ata comments on Human values differ as much as values can differ - Less Wrong

13 Post author: PhilGoetz 03 May 2010 07:35PM

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

Comments (205)

You are viewing a single comment's thread. Show more comments above.

Comment author: Tyrrell_McAllister 05 May 2010 08:25:28PM *  0 points [-]

I assume we would want CEV to exclude the preferences of sociopaths and psychopaths, as well as those of people who are actually mistaken about the beliefs underlying their preferences.

I thought the idea was that, under CEV, sociopaths would just get outvoted. People with mutant moralities wouldn't be excluded, but, just by virtue of being mutants, their votes would be almost entirely drowned out by those with more usual moralities.

[ETA: Eliezer would object to calling these mutant moralities "moralities", because he reserves the word "morality" for the action-preferring algorithm (or whatever the general term ought to be) that he himself would find compelling in the limit of knowledge and reflection. As I understand him, he believes that he shares this algorithm with nearly all humans.]

Comment author: ata 06 May 2010 08:06:09AM *  1 point [-]

I wonder if, under the current plan, CEV would take into account people's volition about how CEV should work — i.e. if the extrapolated human race would want CEV to exclude the preferences of sociopaths/psychopaths/other moral mutants, would it do so, or does it only take into account people's first-order volition about the properties of the FAI it will build?

Comment author: Vladimir_Nesov 06 May 2010 11:11:34AM 1 point [-]

Ultimately, preference is about properties of the world, and AI with all its properties is part of the world.