Updates

Our research

Evaluations, interpretability and governance work on deceptive and scheming behaviour in frontier AI systems.

Stress Testing Deliberative Alignment for Anti-Scheming Training

We partnered with OpenAI to assess frontier language models for early signs of scheming — covertly pursuing misaligned goals — in controlled stress-tests (non-typical environments), and studied a training method that can significantly reduce (but not eliminate) these behaviors. Our results are complicated by models’ increasing ability to recognize our evaluation environments as tests of their alignment.

17 September 2025

Read paper

Science of Scheming

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

AI systems that "think" in human language offer a unique opportunity for research: we can monitor their chains of thought (CoT) for the intent to misbehave.

15 July 2025

Read paper

Evaluations

Frontier Models are Capable of In-Context Scheming

We evaluated six frontier models for in-context scheming capabilities. We found that multiple frontier models are capable of in-context scheming when strongly nudged to pursue a goal.

05 December 2024

Read paper

Evaluations

Latest

All Publications

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

17 March 2025

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

Evaluations

Notes

Evaluations

Notes

24 February 2025

Forecasting Frontier Language Model Agent Capabilities

Evaluations

Evaluations

11 February 2025

Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition

Interpretability

Interpretability

06 February 2025

Detecting Strategic Deception Using Linear Probes

Interpretability

Interpretability

23 January 2025

Demo Example - Scheming Reasoning Evaluations

Evaluations

Evaluations

05 December 2024

Frontier Models are Capable of In-Context Scheming

Evaluations

Evaluations

11 November 2024

The Evals Gap

Evaluations

Evaluations

31 October 2024

Towards Safety Cases For AI Scheming

Evaluations

Evaluations

15 August 2024

An Opinionated Evals Reading List

Evaluations

Evaluations