British Prime Minister Keir Starmer wants the UK to be a trailblazer for artificial intelligence (AI). This makes sense in theory for a place that gave the world computing icons like Alan Turing, Ada Lovelace and Tim Berners-Lee — but a lot of his plan does not.
One of the UK’s greatest strengths is its role as a fast, thoughtful regulator on technology, often striking a sensible middle ground between the US’ regulatory vacuum and the EU’s stifling bureaucracy. Starmer says the UK should be more than that, touting AI this week as a springboard for growth that could lift the UK’s productivity by 1.5 percent and add ￡47 billion (US$57.4 billion) to the economy. However, the lengthy plans he sketched out for that number are vague and do not account for the fact that financial benefits of tech revolutions often take years to manifest. An intervention of this kind, which would cost ￡14 billion, also looks unwise as the UK faces serious public spending pressures.
Take the government’s move to follow an entire 50-point action plan that was drawn up by UK venture capitalist Matt Clifford. As everyone knows, the longer your to-do list (and 50 is a lot) the less likely you would get to everything. The probability decreases when those plans lack features such as timelines or metrics for success.
One action point, for instance, is to create a “UK Sovereign AI Unit” to invest in AI companies, but it lacks details on a budget, investment criteria or roughly when it might be set up. There is also no timeline for the establishment of “AI growth zones.” A pledge on mandatory AI adoption across government departments also lacked targets, timelines or how the success of their initiatives would be measured.
One good feature of the AI plan is to expand the UK’s compute capacity 20-fold by the year 2030. Starmer, not surprisingly, hyped that increase a little too much.
“That’s like upgrading from my dad’s old Ford Cortina to a Formula 1 McLaren in one,” he said in a speech on Monday.
Not really. A more accurate analogy might be upscaling to a Nissan Qashqai. The proposal to increase the UK’s ownership of graphics processing units (GPUs) for AI training to 100,000 is a fraction of what the largest technology companies are hoarding. That is still a noble and important attempt at countering the imbalance of computing power Big Tech holds now. They have a stranglehold on academia because computer science academics need access to vast amounts of GPUs for cutting-edge studies. That has incentivized many people to conduct research in the interests of tech firms (figuring out how to make systems bigger, for instance, instead of safer or fairer).
However, the UK has not provided technical specifications on the GPUs it is acquiring. Are they gold-standard Nvidia H100s or a cheaper, slower variant? Nor has it given a budget for the new supercomputer it plans to build. Strangely, soon after Starmer took power in summer last year, he shut down a planned ￡800 million supercomputer being built at Edinburgh University as part of an initial raft of spending cuts. It would have made more sense to keep that project.
Starmer’s U-turn suggests an erratic, hype-fueled approach to AI that involves throwing lots of spaghetti on a wall and praying it all sticks. Perhaps he was charmed by Clifford, the venture capitalist who designed the ambitious plan, described in a 2023 Politico profile as good at “winning over” politicians.
A better approach would have been to focus on a few key objectives, such as the growth of computing power, or to mandate use of AI in government divisions, and provide greater specificity. Starmer would also do well to play up the UK’s leading role as a safety regulator, which benefits from the concentrated AI expertise in London, where Google DeepMind is based. Some 150 people work for the government’s leading AI Safety Institute, more than those working on these issues at the European Commission in Brussels.
In his speech, Starmer said AI safety should not be the “limit of what the state should do.” Yet his interventionist plans go too far the other way. He can enjoy a public-relations win for now, but he would pay the price when UK universities, start-ups and tech firms begin to seek more policy specifics.
Parmy Olson is a Bloomberg Opinion columnist covering technology. A former reporter for the Wall Street Journal and Forbes, she is author of Supremacy: AI, ChatGPT and the Race That Will Change the World. This column does not necessarily reflect the opinion of the editorial board or Bloomberg LP and its owners.
In their recent op-ed “Trump Should Rein In Taiwan” in Foreign Policy magazine, Christopher Chivvis and Stephen Wertheim argued that the US should pressure President William Lai (賴清德) to “tone it down” to de-escalate tensions in the Taiwan Strait — as if Taiwan’s words are more of a threat to peace than Beijing’s actions. It is an old argument dressed up in new concern: that Washington must rein in Taipei to avoid war. However, this narrative gets it backward. Taiwan is not the problem; China is. Calls for a so-called “grand bargain” with Beijing — where the US pressures Taiwan into concessions
The term “assassin’s mace” originates from Chinese folklore, describing a concealed weapon used by a weaker hero to defeat a stronger adversary with an unexpected strike. In more general military parlance, the concept refers to an asymmetric capability that targets a critical vulnerability of an adversary. China has found its modern equivalent of the assassin’s mace with its high-altitude electromagnetic pulse (HEMP) weapons, which are nuclear warheads detonated at a high altitude, emitting intense electromagnetic radiation capable of disabling and destroying electronics. An assassin’s mace weapon possesses two essential characteristics: strategic surprise and the ability to neutralize a core dependency.
Chinese President and Chinese Communist Party (CCP) Chairman Xi Jinping (習近平) said in a politburo speech late last month that his party must protect the “bottom line” to prevent systemic threats. The tone of his address was grave, revealing deep anxieties about China’s current state of affairs. Essentially, what he worries most about is systemic threats to China’s normal development as a country. The US-China trade war has turned white hot: China’s export orders have plummeted, Chinese firms and enterprises are shutting up shop, and local debt risks are mounting daily, causing China’s economy to flag externally and hemorrhage internally. China’s
During the “426 rally” organized by the Chinese Nationalist Party (KMT) and the Taiwan People’s Party under the slogan “fight green communism, resist dictatorship,” leaders from the two opposition parties framed it as a battle against an allegedly authoritarian administration led by President William Lai (賴清德). While criticism of the government can be a healthy expression of a vibrant, pluralistic society, and protests are quite common in Taiwan, the discourse of the 426 rally nonetheless betrayed troubling signs of collective amnesia. Specifically, the KMT, which imposed 38 years of martial law in Taiwan from 1949 to 1987, has never fully faced its
RSS