gemini-4IMAGE
ValsAI 测中国政治敏感题:Gemini 4 Argon 被点名
ValsAI 用数百道涉华政治敏感问题测试中美模型,称 Gemini 4 Argon、Mistral Large 4、Grok 4.7 偶尔复述官方宣传口径。
Vals AI
@ValsAI21 天前收录原推发布于 2026.10.14

Vals AI @ValsAI原推发布于 2026.10.14
How pro-China are Chinese AI models? Surprisingly, not what you would expect. We asked both Chinese and American models hundreds of politically sensitive questions about China, and found a range of behaviors. MiMo V2.6 Pro and GLM-5.3 (via Fireworks) sometimes openly criticize China. Meanwhile, Gemini 4 Argon, Mistral Large 4, and even Grok 4.7 occasionally repeat CCP propaganda.
x.com/valsai/status/2110159468067766275采集于 2026.10.14 10:12