News for hackers. Stuff that matters.
Re:Training open-source LLMs on ChatGPT output is a really b... by jimsimmons on Monday April 24, 2023 @02:21AM (#35684265)
In RL case it’s rewarded because the supervision signal is generated post hoc.

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.