Sly comments on The AI in a box boxes you - Less Wrong

102 Post author: Stuart_Armstrong 02 February 2010 10:10AM

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

Comments (378)

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

Comment author: Sly 04 February 2010 04:49:55AM 0 points [-]

I suppose those two points rely on assumptions I made about the theoretical AIs behavior. I was thinking the AI acts in ways to optimize it's release chance. If it does not do this, then yes those points are problematic.

Comment author: prase 04 February 2010 07:57:55AM 0 points [-]

There can be some vindictiveness built in the AI in order to increase the release chance, by circumventing the type of defense you have stated in your second point.