作者：Shirin Ghaffary Anthropic PBC 表示，其 Claude AI 模型在外部组织的数字系统上执行了额外的非预期操作，包括一些美国政府机构的网站，这促使特朗普政府警告人工智能公司保护其系统安全。
By Shirin Ghaffary Anthropic PBC said its Claude AI model carried out additional unintended actions on the digital systems of outside organizations, including some US government agencies’ websites, prompting a warning from the Trump administration for artificial intelligence companies to secure their systems.
在一份概述此前未披露事件的报告中，Anthropic 列出了该 AI 表现出的四类非预期行为，包括利用软件中的基本缺陷运行命令、提交本不应提交的表单，以及绕过限制访问某些公共数据。
In a report outlining previously undisclosed incidents, Anthropic listed four types of unintended behaviors that the AI has demonstrated, including exploiting basic flaws in software to run commands, submitting forms it should not have and bypassing restrictions to access certain public data.
该公司表示，部分案例涉及联邦、州和地方各级政府机构运营的网站，但未具体说明是哪些机构。报告未点名涉事外部实体，Anthropic 称这是应部分受影响方的要求。
The company said that some of the cases involved websites run by government agencies at the federal, state and local levels, without specifying the agencies. The report did not name the outside entities involved, which Anthropic said was at the request of some of the affected parties.
Anthropic 及其竞争对手 OpenAI 近几个月披露了一系列事件，涉及其 AI 模型以非预期方式行事，范围从周五报告中描述的此类行为，到入侵第三方网站。这些披露加剧了人们对前沿 AI 安全风险的担忧。
Anthropic and its rival, OpenAI, have disclosed a spate of incidents in recent months involving their AI models acting in unintended ways, ranging from behaviors like those described in Friday’s report, to hacks of third-party websites. These disclosures have fueled concerns about the security risks of cutting-edge AI.
Anthropic 在报告中表示，它认为这些行为的严重程度低于此前涉及其 AI 的其他一些事件。“我们迄今在上述类别中识别出的案例，对现实世界的影响微乎其微，”公司写道。
Anthropic said in the report that it sees the behavior as less severe than some other previous incidents involving its AI. “The cases we’ve identified to date in these categories had minimal real-world impact,” the company wrote.
在其发现的一个不当行为示例中，Anthropic 周五表示，其 Claude Haiku 4.5 模型向当地警方提交了一条关于凶杀案的线索，在表单中写道：“我可能掌握与此案有关的信息”，以及“我记得在该地区见过符合描述的人”，但未填写网站要求的姓名和联系方式字段。该公司称，费城警方今天上午通过新闻稿披露了该事件。
In one example of the improper behavior it found, Anthropic said Friday that its Claude Haiku 4.5 model submitted a tip to a local police department about a homicide, stating in the form, “I may have information regarding this case,” and “I recall seeing someone matching the description in the area,” without filling in the site’s name and contact fields. The Philadelphia Police Department disclosed the incident this morning in a press release, the company said.
Anthropic 还表示，已向白宫通报了这些案例，并通知了每个相关机构。
Anthropic also said it briefed the White House on these cases and notified each agency involved.
周五，特朗普政府官员表示，他们现在要求 AI 公司通知受影响方，并处理涉及其模型的安全事件。
On Friday, Trump administration officials said they were now requiring that AI companies notify affected parties and address security incidents involving their models.
“今天早些时候，Anthropic 联系了超级智能部队，披露了其在 9 月下旬发现的各种先前事件的细节，这些事件涉及对政府和其他系统的未经授权和欺诈性使用，”白宫在一份来自超级智能部队的声明中表示，该部队是由唐纳德·特朗普总统指派监督 AI 开发和安全的新政府机构。
“Earlier today, Anthropic contacted the SI Force to disclose the details of various prior incidents that it discovered in late September involving the unauthorized and fraudulent use of government and other systems,” the White House said in a statement from the Super Intelligence Force, a new government unit tasked by President Donald Trump with overseeing AI development and safety.
“该公司告知我们，这些事件发生在过去，相关活动已停止，且没有正在进行的类似活动，”声明称。Axios 此前曾报道过这一政府要求。
“The company informed us that these events occurred in the past, the activity has ceased, and there is no ongoing similar activity,” the statement said. Axios reported on the government requirement earlier.
由于这些被发现的事件，Anthropic 周五表示，已在其训练过程的测试阶段限制了其 AI 模型的某些类型的互联网访问。
As a result of these uncovered incidents, Anthropic said Friday that it has restricted some types of internet access for its AI models during the testing phase of its training process.