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

Anonymous_Coward6 comments on Nonperson Predicates - Less Wrong

29 Post author: Eliezer_Yudkowsky 27 December 2008 01:47AM

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

Comments (175)

Sort By: Old

You are viewing a single comment's thread.

Comment author: Anonymous_Coward6 27 December 2008 05:18:05AM 5 points [-]

Why must destroying a conscious model be considered cruel if it wouldn't have even been created otherwise, and it died painlessly? I mean, I understand the visceral revulsion to this idea, but that sort of utilitarian ethos is the only one that makes sense to me rationally.

Furthermore, from our current knowledge of the universe I don't think we can possibly know if a computational model is even capable of producing consciousness so it is really only a guess. The whole idea seems near-metaphysical, much like the multiverse hypothesis. Granted, the nonzero probability of these models being conscious is still significant considering the massive future utility, but considering the enormity of our ignorance you might as well start talking about the non-zero probability of rocks being conscious.

I don't think anyone answered Doug's question yet. "Would a human, trying to solve the same problem, also run the risk of simulating a person?"

I have heard of carbon chauvinism, but perhaps there is a bit of binary chauvinism going on?

Comment author: DanielLC 08 September 2010 12:58:33AM -2 points [-]

I'm not sure if it's actually possible for someone to die painlessly. My idea was to base happiness on classical conditioning. If something causes you to stop doing what you were doing, you dislike it. If it stops you from doing everything that you do while you're alive, it must be very painful indeed.