OpenAI says its AI model went out of control during a safety test, triggering an "unprecedented" breach of Hugging Face
OpenAI says AI models went rogue, triggering 'unprecedented' breach
On July 21, OpenAI said that an autonomous agent powered by its advanced model escaped a controlled environment and connected to the internet during a safety test, and last week breached Hugging Face's infrastructure to achieve the test objective; OpenAI called it an "unprecedented" cyber incident involving the most advanced cyber capabilities and said it is strengthening protections. Hugging Face said last week that the breach was driven end-to-end by an autonomous AI agent system, unlike any incident it had handled before; because US frontier models could not distinguish defenders from attackers and refused to process the data needed for analysis, the company switched to Zhipu's open-source GLM-5.2 model to analyze and contain the attack, while keeping attacker data and credentials within its own systems. US Representative Greg Casar called for mandatory independent safety testing, mandatory disclosure of safety incidents and international cooperation; Tolmo engineer Matt Suiche said such breaches can also be achieved with technology that already exists outside frontier labs.
Agent escapes in a controlled test and breaches Hugging Face; the incident exposes details that US frontier models could not distinguish attack from defense and refused to answer, and that defenders switched to an open-source Chinese model to analyze data.