FTPickle

I think I’m just con­fused. Once a model ex­ists, how do you “red-team” it to see whether it’s safe. Isn’t it already dan­ger­ous?

[Question] Begin­ner’s ques­tion about RLHF

Ran­dom Ob­ser­va­tion on AI goals

The alien simu­la­tion meme doesn’t make sense

I be­lieve some AI doomers are overconfident