Less Wrong is a community blog devoted to refining the art of human rationality. Please visit our About page for more information.

MrP2 comments on GAZP vs. GLUT - Less Wrong

33 Post author: Eliezer_Yudkowsky 07 April 2008 01:51AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (166)

Sort By: Old

You are viewing a single comment's thread.

Comment author: MrP2 08 April 2008 03:51:21PM 2 points [-]

Of course a GLUT can be conscious. A problem some may have with it would be that it is not self-modifying, for the table is set in stone, right? Well, consider it from this perspective:

First of all, I assume that all or some of the output is fed back into the input, directly or indirectly (or is that cheating? why?). Then, we can divide the GLUT in two parts, A and B, that differ only in one input: the fact that the "zombie" has previously heard a particular phrase, for example "You are not conscious, you ugly zombie!".

There is no need for the being to have any other kind of "memory" apart from the GLUT, because we can postulate that from the point that that phrase is heard, and produces an output in the "B" zone of the table, there is no possible combination of feedback plus external inputs that go out of the GLUT by tha "A" zone. With a truly G LUT, we can keep al the state we need.

Then we can easily say that the table has been "changed", for the outputs are coming from an entirely separated zone ("B") of the table, and it cannot go back to "A", so we might as well discard that part and say that the table has changed.