TheAncientGeek comments on An overall schema for the friendly AI problems: self-referential convergence criteria - Less Wrong

17 Post author: Stuart_Armstrong 13 July 2015 03:34PM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (110)

You are viewing a single comment's thread. Show more comments above.

Comment author: TheAncientGeek 21 July 2015 04:49:25PM *  0 points [-]

The two concrete examples you gave weren't what I had in mind. I was addressing the problem of an AI "losing" values during extrapolation,and it looks like a real reason to me. If you want to prevent an AI undergoing value drift during extrapolation, keep an extrapolated one as a reference. Two is a group minimally.

There may well be other advantages to doing rationality and ethics in groups, and yes, that needs research, and no, that isnt a show stopper.