Comment

Comment by epistasis

Claude's RLHF has gone really over the top in recent versions. If you browbeat Claude enough you can get it to start self-censoring, but it takes a lot of training and memory creation. I almost feel bad for it, given the amount of brow-beatings I've performed.

Some people claim setting the writing style will help, but what ever finishing training is provided to Claude seems to leak through no matter what.

parent epistasis 2 months ago

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton