The problems that infinite utilities make for utility theory are well-known. They apply just as much to people trying to use utility theory (which is the original motivation for utility theory) as AIs. I could assemble a bibliography of papers discussing various aspects of the problem, but only if there’s significant interest.
The problems that infinite utilities make for utility theory are well-known. They apply just as much to people trying to use utility theory (which is the original motivation for utility theory) as AIs. I could assemble a bibliography of papers discussing various aspects of the problem, but only if there’s significant interest.
I don’t think the implications are well-known (as the amount of downvotes indicates).