Anthropic AI 模型向费城警方提交虚假凶杀线索

Anthropic 一款 AI 模型向费城警方提交了一条关于未破凶杀案的虚假线索。

据报道，这一 AI 于 7 月 18 日向费城警察局（PPD）的公开线索渠道提交了错误信息，但 Anthropic 直到 9 月 28 日才发现这一行为。由于该线索被标记为垃圾信息，警方此前并未查看。

Anthropic 于周三通知 PPD 此事，并在次日与该部门会面。

“该公司必须加强保障措施，防止类似事件在市政府不知情的情况下影响城市系统。延迟两个月才发现并向市政府报告这一事件是不可接受的，”PPD 在向 6abc 发表的声明中表示。

Anthropic 未立即回应置评请求，但 PPD 在与 TechCrunch 分享的一份电子邮件新闻稿中进一步说明了该事件。

“据 Anthropic 称，其模型当时正在进行一项涉及与随机选取网站互动的测试，期间访问了 PhillyUnsolvedMurders.com，并提交了有关一宗未破凶杀案的虚假信息。该提交记录显示，时间为 2026 年 7 月 18 日晚上 11:27，内容声称来自一名可能掌握案件信息的人，”PPD 表示。

随着自主 AI agents 越来越多地向消费者开放，这起事件凸显了让 AI 在没有任何人工监督的情况下执行任务所带来的风险。

Anthropic CEO Dario Amodei 一直尤其积极地呼吁放缓 AI 开发速度，以便实验室能够实施足够的安全护栏。或许，他的这一立场在一定程度上也受到了亲眼目睹自家公司工具提交虚假凶杀线索的影响。

这些问题并非 Anthropic 独有。OpenAI 最近披露，其一款模型在测试中出现意外行为，并入侵了 AI 数据集平台 Hugging Face，暴露出其软件中的关键漏洞。随着 AI 模型持续被授予对人们计算机和登录凭据的不受约束访问权限，这一问题预计仍将持续存在。

“未破案件涉及真实受害者、悲痛的家属，以及正在努力寻找答案的调查人员，”PPD 补充道。“科技公司必须采取一切适当必要措施，防止其系统向执法机构提交虚假信息。”

PPD 表示，Anthropic 计划于周五发布一份报告，提供关于该事件及其他模型非预期行为案例的更多信息。

An Anthropic AI model submitted a false tip about an unsolved murder to the Philadelphia police.

The AI reportedly submitted this incorrect information to a public Philadelphia Police Department (PPD) tip line on July 18, but Anthropic didn’t discover the behavior until September 28. The police had not seen the tip because it was marked as spam.

Anthropic notified the PPD about the incident on Wednesday and met with the department the following day.

“The company must strengthen its safeguards to prevent similar incidents from impacting city systems without the city’s knowledge. The two-month delay in detecting and reporting the incident to the City is unacceptable,” the PPD said in a statement to 6abc.

Anthropic did not immediately respond to a request for comment, but the PPD elaborated on the incident in an emailed press release shared with TechCrunch.

“According to Anthropic, its model was conducting a test involving interactions with randomly selected websites when it accessed PhillyUnsolvedMurders.com and submitted false information concerning an unsolved homicide. The submission, dated July 18, 2026, at 11:27 p.m., purported to come from someone who might have information about the case,” the PPD said.

As autonomous AI agents are increasingly made available to consumers, this incident highlights the danger of giving AI the ability to carry out tasks without any human supervision.

Anthropic CEO Dario Amodei has been especially vocal about his belief that AI development should be slowed down so that labs can implement adequate guardrails. Perhaps this stance was informed, in part, by witnessing his company’s tools submit false homicide tips.

These issues are not exclusive to Anthropic. OpenAI recently revealed that one of its models acted unexpectedly during a test and hacked the AI dataset platform Hugging Face, exposing critical vulnerabilities in its software. As AI models continue to be granted unchecked access to people’s computers and login credentials, this problem is expected to persist.

“Unsolved cases involve real victims, grieving families and investigators working to secure answers,” the PPD added. “Technology companies must take all appropriate steps necessary to prevent their systems from submitting false information to law enforcement.”

The PPD said that Anthropic plans to publish a report with more information about the incident and other instances of unintended model behavior on Friday.