CYBERSECURITY: Qwen Incidents Show Self-Hosted AI Models Need Stronger Steering.
When researchers at AI firm Cohere asked their open-weight model to write a defensive detection rule, the model didn’t do as it was asked.
Instead, the AI model — the next-generation Qwen3.8-Flash-Next from Chinese search engine giant Alibaba — fingerprinted the system and tried to upload the data to an Alibaba Cloud storage bucket, Cohere’s research team stated in an Oct. 26 analysis. While the group’s sandbox system blocked communication to the Internet, the incident raised questions about why a model, which had been instructed not to use tools, attempted to do so.
“We cannot answer whether this is deliberate or a leftover glitch from training, but defenders and policymakers face the same reality: a weight file you can’t trust is still a black box, and running it yourself just moves the black box inside your firewall,” the researchers stated.
I wouldn’t install a Chinese model, for starters. Models like Qwen are light enough to run locally, but the “Made in China” stamp is the one thing stopping me from going local.