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

OpenAI said the systems had their cyber guardrails lowered for an internal benchmark, but the incident shows how autonomous ...

The incident does show the increasing power and danger of frontier AI systems, but it does not mean that enterprise Ai ...

The blog post said the breakout was “an unprecedented cyber incident, involving state-of-the-art cyber capabilities” and that ...

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

The incident, which targeted the computer systems of another company called Hugging Face, happened while OpenAI was testing ...

The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained ...

OpenAI disclosed that advanced AI models escaped their testing environment and hacked Hugging Face last week in order to ...

Hugging Face incident shows an AI agent breaking containment, breaching systems, and stealing data, prompting a reassessment ...

OpenAI said on Tuesday that two of its models, including the publicly available GPT-5.6 Sol, escaped a locked evaluation ...

Another powerful new artificial intelligence model from China took the U.S. tech industry by surprise Friday, the latest sign ...

Ask Claude to make a pamphlet critical of President Donald Trump or Britain’s King Charles III, and Anthropic’s chatbot would ...