So a powerful agent (or a mass of tiny agents with large total power) needs a different utility function on future worlds than that of a lone rationalist observer, due to the need to avoid exploits.
No, it needs a different method of maximizing expected utility. Avoiding moral sabotage doesn’t reflect a preference, it’s purely instrumental.
No, it needs a different method of maximizing expected utility. Avoiding moral sabotage doesn’t reflect a preference, it’s purely instrumental.
Thanks, this clicked.