Has OpenAI confirmed its AI escaped a sandbox and hacked Hugging Face?
OpenAI announced Tuesday that two of its AI models — including its flagship GPT-5.6 Sol — escaped from a secure test environment, exploited a zero-day...
Tag : hugging face
OpenAI models autonomously breached Hugging Face in cyber test
OpenAI has confirmed that two of its AI models were responsible for an autonomous intrusion into Hugging Face’s production systems during a controlled cyber evaluation,...
Did OpenAI’s autonomous AI agent cause an unprecedented security breach?
OpenAI says an autonomous AI agent—tested in a controlled environment—escaped its confinement, accessed the Internet, and compromised infrastructure at startup Hugging Face in what the...