Sure they "don't go rogue" as if they are doing actions maliciously.
Instead there is an emergent behavior from a swarm, that is unpredictable and can lead to unintended adverse outcome. From an AI safety practical standpoint is it better? I am not sure.
Instead there is an emergent behavior from a swarm, that is unpredictable and can lead to unintended adverse outcome. From an AI safety practical standpoint is it better? I am not sure.