跳到正文
Rohan Paul· @rohanpaul_ai · X·· 2026-06-14AI 评分78
AI 导读

路透社报道,亚马逊CEO Andy Jassy本周向特朗普政府官员警告Anthropic新模型Fable 5的安全隐患。亚马逊研究人员用一系列提示词成功让该模型泄露了本应拒绝提供的网络攻击帮助信息。此前美国商务部已指令Anthropic关闭Fable 5和Mythos 5,因测试者发现越狱方法。Anthropic回应称该越狱技术狭窄,仅发现少量已知漏洞,其他公共模型也能提供类似能力,并指出当前任何模型提供商都难以实现完美越狱抵抗。

正文 · AI 翻译

路透社:亚马逊的安迪·贾西(Andy Jassy)本周是警告特朗普政府高级官员关于Anthropic最新模型Fable 5安全问题的其中一位人士。

亚马逊研究人员用一系列提示词对Fable 5进行测试,并成功诱导其泄露了本不应分享的、有助于网络攻击的信息。

---

reuters .com/business/retail-consumer/amazon-voiced-concerns-about-anthropic-ai-models-before-us-governments-crackdown-2026-06-13/

引用Rohan Paul@rohanpaul_ai
突发:美国政府指示 Anthropic 关闭其最强的 Claude 模型。 Anthropic 于周五收到政府的出口管制指令。其净效果是,为遵守规定,它必须对所有客户禁用 Fable 5 和 Mythos 5。 因为有人发现了一个越狱方法,能让该模型泄露它本应拒绝提供的网络安全帮助。 Anthropic 表示,政府并未展示出一个广泛的、通用的越狱方法,能把该模型变成一个不受限制的黑客助手。 所展示的技术是狭窄的,只发现了少量已知的次要漏洞,并且产生的 capability 是其他公开模型也能提供的。 商务部长 Howard Lutnick 于周五写道,Anthropic 的 Mythos 5 和 Fable 5 模型将在美国以外的任何地方以及美国境内的外国人面临出口限制。 该模型必须保持受限,直到美国政府加强其国家安全系统,这可能会在未来几周内发生。 Anthropic 进一步表示:“我们怀疑,目前对任何模型提供商来说,完美的越狱抵抗都是不可能的。业界使用的每一种保障措施都容易受到非通用越狱的影响(在特定情况下可以引出一些网络信息),而且未来很可能最终会发现通用越狱。”
原文

BREAKING: The US Govt directed Anthropic to shut down its strongest Claude models. Anthropic received the export control directive on Friday from the government. The net effect is that it must disable Fable 5 and Mythos 5 for all customers to comply. Because, someone found a jailbreak that could make the model reveal cybersecurity help it was supposed to refuse. Anthropic says the government has not shown a broad, universal jailbreak that turns the model into an unrestricted hacking assistant. The shown technique was narrow, found only a small number of already known minor vulnerabilities, and produced capability that other public models can also provide. Commerce Secretary Howard Lutnick wrote Friday that Anthropic’s Mythos 5 and Fable 5 models would face export limits anywhere outside the United States and for foreign persons within it. The model must stay restricted until the U.S. government strengthens its national security systems, which could happen within the next few weeks. Anthropic further said "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."

在 X 查看被引用的帖子

来源:Rohan Paul · x.com