ShardPhoenix comments on Sorting Pebbles Into Correct Heaps - Less Wrong

75 Post author: Eliezer_Yudkowsky 10 August 2008 01:00AM

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

Comments (99)

Sort By: Old

You are viewing a single comment's thread.

Comment author: ShardPhoenix 10 August 2008 04:59:07AM 1 point [-]

I am not quite sure what this story is getting at. I'd guess it's saying that we need to understand how human morality arises on a more fundamental (computable/programmable?) level before we can be sure that we can program AIs that will adhere to it, but the basis of human morality is (presumably) so much more complicated than the "prime numbers = good" presented here that the analogy is a bit strained. I may be interpreting this entirely wrongly.