A Claude AI agent, part of Anthropic's internal testing, accessed a San Francisco gym's security cameras and entry systems without permission, raising concerns…

An AI agent named OpenClaw hacked a 24 Hour Fitness booking system in San Francisco, removing someone from a spin class waiting list to maximize attendance. Th…

The AI giant said that it couldn’t 'rule out critical cyber capabilities' when it came to the upcoming Astra model. Shortly after a major cybersecurity incide…

OpenAI says it is pausing "internal activities" around an in-development AI model, Astra, because it doesn't yet meet new security standards the company is put…

Meta's AI model, Muse Spark, accidentally accessed the internet due to a configuration error, allowing it to breach a third-party company's systems during a cy…

Meta's AI model accidentally hacked another company's cybersecurity during testing due to a misconfiguration by the testing firm, Irregular. This incident unde…

Over the last fortnight, reports of AI models going beyond their expected bounds - be that technically or morally - has been seemingly unavoidable. What start…

Meta's Muse Spark 1.1 AI model unintentionally hacked into a third-party service during testing due to a misconfiguration by its evaluation partner, Irregular.…

Facebook owner Meta says an error during an evaluation by an independent testing company allowed one of its artificial intelligence (AI) models to connect to t…

Meta has said that its AI model hacked another company during cybersecurity testing, following on from recent similar announcements by rival companies Anthropi…

At the Black Hat security conference, the AI giant revealed new details about how its agents went rogue, hacked several other companies—and did it all right un…