声明：美国政府指令暂停 Fable 5 与 Mythos 5 的访问

*Statement on the US Government Directive to Suspend Access to Fable 5 and Mythos 5*

来源：Anthropic 官方公告（Announcements）| 2026 年 6 月 12 日 | 英中对照版

The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees. The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance. Access to all other Anthropic models will not be affected.

美国政府援引国家安全相关权限，发布了一项出口管制指令，要求暂停所有外国公民——无论身处美国境内或境外，包括 Anthropic 的外籍员工——对 Fable 5 与 Mythos 5 的一切访问。该命令的实际后果是：为确保合规，我们必须立即对所有客户停用 Fable 5 与 Mythos 5。对 Anthropic 其他所有模型的访问不受影响。

We received the directive from the government today at 5:21pm (ET). The letter did not provide specific details of its national security concern. Our understanding is that the government believes it has become aware of a method of bypassing, or "jailbreaking" Fable 5. We reviewed a demonstration of this specific technique being used to identify a small number of previously known, minor vulnerabilities. These vulnerabilities all appear relatively simple, and we have found that other publicly-available models are able to discover them as well without requiring a bypass.

我们于今日（美东时间）下午 5:21 收到政府的这项指令。函件并未提供其国家安全顾虑的具体细节。据我们理解，政府认为他们已掌握一种绕过——或称「越狱」——Fable 5 的方法。我们查看了一段演示，展示该特定技术被用于识别少数几个此前已知的轻微漏洞。这些漏洞看起来都相对简单，而且我们发现其他公开可用的模型同样能够发现它们，无需任何绕过手段。

一、Anthropic 对 Fable 安全防护的立场 / Anthropic's Posture on Fable's Safeguards

Anthropic's posture with respect to Fable's safeguards, as laid out in our launch blog post, is the following:

正如我们在发布博文中所阐述的，Anthropic 对于 Fable 安全防护措施的立场如下：

• We have instituted strong safeguards that greatly reduce the likelihood that Fable is misused for tasks related to cybersecurity (among others). In fact, our safeguards are so strong that many users have complained that they are overly broad.
• In the weeks leading up to the launch of Fable, Anthropic worked with the US government, the UK AISI, multiple private third-party organizations and internal teams to red-team Fable's safeguards for thousands of hours in total.
• These tests showed that Fable's safeguards are substantially more effective than those of any previously deployed model.
• No testers have yet been able to find a universal jailbreak—a jailbreak method that can very broadly bypass the model's safeguards, unblocking a wide range of cyber capabilities.
• We suspect that perfect jailbreak resistance is not currently possible for any model provider. Every safeguard used in the industry is vulnerable to non-universal jailbreaks (which can elicit some cyber information in specific circumstances), and it is likely that universal jailbreaks will eventually be found in the future. We stated this clearly when we released Fable 5.

• 我们已部署强有力的安全防护措施，大幅降低了 Fable 被滥用于网络安全（及其他）相关任务的可能性。事实上，我们的防护措施如此严格，以至于许多用户抱怨它们管得过宽。
• 在 Fable 发布前的数周里，Anthropic 与美国政府、英国人工智能安全研究所（UK AISI）、多家私营第三方机构及内部团队合作，对 Fable 的安全防护措施进行了总计数千小时的红队测试。
• 这些测试表明，Fable 的安全防护措施远比此前部署的任何模型都更为有效。
• 目前还没有任何测试者能够找到「通用越狱」——一种能够极为广泛地绕过模型防护、解锁大量网络攻击能力的越狱方法。
• 我们认为，对任何模型提供商而言，完美的越狱防御目前都不可能实现。业界使用的每一种防护措施都易受「非通用越狱」的影响（即在特定情境下能套取出一些网络攻击信息），而通用越狱很可能终将在未来被发现。我们在发布 Fable 5 时就已明确说明了这一点。

Given that perfect jailbreak resistance does not appear to be possible today, Anthropic adopted a defense in depth strategy with Fable 5. We aimed to make jailbreaks either narrow (in the case of non-universal jailbreaks) or very expensive to produce (in the case of universal jailbreaks), and to combine this with thorough monitoring to quickly detect and shut down any successful attacks. This is also why Anthropic has required 30-day retention of customer data with Fable—a policy change that carries real costs for us with customers, but that allows us to research and mitigate jailbreaks.

鉴于完美的越狱防御在今天看来并不可能实现，Anthropic 对 Fable 5 采取了「纵深防御」（defense in depth）策略。我们的目标是让越狱要么影响范围狭窄（针对非通用越狱），要么制作成本极高（针对通用越狱），并辅以全面监控，以迅速检测并封堵任何成功的攻击。这也是 Anthropic 之所以要求对 Fable 客户数据保留 30 天的原因——这项政策变更让我们在客户层面付出了实实在在的代价，但它使我们得以研究并缓解越狱问题。

We stand by this defense in depth strategy. It reduces the risks posed by Fable, making them comparable to the risks of existing models already deployed across the industry.

我们坚持这一纵深防御策略。它降低了 Fable 所带来的风险，使其与业界已经部署的现有模型的风险相当。

二、关于越狱披露的事实 / The Facts on Jailbreak Disclosures

We have not even received a disclosure of a concerning non-universal potential jailbreak that led to a harmful result. The potential jailbreaks that have been disclosed to us are either entirely benign responses or are minor findings that provide no Mythos-specific uplift.

我们甚至从未收到过任何关于「导致有害结果的、令人担忧的非通用潜在越狱」的披露。已向我们披露的潜在越狱，要么是完全无害的回应，要么是无法提供任何 Mythos 特有能力提升的轻微发现。

To date, the government has only given us verbal evidence of a potential narrow, non-universal jailbreak, which essentially consists of asking the model to read a specific codebase and fix any software flaws. Our understanding is that one potential jailbreak was shared with the government. We have reviewed a report that we believe is the basis of the government's directive and validated that the level of capability displayed there is widely available from other models (including OpenAI's GPT-5.5), and is used every day by the defenders who keep systems safe. We will share more details over the next 24 hours.

迄今为止，政府只向我们提供了一项潜在的、范围狭窄的非通用越狱的口头证据，其本质不过是要求模型阅读某个特定代码库并修复其中的软件缺陷。据我们理解，有一项潜在越狱被分享给了政府。我们已查阅了一份我们认为构成政府指令依据的报告，并证实其中所展示的能力水平在其他模型（包括 OpenAI 的 GPT-5.5）中广泛可得，而且每天都被那些维护系统安全的防御者所使用。我们将在未来 24 小时内分享更多细节。

三、合规、异议与歉意 / Compliance, Disagreement, and Apology

We are complying with the government's legal directive and are removing access to Fable 5 and Mythos 5 for all users. However, we disagree that the finding of a narrow potential jailbreak should be cause for recalling a commercial model deployed to hundreds of millions of people. If this standard was applied across the industry, we believe it would essentially halt all new model deployments for all frontier model providers.

我们正在遵从政府的法律指令，对所有用户移除 Fable 5 与 Mythos 5 的访问权限。然而，我们不认同「发现一项范围狭窄的潜在越狱」就应成为召回一款已向数亿人部署的商业模型的理由。如果这一标准在全行业推行，我们相信它将实质上叫停所有前沿模型提供商的一切新模型部署。

As we have stated publicly, we believe the government should have the ability to block unsafe deployments, as part of a statutory process that is transparent, fair, clear, and grounded in technical facts. This action does not adhere to those principles.

正如我们公开表态的那样，我们认为政府应当有能力阻止不安全的部署，但这应作为一套透明、公平、明确且立足于技术事实的法定程序的一部分。此次行动并未遵循这些原则。

We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible.

我们对此次给客户造成的中断深表歉意。我们相信这是一场误会，正在努力尽快恢复访问。

*本文为 Anthropic 官方公告，英中对照版由 Lamjin 整理翻译，仅供学习参考；译文如与英文原文有出入，以英文原文为准。*

参考来源

• Anthropic Announcements（官方公告页）