What rebuilding AlphaGo teaches us about self-play, RL, and future of LLMs - Eric Jang

Walks through reimplementing AlphaGo and what self-play and amortized search imply for future RL and LLM training.

• LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.

• videoTyler Cowen — The #1 bottleneck to AI progress is humans
• videoChina is killing the US on energy. Does that mean they’ll win AGI? — Casey Handmer
• videoWhat are we scaling?
• videoThe most important question nobody's asking about AI.

• podcastEric Jang – Building AlphaGo from scratchDwarkesh Patel
• podcastReiner Pope – The math behind how LLMs are trained and servedDwarkesh Patel
• articleAcademia is for Ambition — Alex Zhang, MITwww.latent.space

Checking sign-in…

Loading comments…