But now take that understanding to the AI: clearly we can build systems tat achieve higher integrity with whatever purpose they identify with. Also, it can be moral for you to eat meat if animal suffering does not make animals moral subjects (= if you don’t share their purposes).
Exactly, but they also tend to compute easy stuff in not very heterogeneous domains. If we can get them to compute what your mind does, can we give them higher integrity? Pretty sure we can.
-
-
i'm going to go with "no" here. -
Because Alpha Zero can turn chess into funky Tic Tac Toe in half a day, by considering Billions of games without losing coherence. Human brains cannot do that.
- 5 more replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.