Archimedes comments on How might we safely pass the buck to AI?

[Archimedes]

A separate argument is that I’m think if you just do random search over training ideas, rejecting if they don’t get a certain validation score, you actually don’t goodhart at all. Might put that argument in a top level post.

I’d be interested in seeing this argument laid out.

[mattmacdermott]

I wrote it out as a post here.