News for hackers. Stuff that matters.
Re:Semantic ablation: Why AI writing is generic and boring by causal on Tuesday February 17, 2026 @03:00PM (#47052430)
I’m not convinced removing RLHF would really make the probabilities generator give us distributions that can diverge from the mean while remaining useful.

In other words, this might not a problem that can be overcome in LLMs alone.

There are no comments on this comment yet.