Charles's First Org

AI & ML interests

None defined yet.

Recent Activity

JonasGeiping  submitted a paper about 2 months ago

NESSiE: The Necessary Safety Benchmark -- Identifying Errors that should not Exist

kotekjedi  authored a paper 6 months ago

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols

kotekjedi  authored a paper 7 months ago

Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM

View all activity

Team members 15