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

mitchell_porter2 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: mitchell_porter2 07 April 2008 05:05:33AM 5 points [-]

"The GLUT is no more a zombie, than a cellphone is a zombie because it can talk about consciousness while being just a small consumer electronic device. The cellphone is just transmitting philosophy speeches from whoever happens to be on the other end of the line. A GLUT generated from an originally human brain-specification is doing the same thing."

You begin by saying that you are using "zombie" in a broader-than-usual sense, to denote something that "behave[s] exactly like a human without being conscious". The GLUT was constructed by observing googols of humans, but no human being plays a part in its operation. Are you going to call it conscious just because humans were an input to the design process? And even that's not true, in the extremely improbable but still possible case where the GLUT is generated by a random process. Is the presence of consciousness supposed to depend on the manner of creation, even though the result be physically identical?

It is possible that the point of this essay was just to say that if something talks with facility about being conscious, then with overwhelming probability the real thing is somewhere causally upstream, and that you were not taking a stand as to whether the GLUT in itself is conscious or not. But the evidence suggests otherwise: you do say that the randomly generated GLUT is not conscious, and you say that the GLUT generated by brute-force observation "is not a zombie". In which case I ask again, Is the presence of consciousness supposed to depend on the manner of creation, even though the result be physically identical?

And a bonus question: Suppose we incrementally modify the GLUT so that more and more of its responses are generated through computation, rather than just being looked up. Evidently there is something of a continuum between pure GLUT and shortest possible program implementing exactly the same responses. Where in this continuum is the boundary between consciousness and unconsciousness?