‘The prospect of creating beings with intelligence far beyond our own is hugely exiting. It is also hugely worrying because we don’t yet know if the immense power that we believe these agents would possess is going to be wielded in a way that helps or hurts us. That is, we are unsure of our ability to control powerful AIs if they are created, and equally unsure if they will act in a way that benefits humanity should they be fully autonomous. A way of insuring that autonomous AIs promote human interests rather than infringe on them, is to make sure they are programmed with the right conception of moral value, as well right and wrong.’ Olivier Couttalenc
2019-07-21