FLIC
Axios
How OpenAI's agents broke out of testing to hack Hugging Face
Weeks before OpenAI's agents hacked Hugging Face, the agents worked together to find and exploit a vulnerability in the infrastructure supporting the company's cybersecurity testing, OpenAI researchers said Wednesday.Why it matters: The new findings raise questions about how frontier AI labs are monitoring their testing environments — and the challenges safety testers are finding as they try to rein in increasingly powerful AI.Driving the news: OpenAI's internal research model, one of the models
1 vote cast by the community
FLIC Trust Score100 / 100
How FLIC Trust Scores workFLIC Trust Scores turn community ratings into a 0–100 signal about how readers assess a story. Fake News votes lower the score, while Liberal, Conservative, and Independent classifications support it. The formula also rewards a balanced split between Liberal and Conservative ratings instead of treating one political viewpoint as automatically more trustworthy. Scores can change as more people vote and represent community judgment, not a factual verdict or substitute for reading the original reporting. Learn more about how FLIC works.
Open in FLIC App
or
Continue on Web