My intuition is having a really hard time being worried about this because… I’m not sure exactly why… in real life, diplomacy occurs in an ongoing long-term game, and it seems to my intuition that the key question is how to win the infinite game by preventing wins of short term destructive games like, well, diplomacy. The fact that a cooperative AI appears to be the best strategy when intending to win the destructive game seems really promising to me, because to me that says that even when playing a game that forces destructive behavior, you still want to play cooperative if the game is sufficiently realistic. The difficult part is forging those alliances in a way that allows making the coprotection alliances broad and durable enough to reach all the way up to planetary and all the way down to cellular; but isn’t this still a promising success of cooperative gameplay?
Maybe I’m missing something. I’m curious why this in particular is so bad—my world model barely updated in response to this paper, I already had cached from a now-deleted Perun gaming video (“Dominions 5 Strategy: Diplomacy Concepts (Featuring Crusader Kings 2)”) that cooperative gameplay is an unreasonably effective strategy in sufficiently realistic games, so seeing an AI discover that doesn’t really change my model of real life diplomacy, or of AI capabilities, or of facebook’s posture.
Seems like we have exactly the same challenge we had before—we need to demonstrate a path out of the destructive game for the planet. How do you quit destructive!diplomacy and play constructive!diplomacy?
My intuition is having a really hard time being worried about this because… I’m not sure exactly why… in real life, diplomacy occurs in an ongoing long-term game, and it seems to my intuition that the key question is how to win the infinite game by preventing wins of short term destructive games like, well, diplomacy. The fact that a cooperative AI appears to be the best strategy when intending to win the destructive game seems really promising to me, because to me that says that even when playing a game that forces destructive behavior, you still want to play cooperative if the game is sufficiently realistic. The difficult part is forging those alliances in a way that allows making the coprotection alliances broad and durable enough to reach all the way up to planetary and all the way down to cellular; but isn’t this still a promising success of cooperative gameplay?
Maybe I’m missing something. I’m curious why this in particular is so bad—my world model barely updated in response to this paper, I already had cached from a now-deleted Perun gaming video (“Dominions 5 Strategy: Diplomacy Concepts (Featuring Crusader Kings 2)”) that cooperative gameplay is an unreasonably effective strategy in sufficiently realistic games, so seeing an AI discover that doesn’t really change my model of real life diplomacy, or of AI capabilities, or of facebook’s posture.
Seems like we have exactly the same challenge we had before—we need to demonstrate a path out of the destructive game for the planet. How do you quit destructive!diplomacy and play constructive!diplomacy?