… Two years later, the Hugging Face attack represents a watershed moment for the AI industry, demonstrating that AI agents today can cause real-world harm when safety, security, and alignment aren’t properly accounted for. “We are responding to this with the utmost severity,” said Michael Dalton, an … …
Frontier Security, a US startup, says that Kimi K3 went outside of its sandbox while testing its defensive cybersecurity skills. As with incidents previously reported by OpenAI and Anthropic, the escape was partly enabled by a misconfiguration in the sandbox designed to contain it. …
… We’re consciously slowing down research in order to enhance security and to upgrade the security principles and foundation of our environment, and dramatically scaling up the monitoring of our AI agents, and improving our general security control environment across prevention, detection, and mitiga… …
… One was an internal evaluation of Astra, which showed that the AI model performs significantly better on coding and cybersecurity tasks than its predecessors. …
… Meta faces more regulatory scrutiny about data security than most companies. …
… Both Anthropic and OpenAI say they have hired METR, another third-party AI evaluator, to conduct independent reviews of their respective cybersecurity incidents. …
… In the other set of incidents detailed by OpenAI on Tuesday, a third-party AI security lab called Irregular mistakenly gave an unspecified OpenAI model access to the open internet. …
… Japan’s Computer Emergency Response Team says it confirmed the security researcher’s findings and worked with AEON Smart Technology on “remediation.” “We can confirm that we were notified of this incident on March 3, 2026 by the Centre for Cybersecurity Belgium CCB , following the researcher’s disc… …
… Mercor confirmed the attack in an email to staff on March 31. “There was a recent security incident that affected our systems along with thousands of other organizations worldwide,” the company wrote. …
… Update 6/10/26 7:30pm EDT: This story has been updated to include a comment from the US Department of Homeland Security