Stuart_Armstrong comments on The president didn't die: failures at extending AI behaviour - Less Wrong Discussion
You are viewing a comment permalink. View the original post to see all comments and the full post content.
You are viewing a comment permalink. View the original post to see all comments and the full post content.
Comments (2)
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...