paulfchristiano comments on Cryptographic Boxes for Unfriendly AI - Less Wrong
You are viewing a comment permalink. View the original post to see all comments and the full post content.
You are viewing a comment permalink. View the original post to see all comments and the full post content.
Comments (155)
I agree completely. I don't think that renders a strong quarantine system useless though, because we don't really get to decide whether we find FAI or uFAI first, whoever discovers the first AI does.