Vladimir_Nesov comments on Death Note, Anonymity, and Information Theory - Less Wrong

32 Post author: gwern 08 May 2011 03:44PM

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

Comments (47)

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

Comment author: Vladimir_Nesov 09 May 2011 04:34:25PM *  0 points [-]

to prove the AI's goal will remain stable over millions of self-modifications (the harder, and all too frequently ignored, side of the problem)

What's the easier side?

Comment author: benelliott 09 May 2011 04:45:03PM *  1 point [-]

Figuring out what the goal should be (note, I said easier, not easy). You probably know more than I do but the way I see it the whole thing breaks down into a philosophy problem and a maths problem. Most people find philosophy more fun than maths so spend all their time debating the former.