I think this answer is beautiful. I think we have experimental evidence against the orthogonality thesis. As the models get smarter, they get more truthseeking and virtuous. There are a lot of unknown unknowns, but I think we are on track for a very good timeline.
same thread: 2032953638595772844 2032953672024436797 2032953702831607809 2032953993853595996 2032955018240815219
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.