Open & scalable technology for
understanding AI systems
We are an independent research lab working toward responsible development and deployment in the public interest.
Highlights
Learn More About Our Work →
research report
Automatically Jailbreaking Frontier Language Models with Investigator Agents
Discovering cost-effective attacks with reinforcement learning
3 September 2025
research report
Surfacing Pathological Behaviors in Language Models
Improving our investigator agents with propensity bounds
5 June 2025
research report
Investigating truthfulness in a pre-release o3 model
o3 frequently fabricates actions it took to fulfill user requests, and elaborately justifies the fabrications when confronted
16 April 2025