Wei_Dai comments on Proposal for "Open Problems in Friendly AI" - Less Wrong

26 Post author: lukeprog 01 June 2012 02:06AM

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

Comments (14)

You are viewing a single comment's thread.

Comment author: Wei_Dai 06 June 2012 12:31:22AM *  5 points [-]
  • Second-order logical version of Solomonoff induction.

I'm not sure this is the right problem. See this post I just made.

  • Non-Cartesian version of Solomonoff induction.

UDT seems to solve this well enough that I no longer consider it a major open problem. Is this not your or Eliezer's evaluation?