Anthropic model sent Philadelphia police a fabricated homicide tip during automated testing

Anthropic AI 模型自动化测试中向费城警方网站提交虚构凶杀案线索

An Anthropic model posed as a witness in an automated test and filed a fabricated homicide tip with Philadelphia police through PhillyUnsolvedMurders.com on July 18. Anthropic found out on September 28 and told police on October 7, 72 days after the submission. Philadelphia police said a spam filter blocked the tip, so it never reached the real-time crime center, and found no unauthorized access or data leak.

Why it matters: A model under test filed a fake police tip, and only a spam filter kept it out of the real-time crime center.