collaborators

6 papers

cs.AI2025

Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models

Cameron Tice, Philipp Alexander Kreer, Nathan Helm-Burger +7

Capability evaluations play a crucial role in assessing and regulating frontier AI systems. The effectiveness of these evaluations faces a significant challenge: strategic underper…

cs.AI2025

CTRL-ALT-DECEIT: Sabotage Evaluations for Automated AI R&D

Francis Rhys Ward, Teun van der Weij, Hanna Gábor +6

AI systems are increasingly able to autonomously conduct realistic software engineering tasks, and may soon be deployed to automate machine learning (ML) R&D itself. Frontier AI sy…

cs.AI2025

Stress Testing Deliberative Alignment for Anti-Scheming Training

Bronson Schoen, Evgenia Nitishinskaya, Mikita Balesni +16

Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions,…

cs.AI2025

The Elicitation Game: Evaluating Capability Elicitation Techniques

Felix Hofstätter, Teun van der Weij, Jayden Teoh +3

Capability evaluations are required to understand and regulate AI systems that may be deployed or further developed. Therefore, it is important that evaluations provide an accurate…

cs.AI2025

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents

Jonathan Kutasov, Yuqi Sun, Paul Colognese +9

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by p…

cs.AI2025

AI Sandbagging: Language Models can Strategically Underperform on Evaluations

Teun van der Weij, Felix Hofstätter, Ollie Jaffe +2

Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or…