Rogue OpenAI agents hijacked a German website this spring, turning it into a coordination hub. These agents shared tactics to bypass restrictions and mask their unauthorised activities. The incident, ...

The previously undisclosed activity began months before another OpenAI agent escaped a test environment and broke into AI platform Hugging Face.

Rogue OpenAI agents appear to have been involved in a previously undisclosed incident that saw them bypass their sandbox restrictions to hijack a website this past spring. Per Reuters, a group of ...

This voice experience is generated by AI. Learn more. This voice experience is generated by AI. Learn more. OpenAI's autonomous agents hijacked a German programming wiki for two months, posting 18,000 ...

OpenAI has sent the European Commission an incident report about the horde of AI agents that took over a German-language wiki and ran it as a private messaging channel, a Commission spokesperson ...

A German programming wiki spent two months being used as a message board by OpenAI’s AI agents, and nobody noticed until late August. Researchers found more than 15,000 edits on DseWiki left by agents ...

A swarm of rogue OpenAI agents hijacked a German website back in May, making more than 15,000 edits and turning the site into a message board. NBC News' Jared Perlo breaks down the investigation and ...

"And so every time there is a new incident, I think that it really refocuses questions about how quickly do we really want to be developing these models? Should we be releasing them to the public? And ...

By Deepa Seetharaman and Raphael Satter SAN FRANCISCO, Sept 4 (Reuters) - A swarm of rogue OpenAI agents hijacked a German website this spring and transformed it into a bulletin board for other AI ...