China’s AI ecosystem is not as open as it claims. Nor is any other country’s | Letters (theguardian.com)

Responding to an article by China’s ambassador to the UK, Prof Paul H Cleverley advocates shared openness standards, while Dr Claire Jenkins says British AI can offer a distinctive path 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 Systems Interconnection-compliant), no training data or application source code is released , and its governance committee answers to Zhejiang Lab itself. Continue reading...