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.

NancyLebovitz comments on Open Thread, November 1 - 7, 2013 - Less Wrong Discussion

5 Post author: witzvo 02 November 2013 04:37PM

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

Comments (299)

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

Comment author: Eliezer_Yudkowsky 02 November 2013 08:42:48PM 4 points [-]

Torture might stand too great a chance of destroying the encryption key. Though I suppose if nanotech were sufficiently difficult to obtain, the possible key-destructive effects of torture might be balanced against the probability of a car running over the keyholder in the meantime.

Comment author: NancyLebovitz 02 November 2013 10:18:32PM 5 points [-]

I would think that confusion (set things up so the key-keeper is confused and distracted, then do some phishing) is in the same reliability range as torture, and less likely to get the AI in trouble.