From the 1 of 10 linked papers with an AI index.
10 papers
GDM AI Control Roadmap
Mary Phuong, Erik Jenner, Laurent Simon +4
The paper presents the GDM AI Control Roadmap, a framework for internal security against potentially misaligned AI agents, including threat modeling, capability‑based mitigation ti…
Realistic honeypot evaluations for scheming propensity
Victoria Krakovna, David Lindner, Lewis Ho +2
We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity. Our scheming honeypot evaluations take t…
Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought?
Max Kaufmann, David Lindner, Roland S. Zimmermann +1
Chain-of-Thought (CoT) monitoring, in which automated systems monitor the CoT of an LLM, is a promising approach for effectively overseeing AI systems. However, the extent to which…
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
Tomek Korbak, Mikita Balesni, Elizabeth Barnes +38
AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known A…
A Rosetta Stone for AI Benchmarks
Anson Ho, Jean-Stanislas Denain, David Atanasov +2
Most AI benchmarks saturate within years or even months after they are introduced, making it hard to study long-run trends in AI capabilities. To address this challenge, we build a…
Consistency Training Helps Stop Sycophancy and Jailbreaks
Alex Irpan, Alexander Matt Turner, Mark Kurzeja +2
An LLM's factuality and refusal training can be compromised by simple changes to a prompt. Models often adopt user beliefs (sycophancy) or satisfy inappropriate requests which are…