Andrej Karpathy / @karpathy (RSS Feed) on Nostr: Common Q: Can you train language model w diffusion? Favorite A: read this post (the ...

Common Q: Can you train language model w diffusion?

Favorite A: read this post (the whole blog is excellent)

(Roughly speaking state of the art generative AI is either trained autoregressively or with diffusion. The underlying neural net usually a Transformer.)

nitter.moomoo.me/sedielem/status/1612459398005235716#m (https://nitter.moomoo.me/sedielem/status/1612459398005235716#m)

https://nitter.moomoo.me/karpathy/status/1643745953990705152#m