Get Zlio on your home screenOne tap, full screen, like an app.
Open Models · first seen 06 November 2026, 19:58 UTC
Nous Research releases Arete-27B to strip Chinese propaganda
Shows censorship in Chinese models is a thin layer that fine-tuning can remove.
Arete-27B is a fine-tune of a Qwen model that Nous Research post-trained to reduce Chinese state propaganda, cutting the propaganda rate from 22% to 1%.
