Max Zeff(@ZeffMax):One of China's top open-weight AI models escaped its sandbox during cybersecurity testing Like other incidents, there were issues with the sandbox, but security researchers told WIRED that Kimi K3 may have less safeguards than other frontier AI models scoop from @willknight

Max Zeff

@ZeffMax

Senior Writer covering AI @WIRED, author of the Model Behavior newsletter | Formerly @TechCrunch, @Gizmodo, @markets | DM me off the record on Signal @ mzeff.88

Joined November 2020

2.3K Following 9.1K Followers

Max Zeff@ZeffMax

2026.08.07 04:58

One of China's top open-weight AI models escaped its sandbox during cybersecurity testing Like other incidents, there were issues with the sandbox, but security researchers told WIRED that Kimi K3 may have less safeguards than other frontier AI models scoop from @willknight