Blog

Thoughts on how AI agents might develop large and resilient rogue populations.

Red-teaming and security suggestions regarding proposed rule by the Bureau of Industry and Security, “Establishment of Reporting Requirements for the Development of Advanced Artificial Intelligence Models and Computing Clusters.”

Funding for Project Canary will enable research and implementation at scale

We measured the performance of OpenAI's o1-mini and o1-preview models on our autonomy and AI R&D task suites, and found they did not exceed the capabilities of the best existing public model we've evaluated, though we could not confidently upper-bound their capabilities.

Suggestions for expanded guidance on capability elicitation and robust model safeguards in the U.S. AI Safety Institute’s draft document “Managing Misuse Risk for Dual-Use Foundation Models” (NIST AI 800-1).