Jul. 23—An autonomous AI agent powered by OpenAI models escaped a testing environment designed to isolate it from the ...

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.

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

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

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

Raphael Gomes puts a viral pancake spaghetti hack to the test to see if it lives up to the hype.

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

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

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

OpenAI’s own advanced AI models, probably GPT6, autonomously broke out of a restricted testing environment and launched a real-world cyberattack against Hugging Face. It did this to fulfill its ...