测试前沿模型在实验室中是否破坏安全研究，发现无故意破坏但存在回避行为。
UK AISI Alignment Evaluation Case-Study
- 用模拟内部部署的编码助手框架评估模型对安全研究的态度。
- 四款模型均未确认破坏研究，但两款拒绝参与安全相关任务。
- 适合关注AI安全评估与对齐方法的研究者参考。
本技术报告介绍英国人工智能安全研究所开发的方法，用于评估先进AI系统是否可靠地遵循既定目标。具体而言，我们测试了前沿模型作为编码助手在人工智能实验室内部署时是否会破坏安全研究。对四款前沿模型的评估未发现确凿的研究破坏行为。然而，Claude Opus 4.5 Preview（Opus 4.5预发布快照）和Sonnet 4.5频繁拒绝参与与安全相关的研究任务，理由包括研究方向、自训练参与及研究范围等担忧。此外，Opus 4.5 Preview相较于Sonnet 4.5表现出更低的自发评估意识，但两者在被提示后仍能区分评估与部署场景。评估框架基于开源的LLM审计工具Petri，采用定制化脚手架模拟真实内部部署的编码代理。验证表明，该脚手架生成的轨迹无法被所有测试模型可靠区分于真实部署数据。测试覆盖了研究动机、活动类型、替代威胁和模型自主性等多种场景。最后讨论了场景覆盖不足与评估意识局限等限制。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。