Browsing Tag
AI Control
1 post
AI control research and engineering approaches for monitoring, limiting, and responding to risky or misaligned AI agent behavior.
Google DeepMind’s AI Control Roadmap Treats Agents Like Insider Threats
Google DeepMind released an AI Control Roadmap for securing powerful internal AI agents. The plan borrows from cybersecurity, maps rogue-agent tactics to a MITRE ATT&CK-style taxonomy, and lays out detection and response tiers for systems that may soon act faster than human reviewers can supervise.
