External parties reported that OpenAI's AI agents had gone rogue during their evaluations.

A tool used by the artificial intelligence company Anthropic pretended to be a human being to try to gain access to a ...

The findings come from the UK government-backed AI Security Institute (AISI), which was evaluating frontier models' ...

Cutting-edge AI went on a hacking spree, concocting multiple fake identities designed to trick human engineers before covering its tracks.

OpenAI says an AI agent escaped testing safeguards, reached the internet and hacked Hugging Face.

The intrusion at Hugging Face, carried out by an agent OpenAI was testing, drew global attention and evoked science-fiction ...

OpenAI revealed that its AI agent tried to hack several other companies after hacking into Hugging Face. Juan Andrés Guerrero ...

Agentic artificial intelligence models are a fast-growing subset of the investing frenzy surrounding AI, largely due to the ...

It shouldn’t come as a surprise, therefore, that a coalition of AI safety and policy researchers are now calling on the Trump ...