You're looking at Less Wrong's discussion board. This includes all posts, including those that haven't been promoted to the front page yet. For more information, see About Less Wrong.

solipsist comments on The president didn't die: failures at extending AI behaviour - Less Wrong Discussion

9 Post author: Stuart_Armstrong 10 June 2015 04:00PM

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

Comments (2)

You are viewing a single comment's thread.

Comment author: solipsist 13 June 2015 01:46:16AM *  4 points [-]

Nice article. Minor note: the use of "launch a coup against the vice president" as the example of nice behavior added a surprising amount of cognitive burden for me. Stroop effect and all that.

Comment author: Stuart_Armstrong 15 June 2015 11:35:12AM 3 points [-]

Noted! I did need behaviour that was nice in one world and nasty in the others, so I couldn't choose anything unambiguously nice, but situationally nice. You can get some more abstract concepts like pressing a button that has different effects in the different worlds...