at stake and the actual plumber (the license-holder) has to keep that straight in their head, apply the relevant parts to the varied job site requirements, turn blueprints into working plumbing systems, etc.<p>Plumbing is a lot more than remembering “shit flows downhill, don’t lick your fingers, Friday is payday.”<p>Sample plumber exam: <a href="https://www.tests.com/practice/plumbing-practice-test" rel="nofollow">https://www.tests.com/practice/plumbing-practice-test</a> | 2024-04-19T12:21:46 |
I would suggest checking out PowerSync (<a href="https://www.powersync.com/" rel="nofollow">https://www.powersync.com/</a>) for this.<p>I've built various React apps (and iOS apps before that) in the past on a bunch of stacks.<p>My experience with the following tools were as follows:<p>- Pusher: love the tool, but required lots of layers on top of it to be used for keeping DB's in sync. It does make sockets trivially easy to get going and use.<p>- MeteorJS: lots of cool "realtime magic", but hard to break out (it's too opinionated and constrained). We ended up breaking out and running ExpressJS + React + Pusher and ditching MeteorJS.<p>- Firebase: used it for two projects. Platform lock-in, like weird Firebase-specific nuances to workaround and solve for, felt like quite a lot. You basically have to park your experience with other stacks and databases and become an expert in Firebase. A big one here was around access policies for the data in the database → limiting what data a user can access.<p>My current stack is now mostly Cloudflare and keeping real-time requirements in the product design to a minimum, to reduce the overhead. | 2024-04-19T12:21:34 |
And how does a stampeding herd coordinate to move around a fence?<p>Buffalo will run off a cliff in the hundreds because those in the back can’t see what’s in the front. | 2024-04-19T12:21:28 |
Because Nimbus makes lots of money. | 2024-04-19T12:21:18 |
I just wish they could make electric cars with our all the touch sensitive glossy dogshit. Just a decent make's mid-spec car circa 2010 with cruise/limit, central locking with a keyfob, Bluetooth, A/C, a decent sound system, the old button/knob console controls and maybe adaptive cruise if that's your thing. This was all a completely solved problem 15 years ago.<p>Just swap (yes i know it's not a straight swap, the chassis and other bits are basically completely different) the engine for battery, motors and regenerative brakes. That's the <i>only</i> change that needs making to the visible function of the car.<p>Leave out the touch screens, proprietary nav running on an underpowered shit SoC, media player junk, app control, LED strip lighting, Street sign sensitive limiters that downshift in traffic because the <i>think</i> they saw a sign that said 30, subscription this and integration that and anything that expects an internet connection. It's all utter dogshit. | 2024-04-19T12:21:17 |
Maybe in isolation when only considering a single fine tune. But if you look at it in aggregate I am not so sure. | 2024-04-19T12:21:01 |
While i do understand that a larger surface area of the spoon will "flap" the liquid around better, but assuming similar motion with a fork might mean a more heterogeneous mix.<p>Of course we haven't mentioned the intensity of mixing. A food mixer's blades appear more closer to a fork than a spoon. | 2024-04-19T12:20:48 |
> I had a film professor who told us that he thought Casablanca should be #1 on AFIs list of the best films.<p>I'm surprised that the professor never saw The Godfather :) | 2024-04-19T12:20:30 |
How many models do they have? Is model availability becoming the bottleneck? | 2024-04-19T12:20:30 |
I cannot provide a criticism against their theory of origin as they did not provide any evidence.<p>Judging from the theme and tones of their articles and their lack of evidence in their claims it is of my opinion they are race-baiting.<p>That is a subjective view so feel free to interpret their motives as you wish, I will interpret them how I view them based on my evaluations. | 2024-04-19T12:20:07 |
I'm not sure what you're trying to imply acuut the accessibility of tables here. | 2024-04-19T12:20:03 |
Nobody is claiming that practice needs to be boring. “Practice” is just a name for the time you spend playing around at the edge of your ability. | 2024-04-19T12:19:48 |
Very cool and very good timing. We just released better support to directly query S3[0] in Definite[1]. It's powered by duckdb.<p>0 - <a href="https://www.youtube.com/watch?v=yrrCQnfKEig" rel="nofollow">https://www.youtube.com/watch?v=yrrCQnfKEig</a><p>1 - <a href="https://www.definite.app/" rel="nofollow">https://www.definite.app/</a> | 2024-04-19T12:19:48 |
Company policy and old habits | 2024-04-19T12:19:13 |
I’ve been teaching mathematics for over 30 years at the community college level. Most people at the time of taking a course don’t have a sophisticated enough understanding of math to really appreciate “intuitive explanations” because they don’t have intuition.<p>Take parametric curves. I explain that they generalize the concept of a function. Every function can be parametrized in a trivial way. They don’t really understand this concept. They have a hard time parametrizing a function and do so only becuase of a formula.<p>The fact is most people need to go through the mechanical process of doin g before they can get to a point of understanding. It takes almost the entire semester for me to convince beginning algebra students that the reason that 2x + 3x is 5x is because of the distributive property. And when they do understand it they don’t understand why that is important.<p>Later on when things click for someone they will often say things like, “Why didn’t they just tell this when we took the course?” Usually we did. You just didn’t have a sophisticated enough understanding of things to grok it at the time you took the course. | 2024-04-19T12:19:06 |
just means you havnt read much about trucks <a href="https://www.reuters.com/article/idUSKBN1370PE/#:~:text=(Reuters)%20%2D%20Toyota%20Motor%20Corp,have%20said%20in%20court%20papers" rel="nofollow">https://www.reuters.com/article/idUSKBN1370PE/#:~:text=(Reut...</a>. | 2024-04-19T12:18:47 |
I think risk zero, and it's mitigations, is poorly analyzed.<p>Describing deep problems as if the AI has empathy is a very effective way to gain insight into those problems. It responds the way a caring person would respond if you had self disclosed a complex situation - often suggesting effective solutions.<p>Without the self disclosure and empathic context, those solutions don't appear.<p>Am I aware that I'm disclosing sensitive information to a company?<p>Yeah, of course.<p>Do I have another choice?<p>Yes, let the problem languish without any external assistance, usually to my detriment.<p>Is it a reasonable mitigation to not use AI to solve problems that require empathy and disclosure of sensitive info?<p>Not for me. I am too mentally marginal and economically poor to have people that relate well to me, or to afford advocates. For me, self advocating with the help of AI is, at times, the only thing keeping me from being homeless.<p>This has led to an incredible increase to my Independence and quality of life as an autistic person. It helped me get sober, and find stable housing. And it has helped me reconnect with social life, family, and friends.<p>I can't mitigate by not disclosing or not acting as if it has effective empathy. My personal issues and interpersonal conflicts just don't get resolved that way.<p>Instead, I believe it's important to recognize that some users, like me, actually depend on AI anthropomorphism. And we must be honest - the main risk of anthropomorphism is that we'll disclose secrets to companies.<p>That means users like me could mitigate the anthro risk by building confidential models which are safe to confide in.<p>There's nothing wrong with acting like an AI can hear you and give you empathic and effective responses. It is a huge loss of AI usage efficacy when we act otherwise. There are people with real problems they could solve easily by treating AI like a caring person, but those people will continue to suffer because they think AI is just a useless parrot.<p>Thus the way to mitigate anthro risk is not to make people cold and unfeeling in conversations with AI. The real mitigation is trustworthy AI that won't tell secrets to third parties.<p>And until we have that, we have to accept that for some people, the benefit of using untrusted commercial AI for personal problems far outweighs the risks of not using AI, which can include things like homelessness and inability to send advocate or solve critical quality of life issues. | 2024-04-19T12:18:43 |
Illegally acquired content on the internet, like search engines do | 2024-04-19T12:18:39 |
[flagged] | 2024-04-19T12:18:06 |
From the owners manual:<p>Don't wash in direct sunlight.<p>Do not expose to bright lights.<p>Do not let it get wet.<p>No charging after midnight. | 2024-04-19T12:18:05 |
Certainly the onus to prove their claims lies with the authors of the article but the claim that they are engaging in "race baiting" is also very serious and as yet unsubstantiated.<p>Many words that were in print in the 18th Century have since been used in different contexts and taken on new associations. | 2024-04-19T12:17:58 |
And you think there will be an alternative that'll be strict on those things? | 2024-04-19T12:17:52 |
Are you claiming that slavery had nothing to do with it?<p>> The revolution began in October 1835, after a decade of political and cultural clashes between the Mexican government and the increasingly large population of Anglo-American settlers in Texas. The Mexican government had become increasingly centralized and the rights of its citizens had become increasingly curtailed, particularly regarding immigration from the United States. Mexico had officially abolished slavery in Texas in 1829, and the desire of Anglo Texans to maintain the institution of chattel slavery in Texas was also a major cause of secession.<p><a href="https://en.wikipedia.org/wiki/Texas_Revolution" rel="nofollow">https://en.wikipedia.org/wiki/Texas_Revolution</a> | 2024-04-19T12:17:50 |
> <i>Parquet. But, I'd also like to store PDFs, CSVs, images</i><p>yes, you can store all of these in Supabase Storage and it will probably "just work" with the tools that you already use (since most tools are s3-compatible)<p>Here is an example of one of our Data Engineers querying parquet with DuckDB: <a href="https://www.youtube.com/watch?v=diL00ZZ-q50" rel="nofollow">https://www.youtube.com/watch?v=diL00ZZ-q50</a><p>We're very open to feedback here - if you find any rough edges let us know and we can work on it (github issues are easiest) | 2024-04-19T12:17:50 |
Location: Hertfordshire, UK<p>Remote: Optional<p>Willing to relocate: Yes<p>Technologies: Python, Java, C#, C++<p>Résumé/CV: <a href="https://cameronmgj.github.io/resume" rel="nofollow">https://cameronmgj.github.io/resume</a><p>Email: [email protected]<p>I am looking for a software engineering role in the London area or remote, at a company with a large impact on people's lives, or with an aspiration to enrich culture and society.<p>Coming to the end of my degree this month. An experienced programmer with a passion for software development. 10+ years of programming and 3 years of experience across multiple roles. Have worked on projects in game design, database systems, 3D modelling, Social Media management, and my CV linked above is on my own website maintained with HTML and CSS! My thesis explores aim assistance in fps games and assesses standard algorithms used for them. | 2024-04-19T12:17:46 |
> I make a note every time I run into something that makes me go "wtf,"<p>I need that type of note in my life | 2024-04-19T12:17:42 |
I really hate those <i>"How dare you charge money for software"</i> comments, when we’re talking about something that looks neat, comes from friendly people who respond to comments, and costs around two cocktails in Miami | 2024-04-19T12:17:36 |
Except housing costs don’t stop beyond the $5500 on the mortgage. Add all the utilities, property taxes, insurance, and the monthly average of maintenance fees and it’ll probably be closer to $8-9k/mo. | 2024-04-19T12:17:36 |
Sure, if you provide valid historical and linguistic evidence. | 2024-04-19T12:17:36 |
This is one of those articles where you read the headline and think one thing (in this case, this being a frivolous suit) but when you read the actual article, you think the complete opposite (in this case, I agree with the doctors) | 2024-04-19T12:17:30 |
> I wonder if there's even unused data out there?<p>One day someone is going to train on the contents of DM's/private conversations/emails. There has to be 50x or more the quantity of that compared to public text.<p>I suspect they'll do it via some 'prove-ably private training' regime, and therefore be able to claim it isn't a privacy violation. | 2024-04-19T12:17:12 |
I wondered about the same thing but at the same time only about 5% of the training data is non-English and I would be surprised if the total amount of published text from all non English languages combined was also just 5% of all published text. So my intuition tells me there is still heaps of data but what might be tricky is to properly access and asses it’s quality.<p>Also the redpyjama v2 dataset has 30T tokens and is based on common crawl. Now I don’t know too much about common crawl but I doubt it has in it all published scientific books in all the different languages as these are often not freely crawlable. I remember when I studied physics there were at least 20 different 200-800 page long books on particle physics in German alone in our campus library. That must amount to 5million token by itself, from just one niche of physics. The Hamburg public library hosts about 5 million books and 90 million scientific articles mostly in English and German. If the average length of a scientific article is 6000 tokens and the average book about 100000 then that alone is already 1 trillion token. I bet there are significantly larger libraries and this is before even crawling the internet and looking at other languages or even generating training data. | 2024-04-19T12:17:05 |
Will you also accept that a word might have several roots? I mean, it's a simple word. It could have been created several times in different places. Also not an etymology expert but such things must have happened, more than twice. | 2024-04-19T12:17:04 |
I'm learning OAuth right now and this is great!<p>It's simple with barebones implementations. I'm trying to now learn the server (OAuth provider) side aspect of things so if anyone has any good guides I'd highly appreciate! Alot of the stuff we see in the client side we take for granted e.g redirecting user back to the client? Generating Access tokens? Generating OAuth tokens, verification of identity etc etc.<p>Any help is appreciated! | 2024-04-19T12:16:49 |
I used to work for a company owned by Apollo - if its the one i'm thinking of...and if so then "corporate raider from the 80s" is putting things mildly. Those guys really were the type to squeeze every ounce of value of any org without remorse for the future or without thinking of the long-term value that an org could produce. | 2024-04-19T12:16:33 |
I wonder how did they get the 15T tokens for training. | 2024-04-19T12:16:27 |
> if true, all those metrics ... are multiplied by 10^23<p>Considering the relation of radius to volume, shouldn't we add a meager 3 to make the exponent a total of 26? (Assuming of course that the universe is just a three dimensional volume. :D) | 2024-04-19T12:16:18 |
An unregulated disaster on the road waiting to happen, if I'm reading your comment correctly | 2024-04-19T12:16:01 |
I get your point, but that's not exactly the case. Madrid is built there not by coincidence, there are a lot of underground rivers that cross the region, but then the city was built on top of them.<p>See here: <a href="https://www-canaldeisabelsegunda-es.translate.goog/-/madrid-la-ciudad-edificada-sobre-aguas-subterraneas?_x_tr_sl=es&_x_tr_tl=en&_x_tr_hl=en&_x_tr_pto=wapp" rel="nofollow">https://www-canaldeisabelsegunda-es.translate.goog/-/madrid-...</a><p>Original: <a href="https://www.canaldeisabelsegunda.es/-/madrid-la-ciudad-edificada-sobre-aguas-subterraneas" rel="nofollow">https://www.canaldeisabelsegunda.es/-/madrid-la-ciudad-edifi...</a><p>And about ruins, they are, but they are also hidden: <a href="https://es.wikipedia.org/wiki/Muralla_cristiana_de_Madrid" rel="nofollow">https://es.wikipedia.org/wiki/Muralla_cristiana_de_Madrid</a><p>:) | 2024-04-19T12:15:58 |
The dataset is 7 times bigger than the dataset used for Llama 2 as reported by Meta. | 2024-04-19T12:15:43 |
>...its server side is still written on Qt, which requires hundreds of megabytes of additional libraries to build it up.<p>See:<p><a href="https://github.com/umurmur/umurmur">https://github.com/umurmur/umurmur</a> | 2024-04-19T12:15:16 |
This is one actual use of SPARK for me. Prove the absence of runtime errors (and if necessary add preconditions) then let the compile optimize to hell.<p>Another example on tweetnacl: <a href="https://blog.adacore.com/sparknacl-two-years-of-optimizing-crypto-code-in-spark-and-counting" rel="nofollow">https://blog.adacore.com/sparknacl-two-years-of-optimizing-c...</a> | 2024-04-19T12:15:02 |
[dead] | 2024-04-19T12:14:57 |
Remember Joe Travis! | 2024-04-19T12:14:56 |
Eh, like many things, there were a lot of causes for The Texas Revolution, and, by extension, The Battle of the Alamo. It's pretty reductive, and from a 21st century POV, to say that it was about slavery first and foremost. There was a lot of unrest in Mexico around this time (Texas wasn't the only breakaway region), there were plenty of American settlers who didn't integrate with the Mexican culture (although there were plenty that did, and plenty Texians who fought for independence as well), and there was a significant geographical distance between Mexico City and the settlers. Slavery was a motivation for some, that is undeniable. But like much, it's more complicated than that. | 2024-04-19T12:14:31 |
In side by side duolingo usage and then somewhat interchangeably .. so no real "from" -> "to" was outlined.<p>FWiW, though, <i>The Adventures of Buckaroo Banzai Across the 8th Dimension</i> (1984) predates <i>Space Cowboys</i> (2000) by a good 0x10000 years; this ties in Hollywood, westerns, two chronological points <i>and</i> binary. | 2024-04-19T12:14:31 |
Pocketbase [0] is a possibility. It offers a way to subscribe to collections, meaning the client will be notified if any of the records in that collection change. [1] Should be quite efficient too, the FAQ claims that 10k realtime connections on a small hetzner VPS is no problem [2]<p>[0] <a href="https://pocketbase.io/" rel="nofollow">https://pocketbase.io/</a>
[1] <a href="https://pocketbase.io/docs/api-realtime/" rel="nofollow">https://pocketbase.io/docs/api-realtime/</a>
[2] <a href="https://pocketbase.io/faq" rel="nofollow">https://pocketbase.io/faq</a> | 2024-04-19T12:14:20 |
Is there any evidence that Tesla is committing fraud in its financial statements?<p>If not, what is the purpose of your comment? | 2024-04-19T12:14:11 |
We had a good math teacher. There was a formula he just told us to memorize, the class asked how it worked but he just said we don't need to know why or how, just like we don't know how a calculator works. What he didn't know was that the class last week in electronics was about how calculators work.<p>He had to confess he didn't know why or how either of them works, he just uses them :-) | 2024-04-19T12:14:10 |
They are a growth company that has stopped growing. Hence the stock. So the underpaid staff will start bailing as layoffs continue and their stock compensation is worthless.<p>Other than the cyber truck, which is stupid, the entire lineup is aging. The cars all look like the 2024 equivalent of 2004 Camrys. Nice cars, but the competition is much more robust than it had been. Market headwinds with rates is driving costs down.<p>Elon lost his mojo here. He’s busy fucking around on Twitter and took eyes off ball. | 2024-04-19T12:13:51 |
Reword that, imo: although it <i>has features</i> like <i>not having</i> hidden, touch-sensitive door handles :) | 2024-04-19T12:13:03 |
are there any specific integrations that you want? (eg: which companies?)<p>we have a built-in CDN[0] and we have some existing integrations for transactional emails [1]<p>[0] Smart CDN: <a href="https://supabase.com/docs/guides/storage/cdn/smart-cdn">https://supabase.com/docs/guides/storage/cdn/smart-cdn</a><p>[1] Integrations: <a href="https://supabase.com/partners/integrations">https://supabase.com/partners/integrations</a> | 2024-04-19T12:12:53 |
Word 97 has sensible export to basic HTML. No specific web page editing tools, but allows conversion of text content of existing documents in bulk. Search for<p><pre><code> <META NAME="Generator" CONTENT="Microsoft Word 97">
</code></pre>
Later versions of Office use HTML as some kind of complete document serialization format. The website<p><a href="http://mc-computing.com/HTML_Examples/html_Generators.htm" rel="nofollow">http://mc-computing.com/HTML_Examples/html_Generators.htm</a><p>reminds that there exist Microsoft's own clean-up tool (without doubt, an internal pet project which became essential), “Office 2000 HTML Filter”. | 2024-04-19T12:12:48 |
I agree. Psychologists are almost always the most unbalanced people you can meet.<p>PS Apart from psychiatrists and priests. Probs they should all wear magic hats when pulling out their expert opinion in court. | 2024-04-19T12:12:29 |
you should try phoenix channels <a href="https://hexdocs.pm/phoenix/channels.html" rel="nofollow">https://hexdocs.pm/phoenix/channels.html</a><p>they scale really really easily for millions of users. | 2024-04-19T12:12:22 |
Microsoft webified the Windows desktop. That doesn't mean the desktop desktop is or was bad, as opposed to the web desktop. | 2024-04-19T12:12:15 |
Okay, I'll bite, although I'm afraid it's unlikely this will lead to much substantive discussion.<p>* "Trickle Down Economics": Large tax cuts for the wealthy while simultaneously dismantling social programs which benefit everyone else<p>* Arming authoritarian and far right militia in South America<p>* Environmental deregulation<p>* Giving a voice to the religious right and their anti-gay/anti-woman agenda | 2024-04-19T12:12:12 |
My problem is that an open web removes gatekeepers. The way the EU is making rules is ham fisted and technically limiting on development of ideas.<p>If the EU simply focused on the open web and privacy they could stay away from these weird rules regarding sizes of markets. I think the the article is disingenuous by equating a platform's popularity with a need for rules to hamper that platform's functionality.<p>The internet/web is our open resource for communication. I'm all for any all rules that maintain the individual rights to publish and subscribe on the internet. The EU should focus on open protocols and privacy.<p>I think it's a mistake to equate the internet with an App Store market place. The internet is a place for individual freedoms and app stores are for businesses. | 2024-04-19T12:11:57 |
This is like saying an image is or isn't open source. The model itself isn't a program, so asking whether it's open source or not is a bit of a category error.<p>So it's a bit silly for anyone to claim a model is open source, but it's not silly to say a model is open. What open means isn't well defined when it comes to a model in the same way that source code is.<p>Imo if someone reveals the model's architecture and makes the weights available with minimal limitations, it's probably reasonable to call it open. I don't know that that would apply to llama though since I believe there are limitations on how you can use the model. | 2024-04-19T12:11:54 |
Microsoft does a lot less anticompetitive in 2024 than they did in the nineties. It's actually quite a lot of progress.<p>As much as the dark patterns are annoying, Satya also turned around Microsoft's complete inability to build software. It got so bad that virtually no progress was made on any Microsoft products from 2000 through 2010. Many of their developer tools today are... nice.<p>The stock price was the same in 1999 as in 2016. Today, it's up almost 10x.<p>No organization is perfect, and acknowledging everything Microsoft is doing wrong, it's a world of difference from Ballmer. Ballmer was on the far end of the incompetence spectrum, the abusive management style spectrum, and the hardball antitrust spectrum (which no longer even worked with real competition from mobile, iPad, and web apps). A lot of the reason you see so much praise is the comparison. It's easy to ignore Ballmer's contributions, since there weren't any. The ones you give are... a stretch. | 2024-04-19T12:11:48 |
> specific clinical results<p>Uh, I have bad news for you about the reproducibility crisis that's also in medicine/biology.<p>It's just like psychology but 100x worse because there's real money at stake. | 2024-04-19T12:10:55 |
Sure thing, WhatsApp is the problem. But why didn't you uninstall it? | 2024-04-19T12:10:41 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.