News for hackers. Stuff that matters.
Re:RLHF is just barely RL by rafaelmn on Thursday August 08, 2024 @11:29AM (#41192586)
If you have a test that completes with the expected outcome and hits the expected code paths you have a working test - I'd say that heuristic will get you really close with some tweaks.

There are no comments on this comment yet.