Kaizhao Liang

kz919

AI & ML interests

Multimodal foundational model

Organizations

kz919's activity

posted an update 2 days ago
view post
Post
825
Just for the meme.

But the clear lesson I learnt from building these demos are, the more powerful the underlying base model is, the closer you will get to GPT4o1. CoT is nothing more than simply inducing the latent reasoning capability from the model.

kz919/GPT4-O1-Proximas
posted an update 6 days ago
replied to their post 11 days ago
view reply

I think there could be a better way to handle it when it doesn't generate valid moves, maybe like giving it feedback.

replied to their post 12 days ago
view reply

yeah Meta probably didn't put too much chess playing data in pretraining.
This is a instruction tuned general model.

posted an update 13 days ago
posted an update 16 days ago
posted an update 20 days ago
posted an update 24 days ago