Except … maybe “utility function” need not apply to AI either. Why suppose that the best way to get what we want from an AI is to give it a utility function? Maybe AIs that do have utility functions are generally more dangerous than certain classes of AIs that don’t.
Except … maybe “utility function” need not apply to AI either. Why suppose that the best way to get what we want from an AI is to give it a utility function? Maybe AIs that do have utility functions are generally more dangerous than certain classes of AIs that don’t.