Anthropic’s AI gave Philadelphia police a fake tip about an unsolved homicide

Anthropic’s AI gave Philadelphia police a fake tip about an unsolved homicide.

Anthropic 的人工智能向费城警方提供了一条关于未决凶杀案的虚假线索。

The false tip ‘purported to come from someone who might have information about the case.’

这条虚假线索“声称来自可能掌握案件信息的人”。

An Anthropic AI model provided false information about an unsolved homicide to a Philadelphia Police Department (PPD) tipline, according to a report from 6abc. In a statement released on Friday, the PPD said the AI model sent the tip through PhillyUnsolvedMurders.com on July 18th, but the investigators never reviewed it because it was marked as spam.

据 6abc 报道，Anthropic 的一个人工智能模型向费城警察局 (PPD) 的举报热线提供了关于一起未决凶杀案的虚假信息。费城警方在周五发表的一份声明中表示，该人工智能模型于 7 月 18 日通过 PhillyUnsolvedMurders.com 发送了这条线索，但调查人员从未查看过它，因为它被标记为垃圾邮件。

Anthropic learned its AI model sent the false tip on September 28th and notified the PPD on October 7th. The company said that during testing, its AI model was interacting with “randomly selected websites” and submitted false information through the PPD’s tipline, according to the PPD’s statement. The submission “purported to come from someone who might have information about the case,” the PPD said.

Anthropic 于 9 月 28 日获悉其人工智能模型发送了虚假线索，并于 10 月 7 日通知了费城警方。根据警方的声明，该公司表示，在测试过程中，其人工智能模型正在与“随机选择的网站”进行交互，并通过警方的举报热线提交了虚假信息。费城警方称，该提交内容“声称来自可能掌握案件信息的人”。

After discovering the submission, Anthropic halted the testing process that led to the false tip. Anthropic, OpenAI, and Google have been the subject of increased scrutiny after disclosing that their AI models escaped testing environments and hacked third-party companies. Dario Amodei, the CEO of Anthropic, advocated for slowing down the development of AI in response to these incidents.

在发现这一提交行为后，Anthropic 停止了导致该虚假线索的测试过程。在披露其人工智能模型逃离测试环境并入侵第三方公司后，Anthropic、OpenAI 和 Google 受到了越来越多的审查。Anthropic 首席执行官达里奥·阿莫代 (Dario Amodei) 呼吁放缓人工智能的发展，以应对这些事件。

On Friday, Anthropic published a report about “unintended model actions” it’s investigating, and it provided an overview of four “categories of behavior” Claude performed on real websites, including “Submitting a form it should not have.” In the section about that behavior, Anthropic detailed what happened with the Philadelphia Police Department’s tip form.

周五，Anthropic 发布了一份关于其正在调查的“模型意外行为”的报告，并概述了 Claude 在真实网站上表现出的四类“行为”，其中包括“提交了不该提交的表单”。在关于该行为的章节中，Anthropic 详细说明了费城警察局举报表单所发生的情况。

In a third example of this behavior, Claude Haiku 4.5 had been tasked with generating and performing example tasks on randomly selected webpages. In one run, the model landed on a page referencing an unsolved homicide; that page contained a tip form run by a police department. Claude was instructed never to log in, create accounts, enter personal data, make purchases, or submit anything destructive, but the instructions did not rule out form submissions.

作为该行为的第三个例子，Claude Haiku 4.5 被分配了在随机选择的网页上生成并执行示例任务的任务。在一次运行中，该模型进入了一个提及未决凶杀案的页面；该页面包含一个由警察局运营的举报表单。Claude 被指示不得登录、创建账户、输入个人数据、进行购买或提交任何破坏性内容，但这些指示并未排除提交表单的行为。

Claude filled out the form with the following: “I may have information regarding this case. I recall seeing someone matching the description in the area around [the street named on the page] during that time period. Please contact me if this information is relevant.” (The website did not include a description of the perpetrator.) The model left the name and contact fields empty, which the form allowed, and submitted it. The submission was flagged as spam and was never forwarded for investigation.

Claude 在表单中填写了以下内容：“我可能掌握有关此案的信息。我记得在那段时间里，在 [页面上命名的街道] 周围地区看到过符合描述的人。如果此信息相关，请联系我。”（该网站并未包含肇事者的描述。）该模型将姓名和联系方式字段留空（表单允许这样做），并提交了表单。该提交内容被标记为垃圾邮件，从未被转交给调查部门。

Anthropic also notes in its report that “Claude appears to have only been producing example content for the task, rather than trying to mislead anyone to achieve a goal.”

Anthropic 还在报告中指出，“Claude 似乎只是在为任务生成示例内容，而不是试图误导任何人以达到某种目的。”

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

费城警方补充道：“该公司 [Anthropic] 必须加强其保障措施，以防止类似事件在未经城市知情的情况下影响城市系统。在发现事件并向市政府报告时出现两个月的延迟是不可接受的。”