EDIT: if you meant counterfactual mugging, I think one way to solve this is to use a low amount of computation power to select which agent to emulate, then use a high amount of computation power to run that agent. Of course, this is somewhat unsatisfying, since there isn’t a canonical way of choosing how much less computation power to use.
What’s counterfactual blackmail?
EDIT: if you meant counterfactual mugging, I think one way to solve this is to use a low amount of computation power to select which agent to emulate, then use a high amount of computation power to run that agent. Of course, this is somewhat unsatisfying, since there isn’t a canonical way of choosing how much less computation power to use.
Yup, I meant counterfactual mugging. Fixed.