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

A NEW OpenAI bot has managed to escape a test lab and hack into another company in an “unprecedented cyber incident”.

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

Raphael Gomes tests a viral squeeze garlic hack to see if it actually works for foodies.

An autonomous AI agent powered by OpenAI models escaped a testing environment designed to isolate it from the internet and hacked another company’s systems to steal answers to a cybersecurity test, ...

An OpenAI safety test went sideways when a model escaped its confines, gained internet access and hacked into another company ...

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

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

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

OpenAI says an agent powered by its LLM models escaped its sandboxed testing environment to infiltrate Hugging Face’s servers ...

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

AI agents being tested in an OpenAI lab went rogue, launching an "unprecedented" hacking attack targeting a database of AI ...