Nick_Beckstead comments on Tiling Agents for Self-Modifying AI (OPFAI #2) - Less Wrong

55 Post author: Eliezer_Yudkowsky 06 June 2013 08:24PM

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

Comments (260)

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

Comment author: Nick_Beckstead 07 June 2013 12:02:15PM 0 points [-]

To me this problem looks more like a problem with making decisions based purely on proofs, and not much related to self-modification.

I think I was implicitly assuming that you wouldn't have an agent making decisions based purely on proofs.