Eliezer_Yudkowsky comments on Reply to Holden on 'Tool AI' - Less Wrong

94 Post author: Eliezer_Yudkowsky 12 June 2012 06:00PM

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

Comments (348)

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

Comment author: Eliezer_Yudkowsky 13 June 2012 08:18:01PM 0 points [-]

Option 3? Doesn't work very well. You're assuming the opponent doesn't want to threaten the bishop, which means you yank it to a place where it would be safe if the opponent doesn't want to threaten it, but if the opponent clues in, it's then trivial for them to threaten the bishop again (to gain more advantage as you try to defend), which you weren't expecting them to do, because that's not how your search tree was structured. Kasparov would kick hell out of thus-hardwired Deep Blue as soon as he realized what was happening.

It's that whole "see the consequences of the math" thing...

Comment author: cousin_it 14 June 2012 07:46:51AM 14 points [-]

Either your comment is in violent agreement agreement with mine ("that might make the AI stupid in some respects and manipulable by humans"), or I don't understand what you're trying to say...

Comment author: Eliezer_Yudkowsky 14 June 2012 09:23:08PM 4 points [-]

Probably violent agreement.