Re: Identity

Eliezer S. Yudkowsky (sentience@pobox.com)
Tue, 24 Nov 1998 00:09:09 -0600

I'd just like to note, for the record, that I made the following two predictions back when this thread was started:

  1. None of the questions have real answers (for Turing processes).
  2. Nobody will change their opinion as a result of this debate.

That having been said:

Suppose you make a recording of a Turing machine, and play it back - load the state and tape from each tick back into memory. Is that an instantiation?

Suppose you run the Turing machine again, except this time you compare it with the recording and destroy it if it differs. Is that an instantiation?

Suppose that for each state transition, you look up the "real" transition using the standard state transition diagram (STD), but you actually transition to the state used last time (at that tick) according to the record. Is that an instantiation?

Suppose that for each state transition, you look up the real transition using the STD, compare it to the record, and replace it with the record if the record differs. But the record never does differ. Is it a real instantiation or just a recording?

If these processes are AIs, which of them are conscious?

It's questions like these, admittedly carried a bit farther, that converted me from my former position of Strong AI to a Penrosian noncomputationalist.
-- 

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