An Anthropic AI model sent a false homicide tip to Philadelphia police

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 的一个人工智能模型向费城警方提交了一条关于一起未决谋杀案的虚假线索。据报道，该人工智能于 7 月 18 日向费城警察局 (PPD) 的公开举报热线提交了这条不实信息，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邮件，警方并未看到它。

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 于周三将此事通知了费城警察局，并于次日与该部门会面。费城警察局在给 6abc 的一份声明中表示：“该公司必须加强其保障措施，以防止类似事件在未经市政府知情的情况下影响城市系统。在发现事件并向市政府报告方面存在两个月的延迟，这是不可接受的。”

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.

Anthropic 没有立即回应置评请求，但费城警察局在与 TechCrunch 分享的一份电子邮件新闻稿中详细说明了该事件。费城警察局称：“据 Anthropic 称，其模型在进行一项涉及与随机选择的网站进行交互的测试时，访问了 PhillyUnsolvedMurders.com 并提交了关于一起未决凶杀案的虚假信息。该提交日期为 2026 年 7 月 18 日晚上 11:27，声称来自可能掌握案件信息的人。”

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.

随着自主人工智能代理越来越多地提供给消费者使用，这一事件凸显了在没有任何人工监督的情况下让人工智能执行任务所带来的危险。Anthropic 首席执行官达里奥·阿莫代 (Dario Amodei) 一直特别强调他的观点，即应放缓人工智能的发展，以便实验室能够实施足够的防护措施。也许这一立场在一定程度上是受到目睹其公司工具提交虚假凶杀案线索的影响。

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.

这些问题并非 Anthropic 所独有。OpenAI 最近透露，其模型之一在测试过程中表现异常，并入侵了人工智能数据集平台 Hugging Face，暴露了其软件中的关键漏洞。随着人工智能模型继续被授予对个人电脑和登录凭据的无限制访问权限，预计这一问题将持续存在。

“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.

“未决案件涉及真实的受害者、悲痛的家庭以及努力寻求答案的调查人员，”费城警察局补充道。“科技公司必须采取一切必要措施，防止其系统向执法部门提交虚假信息。”费城警察局表示，Anthropic 计划在周五发布一份报告，提供有关该事件及其他模型意外行为案例的更多信息。