It would surely create new failure modes for Friendliness: e.g. kill all humans to spawn a trillion barely sentients copy of an AI. But on the other hand I would say: not much. You’ll still have the hard problems of instilling a very fragile ontology (what is a conscious being, from the bottom up?), analyzing the consequences of the actions performed by the AI, judging carefully which values it is fulfilling or breaking and how much, etc.
It would surely create new failure modes for Friendliness: e.g. kill all humans to spawn a trillion barely sentients copy of an AI.
But on the other hand I would say: not much. You’ll still have the hard problems of instilling a very fragile ontology (what is a conscious being, from the bottom up?), analyzing the consequences of the actions performed by the AI, judging carefully which values it is fulfilling or breaking and how much, etc.