Stuart_Armstrong comments on Domesticating reduced impact AIs - All

9 Post author: Stuart_Armstrong 14 February 2013 04:59PM

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

Comments (104)

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

Comment author: Stuart_Armstrong 15 February 2013 12:13:39PM 2 points [-]

Extra clarification: in this example, I'm assuming that we don't observe the AI, and that we are very unlikely to detect the paperclip. How to get useful work out of the AI is the next challenge, if this model holds up.

Comment author: CCC 16 February 2013 05:53:07AM 0 points [-]

Ah. I see. That does, at least temporarily, resolve my point, though as you point out, it raises the question of how to get anything useful out of the system.