News for hackers. Stuff that matters.
Re:Controllable Fast and Slow Thinking by Learning with Rand... by hislaziness on Wednesday October 23, 2024 @01:03AM (#41921983)
As I understand, the LLM uses the techniques of searchformer - https://arxiv.org/abs/2402.14083. To do "slow thinking" doing a A* search using a transofrmer.

There are no comments on this comment yet.