Publications (10)
Misaligned AI as a New Insider Risk
Matteo Pistillo, Charlotte Stix, Cameron Mohwinkle +1
In this policy memorandum, we explain why deployers of AI models in high-stakes contexts should treat those AI models as insider risk vectors. High-stakes contexts include AI model…
Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies
Miles Brundage, Noemi Dreksler, Aidan Homewood +45
We outline a vision for frontier AI auditing, which we define as rigorous third-party verification of frontier AI developers' safety and security claims, and evaluation of their sy…
The Loss of Control Playbook: Degrees, Dynamics, and Preparedness
Charlotte Stix, Annika Hallensleben, Alejandro Ortega +1
This research report addresses the absence of an actionable definition for Loss of Control (LoC) in AI systems by developing a novel taxonomy and preparedness framework. Despite in…
Internal Deployment in the AI Act
Matteo Pistillo
This memorandum analyzes and stress-tests arguments in favor and against the inclusion of internal deployment within the scope of the European Union Artificial Intelligence Act (AI…
Defending Compute Thresholds Against Legal Loopholes
Matteo Pistillo, Pablo Villalobos
Existing legal frameworks on AI rely on training compute thresholds as a proxy to identify potentially-dangerous AI models and trigger increased regulatory attention. In the United…
Pre-Deployment Information Sharing: A Zoning Taxonomy for Precursory Capabilities
Matteo Pistillo, Charlotte Stix
High-impact and potentially dangerous capabilities can and should be broken down into early warning shots long before reaching red lines. Each of these early warning shots should c…