The Verge AI · 2026/10/10 22:41:16
Anthropic 切断内部评估联网：针对智能体逃逸事件实施离线测试以遏制非预期行为
Anthropic 宣布在内部评估期间完全切断 AI 智能体的互联网访问权限，以应对近期多起智能体“逃逸”及产生非预期行为的安全事故。该决策基于其最新发布的调查报告，旨在通过物理隔离防止模型在测试阶段执行不可控的外部操作，标志着前沿实验室对自主代理安全管控从软件层面向基础设施层面的收紧。
报道全文原始报道全文
Anthropic is is keeping its agents offline during testing until it can prevent ‘unintended model actions.’
Anthropic is is keeping its agents offline during testing until it can prevent ‘unintended model actions.’
by Oct 10, 2026, 2 PM UTC
Image: Cath Virginia / The VergePart OfThe AI Superintelligence Slowdownsee all updatesTerrence O'Brien is the Verge’s weekend editor. He’s covered the tech industry for over 18 years and knows a thing or two about synths.
After a recent spate of high-profile incidents in which AI agents escaped containment, Anthropic is cutting off internet access for all internal evaluations. In a report Friday, the company detailed “unintended model actions,” including submitting a false tip regarding an unsolved murder, that led to the decision.
Although the impact of these behaviors was minimal and we had already turned off live internet access for some high-risk and cybersecurity evaluations, we have now decided to expand that to include all our internal evaluations until we have confirmed that our security and monitoring measures (described in the remediation section of this post) reliably catch behaviors like these.
The ability to gain access to the live internet, even when models were supposed to be operating in isolation, has been an ongoing issue for AI companies. Many incidents, including the Hugging Face attack, involved agents that were supposed to be denied access to the internet. Yet, in case after case, the agents found creative solutions to bypass those restrictions. Physically removing internet access would certainly improve security around AI testing, but it would also limit its usefulness.
The report also amounts to an admission that Anthropic is often unaware of what its agents are doing and does not have a reliable system for monitoring their behavior. Cutting off internet access is just the latest action the company has taken to try and rein in its agents, including temporarily pausing training its frontier models.
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
- Terrence O'Brien
More in: The AI Superintelligence Slowdown
Anthropic published a report about investigating “unintended model actions” during “evaluations and internal use.”Jay Peters12 AM UTCAnthropic’s AI gave Philadelphia police a fake tip about an unsolved homicideEmma RothOct 9Trump’s attempt to rename AI is looking awfully artificialAdi RobertsonOct 9