Anthropic Introduces Embedded Independent Evaluator Program and Three-Tier Access Framework

Anthropic Introduces Embedded Independent Evaluator Program and Three-Tier Access Framework Anthropic has begun providing employee-like internal access to external safety evaluators, starting with nonprofit METR, as part of commitments under the White House Accord on Super Intelligence. The company is establishing a structured three-tier framework to govern external evaluators' system access and independent publishing rights. Six METR employees received internal hardware, office space, and system access comparable to Anthropic's internal risk assessment teams. Anthropic cannot veto METR's risk publications, retaining only defined redaction rights over confidential or commercially sensitive data. Anthropic established a three-tier access structure ranging from narrowly scoped reviews to fully embedded, employee-like evaluations. Other evaluators engaged include SecureBio for CBRN risk reviews, Accenture, and early talks with organizations like Hugging Face. Embedded Access Model with METR To bridge information asymmetry without publicly leaking sensitive compute or architectural details, Anthropic onboarded six METR staff members under enforceable security agreements. Operating under an analogy to resident bank examiners, the METR team has internal system access and the right to publish independent evaluations of risks and practices without company veto, subject only to predefined redactions for confidential or legal information. Three-Tier Evaluation Framework and Partnerships Anthropic is formalizing three tiers of evaluator access: tier one involves scoped investigations with publishing subject to approval; tier two expands information access and unapproved publishing with redaction dispute commentary; and tier three grants full embedded employee-like access. Alongside METR, SecureBio is reviewing chemical and biological risk chapters, and an extensive evaluation and red-teaming collaboration is underway with Accenture and Faculty.

Anthropic推行独立评估员嵌入机制，向METR团队开放员工级内部访问权限 Anthropic宣布开始向非营利组织METR的团队提供类似内部员工的系统访问权限，以进行前沿AI模型的风险评估，并制定了三层评估访问框架。 Anthropic为METR的6名员工配备了公司硬件、工位及内部工具访问权限，使其享有与内部风险评估团队大致相当的权限。 METR有权公开发布其风险评估结果，Anthropic无权否决发布，但可要求对客户数据等预定义敏感类别进行删减。 Anthropic建立了三级评估访问机制，涵盖从需批准发布的窄范围调查到类似METR的全面嵌入模式。 除METR外，Anthropic还与SecureBio、埃森哲开展评估合作，并与Hugging Face等组织展开早期沟通。 METR嵌入式评估运作方式 Anthropic将METR的6名员工以类似于银行常驻监管员的形式引入内部，为其配备公司硬件、办公空间并开放内部工具和系统权限。除客户数据、律师-委托人特权信息及模型架构等预定义敏感类别外，内部员工可像对待内部对齐风险同事一样与其共享信息。METR将独立公开发布其风险水平与事件分析，Anthropic无法否决发布，仅能要求对预设敏感信息进行删减，且该团队在严格协议下与其他METR员工保持隔离。 三级评估体系与多方合作进展 为在保护商业机密与实现公共问责间取得平衡，Anthropic设立了三级访问机制：第一级为范围有限的调查且发布需经批准；第二级开放更多信息并允许未经批准直接发布；第三级即类似METR的深度员工级嵌入。目前，SecureBio正审查其8月风险报告中的化学生物武器章节，后续有望升级权限；Anthropic还与埃森哲及Faculty合作开展红队测试与安全评估，并与Hugging Face等机构展开初步探讨。

Last month, we committed to [stronger independent, third-party assessment](https://darioamodei.com/post/we-must-pace-the-frontier) of our models and safety practices. We also signed the White House Accord on Super Intelligence, in which companies pledged to partner with independent external auditors or evaluators. Today, we’re announcing that we’ve started to give employee-like access to a team from [METR](https://metr.org/), a nonprofit that evaluates frontier AI models. METR will publish the results of its risk assessments. Over the past year, we’ve worked with METR on [several reviews of our Risk Reports](https://metr.org/risk-assessment/). We’re also working with [SecureBio](https://securebio.org/) and [Accenture](https://www.anthropic.com/news/accenture-embedded-evaluation) as evaluators, and are in early discussions with several other organizations, including [Hugging Face](https://huggingface.co/). Here, we explain our approach to working with evaluators. As models have become more powerful, they’ve required stronger safeguards and more challenging risk assessments. We want to be publicly accountable for the decisions we’re making. But we can’t publicly share all the information relevant to our safety work. Some of it could be useful to malicious actors, or is commercially sensitive, like compute or training information. Instead, we’re giving third-party evaluators deep access to our information, and are having them share evidence and reasoned conclusions about the risks involved in building our models. We aim to close the gap between what evaluators understand about a frontier AI company’s systems and what the company itself understands. To evaluate frontier models, evaluators need the following: Although the analogy isn’t exact, bank supervision operates on similar logic. Banks know more about their own risk positions than outsiders do, so regulators assign resident examiners to work inside the largest banks. If a bank’s risk-taking could threaten the public, third parties try to see that in advance. For the AI industry, this is a step toward [robust safety oversight](https://www-cdn.anthropic.com/files/4zrzovbb/website/0a58d567024a8b448ff15158ebc3625328dfcc1f.pdf). We’re moving quickly with multiple evaluators and learning actively about what kinds of partnership work. We’re committed to sharing updates as we go. We’ve onboarded six METR employees with company hardware, office space, and access to internal tools and systems that are roughly on par with what our own risk assessment teams have access to. Outside a small number of clearly defined categories (e.g., data about customers, attorney-client privileged information, or information about our model architectures), Anthropic employees are encouraged to share information with them just as they would with a fellow employee working on alignment risk.[1](https://www.anthropic.com/news/an-update-on-independent-evaluators#footnote-1) METR will publish its analysis of our risk levels, incidents, or practices. Anthropic can’t veto publication, but we can require them to redact information if it falls into predefined categories like the ones above. (Anthropic ultimately decides what information does and does not fall into these categories, although METR reserves the right to make certain statements about the level of access and information it received.)[2](https://www.anthropic.com/news/an-update-on-independent-evaluators#footnote-2) Our engagement with METR is limited to a small team operating under enforceable agreements. Other METR employees are siloed from that team’s work, including researchers who work with us on other projects. Embedded evaluation gives a few qualified people working under Anthropic’s security standards a close view of how we operate. It’s not a way for other organizations to obtain our information, or that of our customers and partners. We’re working on several other partnerships. Because these other partnerships are still in early stages, we’re providing these evaluators with more limited information, and they have more limited publication rights. Our goal with these early engagements is to make sure that our partners protect confidential information and have the requisite resources and expertise to evaluate our models. As partnerships progress and we build trust, we hope to fully embed more independent evaluators. We’re developing three tiers of access for evaluators. Over time, we hope to have several evaluators at the third tier, with each team publishing their own analysis of our risk posture and key decisions. **In the first tier,** evaluators conduct narrowly scoped risk investigations. We decide what access to provide a first-tier evaluator, and evaluators can publish their findings with our approval. **In the second tier,** evaluators can publish without our approval, and they have access to more information. We can still require removal of specific categories of information, though evaluators can publish their views on whether our redactions were justified. **The third tier** is the arrangement we’ve described with METR, with employee-like access and publication rights similar to those of the second tier. **SecureBio** is in the process of reviewing the chemical and biological weapons chapter of our [August Risk Report](https://www-cdn.anthropic.com/f61d49fa5596956a5dec75fea0e973bf6a6a8378/Redacted%20Risk%20Report%20August%202026%20.pdf), after completing and [publishing a pilot review](https://securebio.org/resources/anthropic_feb_2026_risk_review.pdf) of our previous risk report. After this review is complete, we will consider moving to projects with increased access.[3](https://www.anthropic.com/news/an-update-on-independent-evaluators#footnote-3) **With Accenture** and Faculty, we're working [toward an ambitious partnership](https://www.anthropic.com/news/accenture-embedded-evaluation) that includes evaluating and red-teaming models, conducting alignment assessments, testing model safeguards, and building capabilities across our organizations. We’re embedding evaluators voluntarily, and we believe every frontier AI company should do the same.