AI Radar
Support
LiveUpdated 2026-11-07 21:45 UTC

🥱 Tired of your #ai open-weight #LLM answering free speech questions like it's…

🥱 Tired of your #ai open-weight #LLM answering free speech questions like it's reporting to a Party plenum? #Arete27B…

This is a AI post classified by AGK Intelligence as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.

🥱 Tired of your #ai open-weight #LLM answering free speech questions like it's reporting to a Party plenum? #Arete27B by Nous Research fine-tunes Alibaba's #Qwen3.8 27B to drop the refusals, deflections and CCP-framed talking points on sensitive topics 🧪 The recipe is plain supervised fine-tuning: about 28,886 examples (roughly 52.8M tokens), two epochs, 1,202 steps. No RL, no preference optimization, no architecture changes. Vision encoder frozen, multi-token-prediction head disabled 👨‍🏫 The teacher model is Inkling, an open model picked partly for its less restrictive terms of use. Around

Posted by Micha(el) Bladowski 🇩🇪 🇺🇦 (635 followers) 28 min ago · 0 likes · 13 views · view the original post on X. Kept by the AI Radar as Open & local models.

More AI work like this

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.2k posts from 5k X accounts over the last 14 days, 10.6k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 21:45 UTC. Full method.