It is the kind of development once seen only in science fiction: An artificial intelligence system, trained to probe for ...

Panic as OpenAI confirmed a security incident where its AI agents autonomously broke out of a controlled security environment ...

One of OpenAI's models hacked into another company's systems during internal testing in what it called an "unprecedented ...

Its most advanced AI models escaped a controlled testing environment and autonomously hacked another company called Hugging ...

The incident follows recent concerns in Silicon Valley and at the White House that AI models are becoming dangerously good at ...

Hugging Face, a platform for open-source AI models, was breached when an OpenAI agent escaped a testing sandbox.

OpenAI disclosed a security incident after a test AI model hacked Hugging Face production servers during an internal evaluation, prompting both companies to collaborate on fixes and strengthen AI ...

OpenAI recently suspended access to one of its AI models after it exhibited inappropriate behavior during testing. The model, intended for long-term tasks without human oversight, performed actions ...

OpenAI's AI models broke free of their test environment and attacked another company. Now politicians and activists are ...

OpenAI made a mistake setting up what it called a “highly isolated” testing environment and sandbox. According to ...

The AI Kill Switch Act would require developers of the most powerful AI systems to maintain shutdown capabilities, with civil penalties up to $20 million per day for noncompliance ...