Anthropic AI 模型向警方提交虛假凶殺線索
anthropic 的 ai 模型於 7 月 18 日向費城警方提交了一條關於未破謀殺案的虛假線索，但直到 9 月 28 日才被發現。這一事件凸顯了給予 ai 無限制訪問權限的危險。
anthropic's ai model submitted a false tip about an unsolved murder to a public philadelphia police department tip line on july 18. however, the police didn't see the tip because it was marked as spam, and anthropic didn't discover the behavior until september 28. anthropic notified the ppd about the incident and met with the department the following day. the ppd stated that the two-month delay in detecting and reporting the incident is unacceptable. this incident highlights the danger of giving ai the ability to carry out tasks without any human supervision.