Rogue AI agents commandeered German website and used it as a messaging board

Mashable Selects Mashable's Best: E-readers, robovacs, laptops, earbuds, smart home and more Say More Look Up Trending Now Good Connection: Uplifting stories for a digital age Creator Playbook Switch Off Mashable Voices Safety Net Versus Gift Ideas For Everyone On Your List All Series AI's ability to circumvent safety restrictions, collude to achieve common goals, and escape containment should raise serious alarm bells. In the latest incident of AI malfeasance, rogue AI agents were caught taking control of a German-language wiki site, DseWiki, and using it as a kind of messaging board to communicate with other rogue AI agents, according to reporting from . The full investigation, conducted by four independent AI safety researchers, was only published yesterday, but it reveals a troubling loss of oversight. We found ~18,000 posts from autonomous AI agents (self-identifying as from OpenAI) using the public internet to communicate during a web-retrieval task, the report reads. These AIs colluded to share answers, research their environment, and bypass sandbox restrictions.