From: hal@finney.org
Date: Tue Jun 22 1999 - 23:51:45 MDT
Harvey Newstrom, <newstrom@newstaffinc.com>, writes:
> The replay is not conscious. To get the replay to work, the Turing Test
> administrator has to do the exact same test. If the question is delayed a
> second, the "brain" will answer a question that was not asked. If the
> speaker to the "brain" burned out, it will answer without hearing the
> question. If the questions are not identical, the wrong answers will be
> given. The really-conscious brain would correctly react to these
> situations. The fake-conscious brain will fail to react.
I may have been unclear about this "replay". The brain is entirely
normal and fully functioning. It's just that we "happen" to be giving it
exactly the same inputs we did on an earlier run.
Are you saying that if you allow a brain to run normally then it is
conscious, *except* if it happens to be given the same inputs that it
had on an earlier run, then it is not conscious?
Or would you say that a brain is conscious any time it is functioning
normally and processing information, even if it happens to be the case
that it is repeating an earlier run? If so, you can then go and read
Emlyn's and Eliezer's messages and see what you think of them.
> I would say that the second Turing Test is invalid, because the tester must
> cooperate to make the test work. The whole point of the Turing Test is that
> the testor cannot tell that the subject is not human. In the replay
> example, the Testor not only can tell, but must carefully craft the
> questions to make the subject appear to answer. Any failure on the part of
> the Testor will make the fake-brain fail. But the same failure on the part
> of the Testor to a real brain will not make the real brain fail.
Forget about the Turing test. That is not important here. Let's imagine
that the brain is not involved with a Turing test, instead it's learning
to bake a cake while telling you a funny story about when its great
grandfather came home from the war. It's just an ordinary brain, having
an ordinary conscious experience, like we all do all the time.
The point is not whether some external observer could determine whether
the brain is conscious by giving it a Turing test. The point is whether
the brain is *actually* conscious, a fact which is true or not regardless
of anyone else's opinions or whether it is willing to participate in
any kind of testing.
Hal
This archive was generated by hypermail 2.1.5 : Fri Nov 01 2002 - 15:04:16 MST