- A new report states that most countries will fail at trying to build their own national large language models
- South Korea’s AI voucher program offers a more practical way to spread AI across everyday businesses and services
- Versions of it could bring more useful AI to the lives of more people
The big new idea in government AI circles has been easy to summarize and expensive to pursue: if artificial intelligence is going to shape the future, every serious country should probably have its own giant language model. The problem, according to Boston Consulting Group, is that this logic is already collapsing under the weight of reality. The better policy may turn out to be a simple government-backed voucher, much like the one undergoing testing in South Korea right now.
In a new report, BCG argues that the global race to build “sovereign AI” is veering into fantasy for most countries. The dream has been simple enough to understand. If large language models are becoming core infrastructure, then nations should build their own.
But BCG comes to the opposite conclusion. Full AI sovereignty is largely an illusion. The better target, it says, is “AI resilience,” meaning the ability to actually use AI broadly and effectively across the economy, even if a country does not own every part of the stack. And if you want to see what that looks like in practice, the firm says, look at South Korea’s AI voucher program.
AI paperwork future
The Korean program provides financial support to small and mid-sized businesses to adopt AI tools and services from approved vendors. In some versions of the scheme, companies have been eligible for support of as much as $140,000 to help them integrate AI. The businesses just need to know where AI could help and have a way to afford it.
This is the kind of policy that can sound almost disappointingly practical until you think about what it means in real life. A smaller manufacturer can use AI to improve quality control or reduce waste. A local logistics company can use it to forecast demand more accurately. A clinic can automate paperwork or streamline patient communication.
The program is aiming for practicality over looking futuristic. That's a different ambition from the one currently dominating AI politics in much of the world.
National chatbot delusion
Governments have fallen over themselves in their rush to talk about “AI sovereignty,” a combination of national data centers, homegrown models, and domestic chips in recent years. The idea has intuitive appeal. If AI is going to be economically and politically transformative, countries do not want to be entirely dependent on a handful of U.S. or Chinese firms to provide it.
But BCG’s point is that the most visible part of the AI stack, namely giant foundational models, is also the least realistic place for many countries to compete. Building a state-of-the-art large language model is now a brutally expensive and highly concentrated business. Even government-scale efforts are often tiny compared with private-sector AI infrastructure.
That does not mean countries should stop caring about domestic AI capacity. But they should be more strategic about where independence matters and where it's less relevant.
“Pursuing a more flexible AI agenda is proving to be more practical and sustainable than attempting to achieve AI autonomy," the report concludes.
South Korea’s voucher model sidesteps that trap by focusing on diffusion rather than symbolism. It simply asks, how do you get AI into the hands of businesses that could benefit from it right now?
That matters a lot more to most people than rhetoric about “sovereign AI.” Consumers wonder whether AI can make grocery delivery windows more accurate and medical admin less maddening, not whether their local grocery chain uses a nationally branded LLM.
And Korea’s approach seems to be doing exactly that kind of quiet groundwork. Official materials say broader voucher-style digital transformation programs have reached 127,000 businesses. It's not exciting, but it does seem to work.
It may turn out that, as AI reshapes work and life, the countries that benefit most may not be the ones that try to own every element of an AI experience. Just making it easy, affordable, and useful will do.
