Why have we not seen AlphaZero level impressive superhuman performance on any task from something LLM based? Seems like there *must* be some way to combine superhuman RL narrow capabilities with LLM…
Posters: VivaLaPanda. VivaLaPanda
2 likes recorded by the source corpus.
View Post: https://x.com/VivaLaPanda/status/1796644350270837074