News for hackers. Stuff that matters.

A comment on RLHF is just barely RL. Parent comment

Re:RLHF is just barely RL by jgalt212 on Thursday August 08, 2024 @07:23AM (#41190267)
But what makes you think the ai generated tests will correctly represent the problem at hand?
[ Parent | on HN ]

There are no comments on this comment yet.