All Science Papers

Table of Contents

Evaluating anti-scheming training

Share this article

Evaluations

1 min read

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Published on

15 July 2025

Table of Contents

Evaluating anti-scheming training

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 AI oversight methods, CoT monitoring is imperfect and allows some misbehavior to go unnoticed. Nevertheless, it shows promise and we recommend further research into CoT monitorability and investment in CoT monitoring alongside existing safety methods. Because CoT monitorability may be fragile, we recommend that frontier model developers consider the impact of development decisions on CoT monitorability.

Share this article

oUR FINDINGS

More papers

17 March 2025

Claude Sonnet 3.7 (often) knows when it’s in alignment evaluations

We evaluate whether Claude Sonnet 3.7 and other frontier models know that they are being evaluated.

Read More

Evaluations

Notes

05 July 2026

We need 3rd party Training-Run Assessments

Training-run assessments conducted by a 3rd party should become a standard part of frontier AI safety.

Read More

Science of Scheming

21 July 2026

Measuring Reward-Seeking via Contrastive Belief Updates

Visible forms of misbehavior are dropping in frontier models. Does that mean the models are becoming aligned, or are they just getting better at doing whatever they believe their grader rewards? Our paper finds that production reinforcement learning increases reward-seeking.

Read More

Science of Scheming

22 January 2024

We Need A ‘Science of Evals’

We argue that if AI model evaluations (evals) want to have meaningful real-world impact, we need a “Science of Evals”, i.e. the field needs rigorous scientific processes that provide more confidence in evals methodology and results.

Read More

Evaluations