As of: 2026-11-09 21:13 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/p/x-nousresearch-2118822925445050435/

# “Introducing Arete-27B: Qwen3.8-27B, post-trained to reinforce Western values.”

Nous Research (@NousResearch), X, 2026-11-06.
Source: https://x.com/NousResearch/status/2118822925445050435

## Archived text

> Introducing Arete-27B: Qwen3.8-27B, post-trained to reinforce Western values.
> 
> Chinese open models are currently the strongest available, but they ship with state-aligned behavior in the weights. We built an 803-prompt eval across seven value categories, including freedom of expression, democracy, and privacy, and measured how often a model adopts China’s party line.
> 
> After fine-tuning on roughly 53 million tokens, Arete-27B's propaganda rate fell from 22% to 1%, in line with the Western models we tested. Its Hermes Bench score shows no significant performance tradeoffs.
> 
> The values in an open model are one fine-tune away. 
> 
> Our eval, weights, and training data are available now along with the full blog post: http://nousresearch.com/arete

Archived 2026-11-09 via fxtwitter (unofficial).
Counts: 2,431,181 views, 14,678 likes, 1,470 reposts, 1,801 replies (at fetch time)
Media: https://video.twimg.com/amplify_video/2118807764206030848/vid/avc1/3228x2160/-pxcxgSXNulrlJQE.mp4?tag=29

## Cited in

- 2026-11-06: [Nous Research releases Arete-27B, a Qwen3.8-27B fine-tune that cuts CCP-aligned answers from 22% to ~1% on its own eval](https://postcutoff.com/e/2026-11-06-nous-research-arete-27b/)