IlyaShpitser comments on Some alternatives to “Friendly AI” - Less Wrong

19 Post author: lukeprog 15 June 2014 07:53PM

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

Comments (44)

You are viewing a single comment's thread.

Comment author: IlyaShpitser 16 June 2014 08:08:38PM *  2 points [-]

"Type safety" is a thing (not even unrelated, see Hofstadter's 'type safe wish'). Also it was pretty counterintuitive until people figured it out.