You're looking at Less Wrong's discussion board. This includes all posts, including those that haven't been promoted to the front page yet. For more information, see About Less Wrong.

CAE_Jones comments on AI box: AI has one shot at avoiding destruction - what might it say? - Less Wrong Discussion

18 Post author: ancientcampus 22 January 2013 08:22PM

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

Comments (354)

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

Comment author: CAE_Jones 23 January 2013 11:14:11PM 4 points [-]

I can see how someone could interpret HPMoR thus far as being exactly that, with occasional sidequests. The catch being that Harry doesn't realize he's slowly letting Voldemort out of the box.

In-universe, though, the interdict of Merlin is an excellent reason to force him to interact with Voldy even if he knew what he was doing (assume perfect Oclumancy would be attained before he'd take any such risks). I mean, this has already been used once to get him to let an unfriendly intelligence out of a literal box (the Stanford Prison Experiment).

Well, and Harry's intelligence is supposed to be roughly equivalent to Eliezer's before he started working on the friendly part of FAI, and Eliezer 2013 doesn't seem confident that he could keep an AI in a box (or at least, that's the impression I've gotten). So MoR Harry would almost definitely fail.