3 papers
cs.CY2026
Expanding External Access To Frontier AI Models For Dangerous Capability Evaluations
Jacob Charnock, Alejandro Tlaie, Kyle O'Brien +2
Frontier AI companies increasingly rely on external evaluations to assess risks from dangerous capabilities before deployment. However, external evaluators often receive limited mo…
cs.CY2025
Securing External Deeper-than-black-box GPAI Evaluations
Alejandro Tlaie, Jimmy Farrell
This paper examines the critical challenges and potential solutions for conducting secure and effective external evaluations of general-purpose AI (GPAI) models. With the exponenti…
cs.CY2025
Assessing confidence in frontier AI safety cases
Stephen Barrett, Philip Fox, Joshua Krook +3
Powerful new frontier AI technologies are bringing many benefits to society but at the same time bring new risks. AI developers and regulators are therefore seeking ways to assure…