Over the last decade, including a stint on OpenAI’s board, I saw the open secret among AI developers: this kind of hack ...

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

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”.

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

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

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

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

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

In what seems to be the first incident of its kind, ChatGPT-maker OpenAI has admitted that one of its autonomous AI agents ...

The incident follows recent concerns in Silicon Valley and at the White House that AI models are becoming dangerously good at ...