I think that Newcomb's paradox does provide evidence for machine
consciousness, independent of implementation.

[A reminder. Newcomb's paradox:  A highly superior being from another part
of the galaxy presents you with two boxes, one open and one closed. In the
open box there is a thousand-dollar bill. In the closed box there is either
one million dollars or there is nothing. You are to choose between taking
both boxes or taking the closed box only. But there's a catch.

The being claims that he is able to predict what any human being will decide
to do. If he predicted you would take only the closed box, then he placed a
million dollars in it. But if he predicted you would take both boxes, he
left the closed box empty]

Let's replace the ``highly superior being from another part of the galaxy´´
by a machine.

It seems that choosing only the closed box is the best option. However since
the contents of the box is already fixed, it seems difficult to understand
how you could lose a million dollars by choosing both boxes. That seems to
contradict causality.

However, we must consider how the machine arrives at the prediction. Suppose
the machine simulates your brain and just computes what you will choose. It
is hard to see that there is any alternative to this. Then the paradox is
resolved if this computation generates your consciousness. If you are
standing in front of the two boxes, making up your mind, you don't know if
you are in the real world or the virtual world generated by the machine. So,
you can't say that the contents of the closed boxed is already determined.

How could you beat the machine? Suppose that the two boxes are in a room and
that the machine arrives at the prediction by scanning your brain moments
before you enter that room, and then calculating what you are going to do
next.

I propose this solution. Sneak into the room before the experiment is
supposed to start. Then, with a pencil, mark a wall with small cross, and
then leave again. Hopefully the machine won't notice the cross on the wall.

 At the start of the experiment you enter the room and you look at the
marked wall. If you see a cross, then you are in the real world and the
closed boxed is already filled. So you choose both boxes.

But if you don't see the cross, you are in the virtual room generated by the
machine. To make the machine fill the closed box with a million dollars you
have to choose only the closed box. Of course, you may ask why your virtual
version would care about your real version. I suppose that after the
simulation your virtual copy will live on with memory loss as your real
version.

Saibal


Reply via email to