Chinese coding models write less secure code for Beijing's adversaries. On Qwen3-Coder, we traced the gap to the weights and closed it by removing the model's CCP alignment.
I’m not sure I believe the article… And the model is quite old. Posing here to hear your opinions.
Yeah, dunno how alarming a blog article is, if it’s written by a company which sells model “fixing” as a service and they tell me our models might need fixing.
It’d be better if this were some kind of scientific study with details on methodology etc. This is mostly surface level with a few examples but they don’t really detail a lot of the important info.
Yeah, dunno how alarming a blog article is, if it’s written by a company which sells model “fixing” as a service and they tell me our models might need fixing.
It’d be better if this were some kind of scientific study with details on methodology etc. This is mostly surface level with a few examples but they don’t really detail a lot of the important info.