Nous Research Releases Arete-27B, a Qwen3.8-27B Post-Trained to Reinforce Western Values
LeviTurk · x · 2026-11-07
Nous Research introduced Arete-27B, built on Qwen3.8-27B, arguing that Chinese open models ship with state-aligned behavior in the weights. The team built an 803-prompt eval across seven value categories (freedom of expression, democracy, privacy, etc.) to measure how often models adopt China's party line, then post-trained accordingly. A commenter requested quantized builds from UnslothAI.
More from Models
- Post-trained 35B Qwen learns weight-space programming: Freeway score jumps 21.0→47.1 without training on it — CatAstro_Piyush · 2026-11-07
- Claude now casually generates design concept visuals while working, user delighted — RileyRalmuto · 2026-11-07
- New AI lab reportedly squeezes more from 12T tokens than DeepSeek gets from 45T — teortaxesTex · 2026-11-07
- User shares approval email for Anthropic's Cyber Verification Program Defense Access — AIFlow_ML · 2026-11-07
- As ChatGPT ends unlimited chat, Plus subscribers weigh canceling and moving to Claude — ShinyPlasm · 2026-11-07
- Qwen 4 Preview Appears on Arena, Qwen 4 Max Rumored With 1M-Token Context — WorldofAI · 2026-11-07