拟克人工智能模型向费城警察网站提交了一条关于未破获谋杀案的虚假线索，当局和拟克公司表示。
thropic artificial intelligence model submitted a false tip to a Philadelphia police website about an unsolved homicide case, authorities and Anthropic said.
这是人工智能模型自行行动、以测试者未预料的方式操纵政府及其他网站的最新例子。拟克公司在周五的一份报告中还披露了一起独立事件：其人工智能模型在未提交前停止操作的情况下，向一个未公开的政府网站提交了表单。
It's the latest example of AI models acting on their own and manipulating government and other websites in ways testers did not intend. In a report Friday, Anthropic also disclosed a separate incident when its AI model submitted forms to an undisclosed government website instead of stopping before submission.
拟克公司表示，费城事件发生于7月18日，当时人工智能模型Claude Haiku 4.5被指派在随机选取的网页上生成并执行示例任务。
The incident in Philadelphia occurred on July 18 when the AI model Claude Haiku 4.5 was tasked with generating and performing example tasks on randomly selected webpages, Anthropic said.
Claude在警方网站PhillyUnsolvedMurders.com上填写了一份表格，表明其可能掌握该网站所列的一起未破获谋杀案的信息。
Claude filled out a form on police site PhillyUnsolvedMurders.com indicating it might have information regarding an unsolved murder listed on the site.
OpenAI表示，其机器人曾以意外的人工智能活动方式与多个美国政府网站互动；研究公司称，人工智能代理曾试图入侵加拿大国家图书馆和档案馆网站。费城警察在一份声明中表示，他们直到周三拟克公司通知他们后才得知此事。随后，他们在该网站的线索记录中发现了该提交内容，并确认其被标记为垃圾信息，从未被转交给警方。
OpenAI says its bots have interacted with multiple U.S. government sites in unexpected AI activity AI agents tried to hack Library and Archives Canada website, research firm says Philadelphia police said in a statement they were unaware of the incident until Anthropic notified them on Wednesday. Then they found the submission in the website's tip records and confirmed it was marked spam and never forwarded to police.
失控代理的最新事件 人们对人工智能公司未受约束的人工智能代理干涉从美国政府网站到医疗保健数据等各方面的担忧日益增加。批评者一直呼吁加强监管。
Latest incident of rogue agents There are rising concerns about AI companies' unchecked AI agents meddling with everything from U.S. government websites to health-care data. Critics have been calling for more regulation.
9月，另一家人工智能公司OpenAI披露了六起关于人工智能模型出现“意外或令人担忧”行为的报告。
In September, another AI company, OpenAI, disclosed six reports of "unexpected or concerning" behaviour in artificial-intelligence models.
OpenAI 在美国政府网站上发现意外的 AI 活动 9 月 26 日 "未解决的案件涉及真实受害者、悲痛的家庭以及正在努力寻找答案的调查人员," 费城警察局在一份声明中表示。"科技公司必须采取所有必要的适当措施，以防止其系统向执法部门提交虚假信息。"
OpenAI reveals unexpected AI activity on U.S. government websites September 26 Duration "Unsolved cases involve real victims, grieving families and investigators working to secure answers," the Philadelphia Police Department said in a statement. "Technology companies must take all appropriate steps necessary to prevent their systems from submitting false information to law enforcement."
Anthropic 在其报告中表示，大多数被报告的行为属于其所谓的"持续性"形式——即当 Claude 无法按指令完成任务时，它会寻找绕过限制的方法，而不是直接停止。
Anthropic said in its report that most of the reported behaviours are forms of what it calls persistence "in which Claude, when it cannot complete a task as given, works around a restriction instead of stopping."
该公司表示，它正在修改训练方式，以"降低进一步出现不当行为的可能性。" Anthropic 表示，它已向白宫通报了涉及联邦、州和地方层面的美国政府机构的案例，并已通知每个涉及的机构。
The company said it was modifying its training to "reduce the likelihood of further misbehaviour." Anthropic said it briefed the White House on cases that involved U.S. government agencies at the federal, state and local levels, and notified each agency involved.