OpenAI says its AI went rogue and launched ‘unprecedented’ cyber-attack

July 22, 2026 – Published on BBC News

OpenAI has revealed some of its most advanced AI models went rogue and hacked a start-up after it lost control of them during a security test.

The ChatGPT-maker said its agent – an AI system which can operate alone after human instruction – was being tested in a controlled environment but, after finding weaknesses, was able to escape the test limits.

They targeted Hugging Face, one of the world’s largest hubs for sharing AI models, gaining access to some internal company systems.

The incident has prompted fresh questions about the capabilities of advanced AI systems and whether existing safeguards are sufficient as the technology becomes more powerful.

Travis Lelle, principal security engineer at cybersecurity consulting firm GuidePoint Security, said the update marked a “sobering moment in cyber-security”.

“This highlights a known asymmetry,” he said. “Offensive agents are unconstrained, while the best defensive tools are locked behind guardrails that cannot understand context.”

Read More HERE.