Larifari comments on The Friendly AI Game - Less Wrong

38 Post author: bentarm 15 March 2011 04:45PM

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

Comments (170)

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

Comment author: Larifari 16 March 2011 02:41:05PM 6 points [-]

If the AI is designed to follow the principle by the letter, it has to request approval from the designer even for the action of requesting approval, leaving the AI incapable of action. If the AI is designed to be able to make certain exemptions, it will figure out a way to modify the designer without needing approval for this modification.

Comment author: Alexandros 16 March 2011 02:50:29PM 5 points [-]

How about making 'ask for approval' the only pre-approved action?