handoflixue comments on AI box: AI has one shot at avoiding destruction—what might it say?

handoflixue 22 Jan 2013 21:53 UTC
4 points
I wouldn’t expect any basilisks, given we don’t have any actual boxed AIs laying around. Although if you did come up with one already, I’d love to hear it via Private Message! :)
- Dorikka 22 Jan 2013 22:08 UTC
  12 points
  Parent
  I don’t expect any either, but would be similarly curious if someone thought that they’d found one.
  
  In the mean time I’ll refrain from responding to all the top level comments with “AI DESTROYED”. ;)
  - orthonormal 23 Jan 2013 4:10 UTC
    15 points
    Parent
    
    In the mean time I’ll refrain from responding to all the top level comments with “AI DESTROYED”. ;)
    
    Now I’m tempted to start replying to all top comments and posts on Less Wrong with “AI DESTROYED”.
    What links here?
    orthonormal's comment on Robin Hanson’s Cryonics Hour by orthonormal (30 Mar 2013 15:51 UTC; 6 points)
    - Dorikka 23 Jan 2013 4:14 UTC
      9 points
      Parent
      If a downvote isn’t enough… xD
    - handoflixue 23 Jan 2013 21:53 UTC
      7 points
      Parent
      AI DESTROYED.
      
      Goodness, that “orthonormal” AI was DEFINITELY unfriendly. It threatened to spam LessWrong! ;-)
  - handoflixue 22 Jan 2013 22:15 UTC
    1 point
    Parent
    Well, if you’re refraining I guess I should too. It seemed like a fun joke, too ;(