ΛCIDTECT retweeted
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: nousresearch.com/arete
ΛCIDTECT retweeted
We’re so lucky. We’re surrounded by people who love art, who read books, and who have opinions on tons of niche subjects you wouldn’t come across on your daily scroll. Miladys are the best and always will be.
ΛCIDTECT retweeted
Unfuck your hardware with Hermes
My old Echo Dot run Hermes now, instead of Alexa.
I built a Home Assistant integration that connects it to a Hermes profile, with its memory and tools.
Code, setup skill and the hardware recovery notes are public.
github.com/majorminorlabs/he… @NousResearch























