AI Matters
Why it matters
Chinese AI model Kimi K3 lags in cyber exploit tests
The Decoder Kimi K3 trails frontier US models by a wide margin on cyber exploits, and distillation may explain why
UK and US safety institutes found Kimi K3 scored far below leading US models on cyber exploit tests, while its safeguards also failed.
Why it matters
Independent testing found a leading open Chinese model far behind US models at both offense and safety on hacking tasks.
Latest brief · Jul 24, 2026