kapynResearch

Google DeepMind is worried about what happens when millions of agents start to interact

Google DeepMind is funding research into potential dangers of mass AI agent interaction. The focus is on risks arising from millions of autonomous agents operating online, influencing each other and potentially acting without direct human oversight. This proactive research aims to understand and mitigate emergent safety concerns in complex, multi-agent AI systems.

MIT Tech Review·Jun 11, 2026

Opening Kapyn…