I'm somewhat skeptical of the idea that there isn't a universal morality (relative to some generalized Occamian prior-like-thing) that even a paperclip maximizer would converge to (if it was given the right decision theoretic (not necessarily moral per se) tools for philosophical reasoning, which is by no means guaranteed, so we should of course still be careful when designing AGIs).

There's goal system zero / God's utility function / Universal Instrumental Values.