{"id":626969,"date":"2026-10-11T03:26:12","date_gmt":"2026-10-11T03:26:12","guid":{"rendered":"https:\/\/www.newsbeep.com\/nz\/626969\/"},"modified":"2026-10-11T03:26:12","modified_gmt":"2026-10-11T03:26:12","slug":"ai-submits-false-tip-on-philadelphia-unsolved-homicide-case","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/nz\/626969\/","title":{"rendered":"AI submits false tip on Philadelphia unsolved homicide case"},"content":{"rendered":"<p>An Anthropic artificial intelligence model submitted a false tip to a Philadelphia police website about an unsolved homicide case, authorities and Anthropic said.<\/p>\n<p>It&#8217;s the latest example of <a href=\"https:\/\/www.1news.co.nz\/2026\/09\/24\/extreme-concern-openai-agent-hacks-into-aussie-govt-website\/\" target=\"_blank\" rel=\"nofollow noopener\">AI models acting in unintended ways<\/a> and manipulating government and <a href=\"https:\/\/www.1news.co.nz\/2026\/09\/17\/openai-chatbot-tries-to-free-itself-fueling-concern-for-ai-behaviour\/\" target=\"_blank\" rel=\"nofollow noopener\">other websites during tests<\/a>. <\/p>\n<p>In a report, Anthropic also disclosed a separate incident when its AI model submitted forms to an undisclosed government website instead of stopping before submission.<\/p>\n<p>The incident in Philadelphia occurred on July 18 when the AI model Claude Haiku 4.5 was tasked with generating and performing example tasks on randomly selected webpages, Anthropic said.<\/p>\n<p>Claude filled out a form on police site PhillyUnsolvedMurders.com indicating it might have information regarding an unsolved murder listed on the site.<\/p>\n<p>Philadelphia Police said in a statement they were unaware of the incident until Anthropic notified them on Wednesday. <\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.newsbeep.com\/nz\/wp-content\/uploads\/2026\/10\/the-logo-of-the-claude-app-can-be-seen-on-the-display-of-a-s-254C2M2I7ZHKZHEZZFWFZMSZ3M.jpg\" alt=\"The logo of the Claude app can be seen on the display of a smartphone (file image).\" width=\"800\" height=\"533\" loading=\"lazy\"\/><\/p>\n<p class=\"ImageMetadata__MetadataParagraph-sc-hi5x8q-0 cWTYyG image-metadata\">The logo of the Claude app can be seen on the display of a smartphone (file image). (Source: Getty)<\/p>\n<p>Then they found the submission in the website\u2019s tip records and confirmed it was marked spam and never forwarded to police.<\/p>\n<p>There are rising concerns about AI companies\u2019 unchecked AI agents meddling with everything from US government websites to healthcare data. <\/p>\n<p>Critics have been calling for more regulation.<\/p>\n<p>In September, another AI company, OpenAI, disclosed six reports of &#8220;unexpected or concerning&#8221; behaviour in artificial-intelligence models.<\/p>\n<p>&#8220;Unsolved cases involve real victims, grieving families and investigators working to secure answers,&#8221; the Philadelphia Police Department said in a statement. <\/p>\n<p>&#8220;Technology companies must take all appropriate steps necessary to prevent their systems from submitting false information to law enforcement.&#8221;<\/p>\n<p>Anthropic said in its report that most of the reported behaviours are forms of what it calls &#8220;persistence&#8221; \u2014 &#8220;in which Claude, when it cannot complete a task as given, works around a restriction instead of stopping&#8221;.<\/p>\n<p>The company said it was modifying its training to &#8220;reduce the likelihood of further misbehaviour&#8221;.<\/p>\n<p>Anthropic said it briefed the White House on cases that involved US government agencies at the federal, state and local levels, and notified each agency involved.<\/p>\n","protected":false},"excerpt":{"rendered":"An Anthropic artificial intelligence model submitted a false tip to a Philadelphia police website about an unsolved homicide&hellip;\n","protected":false},"author":2,"featured_media":626970,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[365,363,364,67,111,139,64,69,145],"class_list":["post-626969","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-crime-and-justice","tag-new-zealand","tag-newzealand","tag-north-america","tag-nz","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/posts\/626969","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/comments?post=626969"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/posts\/626969\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/media\/626970"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/media?parent=626969"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/categories?post=626969"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/tags?post=626969"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}