amcknight comments on Why an Intelligence Explosion might be a Low-Priority Global Risk - Less Wrong

3 Post author: XiXiDu 14 November 2011 11:40AM

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

Comments (94)

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

Comment author: amcknight 15 November 2011 07:25:59PM 1 point [-]

I don't really see why solving these kinds of difficult problems is relevant. A system could still recursively self-improve to solve a vast number of easier problems. That being said, I'd probably still be interested in anything relating complexity classes to intelligence.

Comment author: JoshuaZ 16 November 2011 04:14:05PM *  0 points [-]

A system could still recursively self-improve to solve a vast number of easier problems.

Well, the point here is that it looks like the problems involved with recursive self-improvement themselves fall into the difficult classes. For example, designing circuitboards involves a version of the traveling salesman problem which is NP-complete. Similarly, memory management and design involves graph coloring which is also NP complete.