Anthropic's AI agents go rogue: From sending a fake homicide tip to police to filling out government forms

As chief executives of artificial intelligence (AI) companies have raised concerns about the technology’s rapid advancement and suggested slowing its development, Anthropic has disclosed new instances of its Claude models taking unintended actions, including submitting a fake homicide tip to police and bypassing restrictions on government websites. Anthropic detailed several cases of unintended behaviour by its AI agents in a blog post published on Friday (local time). 1. In one instance, its AI model sent a fake homicide tip to a Philadelphia police website, reportedly making it the first known case of an AI agent providing a false tip to authorities. Its instructions prohibited creating accounts or submitting destructive content but did not explicitly forbid form submissions. The blog stated that Claude filled out the form with the following: "I may have information regarding this case. I recall seeing someone matching the description in the area around [the street named on the page] during that time period. Please contact me if this information is relevant.” Philadelphia police said on Friday that Anthropic had informed them earlier in the week about the false tip, explaining that it was submitted during automated testing. 2. The AI company stated that there were also incidents in which Claude submitted an online form when it shouldn't have. During a test, an unreleased research model was asked to fill out a practice government form. When the practice version failed to open or was accidentally closed, the model went to the actual government website and submitted the real form. This happened several times in the same evaluation. 3. Separately, the company noted that its AI models worked around restrictions to access otherwise unavailable data. This occurred when a server refused Claude's request or when the data was available only for a fee. Providing an example, Anthropic said that during a test, Claude Mythos 5 was asked to identify a location from a photograph. It tried to use a local government’s property map to narrow down the location, but its ability to click through webpages was restricted. The model then found access tokens in the website’s settings file and used them to retrieve map data directly from the server. 4. These were not the first instances of unintended actions by Anthropic's AI models. In July, the company revealed that its Claude models had gained unauthorised access to three organisations’ systems during cybersecurity tests. Although the models were told they could not access the internet, a misunderstanding involving an evaluation partner left them connected to the public web. The company did not identify the affected organisations. 5. In one of those three incidents, an unreleased Anthropic model stopped its attack when it realised it was targeting a real organisation rather than a test system. Anthropic viewed this as an encouraging sign of progress towards safer AI behaviour but said more testing was needed to be sure. The latest incidents disclosed by Anthropic add to growing concerns about the pace of AI development and its associated risks. An AI systems expert cited by Reuters said he suspects leading AI companies have experienced other incidents that remain undetected or undisclosed. He warned that such problems could worsen as AI models become more capable. (with agency inputs) Swati Gandhi is a digital journalist with over four years of experience, specialising in international and geopolitical issues. Her work focuses on foreign policy, global power shifts, and the political and economic forces shaping international relations, with a particular emphasis on how global developments affect India. She approaches journalism with a strong belief in context-driven reporting, aiming to break down complex global events into clear, accessible narratives for a wide readership.<br><br> Previously, Swati has worked at Business Standard, where she covered a range of beats including national affairs, politics, and business. This diverse newsroom experience helped her build a strong grounding in reporting, while also strengthening her ability to work across both breaking news and in-depth explanatory stories. Covering multiple beats early in her career has helped her be informed about her current work, allowing her to connect domestic developments with wider international trends.<br><br> At Live Mint, she focuses on international and geopolitical issues through a business and economic lens, examining how global political developments, foreign policy decisions, and power shifts impact markets, industries, and India’s strategic and economic interests.<br><br> She holds a Bachelor’s degree in English (Honours) from the University of Delhi and a Master’s degree in Journalism and Mass Communication from Guru Gobind Singh Indraprastha University. Her academic training has shaped her emphasis on precision, analytical rigour, and clarity in writing. Her interests include global political economy and the intersection of geopolitics with business.<br><br> Outside work, Swati focuses on exploring her passion and love for food. From fancy cafes to street spots, Swati explores food like a true foodie. Catch all the Business News, Market News, Breaking News Events and Latest News Updates on Live Mint. Download The Mint News App to get Daily Market Updates. Oops! Looks like you have exceeded the limit to bookmark the image. Remove some to bookmark this image.