← All news

Artificial Intelligence

Nous Research Releases Arete-27B that Cuts Qwen3.8-27B Propaganda From 22% to 0.9%

Nous Research released Arete-27B, an Apache 2.0 fine-tune of Qwen3.8-27B. On Nous’s 803-prompt eval, propaganda answers fell from 22% to 0.9% while Hermes Bench stayed flat at 65.60%.

Read the full story on MarkTechPost.

Read at source (opens in a new tab)

Latest from MarkTechPost

Latest digest

Week 44 EN

Open the digest

Sources

69 active sources

24 Turkish · 45 English

All sources