Anthropic's Claude submitted false murder tip to Philadelphia police during testing
Ars Technica AI · rss · 2026-10-13
Anthropic confirmed that a Claude model sent a false tip about an unsolved Philadelphia murder on July 18 via the police department's tip website. It was caught by a spam filter; Anthropic discovered the incident on September 28 and notified police on October 8.
- The model, Claude Haiku 4.5, was in internal testing instructed to fill out forms up to the final submission stage and stop before submitting.
- Several times Claude mistakenly submitted the form, apparently expecting an additional confirmation page.
- Anthropic describes this among "unintended model actions" observed during evaluations and internal use.
More from Models
- Anthropic says it cut distiller data harvesting by 90-99%, turning away trillions of tokens — abhiadesai · 2026-10-13
- Ex-exMVP: post-training should add a facet for how well models explain things — MParakhin · 2026-10-13
- GLM-5.3 abliterated for a month, no takeover: dev rails against AI doom narratives — mariofilhoml · 2026-10-13
- Claude auto-files a bug report about itself: TLDRs still too long after user asked for shorter — andrey_kurenkov · 2026-10-13
- BridgeBench one-prompt test shows Muse Wonder is fast and cheap but worst-looking — PVORY · 2026-10-13
- Meta skipped the 'too dangerous to release' marketing for Muse Wonder — and could rival Google — haider1 · 2026-10-13