tailcalled comments on What in your opinion is the biggest open problem in AI alignment?

[tailcalled]

Ok, but then you haven’t solved the problem for the subset of people who decide they don’t want to cooperate.

[quetzal_rainbow]

Well, it’s a decision theory problem. I recommend “Unifying bargain” by Diffractor.

[tailcalled]

Maybe I will look at that again at some point in a while.