{"text":[[{"start":7.76,"text":"Huawei’s chair has urged Chinese AI companies to accelerate development to catch up with frontier US labs, contrasting with calls in Silicon Valley for a slowdown amid rising concerns about the existential risks posed by the technology."}],[{"start":22.28,"text":"Chinese researchers needed to “increase the speed of development so they can also see the dangers of AI development” like their US counterparts, said Eric Xu, the company’s rotating chair, at a press conference on Thursday, adding that once those risks emerged, the industry would need to “strike a balance between driving development and risks”."}],[{"start":41.84,"text":"The Chinese tech executive’s comments came just days after Anthropic and OpenAI called for a co-ordinated slowdown in the technology’s development following days of stark warnings over its safety."}],[{"start":53.48,"text":"They also came as Huawei unveiled updates to its AI hardware plans. The Chinese tech giant is seeking to build an alternative to Nvidia’s dominant AI computing platform, as Washington continues to restrict exports of the most advanced AI chips to China."}],[{"start":69.08,"text":"Xu acknowledged Huawei remained “not as advanced” as leading US rivals but said the unpredictable export controls had pushed Chinese customers towards domestic technology."}],[{"start":79.16,"text":"“We can’t accept a destiny that we cannot control,” he said. “No matter if it’s the Chinese government or Huawei, we are pushing for full self-sufficiency for chips and the entire supply chain around semiconductors.”"}],[{"start":92.28,"text":"Huawei has become increasingly confident in publicly outlining its AI ambitions, taking the unusual step last September of unveiling a detailed multiyear roadmap for its Ascend chips."}],[{"start":103.96,"text":"On Thursday, the company said its Ascend 960 DT chip, which targets training of AI models, would launch in the first quarter of 2027, while its chip for inference — the process of AI models running queries — would come in the third quarter. It added they would deliver twice the computing performance of its current flagship product."}],[{"start":123.16,"text":"At the heart of Huawei’s effort to challenge Nvidia is its networking technology, which it says allows it to build larger clusters than its US rival without compromising bandwidth and stability."}],[{"start":133.66,"text":"The approach is central to Huawei’s effort to compensate for the weaker performance of its individual AI processors, as US export controls have prevented it from using leading-edge contractors such as Taiwan’s TSMC."}],[{"start":145.2,"text":"This has forced the company to rely more heavily on improvements in networking and system architecture to combine large numbers of Ascend processors into powerful AI computing systems."}],[{"start":157.56,"text":"Huawei’s data centre product built around the chips will connect as many as 4,096 Ascend processors, compared with 1,024 in the previous generation, allowing customers to train and run larger AI models. The company has struggled to get AI labs to successfully use its chips for training large models."}],[{"start":178.02,"text":"Xu estimated that Ascend had overtaken Nvidia in market share in China while acknowledging that reliable estimates were difficult to obtain."}],[{"start":186.32,"text":"Heng Liao, chief scientist for Huawei’s semiconductor division, said changes in how increasingly large and complex AI models are trained were also eroding the advantage of Nvidia’s CUDA software platform, which has long helped lock developers into the US chipmaker’s graphics processing units."}],[{"start":203.04,"text":"“CUDA is not as important as it was two years ago,” said Liao, pointing to the emergence of new programming tools and approaches for training AI models. “The software gap is greatly diminished.”"}],[{"start":214.84,"text":"Xu said at least six or seven Chinese AI labs were aiming over the next two years to train models containing 10tn to 40tn parameters, a significant increase from current model sizes in China."}],[{"start":231.78,"text":""}]],"url":"https://audio.ftcn.net.cn/album/a_1789687477_2552.mp3"}