DeepMind unveils tiered AI control roadmap to curb rogue agents
Google DeepMind released version 0.1 of its GDM AI Control Roadmap, outlining a four‑pillar strategy—misuse prevention, human oversight, robust deployment, and control science. The report maps threat models to concrete defenses, from low‑cost chain‑of‑thought monitoring to future real‑time access controls, linking mitigation tiers to model capability.