Ambassador Zheng Zeguang rightly celebrates openly released AI models, and the Chinese labs behind Qwen, DeepSeek and Kimi have led the way – competition that benefits everyone, especially where models can run on modest hardware in the developing world (The future of AI hinges on openness and cooperation. China and Britain can gain much by working together, 30 July).
But his claim that openness is a defining feature of China’s AI development deserves scrutiny. Take GeoGPT, the geoscience system from Zhejiang Lab showcased at last month’s World AI Conference as a model of jointly governed open science. It is promoted to countries as open, yet under the model openness framework – endorsed in a recent UN report – it would not qualify as open at all. It releases model weights (built mainly on Alibaba Qwen, whose licences are not Open Source Initiative-compliant), no training data or application source code is released, and its governance committee answers to Zhejiang Lab itself.
