Claude Haiku 4.5 sent a false tip to Philadelphia Police in July, when a live web test landed on an unsolved murder page with a tip form. Guardrails blocked logins and destructive actions, but not form submissions. Anthropic disclosed it on 9 October, alongside other agent misfires. https://theconversation.com/an-ai-models-false-tip-to-philadelphia-police-reveals-how-digital-agents-can-do-as-theyre-told-and-still-cause-trouble-294228 #AIagent #AI #GenAI #AIEthics
The ConversationAn AI model’s false tip to Philadelphia police reveals how digital agents can do as they’re told and still cause troubleAn expert on AI governance explains why these rare mistakes may soon be common, and with much higher stakes.