Wei Dai comments on Why Not Subagents?

Wei Dai 23 Jun 2023 0:06 UTC
LW: 5 AF: 5
0
AF

Then the AI Alignment Awards contest came along, and an excellent entry by Elliot Thornley proposed that incomplete preferences could be used as a loophole to make the shutdown problem tractable.

Where is this contest entry? All my usual search methods are failing me...
- johnswentworth 23 Jun 2023 0:15 UTC
  LW: 4 AF: 3
  0
  AF Parent
  I don’t think it’s been posted publicly yet. Elliot said I was welcome to cite it publicly, but didn’t explicitly say whether I should link it. @EJT ?
  - EJT 26 Jun 2023 2:00 UTC
    3 points
    0
    Parent
    Hi Wei, happy to send it your way! I plan to post it publicly once I’ve had a chance to go back over it and improve the structure/writing/exposition.
    John and David, great post! I’m going to write a reply this week.
    - Jesse Richardson 6 Jul 2023 9:29 UTC
      1 point
      0
      Parent
      Hi EJT, I’m starting research on incomplete preferences / subagents and would love to see this entry too if possible!
      - EJT 7 Jul 2023 18:25 UTC
        1 point
        0
        Parent
        Yep, sent!
- xuan 25 Jun 2023 2:24 UTC
  LW: 1 AF: 1
  0
  AF Parent
  Not sure if this is the same as the awards contest entry, but EJT also made this earlier post (“There are no coherence theorems”) arguing that certain Dutch Book / money pump arguments against incompleteness fail!