Transparency Disclosures for Chain-of-Thought Monitorability
Jacob Davies, Theo Bearman
Abstract
Chain-of-thought (CoT) monitoring is one of the most valuable tools for monitoring advanced AI systems, but it is under threat. We argue that frontier AI developers should report specific indicators to make these threats trackable and to better facilitate coordination to preserve CoT monitorability. We identify five indicators that are both highly relevant and reasonably feasible to disclose, one for each link in a five-step chain on which CoT monitoring depends. The first, third-party CoT access and base architecture specifications, also underpins external verification of the rest. The others span CoT quality (naturalness and faithfulness) and monitoring effectiveness (detection and uplift). An audit of current disclosures by Anthropic, OpenAI, and Google DeepMind shows that no developer covers the full set, but that every indicator has been reported by at least one frontier developer. Because current disclosures rely largely on developers' own evaluations, we also recommend that a cross-developer audit be repeated with deeper access than public disclosures allow, either by embedded evaluators working within developers or by an Independent Verification Organization.
Create a lesson
Related papers
A Success Model at the End of Its Life Cycle: 30 Years of Regionalised Regional Rail in Germany
Lukas Iffländer
Neighbourhood Walkability and Cardiometabolic Morbidity in Greater London: A Fine-Grained Spatial Analysis
Benjamin T. Pike, Stephen Law, Sanja Šćepanović et al.
KeyMem: Temporal Occupancy Control for Robust Streaming VideoLLM Memory
Wei Song, Yuxin Cao, Xiao Cheng et al.
AI-Driven Transformation of Digital Platform Work: A Task-Based Model for Measuring Labour Disruption and Vulnerability, with Early Evidence from Online Freelancing in Kenya
Farhan Latif
Whose Safety? Addressing Anti-Blackness in the Age of AI Safety
Mírian Silva, Serena Oduro
Crisis Governance at the Joints. Mapping the Ethical and Societal Territory of Crisis Management Technologies: The Case of Human-Swarm Teaming
Anthony Longo