Great questions; it sounds like you’ve really thought about this stuff! I don’t have time to answer in satisfying detail right now, but I’d be interested in talking about this. Doing a better post on this and relating it to work and biases in alignment research is on my to-do list.
Great questions; it sounds like you’ve really thought about this stuff! I don’t have time to answer in satisfying detail right now, but I’d be interested in talking about this. Doing a better post on this and relating it to work and biases in alignment research is on my to-do list.