# UK AISI Alignment Evaluation Case-Study

arXiv: https://arxiv.org/abs/2604.00788 · HTML: https://mlsanity.com/paper/2604.00788/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 7 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Builds on (most cited first, 1 of 1)

- [The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness](https://mlsanity.com/paper/2505.14617/) (2025)

## Built on by (most cited first, 6 of 6)

- [Prefill Awareness in Large Language Models](https://mlsanity.com/paper/2606.12747/) (2026)
- [Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands](https://mlsanity.com/paper/2605.15164/) (2026)
- [When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels](https://mlsanity.com/paper/2605.06652/) (2026)
- [Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment](https://mlsanity.com/paper/2606.26071/) (2026)
- [Improving Evaluation Realism with Inference-Time Compute and Deployment Scaffolds](https://mlsanity.com/paper/2609.02302/) (2026)
- [Training LLMs to Verbalize Evaluation Awareness](https://mlsanity.com/paper/2609.36316/) (2026)

## Abstract (arXiv)

This technical report presents methods developed by the UK AI Security Institute for assessing whether advanced AI systems reliably follow intended goals. Specifically, we evaluate whether frontier models sabotage safety research when deployed as coding assistants within an AI lab. Applying our methods to four frontier models, we find no confirmed instances of research sabotage. However, we observe that Claude Opus 4.5 Preview (a pre-release snapshot of Opus 4.5) and Sonnet 4.5 frequently refuse to engage with safety-relevant research tasks, citing concerns about research direction, involvement in self-training, and research scope. We additionally find that Opus 4.5 Preview shows reduced unprompted evaluation awareness compared to Sonnet 4.5, while both models can distinguish evaluation from deployment scenarios when prompted. Our evaluation framework builds on Petri, an open-source LLM auditing tool, with a custom scaffold designed to simulate realistic internal deployment of a coding agent. We validate that this scaffold produces trajectories that all tested models fail to reliably distinguish from real deployment data. We test models across scenarios varying in research motivation, activity type, replacement threat, and model autonomy. Finally, we discuss limitations including scenario coverage and evaluation awareness.