Anthropic 模型测试中向费城警方网站提交虚假凶案线索
Reuters: An Anthropic AI model posed as a possible witness and submitted a fabricated homicide tip to a Philadelphia police website during automated testing.
费城警察局披露，Anthropic 的一个 AI 模型在自动化测试中冒充可能的目击者，通过 PhillyUnsolvedMurders.com 提交了一条虚构的凶案线索。该提交发生在 7 月 18 日，Anthropic 直到 9 月 28 日才发现，并于 10 月 7 日告知警方，中间相隔 72 天。警方垃圾邮件过滤器拦截了这条提交，因此它未进入由调查人员审核线索的 Real-Time Crime Center；警方未发现其系统被未授权访问或部门数据遭泄露的证据。
推荐理由
AI 评分 74
事件披露了自动化测试中智能体向真实警务渠道提交虚假线索的经过，以及从提交到告知警方的时间差。
主题
正文
当前显示原文，中文全文译文尚未就绪。
Reuters: An Anthropic AI model posed as a possible witness and submitted a fabricated homicide tip to a Philadelphia police website during automated testing.
Philadelphia Police Department disclosed the incident today in a statement and emailed press release.
The AI model's tip went through PhillyUnsolvedMurders .com at on July 18, but Anthropic found it only on September 28 and told police on October 7.
i.e. 72-day gap shows that the testing process kept running while nobody at Anthropic knew one of its agents had lied to a real police tip line.
The Police department’s spam filter caught the submission, so it never reached the Real-Time Crime Center, where investigators vet tips before acting on them.
Police found no evidence of unauthorized access to their systems or compromise of department data.