DeepMind launches $10M funding call for multi-agent AI safety research

DeepMind Blog

Google DeepMind and partners announce a $10M funding call for multi-agent AI safety research. The initiative aims to solicit proposals from the broader research community.

DeepMindMulti-agent systemsAI safety

See 3 more sources

When millions of AI agents interact with each other, new collective behaviors can emerge. 🌐...2 days agoGoogle DeepMind

Representational Similarity and Model Behavior in Multi-Agent Interaction5 days agoYujin Potter, Seun Eisape, Shiyang Lai, Alexander Huth, James Evans, Been Kim, Jacob Eisenstein, Dawn Song, Alane Suhr

Google DeepMind is worried about what happens when millions of agents start to interact2 days agoWill Douglas Heaven

DeepMind Blog

3 days ago