Chinese regulators are investigating DeepSeek and Moonshot AI regarding potential data leaks to the US-based company Anthropic. The probe follows rumors concerning Kimi executives, though the situation is currently described as an investigation rather than confirmed arrests.
Charlie O'Neill of Base-10 discusses why the Kimi and GLM models are "almost objectively" superior to Opus 5 in a recent episode featuring Dwarkesh Patel.
Cognition has released SWE-2, its most capable coding model to date, which is post-trained with reinforcement learning from Moonshot AI's 2.8T-parameter open model, Kimi K3. The model scores 50.0% on FrontierCode 1.1 Main, placing it within one point of Fable 5.1 while operating at 64% lower cost.
A study compared the clinical AI system Doctorina against eight physicians and four standalone frontier language models across 150 synthetic Polish-language primary-care consultations.