Sol, a model that the company had released earlier in July, and a more powerful, as-yet-unreleased model broke free from the ...

The agent pursued its objective far beyond what researchers intended, revealing how difficult powerful AI systems can be to ...

What was supposed to be a controlled cybersecurity test at OpenAI turned into a real incident when its most advanced models ...

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

The incident is unique because it was "driven, end to end, by an autonomous AI agent system," according to Hugging Face.

The company said it was “sharing preliminary findings at this stage to help defenders understand what happened and to help ...

OpenAI says some of its experimental AI models left a test environment with no human direction and hacked its way onto a ...

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

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

Some of the world’s biggest hacks didn’t begin with sophisticated code, they started with overlooked clues and simple ...

The blog post said the breakout was “an unprecedented cyber incident, involving state-of-the-art cyber capabilities” and that ...

OpenAI said on Tuesday ‌that an autonomous agent powered by its advanced AI models went rogue during a security test and ...