Re: Yudkowsky's AI (again)

Eliezer S. Yudkowsky (sentience@pobox.com)
Thu, 25 Mar 1999 16:39:35 -0600

Lee Daniel Crocker wrote:
>
> So does that mean I get to make both of your lists: sane persons
> and dangerous persons? :-)

No, just the "sane" list. If I'm not including myself on the No-Upload list, I can hardly include you. Neither of us would dream of doing anything irrevocable without enough superintelligence that we would have arrived at the same truth no matter what ideas we started out with. There's no reason to trust us less for having figured this out ahead of the crowd.

I guess the question everyone else has to ask is whether the possibility that late-term Powers are sensitive to the initial conditions is outweighed by the possibility of some first-stage transhuman running amuck. It's the latter possibility that concerns me with den Otter and Bryan Moss, or for that matter with the question of whether the seed Power should be a human or an AI.

-- 
        sentience@pobox.com          Eliezer S. Yudkowsky
         http://pobox.com/~sentience/AI_design.temp.html
          http://pobox.com/~sentience/singul_arity.html
Disclaimer:  Unless otherwise specified, I'm not telling you
everything I think I know.