Lilian Weng(@lilianweng):Giving your models more time to think before prediction, like via smart decoding, chain-of-thoughts reasoning, latent thoughts, etc, turns out to be quite effective for unblocking the next level of intelligence. New post is here :) “Why we think”:

Lilian Weng

@lilianweng

Co-founder of Thinking Machines Lab @thinkymachines; Ex-VP, AI Safety & robotics, applied research @OpenAI; Author of Lil'Log

加入 December 2009

189 正在關注 275.5K 粉絲

Lilian Weng@lilianweng

2025.05.17 15:09

Giving your models more time to think before prediction, like via smart decoding, chain-of-thoughts reasoning, latent thoughts, etc, turns out to be quite effective for unblocking the next level of intelligence. New post is here :) “Why we think”:

140

3.6K

482

轉發到社區

熱門用戶