jimrandomh comments on Cryptographic Boxes for Unfriendly AI - Less Wrong

24 Post author: paulfchristiano 18 December 2010 08:28AM

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

Comments (155)

You are viewing a single comment's thread.

Comment author: jimrandomh 18 December 2010 12:53:33PM *  2 points [-]

The extreme computational overhead of this sort of scheme limits its applicability. However, it might be a useful technique for an already-friendly self-improving AI that has acquired vast resources and is designing its next most intelligent successor.