timtyler comments on Thoughts and problems with Eliezer's measure of optimization power - Less Wrong

17 Post author: Stuart_Armstrong 08 June 2012 09:44AM

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

Comments (23)

You are viewing a single comment's thread.

Comment author: timtyler 08 June 2012 10:36:37AM *  5 points [-]

OP measures the system's ability to achieve its goals, not how hard these goals are.

Not really. It's often largely a measure of how big the specified solution space is - e.g.:

  • What's the smallest prime larger than a million, and smaller than a billion?

  • What's the smallest prime larger than a million, and smaller than a trillion?

Essentially the same problem, bigger solution space - more EOP [Eliezer Optimization Power].

Comment author: Stuart_Armstrong 08 June 2012 11:09:03AM *  2 points [-]

Thanks, have updated the text with a variant of that problem.