Wei_Dai comments on A Master-Slave Model of Human Preferences - Less Wrong

58 Post author: Wei_Dai 29 December 2009 01:02AM

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

Comments (80)

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

Comment author: Wei_Dai 29 December 2009 09:26:23PM 1 point [-]

If you start with an AI design parameterized by preference, you are not going to enumerate all programs, only a small fraction of programs that have the specific form of your AI with some preference, and so for a given arbitrary program there will be no match.

When I said "all possible implementations of all possible utility functions", I meant to include flawed implementations. But then two different utility functions might map onto the same physical object, so we'd also need a theory of implementation flaws that tells us, given two implementations of a utility function, which is more flawed.

Comment author: Vladimir_Nesov 29 December 2009 09:45:46PM *  2 points [-]

When I said "all possible implementations of all possible utility functions", I meant to include flawed implementations. But then two different utility functions might map onto the same physical object, so we'd also need a theory of implementation flaws that tells us, given two implementations of a utility function, which is more flawed.

This is WAY too hand-wavy an explanation for "in principle, we can go backwards" (from a system to its preference). I believe that in principle, we can, but not via injecting fuzziness of "implementation flaws".