The GPUs were placed in servers that were supposed to be shipped from Taiwan to companies in Southeast Asia. The US Attorney's Office for the Southern District of New York has charged three people with illegally exporting NVIDIA GPUs to China in violation of the Export Control Reform Act. NVIDIA's chips have become a critical component in the rush to train and run increasingly complex artificial intelligence models, one the US has sought to manipulate with export controls and profit-sharing schemes with NVIDIA. The three people, Yih-Shyan Wally Liaw, Ruei-Tsang Steven Chang and Ting-Wei Willy Sun, two employees and one contractor working for US IT company Super Micro Computer, allegedly circumvented export control laws via a multi-step scheme that involved creating fake orders for servers with NVIDIA chips from Southeast Asian companies, that were then secretly sent to China. The plan involved paying a logistics company to repackage the servers in Taiwan, staging dummy servers to be inspected by Super Micro Computer's compliance team and falsifying records so Liaw, Chang and Sun's employer was unaware where the servers were actually being sent.

AI-driven pirated manga is booming. Can AI also help curb it? Japan's content industry -- which includes anime, manga and video games -- is a major export the country. Such exports were valued at ¥6 trillion ($38 billion) in 2024. When it comes to pirated manga online, which is being produced quicker thanks to artificial intelligence, government officials in Japan are planning to fight fire with fire and use AI to crack down on it.

PCWorld reports that Nvidia and Micron are making emotional appeals to consumers while PC users express frustration with big AI companies' practices and self-serving motives. Memory vendors predict DRAM and SSD shortages lasting until mid-2027, while new tariffs on advanced computing chips and potential Steam Machine pricing over $1,000 add to consumer concerns. The article highlights how corporations use emotional messaging to mask financial interests, advising consumers to remain skeptical of such appeals.

Apple's Siri AI will be powered by Gemini The White House names AMD MI325X and NVIDIA H200, in particular. Nvidia founder and CEO Jensen Huang speaks about the Vera Rubin AI platform during a question and answer session with reporters at the annual Consumer Electronics Show (CES) in Las Vegas, Nevada, on January 6, 2026. President Trump has signed a proclamation imposing a 25 percent tariff on "certain advanced computing chips," the White House has announced. As notes, the administration previously threatened much bigger and broader tariffs for chips. Trump even said that he was going to impose a 100 percent tariff on companies unless they invest on semiconductor manufacturing in the United States.

President Trump signed a proclamation on Wednesday to impose a 25 percent tariff on a narrow list of foreign semiconductors, providing a way for the government to earn revenue off the sale of lucrative chips used in artificial intelligence. The tariff, which would take effect Thursday, is far more limited than what the president initially threatened. Last year, the administration began an investigation aimed at encouraging tech companies and chip makers to buy semiconductors made in America. But instead of approving sweeping tariffs that would affect the industry, Wednesday's announcement showed the administration has settled for narrower levies that allow it to take a cut of artificial intelligence chips sold to China. A document released by the White House said a 25 percent tariff would be put on A.I. chips made by companies like Nvidia and AMD that are imported into the United States and then re-exported to other countries. The tariff would not apply to semiconductors that are brought into the country to be used domestically in data centers or in products for American consumers, industry or the government.

Savvy countries will discover there's a way to mitigate the harm incurred by Trump's tariffs--and it'll boost their own economies while making goods cheaper too. In 2026, the leaders of America's (former) trading partners are going to have to grapple with the political consequences of tit-for-tat tariffs. A tariff is a tax paid by consumers, and if there's one thing the past four years have taught us, it's that the public will not forgive a politician who presides over a period of rising prices, no matter what the cause. Luckily for the political fortunes of the world's leaders, there is a better way to respond to tariffs. Tit-for-tat tariffs are a 19th-century tactic, and we live in a 21st-century world--a world where the most profitable lines of business of the most profitable US companies are all vulnerable to a simple legal change that will make things cheaper for billions of people, all over the world, including in the US, at the expense of the companies whose CEOs posed with Trump on the inaugural dais.

Multi-agent role-playing has recently shown promise for studying social behavior with language agents, but existing simulations are mostly monolingual and fail to model cross-lingual interaction, an essential property of real societies. We introduce MASim, the first multilingual agent-based simulation framework that supports multi-turn interaction among generative agents with diverse sociolinguistic profiles. MASim offers two key analyses: (i) global public opinion modeling, by simulating how attitudes toward open-domain hypotheses evolve across languages and cultures, and (ii) media influence and information diffusion, via autonomous news agents that dynamically generate content and shape user behavior. To instantiate simulations, we construct the MAPS benchmark, which combines survey questions and demographic personas drawn from global population distributions. Experiments on calibration, sensitivity, consistency, and cultural case studies show that MASim reproduces sociocultural phenomena and highlights the importance of multilingual simulation for scalable, controlled computational social science.

Trump-Xi meeting: Who has the upper hand? Could Trump go for a third term? Is the US eyeing its next Latin American target? Why is Trump tearing down parts of the White House? United States President Donald Trump and his Chinese counterpart Xi Jinping have agreed to a trade truce under which the US will ease tariffs and Beijing will restart imports of US soya beans, delay the introduction of export restrictions on some of its rare earth metals and intensify efforts to curb illegal fentanyl trafficking.

Is the US eyeing its next Latin American target? Why is Trump tearing down parts of the White House? Trump-Xi meeting: What's at stake and who has the upper hand? United States President Donald Trump expects "a lot of problems" will be solved between Washington and Beijing when he meets China's President Xi Jinping in South Korea for a high-stakes meeting on Thursday, amid growing trade tensions between the two. Relations between the two world powers have been strained in recent years, with Washington and Beijing imposing tit-for-tat trade tariffs topping 100 percent against each other this year, the US restricting its exports of semiconductors vital for artificial intelligence (AI) development and Beijing restricting exports of critical rare-earth metals which are vital for the defence industry and also the development of AI, among other issues. On the sidelines of the Asia-Pacific Economic Cooperation (APEC) summit in Gyeongju, South Korea, on Wednesday, Trump said an expected trade deal between China and the US would be good for both countries and "something very exciting for everybody".

The rapid escalation of computational requirements for training large-scale language models has reinforced structural asymmetries between high-capacity jurisdictions and countries in the Global South. This paper examines the technical and fiscal feasibility of sovereign-scale language model training in Brazil and Mexico under conditions of constrained hardware access, energy availability, and fiscal ceilings. Using a dual-axis design that varies accelerator generation (NVIDIA H100 vs. A100) and training duration (90 vs. 150 days), we estimate compute demand, energy consumption, capital expenditures, and regulatory compatibility for the training of a 10-trillion-token model. Our findings show that while all configurations remain below export-control and electrical infrastructure thresholds, fiscal viability is determined by hardware efficiency. H100-based scenarios achieve training feasibility at a total cost of 8-14 million USD, while A100 deployments require 19-32 million USD due to higher energy and hardware demand. We argue that extending training timelines should be treated as a policy lever to mitigate hardware constraints, enabling the production of usable, auditable, and locally aligned models without competing at the global frontier. This study contributes to the discourse on AI compute governance and technological sovereignty by highlighting context-sensitive strategies that allow middle-income countries to establish sustainable and strategically sufficient AI capabilities.