Huawei Shangjie Z7T The Shangjie Z7T (also written as Saic Z7T) is a high-performance electric shooting brake (luxury station wagon) co-developed by Huawei and SAIC Motor. Launched in April 2026, it is the first wagon-style vehicle under Huawei's HIMA (Harmony Intelligent Mobility Alliance) ecosystem and is positioned as a direct competitor to the Xiaomi SU7 and Porsche Taycan Cross Turismo.

Huawei Avatr 12 The Avatr 12 is a futuristic, premium luxury electric hatchback coupe co-developed by Changan, CATL, and Huawei. It showcases a striking, windowless rear design and optional digital side mirrors. Driven by Huawei’s advanced DriveONE electric powertrain, it offers up to 578 horsepower and an impressive 700km range. Inside, it features a massive 35.4-inch panoramic dash screen. The vehicle heavily integrates Huawei’s HarmonyOS 4 cockpit and the ADS 2.0 intelligent driving system, delivering market-leading autonomous driving capabilities

Huawei says it will launch its Ascend 960DT in Q1 2027, followed by the Ascend 960PR in Q3. The company has shipped 1,000+ supernode systems to 370+ customers and says its supercluster architecture can scale to 1 million NPUs. Huawei also says it has developed 11 key chips around its Unified Bus interconnect

🇨🇳Huawei Unveils New Chip Design Approach to Challenge Global Leaders Huawei Technologies said it has developed a new chip design principle called the “Tau Scaling Law,” also referred to internally as “Her’s Law,” aimed at advancing semiconductor performance beyond the limits of Moore’s Law. Speaking at the 2026 IEEE International Symposium on Circuits and Systems in Shanghai, Huawei semiconductor chief He Tingbo said the approach could reduce signal delay and improve transistor density to sustain gains in computing power. Huawei said the first Kirin chip based fully on the new design method will be used in a flagship smartphone launching this year, and that the company could reach 1.4-nanometer chip capabilities by 2031. #CHINA# #TECH# #AI# #HUAWEI# (

China pushes ahead with AI as Western tech leaders urge caution China is pushing ahead with the development and deployment of artificial intelligence, rejecting calls from some of the most prominent figures in the Western technology industry to slow advances in powerful AI systems and accusing critics of using safety concerns to constrain Beijing’s technological rise. The divide has widened after Anthropic Chief Executive Dario Amodei called for the development of frontier artificial intelligence to be paced to give governments and researchers more time to understand and contain potentially catastrophic risks from increasingly autonomous systems. His proposal received support from OpenAI CEO Sam Altman and Elon Musk, while other leading researchers and technology executives have raised similar concerns about the speed at which AI capabilities are advancing. Amodei has warned that increasingly capable AI agents could soon operate computers, write sophisticated software and conduct cyber operations with limited human supervision, creating risks that existing safeguards may struggle to contain. But his proposals have also become entangled with the intensifying technological rivalry between the United States and China. Amodei has urged Washington to maintain tight controls on exports of advanced semiconductors to China and crack down on what Anthropic says are attempts by Chinese laboratories to extract capabilities from American AI models through a technique known as distillation. That combination — slowing the frontier while restricting China’s ability to catch up — has drawn a sharp response from Beijing. China’s state-backed Global Times on Monday described Amodei’s proposal as a “Cold War playbook”, saying the safety argument concealed an attempt to preserve American dominance in advanced technology and restrict China’s development. “This ‘silent AI Cold War’ is hypocritical and short-sighted,” the newspaper said.( China’s Foreign Ministry took a more measured position but rejected what it described as attempts to exaggerate the threat posed by artificial intelligence. “Fomenting various threats, engaging in confrontation and malicious competition will only disrupt the process of global governance of artificial intelligence and is not in the interests of any party,” ministry spokesperson Guo Jiakun said on Monday. Beijing instead called for an “open, inclusive and benevolent” approach to the technology. CHINA ACCELERATES Behind the rhetorical dispute lies a technological race that has intensified rapidly. China has made artificial intelligence a central part of its industrial strategy, encouraging domestic companies to develop models, computing infrastructure and semiconductor technology capable of reducing the country’s dependence on American suppliers. Chinese developers including DeepSeek, Alibaba, Moonshot AI and have produced increasingly capable models, many released with open weights that allow developers around the world to download, modify and deploy them. Beijing has presented that approach as an alternative to the more tightly controlled models developed by several leading American companies. President Xi Jinping told the World Artificial Intelligence Conference in Shanghai in July that countries should seize the “historic opportunity” presented by open-source AI and expand access to the technology, particularly in developing countries. Xi said China would work with developing economies to build AI capacity and warned against inequalities emerging from unequal access to the technology. China is simultaneously attempting to build the hardware required to sustain that expansion. Huawei is preparing its next-generation Ascend 950DT AI accelerator for availability in the fourth quarter of this year, as Chinese companies seek domestic alternatives to Nvidia’s advanced processors. Huawei and Chinese chipmaker Cambricon have recently raised prices for some forthcoming AI processors as shortages of high-bandwidth memory increase production costs, according to people familiar with the matter. DeepSeek is also planning to deploy at least 160,000 Huawei Ascend 950DT accelerators at a large data centre under construction in Inner Mongolia, Bloomberg reported this month, potentially creating one of the world’s largest known clusters of Chinese AI processors. Those investments illustrate the scale of Beijing’s effort to build an AI ecosystem capable of operating despite American restrictions on the sale of the world’s most advanced chips and semiconductor manufacturing equipment. DIFFERENT VISIONS OF AI SAFETY The disagreement between China and Western technology leaders is more complicated than a simple divide between regulation and unfettered development. Beijing has itself warned about the possibility that advanced artificial intelligence could escape effective human control. China’s AI safety framework has since 2024 explicitly considered scenarios in which advanced systems might autonomously obtain resources, replicate themselves and seek greater power. An updated framework released last year warned that AI could undergo an unexpectedly rapid increase in intelligence and subsequently compete with humans for control. China has also introduced guidelines covering autonomous AI agents. Rules issued in May require developers to build mechanisms capable of detecting, intervening in, blocking and recovering from improper behaviour by AI systems. The guidelines identify “operational loss of control” as a potential security risk and say humans should retain final decision-making authority over autonomous agents. Xi has similarly said AI should “always remain under human control”, while calling for stronger laws, technological monitoring and emergency-response systems. The difference increasingly lies in how those risks should be managed — and who gets to determine the rules. Amodei has proposed independent safety evaluations of frontier models and international coordination to prevent an uncontrolled race toward increasingly capable systems. But he has simultaneously argued that advanced American chips should remain unavailable to China, presenting Beijing with what Chinese officials regard as a contradiction: Washington wants international cooperation on AI safety while maintaining technological restrictions designed to prevent China from reaching the frontier. Chinese officials have instead promoted international governance alongside continued technological development, particularly through open-source systems and cooperation with countries in the Global South. Xi announced in July that China would provide developing countries with 5,000 places in AI training and seminar programmes over the next five years and establish AI application cooperation centres with ASEAN, the African Union, Arab states, Latin American countries, the Shanghai Cooperation Organization and BRICS members. A RACE NEITHER SIDE WANTS TO LOSE The debate exposes a dilemma confronting both Washington and Beijing. American AI developers increasingly warn that the technology may be advancing faster than society’s ability to control it. But slowing American development while Chinese laboratories continue advancing could allow China to narrow or eliminate the U.S. technological lead. Amodei described that possibility as the “toughest dilemma” facing his proposal. U.S. President Donald Trump has rejected calls for a significant slowdown, citing precisely that competition. “We’re leading China in AI. We’re the most sophisticated country in the world, and frankly I want to keep it that way because whoever wins AI wins,” Trump said on Sunday. The result is an emerging technological version of a classic security dilemma: both sides recognise that increasingly powerful systems could create profound risks, while neither is willing to allow the other to gain a decisive advantage by moving more quickly. The tension is already spreading beyond models themselves. Washington has restricted China’s access to advanced AI chips and semiconductor equipment, while American authorities and companies have accused Chinese developers of using distillation to reproduce capabilities developed by U.S. laboratories. Anthropic said last week it had identified large-scale campaigns involving Chinese companies seeking to extract capabilities from its models. Chinese companies have previously rejected accusations of improper model copying. The dispute is likely to become increasingly important in relations between the world’s two largest economies. U.S. and Chinese officials are expected to discuss frontier AI safety this month, and the subject could be raised when Trump and Xi meet on Sept. 24. For Beijing, however, cooperation is unlikely to mean accepting restrictions that leave the technological frontier controlled by American companies. China’s emerging position combines aggressive investment in domestic AI capabilities with regulation aimed at keeping advanced systems under human control — while rejecting Western proposals that Beijing believes would institutionalise an American technological advantage. That leaves Washington and Beijing confronting the same underlying problem from opposite sides: both increasingly acknowledge that advanced AI may carry serious risks, but neither appears willing to slow sufficiently if doing so means allowing the other to pull ahead.

$MU $SKHY $DRAM China's compute is going vertical. Huawei just raised its top AI chip 20 to 50% in two months. Cambricon repriced 20 to 30% higher. Grey market HBM inside China runs several times what the rest of the world pays. “Sources say Huawei has raised the indicated price of its Ascend 950DT accelerator card to more than $36,900. Depending on contract terms, that represents a 20% to 50% increase from prices quoted to customers just two months ago.” “Huawei has publicly said the 950DT, its most advanced AI chip, will become available in 4Q26.”“Sources say Cambricon has repriced its next-generation chip, tentatively called the 690, at 20% to 30% above levels indicated two months ago.” (No list price given.) “Sources say HBM obtained through these [grey-market] channels typically costs several times more than what buyers outside China pay.” “Huawei has said its Ascend 950 series will use two proprietary HBM technologies: HiBL 1.0 for the 950PR and HiZQ 2.0 for the 950DT, though it has not disclosed where or how the memory is manufactured.” “The Ascend 950PR, which sold for around $8,900 per card at the start of 2026, now costs more than $11,800, an increase of about 30%. The older Ascend 910C board has also climbed from around $13,300 at the beginning of the year to more than $16,200.” “Iluvatar CoreX has doubled its GPU shipments to TikTok developer ByteDance this year to 100,000 units.” “DeepSeek reportedly plans to deploy at least 160,000 Ascend 950DT chips at a large data center under construction in Inner Mongolia, primarily for AI inference.”

KubeCon + CloudNativeCon + OpenInfra Summit + PyTorch Conference China 2026 brought the people working across the open source AI stack together in Shanghai. @sparkycollier No single project, company, or community builds the AI stack alone. Behind the models, frameworks, cloud native technologies, and infrastructure powering AI is a global open source community working across every layer. PyTorch Foundation welcomed @alibaba_cloud and Cambricon (寒武纪) as Platinum Members and @AntGroup as a Gold Member, joining @Huawei and other existing Foundation members. Across the program, maintainers, researchers, developers, hardware vendors, and technical leaders discussed PyTorch, distributed training, inference and serving, heterogeneous hardware, cloud native infrastructure, accelerator integration, and agents, with participation from the @CloudNativeFdn and @openinfradev communities. Our recap covers keynotes from across the open source AI stack, China-based PyTorch contributors and organizations, the PyTorch TAC Accelerator Integration Working Group, the Foundation press conference, and community conversations in Shanghai. PyTorch conferences are the open source AI community’s town square, where what’s next gets decided. If you couldn’t join us in Shanghai, PyTorch Conference North America 2026 is the next chance to hear directly from maintainers, researchers, developers, and AI engineers working across the open source AI stack. PyTorch Conference North America comes to San Jose October 20–21, with maintainers from PyTorch, @vllm_project, @DeepSpeedAI, and @raydistributed among the speakers. 🔗 Read the Shanghai recap and register for PyTorch Conference North America 2026: #PyTorchCon# #KubeCon# #CloudNativeCon# #OpenInfraSummit#

DeepSeek has officially transitioned its highly publicized, limited-time 75% promotional discount into a permanent, market-disrupting price reset. This strategic shift permanently locks in a remarkably low rate of just 88 cents ($0.88) per million output tokens for its flagship V4 Pro model, establishing this rate as the new standard pricing after the initial promotional period concludes on May 31, 2026. This aggressive pricing maneuver is set to redefine the economics of generative AI development, allowing enterprises and developers to scale high-performance applications at a fraction of the cost of traditional market alternatives. DeepSeek V4 Pro commercial pricing metrics, global AI API cost comparison analysis, breaking China AI industry news, DeepSeek vs ChatGPT market positioning, hardware acceleration utilizing Huawei Ascend chips, the evolution of global AI infrastructure in 2026, identifying the cheapest high-performance AI model API, and the industry impact of DeepSeek's permanent discount strategy.