News for hackers. Stuff that matters.

A comment on RLHF is just barely RL. Parent comment

Re:RLHF is just barely RL by jononor on Thursday August 08, 2024 @01:47PM (#41194263)
One can image critics and code rewriters that optimize for computational, code style, and other requirements in addition to tests.
[ Parent | on HN ]

There are no comments on this comment yet.