News for hackers. Stuff that matters.

A comment on RLHF is just barely RL. Parent comment

Re:RLHF is just barely RL by acchow on Thursday August 08, 2024 @05:23PM (#41196465)
After much RL, the model will just learn to mock everything to get the test to pass.
[ Parent | on HN ]

There are no comments on this comment yet.