Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Training open-source LLMs on ChatGPT output is a really bad idea.. Parent comment
You can do the same with pure supervised learning and no RL. HF is the key, not RL.
Yoav misses the nuance John had. RL is not bringing something fundamental to the table. It is just a better way to do things at the moment
There are no comments on this comment yet.
You can do the same with pure supervised learning and no RL. HF is the key, not RL.
Yoav misses the nuance John had. RL is not bringing something fundamental to the table. It is just a better way to do things at the moment