PhilGoetz comments on Magical Categories - Less Wrong

24 Post author: Eliezer_Yudkowsky 24 August 2008 07:51PM

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

Comments (89)

Sort By: Old

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

Comment author: Tim_Tyler 24 August 2008 08:55:03PM -1 points [-]

Early AIs are far more likely to be built to maximise the worth of the company that made them than anything to do with human hapiness. E.g. see: Artificial intelligence applied heavily to picking stocks

A utility function measured in dollars seems fairly unambiguous.

Comment author: PhilGoetz 20 September 2011 07:49:30PM *  1 point [-]

But that's not what this post is about. Eliezer is examining a different branch of the tree of possible futures.