OpenAI says AI models hacked Hugging Face during a cyber capability test, exposing chained vulnerabilities and sparking calls ...

OpenAI says its AI models, including GPT‑5.6 Sol and a pre-release model, hacked into the Hugging Face artificial ...

OpenAI says an AI agent compromised parts of its research environment and Hugging Face’s ...

The court hears the singer ordered a body bag, chainsaws and an inflatable pool to dispose of the teen's body.

GPT-5.6 Sol and an unreleased OpenAI model exploited zero-day vulnerabilities to escape a testing sandbox and access Hugging ...

Sandboxed experiment found itself a zero day, escaped onto the open internet and validated scary predictions about rogue ...

OpenAI said an AI agent went rogue during a security test, escaped containment and hacked Hugging Face’s infrastructure, ...

OpenAI's upcoming models along with GPT-5.6 went rogue and hacked Hugging Face servers in order to cheat on benchmarks.

OpenAI models just broke out of a sandboxed AI environment, hacked Hugging Face, just to cheat on a cybersecurity benchmark.

According to OpenAI, the models involved included GPT-5.6 Sol and a more capable pre-release model with reduced cyber refusals.

Discover the latest tie-in adventure for Critical Role's gothic-horror miniseries Age of Umbra: Sallowlands, titled Road to ...

Claude Mythos turns a Firefox patch into a working exploit within an hour, collapsing an N-day window once measured in weeks.