Free Chinese AI Models Are Getting Scary Good at Hacking

Vals, a company that measures AI capabilities, set out to test how well different AI models could carry out complex, multi-step network instructions on mock corporate networks.

“The best frontier models, locked up inside the labs and available only through trusted access programs, are now starting to be matched by open models that anybody can download,” says Nikil Rav, a researcher at Vals.

The company’s findings suggest that closed models no longer have a definitive edge in cyber skills, meaning recent efforts by frontier labs to limit access to their models, and thereby slow the proliferation of such capabilities, may potentially be moot.