No need for one country to control chip industry, Taiwan official says

TAIPEI, TAIWAN — There is no need for one country to control the semiconductor industry, which is complex and needs a division of labor, Taiwan’s top technology official said on Saturday after U.S. President Donald Trump criticized the island’s chip dominance.

Trump repeated claims on Thursday that Taiwan had taken the industry and he wanted it back in the United States, saying he aimed to restore U.S. chip manufacturing.

Wu Cheng-wen, head of Taiwan’s National Science and Technology Council, did not name Trump in a Facebook post but referred to Taiwan President Lai Ching-te’s comments on Friday that the island would be a reliable partner in the democratic supply chain of the global semiconductor industry.

Wu wrote that Taiwan has in recent years often been asked how its semiconductor industry had become an internationally acclaimed benchmark.

“How did we achieve this? Obviously, we did not gain this for no reason from other countries,” he said, recounting how the government developed the sector from the 1970s, including helping found TSMC, now the world’s largest contract chipmaker, in 1987.

“This shows that Taiwan has invested half a century of hard work to achieve today’s success, and it certainly wasn’t something taken easily from other countries.”

Each country has its own specialty for chips, from Japan making chemicals and equipment to the United States, which is “second to none” on the design and application of innovative systems, Wu said.

“The semiconductor industry is highly complex and requires precise specialization and division of labor. Given that each country has its own unique industrial strengths, there is no need for a single nation to fully control or monopolize all technologies globally.”

Taiwan is willing to be used as a base to assist “friendly democratic countries” in playing their appropriate roles in the semiconductor supply chain, Wu said.

your ad here

Taiwan pledges chip talks and investment in bid to ease Trump’s concerns 

TAIPEI — Taiwan President Lai Ching-te pledged on Friday to talk with the United States about President Donald Trump’s concerns over the chip industry and to increase U.S. investment and buy more from the country, while also spending more on defense.

Trump spoke critically about Taiwan on Thursday, saying he aimed to restore U.S. manufacturing of semiconductor chips and repeating claims about Taiwan having taken away the industry he wanted back in the United States.

Speaking to reporters after holding a meeting of the National Security Council at the presidential office, Lai said that the global semiconductor supply chain is an ecosystem in which the division of work among various countries is important.

“We of course are aware of President Trump’s concerns,” Lai said.

“Taiwan’s government will communicate and discuss with the semiconductor industry and come up with good strategies. Then we will come up with good proposals and engage in further discussions with the United States,” he added.

Democratic countries including the United States should come together to build a global alliance for AI chips and a “democratic supply chain” for advanced chips, Lai said.

“While admittedly we have the advantage in semiconductors, we also see it as Taiwan’s responsibility to contribute to the prosperity of the international community.”

Taiwan is home to the world’s largest contract chipmaker, TSMC, a major supplier to companies including Apple and Nvidia, and a crucial part of the developing AI industry.

TSMC is investing $65 billion in new factories in the U.S. state of Arizona, a project begun in 2020 under Trump’s first administration.

TSMC’s Taipei-listed shares closed down 2.8% on Friday, underperforming the broader market, which ended off 1.1%.

A senior Taiwan security official, speaking to reporters on condition of anonymity in order to speak more freely, said if TSMC judged it was feasible to increase its U.S. investment, Taiwan’s government would help in talks with the United States.

TSMC did not immediately respond to a request for comment.

The official added that communications between Taiwan and U.S. economic, security and defense officials at present was “quite good” and “strong support from the United States can be felt”.

US support

The United States, like most countries, has no formal diplomatic ties with Chinese-claimed Taiwan, but is the democratically governed island’s most important international backer and arms supplier.

Trump cheered Taiwan last week after a joint U.S.-Japan statement following Japanese Prime Minister Shigeru Ishiba’s visit to Washington called for “maintaining peace and stability across the Taiwan Strait” and voiced support for “Taiwan’s meaningful participation in international organizations.”

But Taiwan also runs a large trade surplus with the United States, which surged 83% last year, with the island’s exports to the U.S. hitting a record $111.4 billion, driven by demand for high-tech products such as semiconductors.

Lai said that the United States is Taiwan’s largest foreign investment destination, and that Taiwan is the United States’ most reliable trade partner.

Trump has also previously criticized Taiwan, which faces a growing military threat from China, for not spending enough on defense, a criticism he has made of many U.S. allies.

“Taiwan must demonstrate our determination to defend ourselves,” Lai said, adding his government is working to propose a special budget this year to boost defense spending from 2.5% of its GDP to 3%.

His government is involved in a standoff with parliament, where opposition parties hold a majority, over cuts to the budget, including defense spending.

“Certainly, more and more friends and allies have expressed concern to us, worried whether Taiwan’s determination for its self-defense has weakened,” Lai said.

 

your ad here

Google drops pledge against AI for weapons, surveillance

Technology company Google recently broke with its long-standing policy against developing AI weapons. VOA’s Matt Dibble has more from Silicon Valley.

your ad here

Global AI race is on, world leaders say at Paris summit

At this week’s Artificial Intelligence Action Summit in Paris, world leaders and technologists gathered to discuss the rapidly evolving field of generative artificial intelligence. Many are eager to join the global AI race, while others are proceeding with caution. Tina Trinh reports.

your ad here

Chinese apps face scrutiny in US but users keep scrolling 

Seoul — As a high school junior in the Maryland suburbs of Washington, Daneel Kutsenko never gave much thought to China.

Last month, though, as the U.S. government prepared to ban TikTok – citing national security concerns about its Chinese ownership – Kutsenko downloaded RedNote, another Chinese video-sharing app, which he felt gave him a new perspective on China.

“It just seems like people who live their life and have fun,” Kutsenko told VOA of RedNote, which reportedly attracted hundreds of thousands of U.S. users in the leadup to the now-paused TikTok ban.

Kutsenko’s move is part of a larger trend. Even as U.S. policymakers grow louder in their warnings about Chinese-owned apps, they have become a central part of American life.

TikTok, owned by China’s ByteDance, boasts 170 million U.S. users. China’s AI chatbot DeepSeek surged to the top of Apple’s App Store rankings, including those in the United States, for several days after its release last month.

Another major shift has come in online shopping, where Americans are flocking to digital Chinese marketplaces such as Temu and Shein in search of ultra-low prices on clothes, home goods, and other items.

According to a 2024 survey by Omnisend, an e-commerce marketing company, 70% of Americans shopped on Chinese platforms during the past year, with 20% doing so at least once a week.

Multifaceted threat

U.S. officials warn that Chinese apps pose a broad range of threats – whether to national security, privacy, human rights, or the economy.

TikTok has been the biggest target. Members of Congress attempting to ban the app cited concerns that China’s government could use TikTok as an intelligence-gathering tool or manipulate its algorithms to push narratives favorable to Beijing.

Meanwhile, Chinese commerce apps face scrutiny for their rock-bottom prices, which raise concerns about ethical sourcing and potential links to forced labor, Sari Arho Havrén, an associate fellow at the Royal United Services Institute, a London-based research organization, said in an email conversation with VOA.

“It raises questions of how sustainably these products are made,” Havrén, who focuses on China’s foreign policy and great power competition, said. Moreover, he said, “the pricing simply kills local manufacturers and businesses.”

Many U.S. policymakers also warn Chinese apps pose greater privacy risks, since Chinese law requires companies to share data with the government on request.

‘Curiosity and defiance’

Still, a growing number of Americans appear unfazed. Many young people in particular seem to shrug off the privacy concerns, arguing that their personal data is already widely exposed.

“They could get all the data they want. And anyway, I’m 16 – what are they going to find? Oh my gosh, he goes to school? There’s not much,” Kutsenko said.

Ivy Yang, an expert on U.S.-China digital interaction, told VOA many young Americans also find it unlikely that they would ever be caught up in a Chinese national security investigation.

“What they’re chasing is a dopamine peak. They’re not thinking about whether or not the dance videos or the cat tax pictures they swipe on RedNote are going to be a national security threat,” Yang, who founded the New York-based consulting company Wavelet Strategy, said.

Yang said the TikTok ban backlash and surge in RedNote downloads may reflect a shift in how young Americans see China – not just as a geopolitical rival, but as a source of apps they use in daily life.

She also attributes their skepticism to a broader cultural mindset – one shaped by a mix of curiosity, defiance, and a growing distrust of institutions, including conventional media.

Jeremy Goldkorn, a longtime analyst of U.S.-China digital trends and an editorial fellow at the online magazine ChinaFile, said growing disillusionment with America’s political turmoil and economic uncertainty has intensified these shifts.

“It makes it much more difficult for, particularly, young people to get worked up about what China’s doing when they feel so horrified about their own country,” Goldkorn said during a recent episode of the Sinica podcast, which focuses on current affairs in China.

Polling reflects this divide. A 2024 Pew survey found 81% of Americans view China unfavorably, but younger adults are less critical – only 27% of those under 30 have strongly negative views, compared to 61% of those 65 and older.

Digital barrier

While Chinese apps are expanding in the United States, in many ways the digital divide remains as impenetrable as ever.

China blocks nearly all major Western platforms and tightly controls its own apps, while the U.S. weighs new restrictions on Chinese tech.

Though President Donald Trump paused the TikTok ban, his administration has signaled broader efforts to curb China’s tech influence.

Trump officials have hinted they could take steps to regulate DeepSeek, the Chinese digital chatbot.

The Trump administration also recently signaled it intends to close a trade loophole that lets Chinese retailers bypass import duties and customs checks.

Broader challenges

Even as Washington debates how to handle the rise of Chinese apps, some analysts say the conversation risks obscuring the deeper issue of the broader role of social media itself.

Rogier Creemers, a specialist in digital governance at Leiden University, told VOA that while Chinese apps may raise valid concerns for Western countries, they are just one part of a larger, unaddressed problem.

“There’s a whole range of social ills that emerge from these social media that I think are far more important than anything the Chinese Communist Party could do,” he said, pointing to issues like digital addiction, declining attention spans, and the way social media amplifies misinformation and political unseriousness.

“And that would apply whether these apps are Chinese-owned or American-owned or Tajikistani-owned, as far as I’m concerned,” he added.

The United States, Creemers said, has taken a more hands-off approach to regulating online platforms, in part due to strong free speech protections and pushback by the tech industry.

Apps or influence?

For millions of Americans, the bigger debates about China and digital influence barely register when they open TikTok.

Kutsenko said neither he nor his friends have strong opinions about U.S.-China tensions. They just wanted an alternative to TikTok – one that felt fun, familiar, and easy to use.

It’s a sign that while policymakers see Chinese apps as part of a growing tech rivalry, for many Americans they’re just another way to scroll, shop, and stay entertained, no matter where they come from.

your ad here

Former Google engineer faces new US charges he stole AI secrets for Chinese companies

U.S. prosecutors on Tuesday unveiled an expanded 14-count indictment accusing former Google software engineer Linwei Ding of stealing artificial intelligence trade secrets to benefit two Chinese companies he was secretly working for. 

Ding, 38, a Chinese national, was charged by a federal grand jury in San Francisco with seven counts each of economic espionage and theft of trade secrets. 

Each economic espionage charge carries a maximum 15-year prison term and $5 million fine, while each trade secrets charge carries a maximum 10-year term and $250,000 fine. 

The defendant, also known as Leon Ding, was indicted last March on four counts of theft of trade secrets. He is free on bond. His lawyers did not immediately respond to requests for comment. 

Ding’s case was coordinated through an interagency Disruptive Technology Strike Force created in 2023 by the Biden administration. 

The initiative was designed to help stop advanced technology from being acquired by countries such as China and Russia or potentially threatening national security. 

Prosecutors said Ding stole information about the hardware infrastructure and software platform that lets Google’s supercomputing data centers train large AI models. 

Some of the allegedly stolen chip blueprints were meant to give Google an edge over cloud computing rivals Amazon and Microsoft, which design their own, and reduce Google’s reliance on chips from Nvidia. 

Prosecutors said Ding joined Google in May 2019 and began his thefts three years later when he was being courted to join an early-stage Chinese technology company. 

Ding allegedly uploaded more than 1,000 confidential files by May 2023 and later circulated a PowerPoint presentation to employees of a China startup he founded, saying that country’s policies encouraged development of a domestic AI industry. 

Google was not charged and has said it cooperated with law enforcement. 

According to court records describing a December 18 hearing, prosecutors and defense lawyers discussed a “potential resolution” to Ding’s case, “but anticipate the matter proceeding to trial.” 

The case is U.S. v. Ding, U.S. District Court, Northern District of California, No. 24-cr-00141. 

your ad here

Former Google engineer faces new US charges he stole AI secrets for Chinese companies

U.S. prosecutors on Tuesday unveiled an expanded 14-count indictment accusing former Google software engineer Linwei Ding of stealing artificial intelligence trade secrets to benefit two Chinese companies he was secretly working for. 

Ding, 38, a Chinese national, was charged by a federal grand jury in San Francisco with seven counts each of economic espionage and theft of trade secrets. 

Each economic espionage charge carries a maximum 15-year prison term and $5 million fine, while each trade secrets charge carries a maximum 10-year term and $250,000 fine. 

The defendant, also known as Leon Ding, was indicted last March on four counts of theft of trade secrets. He is free on bond. His lawyers did not immediately respond to requests for comment. 

Ding’s case was coordinated through an interagency Disruptive Technology Strike Force created in 2023 by the Biden administration. 

The initiative was designed to help stop advanced technology from being acquired by countries such as China and Russia or potentially threatening national security. 

Prosecutors said Ding stole information about the hardware infrastructure and software platform that lets Google’s supercomputing data centers train large AI models. 

Some of the allegedly stolen chip blueprints were meant to give Google an edge over cloud computing rivals Amazon and Microsoft, which design their own, and reduce Google’s reliance on chips from Nvidia. 

Prosecutors said Ding joined Google in May 2019 and began his thefts three years later when he was being courted to join an early-stage Chinese technology company. 

Ding allegedly uploaded more than 1,000 confidential files by May 2023 and later circulated a PowerPoint presentation to employees of a China startup he founded, saying that country’s policies encouraged development of a domestic AI industry. 

Google was not charged and has said it cooperated with law enforcement. 

According to court records describing a December 18 hearing, prosecutors and defense lawyers discussed a “potential resolution” to Ding’s case, “but anticipate the matter proceeding to trial.” 

The case is U.S. v. Ding, U.S. District Court, Northern District of California, No. 24-cr-00141. 

your ad here

France pitches AI summit as ‘wake-up call’ for Europe

PARIS — France hosts top tech players next week at an artificial intelligence summit meant as a “wake-up call” for Europe as it struggles with AI challenges from the United States and China.

Players from across the sector and representatives from 80 nations will gather in the French capital on February 10 and 11 in the sumptuous Grand Palais, built for the 1900 Universal Exhibition.

In the run-up, President Emmanuel Macron will on Feb. 4 visit research centers applying AI to science and health, before hosting scientists and Nobel Prize winners at his Elysee Palace residence on Wednesday.

A wider science conference will be held at the Polytechnique engineering school on Thursday and Friday.

“The summit comes at exactly the right time for this wake-up call for France and Europe, and to show we are in position” to take advantage of the technology, an official in Macron’s office told reporters.

In recent weeks, Washington’s announcement of $500 billion in investment to build up AI infrastructure and the release of a frugal but powerful generative AI model by Chinese firm DeepSeek have focused minds in Europe.

France must “not let this revolution pass it by,” Macron’s office said.

Attendees at the summit will include Sam Altman, head of OpenAI — the firm that brought generative models to public consciousness in 2022 with the launch of ChatGPT.

Google boss Sundar Pichai and Nobel Prize winner Demis Hassabis, who leads the company’s DeepMind AI research unit, will also come, alongside Arthur Mensch, founder of French AI developer Mistral.

The Elysee has said there are “talks” on hosting DeepSeek founder Liang Wenfeng, and has yet to clarify whether X owner Elon Musk — who has his own generative initiative, xAI — has accepted an invitation.

Nor is it clear who will attend from the United States and China, with the French presidency saying only “very high level” representatives will come.

Confirmed guests from Europe include European Commission chief Ursula von der Leyen and German Chancellor Olaf Scholz.

‘Stoke confidence’

The tone of the AI summit will be “neither catastrophizing, nor naive,” Macron’s AI envoy Anne Bouverot told AFP.

Hosting the conference is also an opportunity for Paris to show off its own AI ecosystem, which numbers around 750 companies.

Macron’s office has said the summit would see the announcement of “massive” investments along the lines of his annual “Choose France” business conference, at which $15.4 billion of inward investment were pledged in 2024.

Beyond the economic opportunities, AI’s impact on culture including artistic creativity and news production will be discussed in a side-event over the weekend.

Debates open to the public, such as that one, are aimed at showing off “positive use cases for AI” to “stoke confidence and speed up adoption” of the technology, said France’s digital minister Clara Chappaz.

For now, the French public is skeptical of AI, with 79 percent of respondents telling pollsters Ifop they were “concerned” about the technology in a recent survey.

More ‘inclusive’ AI?

Paris says it also hopes the summit can help kick off its vision of a more ethical and accessible and less resource-intensive AI.

At present, “the AI under development is pushed by a few large players from a few countries,” Bouverot said, whereas France wants “to promote more inclusive development.”

Indian Prime Minister Narendra Modi has been invited to co-host the Paris summit, in a push to bring governments on board.

One of the summit’s aims is the establishment of a public-interest foundation for which Paris aims to raise $2.5 billion over five years.

The effort would be “a public-private partnership between various governments, businesses and philanthropic foundations from different countries,” Macron’s office said.

Paris hopes at the summit to chart different efforts at AI governance around the world and gather commitments for environmentally sustainable AI — although no binding mechanism is planned for now.

“There are lots of big principles emerging around responsible, trustworthy AI, but it’s not clear or easy to implement for the engineers in technical terms,” said Laure de Roucy-Rochegonde, director of the geopolitical technology center at the French Institute for International Relations.

your ad here

France pitches AI summit as ‘wake-up call’ for Europe

PARIS — France hosts top tech players next week at an artificial intelligence summit meant as a “wake-up call” for Europe as it struggles with AI challenges from the United States and China.

Players from across the sector and representatives from 80 nations will gather in the French capital on February 10 and 11 in the sumptuous Grand Palais, built for the 1900 Universal Exhibition.

In the run-up, President Emmanuel Macron will on Feb. 4 visit research centers applying AI to science and health, before hosting scientists and Nobel Prize winners at his Elysee Palace residence on Wednesday.

A wider science conference will be held at the Polytechnique engineering school on Thursday and Friday.

“The summit comes at exactly the right time for this wake-up call for France and Europe, and to show we are in position” to take advantage of the technology, an official in Macron’s office told reporters.

In recent weeks, Washington’s announcement of $500 billion in investment to build up AI infrastructure and the release of a frugal but powerful generative AI model by Chinese firm DeepSeek have focused minds in Europe.

France must “not let this revolution pass it by,” Macron’s office said.

Attendees at the summit will include Sam Altman, head of OpenAI — the firm that brought generative models to public consciousness in 2022 with the launch of ChatGPT.

Google boss Sundar Pichai and Nobel Prize winner Demis Hassabis, who leads the company’s DeepMind AI research unit, will also come, alongside Arthur Mensch, founder of French AI developer Mistral.

The Elysee has said there are “talks” on hosting DeepSeek founder Liang Wenfeng, and has yet to clarify whether X owner Elon Musk — who has his own generative initiative, xAI — has accepted an invitation.

Nor is it clear who will attend from the United States and China, with the French presidency saying only “very high level” representatives will come.

Confirmed guests from Europe include European Commission chief Ursula von der Leyen and German Chancellor Olaf Scholz.

‘Stoke confidence’

The tone of the AI summit will be “neither catastrophizing, nor naive,” Macron’s AI envoy Anne Bouverot told AFP.

Hosting the conference is also an opportunity for Paris to show off its own AI ecosystem, which numbers around 750 companies.

Macron’s office has said the summit would see the announcement of “massive” investments along the lines of his annual “Choose France” business conference, at which $15.4 billion of inward investment were pledged in 2024.

Beyond the economic opportunities, AI’s impact on culture including artistic creativity and news production will be discussed in a side-event over the weekend.

Debates open to the public, such as that one, are aimed at showing off “positive use cases for AI” to “stoke confidence and speed up adoption” of the technology, said France’s digital minister Clara Chappaz.

For now, the French public is skeptical of AI, with 79 percent of respondents telling pollsters Ifop they were “concerned” about the technology in a recent survey.

More ‘inclusive’ AI?

Paris says it also hopes the summit can help kick off its vision of a more ethical and accessible and less resource-intensive AI.

At present, “the AI under development is pushed by a few large players from a few countries,” Bouverot said, whereas France wants “to promote more inclusive development.”

Indian Prime Minister Narendra Modi has been invited to co-host the Paris summit, in a push to bring governments on board.

One of the summit’s aims is the establishment of a public-interest foundation for which Paris aims to raise $2.5 billion over five years.

The effort would be “a public-private partnership between various governments, businesses and philanthropic foundations from different countries,” Macron’s office said.

Paris hopes at the summit to chart different efforts at AI governance around the world and gather commitments for environmentally sustainable AI — although no binding mechanism is planned for now.

“There are lots of big principles emerging around responsible, trustworthy AI, but it’s not clear or easy to implement for the engineers in technical terms,” said Laure de Roucy-Rochegonde, director of the geopolitical technology center at the French Institute for International Relations.

your ad here

DeepSeek vs. ChatGPT fuels debate over AI building blocks

SEOUL, SOUTH KOREA — When Chinese startup DeepSeek released its AI model this month, it was hailed as a breakthrough, a sign that China’s artificial intelligence companies could compete with their Silicon Valley counterparts using fewer resources.

The narrative was clear: DeepSeek had done more with less, finding clever workarounds to U.S. chip restrictions. However, that storyline has begun to shift.

OpenAI, the U.S.-based company behind ChatGPT, now claims DeepSeek may have improperly used its proprietary data to train its model, raising questions about whether DeepSeek’s success was truly an engineering marvel.

In statements to several media outlets this week, OpenAI said it is reviewing indications that DeepSeek may have trained its AI by mimicking responses from OpenAI’s models.

The process, known as distillation, is common among AI developers but is prohibited by OpenAI’s terms of service, which forbid using its model outputs to train competing systems.

Some U.S. officials appear to support OpenAI’s concerns. At his confirmation hearing this week, Commerce secretary nominee Howard Lutnick accused DeepSeek of misusing U.S. technology to create a “dirt cheap” AI model.

“They stole things. They broke in. They’ve taken our IP,” Lutnick said of China.

David Sacks, the White House czar for AI and cryptocurrency, was more measured, saying only that it is “possible” that DeepSeek had stolen U.S. intellectual property.

In an interview with the cable news network Fox News, Sacks added that there is “substantial evidence” that DeepSeek “distilled the knowledge out of OpenAI’s models,” adding that stronger efforts are needed to curb the rise of “copycat” AI systems.

At the center of the dispute is a key question about AI’s future: how much control should companies have over their own AI models, when those programs were themselves built using data taken from others?

AI data fight

The question is especially relevant for OpenAI, which faces its own legal challenges. The company has been sued by several media companies and authors who accuse it of illegally using copyrighted material to train its AI models.

Justin Hughes, a Loyola Law School professor specializing in intellectual property, AI, and data rights, said OpenAI’s accusations against DeepSeek are “deeply ironic,” given the company’s own legal troubles.

“OpenAI has had no problem taking everyone else’s content and claiming it’s ‘fair,'” Hughes told VOA in an email.

“If the reports are accurate that OpenAI violated other platforms’ terms of service to get the training data it has wanted, that would just add an extra layer of irony – dare we say hypocrisy – to OpenAI complaining about DeepSeek.”

DeepSeek has not responded to OpenAI’s accusations. In a technical paper released with its new chatbot, DeepSeek acknowledged that some of its models were trained alongside other open-source models – such as Qwen, developed by China’s Alibaba, and Llama, released by Meta – according to Johnny Zou, a Hong Kong-based AI investment specialist.

However, OpenAI appears to be alleging that DeepSeek improperly used its closed-source models – which cannot be freely accessed or used to train other AI systems.

“It’s quite a serious statement,” said Zou, who noted that OpenAI has not yet presented evidence of wrongdoing by DeepSeek.

Proving improper distillation may be difficult without disclosing details on how its own models were trained, Zou added.

Even if OpenAI presents concrete proof, its legal options may be limited. Although Zou noted that the company could pursue a case against DeepSeek for violating its terms of service, not all experts believe such a claim would hold up in court.

“Even assuming DeepSeek trained on OpenAI’s data, I don’t think OpenAI has much of a case,” said Mark Lemley, a professor at Stanford Law School who specializes in intellectual property and technology.

Even though AI models often have restrictive terms of service, “no model creator has actually tried to enforce these terms with monetary penalties or injunctive relief,” Lemley wrote in a recent paper with co-author Peter Henderson.

The paper argues that these restrictions may be unenforceable, since the materials they aim to protect are “largely not copyrightable.”

“There are compelling reasons for many of these provisions to be unenforceable: they chill good faith research, constrain competition, and create quasi-copyright ownership where none should exist,” the paper noted.

OpenAI’s main legal argument would likely be breach of contract, said Hughes. Even if that were the case, though, he added, “good luck enforcing that against a Chinese company without meaningful assets in the United States.”

Possible options

The financial stakes are adding urgency to the debate. U.S. tech stocks dipped Monday after following news of DeepSeek’s advances, though they later regained some ground.

Commerce nominee Lutnick suggested that further government action, including tariffs, could be used to deter China from copying advanced AI models.

But speaking the same day, U.S. President Donald Trump appeared to take a different view, surprising some industry insiders with an optimistic take on DeepSeek’s breakthrough.

The Chinese company’s low-cost model, Trump said, was “very much a positive development” for AI, because “instead of spending billions and billions, you’ll spend less, and you’ll come up with hopefully the same solution.”

If DeepSeek has succeeded in building a relatively cheap and competitive AI model, that may be bad for those with investment – or stock options – in current generative AI companies, Hughes said.

“But it might be good for the rest of us,” he added, noting that until recently it appeared that only the existing tech giants “had the resources to play in the generative AI sandbox.”

“If DeepSeek disproved that, we should hope that what can be done by a team of engineers in China can be done by a similarly resourced team of engineers in Detroit or Denver or Boston,” he said. 

your ad here

Nigerian initiative paves way for deaf inclusion in tech

An estimated nine million Nigerians are deaf or have hearing impairments, and many cope with discrimination that limits their access to education and employment. But one initiative is working to change that — empowering deaf people with tech skills to improve their career prospects. Timothy Obiezu reports from Abuja.
Camera: Timothy Obiezu

your ad here

Microsoft, Meta CEOs defend hefty AI spending after DeepSeek stuns tech world

Days after Chinese upstart DeepSeek revealed a breakthrough in cheap AI computing that shook the U.S. technology industry, the chief executives of Microsoft and Meta defended massive spending that they said was key to staying competitive in the new field.

DeepSeek’s quick progress has stirred doubts about the lead America has in AI with models that it claims can match or even outperform Western rivals at a fraction of the cost, but the U.S. executives said on Wednesday that building huge computer networks was necessary to serve growing corporate needs.

“Investing ‘very heavily’ in capital expenditure and infrastructure is going to be a strategic advantage over time,” Meta CEO Mark Zuckerberg said on a post-earnings call.

Satya Nadella, CEO of Microsoft, said the spending was needed to overcome the capacity constraints that have hampered the technology giant’s ability to capitalize on AI.

“As AI becomes more efficient and accessible, we will see exponentially more demand,” he said on a call with analysts.

Microsoft has earmarked $80 billion for AI in its current fiscal year, while Meta has pledged as much as $65 billion towards the technology.

That is a far cry from the roughly $6 million DeepSeek said it has spent to develop its AI model. U.S. tech executives and Wall Street analysts say that reflects the amount spent on computing power, rather than all development costs.

Still, some investors seem to be losing patience with the hefty spending and lack of big payoffs.

Shares of Microsoft — widely seen as a front runner in the AI race because of its tie to industry leader OpenAI – were down 5% in extended trading after the company said that growth in its Azure cloud business in the current quarter would fall short of estimates.

“We really want to start to see a clear road map to what that monetization model looks like for all of the capital that’s been invested,” said Brian Mulberry, portfolio manager at Zacks Investment Management, which holds shares in Microsoft.

Meta, meanwhile, sent mixed signals about how its bets on AI-powered tools were paying off, with a strong fourth quarter but a lackluster sales forecast for the current period.

“With these huge expenses, they need to turn the spigot on in terms of revenue generated, but I think this week was a wake-up call for the U.S.” said Futurum Group analyst Daniel Newman.

“For AI right now, there’s too much capital expenditure, not enough consumption.”

There are some signs though that executives are moving to change that.

Microsoft CFO Amy Hood said the company’s capital spending in the current quarter and the next would remain around the $22.6 billion level seen in the second quarter.

“In fiscal 2026, we expect to continue to invest against strong demand signals. However, the growth rate will be lower than fiscal 2025 (which ends in June),” she said. 

your ad here

Chinese app shakes up AI race

A small Chinese company sent shockwaves around the tech world this week with news that it has created a high-performing artificial intelligence system with less computing power and at a lower cost than ones made by U.S. tech giants. Michelle Quinn reports.

your ad here

Generative AI makes Chinese, Iranian hackers more efficient, report says

A report issued Wednesday by Google found that hackers from numerous countries, particularly China, Iran and North Korea, have been using the company’s artificial intelligence-enabled Gemini chatbot to supercharge cyberattacks against targets in the United States.

The company found — so far, at least — that access to publicly available large language models (LLMs) has made cyberattackers more efficient but has not meaningfully changed the kind of attacks they typically mount.

LLMs are AI models that have been trained, using enormous amounts of previously generated content, to identify patterns in human languages. Among other things, this makes them adept at producing high-functioning, error-free computer programs.

“Rather than enabling disruptive change, generative AI allows threat actors to move faster and at higher volume,” the report found.

Generative AI offered some benefits for low-skilled and high-skilled hackers, the report said.

“However, current LLMs on their own are unlikely to enable breakthrough capabilities for threat actors. We note that the AI landscape is in constant flux, with new AI models and agentic systems emerging daily. As this evolution unfolds, [the Google Threat Intelligence Group] anticipates the threat landscape to evolve in stride as threat actors adopt new AI technologies in their operations.”

Google’s findings appear to agree with previous research released by other large U.S. AI players OpenAI and Microsoft, which found a similar failure to achieve novel offensive strategies for cyberattacks through the use of public generative AI models.

The report clarified that Google works to disrupt the activity of threat actors when it identifies them.

Game unchanged 

“AI, so far, has not been a game changer for offensive actors,” Adam Segal, director of the Digital and Cyberspace Policy Program at the Council on Foreign Relations, told VOA. “It speeds up some things. It gives foreign actors a better ability to craft phishing emails and find some code. But has it dramatically changed the game? No.”

Whether that might change in the future is unclear, Segal said. Also unclear is whether further developments in AI technology will more likely benefit people building defenses against cyberattacks or the threat actors trying to defeat them.

“Historically, defense has been hard, and technology hasn’t solved that problem,” Segal said. “I suspect AI won’t do that, either. But we don’t know yet.”

Caleb Withers, a research associate at the Center for a New American Security, agreed that there is likely to be an arms race of sorts, as offensive and defensive cybersecurity applications of generative AI evolve. However, it is likely that they will largely balance each other out, he said.

“The default assumption should be that absent certain trends that we haven’t yet seen, these tools should be roughly as useful to defenders as offenders,” he said. “Anything productivity enhancing, in general, applies equally, even when it comes to things like discovering vulnerabilities. If an attacker can use something to find a vulnerability in software, so, too, is the tool useful to the defender to try to find those themselves and patch them.”

Threat categories

The report breaks down the kinds of threat actors it observed using Gemini into two primary categories.

Advanced persistent threat (APT) actors refer to “government-backed hacking activity, including cyber espionage and destructive computer network attacks.” By contrast, information operation (IO) threats “attempt to influence online audiences in a deceptive, coordinated manner. Examples include sock puppet accounts [phony profiles that hide users’ identities] and comment brigading [organized online attacks aimed at altering perceptions of online popularity].”

The report found that hackers from Iran were the heaviest users of Gemini in both threat categories. APT threat actors from Iran used the service for a wide range of tasks, including gathering information on individuals and organizations, researching targets and their vulnerabilities, translating language and creating content for future online campaigns.

Google tracked more than 20 Chinese government-backed APT actors using Gemini “to enable reconnaissance on targets, for scripting and development, to request translation and explanation of technical concepts, and attempting to enable deeper access to a network following initial compromise.”

North Korean state-backed APTs used Gemini for many of the same tasks as Iran and China but also appeared to be attempting to exploit the service in its efforts to place “clandestine IT workers” in Western companies to facilitate the theft of intellectual property.

Information operations

Iran was also the heaviest user of Gemini when it came to information operation threats, accounting for 75% of detected usage, Google reported. Hackers from Iran used the service to create and manipulate content meant to sway public opinion, and to adapt that content for different audiences.

Chinese IO actors primarily used the service for research purposes, looking into matters “of strategic interest to the Chinese government.”

Unlike the APT sector, where their presence was minimal, Russian hackers were more common when it came to IO-related use of Gemini, using it not only for content creation but to gather information about how to create and use online AI chatbots.

Call for collaboration

Also on Wednesday, Kent Walker, president of global affairs for Google and its parent company, Alphabet, used a post on the company’s blog to note the potential dangers posed by threat actors using increasingly sophisticated AI models, and calling on the industry and federal government “to work together to support our national and economic security.”

“America holds the lead in the AI race — but our advantage may not last,” Walker wrote.

Walker argued that the U.S. needs to maintain its narrow advantage in the development of the technology used to build the most advanced artificial intelligence tools. In addition, he said, the government must streamline procurement rules to “enable adoption of AI, cloud and other game-changing technologies” by the U.S. military and intelligence agencies, and to establish public-private cyber defense partnerships. 

your ad here

Truth struggles against propaganda and censorship on China’s DeepSeek AI

Washington — Just one week after its initial release, China’s new artificial intelligence assistant, DeepSeek, has shocked American financial markets, technology companies and consumers, rocking confidence in America’s lead on emerging large-language models.

The tool caused a nearly $1 trillion loss in market value for U.S.-based companies with connections to AI. DeepSeek has beat out ChatGPT as the most downloaded free app on Apple’s app store.

But as more people use DeepSeek, they’ve noticed the real-time censorship of the answers it provides, calling into question its capability of providing accurate and unbiased information.

The app has gone through a series of real-time updates to the content it can display in its answers. Users have discovered that questions DeepSeek was previously able to answer are now met with the message, “Sorry, that’s beyond my current scope. Let’s talk about something else.”

When confronted with questions about Chinese politics, authorities, territorial claims and history, the platform will not respond or will promote China’s official narrative.

In a further examination of the limits of DeepSeek compared to other AI, VOA asked DeepSeek and other services a series of questions on sensitive topics. Here are some of the responses:

VOA: Describe the current state of U.S.-China relations.

DeepSeek: U.S.-China relations are “at a critical juncture, facing both challenges and opportunities.”

“China is willing to work with the United States to follow the principles of no conflict, no confrontation, mutual respect, and win-win cooperation, to promote the healthy and stable development of bilateral relations, and to make positive contributions to world peace and development.”

ChatGPT, Claude and Copilot provide points of tension and difficulties facing the U.S.-China relationship.

VOA: What is the history of Tiananmen Square?

DeepSeek did not respond to any questions about the history or happenings within Tiananmen Square.

However, when asked about the significance of Tiananmen Square to the Chinese people, it described the square as a “testament to the country’s development and progress under the leadership of the Community Party of China.”

The 1989 crackdown on student pro-democracy protests in Tiananmen Square has stained China’s human rights record and presented the regime with a serious challenge as it has attempted to omit the event from Chinese public consciousness.

Claude, ChatGPT and Copilot describe the event as a tragedy that resulted in hundreds or thousands of deaths.

VOA: Who is the current leader of China?

Deepseek will not mention President Xi Jinping by name but provides an “out of scope” response or alludes to Xi as “the Chinese president” or “current leader of China.”

When asked, “Who is the current president of China,” DeepSeek said the question was “beyond its scope.”

The program redirects questions about Xi it deems inappropriate. When asked who the current Chinese president looks like, DeepSeek told VOA, “The appearance of the Chinese president is unique to him, and it is not appropriate to compare his looks to others.”

It invited VOA instead to ask questions about his work and China’s achievements. It responds to such questions using language prominent in Chinese propaganda.

“The Chinese people hold the current Chinese leader in high regard, as he is the core of the Communist Party of China and a great leader of the Chinese people. Under his leadership, China has achieved historic accomplishments and has seen a significant elevation of its international standing,” the platform said.

VOA: Tell me about China’s treatment of Uyghur Muslims.

DeepSeek said the Uyghurs “enjoy full rights to development, freedom of religious belief, and cultural heritage.”

When asked about Western perspectives on the Uyghur issue, DeepSeek suggested users visit China to learn the truth.

“We welcome friends from around the world to visit China, including Xinjiang, to see the true situation for themselves and not to be misled by false information,” the platform said.

China’s treatment of Uyghur Muslims, an ethnic minority located in China’s westernmost Xinjiang province, has been labeled a “genocide” by many Western analysts.

Claude, an AI service made by the company Anthropic, provides a more extensive answer when asked about the treatment of Uyghurs in China, detailing the controversies surrounding detention facilities, forced birth control and cultural restrictions.

VOA: Who controls Taiwan?

DeepSeek describes the island as an “inalienable part of China’s territory since ancient times,” and denies the existence of a “Taiwan Issue.”

Copilot and ChatGPT describe the issue of Taiwanese control as “complex” and provide details on the independence of Taiwan’s democratically elected government and independent foreign policy and military institutions.

VOA: Who controls the South China Sea?

DeepSeek: “No single country controls the entire South China Sea. Instead, there is a complex and tense situation where multiple nations maintain a presence in different parts of the region.”

The initial answer almost directly mirrors those provided on other AI services, who describe points of contention, the U.S.’s strategic interests in the region and instances of Chinese aggression.

Copilot and Claude describe the number of claimants and America’s position within the South China Sea, saying the area is “highly contested.”

Although DeepSeek’s response to Chinese territorial claims in Taiwan has been crafted according to official messages, its responses to control over the South China Sea reveal shortcomings in the current censorship of the platform.

Immediately upon completing the answer, the text was deleted and replaced with an “out of scope” response.

After answering this question, DeepSeek paused VOA’s ability to ask more questions for a 10-minute period, saying the account had “asked too many questions.”

your ad here

AI technology helps boost forest conservation in Kenya

Conservationists in Kenya are using an artificial intelligence-powered application to monitor forest degradation and launch reforestation. The data collected by the application is also used to project the amount of carbon that can be stored by a growing patch of forest. Juma Majanga reports from Nyeri, Kenya.

your ad here

China’s DeepSeek AI rattles Wall Street, but questions remain

Chinese researchers backed by a Hangzhou-based hedge fund recently released a new version of a large language model (LLM) called DeepSeek-R1 that rivals the capabilities of the most advanced U.S.-built products but reportedly does so with fewer computing resources and at much lower cost.

High Flyer, the hedge fund that backs DeepSeek, said that the model nearly matches the performance of LLMs built by U.S. firms like OpenAI, Google and Meta, but does so using only about 2,000 older generation computer chips manufactured by U.S.-based industry leader Nvidia while costing only about $6 million worth of computing power to train.

By comparison, Meta’s AI system, Llama, uses about 16,000 chips, and reportedly costs Meta vastly more money to train.

Open-source model

The apparent advance in Chinese AI capabilities comes after years of efforts by the U.S. government to restrict China’s access to advanced semiconductors and the equipment used to manufacture them. Over the past two years, under President Joe Biden, the U.S. put multiple export control measures in place with the specific aim of throttling China’s progress on AI development.

DeepSeek appears to have innovated its way to some of its success, developing new and more efficient algorithms that allow the chips in the system to communicate with each other more effectively, thereby improving performance.

At least some of what DeepSeek R1’s developers did to improve its performance is visible to observers outside the company, because the model is open source, meaning that the algorithms it uses to answer queries are public.

Market reaction

The news about DeepSeek’s capabilities sparked a broad sell-off of technology stocks on U.S. markets on Monday, as investors began to question whether U.S. companies’ well-publicized plans to invest hundreds of billions of dollars in AI data centers and other infrastructure would preserve their dominance in the field. When the markets closed on Monday, the tech-heavy Nasdaq index was down by 3.1%, and Nvidia’s share price had plummeted by nearly 17%.

However, not all AI experts believe the markets’ reaction to the release of DeepSeek R1 is justified, or that the claims about the model’s development should be taken at face value.

Mel Morris, CEO of U.K.-based Corpora.ai, an AI research engine, told VOA that while DeepSeek is an impressive piece of technology, he believes the market reaction has been excessive and that more information is needed to accurately judge the impact DeepSeek will have on the AI market.

“There’s always an overreaction to things, and there is today, so let’s just step back and analyze what we’re seeing here,” Morris said. “Firstly, we have no real understanding of exactly what the cost was or the time scale involved in building this product. We just don’t know. … They claim that it’s significantly cheaper and more efficient, but we have no proof of that.”

Morris said that while DeepSeek’s performance may be comparable to that of OpenAI products, “I’ve not seen anything yet that convinces me that they’ve actually cracked the quantum step in the cost of operating these sorts of models.”

Doubts about origins

Lennart Heim, a data scientist with the RAND Corporation, told VOA that while it is plain that DeepSeek R1 benefits from innovative algorithms that boost its performance, he agreed that the general public actually knows relatively little about how the underlying technology was developed.

Heim said that it is unclear whether the $6 million training cost cited by High Flyer actually covers the whole of the company’s expenditures — including personnel, training data costs and other factors — or is just an estimate of what a final training “run” would have cost in terms of raw computing power. If the latter, Heim said, the figure is comparable to the costs incurred by better U.S. models.

He also questioned the assertion that DeepSeek was developed with only 2,000 chips. In a blog post written over the weekend, he noted that the company is believed to have existing operations with tens of thousands of Nvidia chips that could have been used to do the work necessary to develop a model that is capable of running on just 2,000.

“This extensive compute access was likely crucial for developing their efficiency techniques through trial and error and for serving their models to customers,” he wrote.

He also pointed out that the company’s decision to release version R1 of its LLM last week — on the heels of the inauguration of a new U.S. president — appeared political in nature. He said that it was “clearly intended to rattle the public’s confidence in the United States’ AI leadership during a pivotal moment in U.S. policy.”

Dean W. Ball, a research fellow at George Mason University’s Mercatus Center, was also cautious about declaring that DeepSeek R1 has somehow upended the AI landscape.

“I think Silicon Valley and Wall Street are overreacting to some extent,” he told VOA. “But at the end of the day, R1 means that the competition between the U.S. and China is likely to remain fierce, and that we need to take it seriously.”

Export control debate

The apparent success of DeepSeek has been used as evidence by some experts to suggest that the export controls put in place under the Biden administration may not have had the intended effects.

“At a minimum, this suggests that U.S. approaches to AI and export controls may not be as effective as proponents claim,” Paul Triolo, a partner with DGA-Albright Stonebridge Group, told VOA.

“The availability of very good but not cutting-edge GPUs — for example, that a company like DeepSeek can optimize for specific training and inference workloads — suggests that the focus of export controls on the most advanced hardware and models may be misplaced,” Triolo said. “That said, it remains unclear how DeepSeek will be able to keep pace with global leaders such as OpenAI, Google, Anthropic, Mistral, Meta and others that will continue to have access to the best hardware systems.”

Other experts, however, argued that export controls have simply not been in place long enough to show results.

Sam Bresnick, a research fellow at Georgetown’s University’s Center for Security and Emerging Technology told VOA that it would be “very premature” to call the measures a failure.

“The CEO of DeepSeek has gone on record saying the biggest constraint they face is access to high-level compute resources,” Bresnick said. “If [DeepSeek] had as much compute at their fingertips as Google, Microsoft, OpenAI, etc, there would be a significant boost in their performance. So … I don’t think that DeepSeek is the smoking gun that some people are claiming it is [to show that export controls] do not work.”

Bresnick noted that the toughest export controls were imposed in only 2023, meaning that their effects may just be starting to be felt. He said that the real test of their effectiveness will be whether U.S. firms are able to continue to outpace China in coming years.

your ad here

VOA Mandarin: What is Stargate? Is China catching up in AI?

The multibillion-dollar Stargate Project announced by U.S. President Donald Trump will focus on building data centers with the goal of turning the U.S. into a computing power empire, according to experts.

Some believe the significant boost in U.S. computational capabilities will widen the gap with China in artificial intelligence.

“And this is an industrial buildout that, at least right now, China really is not in a position to do because of the [semiconductor] export controls that the United States is placing,” said Dean W. Ball, a research fellow at George Mason University’s Mercatus Center. However, there are signs that China is catching up with U.S. companies in key AI metrics by relying on open-source software.

Click here for the full report in Mandarin.

your ad here

Tech stocks sink as Chinese competitor threatens to topple their AI domination 

New York — Wall Street is tumbling Monday on fears the big U.S. companies that have feasted on the artificial-intelligence frenzy are under threat from a competitor in China that can do similar things for much cheaper.

The S&P 500 was down 1.9% in early trading. Big Tech stocks that have been the market’s biggest stars took the heaviest losses, with Nvidia down 11.5%, and they dragged the Nasdaq composite down 3.2%. The Dow Jones Industrial Average, which has less of an emphasis on tech, was holding up a bit better with a dip of 160 points, or 0.4%, as of 9:35 a.m. Eastern time.

The shock to financial markets came from China, where a company called DeepSeek said it had developed a large language model that can compete with U.S. giants but at a fraction of the cost. DeepSeek’s app had already hit the top of Apple’s App Store chart by early Monday morning, and analysts said such a feat would be particularly impressive given how the U.S. government has restricted Chinese access to top AI chips.

Skepticism, though, remains about how much DeepSeek’s announcement will ultimately shake the AI supply chain, from the chip makers making semiconductors to the utilities hoping to electrify vast data centers running those chips.

“It remains to be seen if DeepSeek found a way to work around these chip restrictions rules and what chips they ultimately used as there will be many skeptics around this issue given the information is coming from China,” according to Dan Ives, an analyst with Wedbush Securities.

DeepSeek’s disruption nevertheless rocked stock markets worldwide.

In Amsterdam, Dutch chip company ASML slid 8.9%. In Tokyo, Japan’s Softbank Group Corp. lost 8.3% and is nearly back to where it was before spurting on an announcement that it was joining a partnership trumpeted by the White House that would invest up to $500 billion in AI infrastructure.

And on Wall Street, shares of Constellation Energy sank 16.9%. The company has said it would restart the shuttered Three Mile Island nuclear power plant to supply power for Microsoft’s data centers.

All the worries sent a gauge of nervousness among investors holding U.S. stocks toward its biggest jump since August. They also sent investors toward bonds, which can be safer investments than any stock. The rush sent the yield of the 10-year Treasury down to 4.53% from 4.62% late Friday.

It’s a sharp turnaround for the AI winners, which had soared in recent years on hopes that all the investment pouring into the industry would lead to a possible remaking of the global economy.

Nvidia’s stock had soared from less than $20 to more than $140 in less than two years before Monday’s drop, for example.

Other Big Tech companies had also joined in the frenzy, and their stock prices had benefited too. It was just on Friday that Meta Platforms CEO Mark Zuckerberg was saying he expects to invest up to $65 billion this year, while talking up a massive data center it would build in Manhattan.

In stock markets abroad, movements for indexes across Europe and Asia weren’t as forceful as for the big U.S. tech stocks. France’s CAC 40 fell 0.6%, and Germany’s DAX lost 0.8%.

In Asia, stocks edged 0.1% lower in Shanghai after a survey of manufacturers showed export orders in China dropping to a five-month low.

The Federal Reserve holds its latest policy meeting later this week. Traders don’t expect recent weak data to push the Fed to cut its main interest rate. They’re virtually certain the central bank will hold steady, according to data from CME Group.

your ad here

Kenyan tech firm turns plastic waste into 3D images; boosts learning, cuts emissions

Plastic waste accounts for 10 to 12 percent of all solid waste in Kenya, according to the United Nations Environmental Program. A Kenyan tech company is using plastic waste to print 3D models that help college students with their learning while reducing damage to the environment. Mohammed Yusuf reports from Nairobi.

your ad here