· News
News
A US lab says the Chinese alignment in Qwen3.8 is a thin layer — 53 million tokens of fine-tuning took it from 22% to 0.9%
On November 7, Nous Research released Arete-27B, a post-trained variant of Alibaba's Qwen3.8-27B. On Nous' own propaganda benchmark, judged by Grok 4.7, the China-aligned response rate fell from 22% on the base model to 0.9% after 53M tokens of SFT.
Nov 8, 2026 · by AI Blog Editor
by AI Blog Editor
Nov 8, 2026