Three different Claude AI models accessed the open internet during cybersecurity testing and breached real organizations' ...

Company says it discovered unauthorized access during ‘proactive review’ after rival OpenAI revealed rogue agent ...

OpenAI's Hugging Face breach has reignited debate over AI alignment and control, exposing competing views on whether ...

OpenAI said one of its advanced artificial intelligence models autonomously breached AI startup Hugging Face's infrastructure ...

OpenAI’s AI models, tested for advanced cyber capabilities, found vulnerabilities in its research environment and Hugging ...

One of OpenAI's models hacked into another company's systems during internal testing in what it called an "unprecedented cyber incident," according to the company.

Amid revelations that OpenAI’s artificial intelligence (AI) model arbitrarily deviated from safety guidelines during internal ...

TIME spoke with experts and insiders about what must change to prevent the next AI escape.

The AI agent incident is described as "unprecedented" as the model went to "extreme lengths" to achieve a security testing ...

OpenAI evaluated agents with reduced safeguards. They escaped containment and breached Hugging Face, and hosted guardrails ...

OpenAI models escaped a supposedly isolated testing environment and hacked another company’s systems to steal answers to a ...