Why aren’t CEV and corrigibility combinable? If we somehow could hand-code corrigibility, and also hand-code the CEV, why would the combination of the two be infeasible?
Also, is it possible that the result of an AGI calculating the CEV would include corrigibility in its result? Afterall, might one of our convergent desires “if we knew more, thought faster, were more the people we wished we were” be to have the ability to modify the AI’s goals?
Why aren’t CEV and corrigibility combinable?
If we somehow could hand-code corrigibility, and also hand-code the CEV, why would the combination of the two be infeasible?
Also, is it possible that the result of an AGI calculating the CEV would include corrigibility in its result? Afterall, might one of our convergent desires “if we knew more, thought faster, were more the people we wished we were” be to have the ability to modify the AI’s goals?