Stuart_Armstrong comments on Naive TDT, Bayes nets, and counterfactual mugging - Less Wrong

15 Post author: Stuart_Armstrong 23 October 2012 03:58PM

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

Comments (39)

Sort By: Best

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

Comment author: Stuart_Armstrong 23 October 2012 09:18:53PM 2 points [-]

An AGI that functioned as deterministic software would be in actual Newcomb-like situations every time it was copied...

Comment author: JenniferRM 23 October 2012 09:37:54PM 1 point [-]

Yes. In that special case the assumption is definitely valid :-)

Comment author: David_Gerard 24 October 2012 07:32:08AM -1 points [-]

Modulo the halting problem.