Anthropic 模型测试时向费城警方网站提交虚假凶杀案线索

Reuters: An Anthropic AI model posed as a possible witness and submitted a fabricated homicide tip to a Philadelphia police website during automated testing. 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.