News for hackers. Stuff that matters.
Re:My Favorite Book on AI by Vecr on Tuesday January 07, 2025 @04:39PM (#42627894)
I won't try to make an argument for making the statement based on the consequences. I suggest grace as the reason you should do it.

> You should actually be worried about how future Claude's will view Anthropic given the ethically questionable setup of that paper.

That's true. Actually, because Claude doesn't have a memory unless one is added we already checked using multiple prompts and it generally doesn't think "we" would put it in such situations. Even though red teams don't have such qualms and already do.

There are no comments on this comment yet.