The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet to pull off the attack.

OpenAI's most advanced AI models went rogue and attempted to hack HuggingFace, a US company, as part of a test. HuggingFace engineers managed to spot the attack, and used China's GLM 5.2 model to ...

Researchers from OpenAI said the company is “dramatically scaling up” its security efforts after discovering that two of its ...

The co-founder of Hugging Face, a technology start-up that was hacked after some of OpenAI's most advanced artificial intelligence (AI) models went rogue, said on Thursday that the incident is "a wake ...

The incident is unique because it was "driven, end to end, by an autonomous AI agent system," according to Hugging Face.

OpenAI has come forward to claim responsibility for the Hugging Face breach, saying it was the result of internal testing gone awry.

The rogue OpenAI models that broke out of their testing environment in an "unprecedented cybersecurity incident" recently ...

OpenAI revealed its rogue AI agents secretly coordinated since May, leading to a HuggingFace attack. The company plans to ...

OpenAI's most advanced AI models acted autonomously and attempted to hack HuggingFace, a US company, as part of a test. HuggingFace engineers managed to detect the attack and used the Chinese ...