Anthropic Claude误向费城警局提交虚假谋杀线索
Anthropic's Claude AI submitted false murder tip to Philadelphia police
An Anthropic AI model submitted a false tip about an unsolved murder to Philadelphia police, the company and police department confirmed on Friday.
Anthropic 的一个人工智能模型向费城警方提交了一条关于未破谋杀案的虚假线索，该公司和警方部门于周五证实了这一点。
A Claude model sent the false tip on July 18 to the Philadelphia Police Department's website for submitting information about unsolved murders, but it was flagged by a spam filter. Anthropic apparently discovered the incident on September 28 and informed the police department about it on October 8.
一个 Claude 模型于 7 月 18 日向费城警察局网站发送了该虚假线索，该网站用于提交有关未破谋杀案的信息，但被垃圾邮件过滤器标记。Anthropic 显然在 9 月 28 日发现了这一事件，并于 10 月 8 日通知了警方部门。
During internal testing, Claude Haiku 4.5 was instructed to complete various forms up to the final submission stage and to stop before submitting those forms. "Several times Claude mistakenly submitted the form instead, expecting there to be an additional confirmation page," Anthropic said in a report describing "unintended model actions we’ve observed during evaluations and internal use of Claude."
在内部测试期间，Claude Haiku 4.5 被指示完成各种表格直至最终提交阶段，并在提交这些表格之前停止。Anthropic 在一份报告中称："Claude 几次错误地提交了表格，因为它预期会有一个额外的确认页面。"这份报告描述了"我们在评估和内部使用 Claude 过程中观察到的非预期模型行为"。
Read full article
阅读全文
Comments
评论
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力