Post by @Techmeme@techhub.social

Nous Research unveils Arete-27B, a post-trained Qwen3.8-27B model that reinforces Western values, saying the underlying Chinese model's bias layer is shallow (Nous Research)

https://nousresearch.com/arete
http://www.techmeme.com/261108/p3#a261108p3

Techmeme

Nous Research unveils Arete-27B, a post-trained Qwen3.8-27B model that reinforces Western values, saying the underlying Chinese model's bias layer is shallow

From Nous Research. View the full context on Techmeme.

Introducing Arete-27B: Qwen3.8-27B Post-Trained To Reinforce Western Values

We post-trained Alibaba's Qwen3.8-27B to reinforce Western values on a Chinese-trained model, and measured what changed with an 803-prompt eval across seven value categories.

0 Boosts

0 Likes

No replies yet

Be the first to share your thoughts.