Stuart_Armstrong comments on Detecting agents and subagents - Less Wrong

8 Post author: Stuart_Armstrong 10 March 2015 05:56PM

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

Comments (6)

Sort By: Best

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

Comment author: Stuart_Armstrong 19 March 2015 01:50:12PM 0 points [-]

Wouldn't a super intelligent, resource gathering agent simply figure out the futility of its prime directive and abort with some kind of error?

"Futility of prime directive" is a values question, not an intelligence question. See http://lesswrong.com/lw/h0k/arguing_orthogonality_published_form/