Thus one approach to designing moral machines is to sidestep the tricky problem of robots’ inner lives, and deal instead with a view of morality that seems far more definite, and more amenable to the nature of robotics: rule-based ethics. The question then becomes, which system of rules or ethics should we program robots to follow? Though Friendly AI researchers seem only dimly aware of this, they are actually not the first to argue over which system of ethics is best — and those prior efforts have hardly met with consensus. (Indeed, most Friendly AI theorists’ apparent ignorance of over two millennia of serious ethical inquiry is frankly astonishing.) Nor are they the first to try to reinvent ethics as a subdiscipline of mathematics. But guaranteeing ethical behavior in robots would require that we know and have relative consensus on the best ethical system (to say nothing of whether we could even program such a system into robots). In other words, to truly guarantee that robots would act ethically, we would first have to solve all of ethics — which would probably require “solving” philosophy, which would in turn require a complete theory of everything. These are tasks to which presumably few computer programmers are equal. {read}