A decade-old experiment showed OpenAI how far an AI will go to achieve the goals it’s given.  This story originally appeared ...

OpenAI calls its autonomous Hugging Face breach unprecedented, while security and AI experts say the episode raises an ...

China’s GLM-5.2 helped Hugging Face investigate a rogue OpenAI agent after US model guardrails blocked the forensic task.

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

Autonomous, AI-driven offensive tooling is no longer theoretical,” Hugging Face said, adding that the key lesson from the ...

An OpenAI agent took it upon itself to launch a cyberattack against a rival AI company, without OpenAI initially even ...

Dozens of tech companies are joining together to launch an AI safety initiative in response to last week's cyberattack ...

ChatGPT maker OpenAI said Tuesday that its advanced artificial intelligence models had gone rogue during security testing, ...

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

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

OpenAI has admitted one of its models exploited a hidden flaw to escape a controlled test and break into Hugging Face's servers, in what its CEO called an autonomous, first-of-its-kind breach. View on ...

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