Eugine_Nier comments on Moral Error and Moral Disagreement - Less Wrong

14 Post author: Eliezer_Yudkowsky 10 August 2008 11:32PM

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

Comments (125)

Sort By: Old

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

Comment author: Eugine_Nier 18 November 2010 04:23:37PM *  1 point [-]

The argument seems to be, if Preference1<Archimedes> is too different from Preference1<cousin_it>, then Preference1 is a bad method of preference-extraction and should be rethought. A good method Preference2 for preference-extraction should have Preference2<Archimedes> much closer to Preference2<cousin_it>. And since Preference1 is inadequate, as demonstrated by this test case, Preference1<cousin_it> is also probably hugely worse for cousin_it than Preference2<Archimedes>, even if Preference2<cousin_it> is better than Preference2<Archimedes>.

Of course the above constraint isn't nearly enough to uniquely specify Preference2.