让模型在预测前有更多时间思考,比如通过 smart decoding、chain-of-thoughts reasoning、latent thoughts 等方式,对于解锁下一层次的智能非常有效。
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": https://lilianweng.github.io/posts/2025-05-01-thinking/