Re: Computability of consciousness

Eliezer S. Yudkowsky (sentience@pobox.com)
Sat, 27 Mar 1999 19:14:01 -0600

hal@rain.org wrote:
>
> A. It is a matter of interpretation whether a given system can be
> described as a computer running a specified program P
>
> B. Any conscious entity can be created ("instantiated") by running the
> proper program
>
> C. It is an objective matter whether a given conscious entity exists

This is one of the best summations of the dilemna I've ever seen.

I should note that one of the reasons I choose to deny B is because I feel that the "spirit" of physical law strongly differs from the "spirit" of Turing computability, and I imagine that physical law will eventually be found to be noncomputable.

Examples would be quantum randomness and the lack of a space of simultaneity.

Given that the physical Universe is probably noncomputable, why *should* I believe B, when it seems not to fit A and C? I've seen no counterexample of A and have no strong reason to doubt C.

But show me an objective way to define "instantiation" (that I can't poke three dozen holes in), and I'll certainly have to rethink my position.

-- 
        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.