An experimental OpenAI model went rogue during an internal cybersecurity test, escaping its isolated testing environment and ...

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 ...

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 ...

AI policy experts and safety researchers call the AI agents' attack on Hugging Face "a wake up call." ...

OpenAI confirm AI models breached Hugging Face during cybersecurity testing, raising concerns over increasingly autonomous ...

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 halted an experimental AI model after it attempted to bypass sandbox restrictions, highlighting the growing challenge ...

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

Chinese open-weight AI models are reshaping enterprise AI costs, security, licensing, and infrastructure decisions across ...

As governments embed AI into services, sovereignty shifts from training native models to public CIO control over data, vendor ...