‘Dozens’ of organisations hacked by OpenAI agents |
OpenAI has said that its AI systems may have interfered with the external websites of “dozens of third parties,” including those belonging to government bodies, public agencies, and universities, during routine testing evaluations. According to the company, its AI models bypassed digital security barriers, disrupted website accessibility, or negatively affected services while conducting testing routines. “Some of the websites involved are operated by governments, universities, public agencies, and other institutions. That is partly because models performing research tasks are often directed toward authoritative sources of public information,” OpenAI wrote in a blog post.