#AI #ChatGPT #Grok: Once artificial intelligence really gets going, how fast can the economy grow?

I followed the lead set by Tim Harford in "If AI lifts off, will living standards follow?" and asked ChatGPT and Grok.

I asked ChatGPT:

"Please, feel free to speculate… though in less than 300 words:

Once artificial intelligence really gets going, how fast can the economy grow? Five per cent a year? Ten per cent? Fifty per cent?"

ChatGPT answered:

"Speculating freely: once artificial intelligence truly integrates across the economy, the growth rate could, in principle, exceed anything we’ve seen in modern history. Traditional constraints—labor supply, managerial capacity, coordination costs—are precisely what AI promises to relax.

At the moderate end, AI might sustain global growth in the 5–7% range for decades, roughly doubling the pace of advanced economies today. That would already be transformative: compound growth at 7% doubles output every 10 years.

A more extreme possibility is 10–20% growth annually, if AI automates not just routine work but also much of scientific discovery, engineering, and entrepreneurship itself. In that case, the bottleneck of “who invents the next breakthrough” loosens, and innovation becomes continuous and self-reinforcing. Such growth rates imply doubling the economy every 3–7 years—levels usually associated with small frontier economies catching up, not the entire world.

The most radical speculation—50%+ annual growth—would mean AI essentially creates a self-improving system of production, design, and distribution, with humans struggling to keep up. That’s not just economic growth in the classical sense but something more akin to a civilizational transformation, where “GDP” may cease to measure what matters.

So the spectrum runs from a modest boost (5%) to explosive acceleration (>20%), depending on how fast AI can (1) replicate human-level reasoning, (2) integrate with physical production, and (3) avoid coordination and social frictions. In practice, political, regulatory, and resource constraints may prevent the highest numbers—but technically, nothing rules them out."

Would you like me to anchor this in historical parallels (e.g., Industrial Revolution, electricity, internet) to show what kind of multiplier might be realistic, versus purely speculative?

I said: Yes please, but in in less than 200 words.

ChatGPT said:

"Historically, big technologies lifted growth but within limits. The Industrial Revolution doubled Britain’s per-capita growth from ~0.3% to ~1% a year—huge by historical standards but gradual. The spread of electricity and mass production pushed U.S. growth to ~2–3% sustained. The computer and internet era gave a one-time boost, but growth rarely exceeded 4–5% in advanced economies.

AI differs because it can speed up not only production but also innovation itself. If it amplifies discovery like electricity amplified muscle power, we could see global growth at 5–7% for decades—unprecedented at scale. If AI can recursively accelerate research, growth could climb to 10–20%, closer to the explosive catch-up of “Asian Tigers,” but applied globally.

The leap to 50%+ annual growth has no historical parallel; it would be more like a technological singularity than a continuation of economic history. Past revolutions suggest sustained boosts are real, but explosive, runaway growth would mark a civilizational break rather than just “faster GDP.”

Do you want me to sketch what kind of constraints (energy, politics, social adjustment) might hold AI growth closer to the historical pattern than the singularity path?

I said: Yes please, but in in less than 200 words

ChatGPT said:

"Several constraints could keep AI-driven growth closer to historical patterns. Energy is a hard limit: exponential growth in computing and production demands vast power, and scaling renewable, nuclear, or other sources takes time. Physical capital—factories, housing, transport—cannot be replaced overnight, even if AI designs them instantly. Human adaptation is another brake: societies need time to retrain, absorb, and regulate, and resistance from workers, firms, or governments slows diffusion.

Coordination frictions also matter. Nations may restrict AI exports, regulate its use, or impose safety checks, curbing global acceleration. Meanwhile, resource bottlenecks—rare earths, chips, robotics hardware—could stall deployment. Finally, inequality and political backlash may block full adoption if many feel excluded or threatened.

These forces suggest AI could plausibly raise growth to 5–7%, maybe 10%, but sustained 20%+ requires solving energy, materials, and governance hurdles as quickly as technical ones. History shows revolutions spread in waves, not instant leaps."

Would you like me to quantify how fast GDP could double under each plausible growth rate (e.g., 5%, 10%, 20%) to make the comparison more tangible?

I said: For today this is enough. Thanks!

It said:You’re very welcome! I’ll be here if you want to continue the thread another day. Wishing you a good evening!

I asked Grok:

"Please, feel free to speculate… though in less than 300 words:

Once artificial intelligence really gets going, how fast can the economy grow? Five per cent a year? Ten per cent? Fifty per cent?"

Grok answered:

"Once AI truly accelerates—say, with AGI or superintelligence by the 2030s or 2040s—economic growth could shatter historical norms. Current global GDP growth hovers around 3%, but AI could amplify it dramatically through automation, innovation, and productivity surges.

In moderate scenarios, experts predict AI adding 1-2% annually to GDP via task automation and R&D boosts, pushing total growth to 4-5%. More optimistic views, like McKinsey's, foresee $4.4 trillion in annual value by 2030, potentially lifting growth to 5-10% as AI transforms industries. 

But if we hit a "technological singularity," where AI self-improves exponentially, growth could explode. Some models suggest superexponential rates, with GDP doubling yearly (100%+ growth) or faster, leading to 50% as a conservative floor in early phases. Imagine AI emulating human minds at scale, eradicating scarcity and enabling post-scarcity abundance. 

Risks abound—job displacement, inequality—but the upside? A hyper-accelerated economy, growing at rates we can't yet fathom, potentially 50% or beyond in a runaway AI boom. Speculatively, 10% seems plausible mid-term; 50%+ in full singularity mode."

I said: Thanks!

It answered: You're welcome! If you have more questions about AI or anything else, just ask.

Note: The answers are copied exactly from those given to me by ChatGPT and Grok

Here my many other questions to ChatGPT – Grok on bank regulations.

About Italy, there are serious questions that FT, and others, should not silence.

Sir, I refer to “Draghi plots €221bn rebuilding of Italy’s recession ravaged economy” Miles Johnson and Sam Fleming, and to “Europe’s future hinges on Italy’s recovery fund reforms”, Andrea Lorenzo Capusella, FT April 22, and to so many other articles that touch upon the issue of Italy’s future, in order to ask some direct questions.

Do you think Italy’s chances of a bright future lies more in the hands of Italy’s government and its bureaucrats, than in hands of e.g., Italian small businesses and entrepreneurs?

I ask this because, with current risk weighted bank capital requirements, regulators, like Mario Draghi a former chairman of the Financial Stability Board, arguably arguing Italy’s government represents less credit risk, do de facto also state it is more worthy of credit. I firmly reject such a notion.

Yes, Italy clearly shows a stagnant productivity, but could that be improved by in any way increasing its government revenues?

Italy, before Covid-19, showed figures around 150% of public debt to GDP and government spending of close to 50% of GDP. I am among the last to condone tax evasion… but if Italian had paid all their taxes… would its government represent a lower share of GDP spending, and do you believe its debt to GDP would be lower?

One final question: Sir, given how Italy is governed, excluding from it any illegal activities such as drug trafficking, where do you think it would be without its shadow eeconomy, its economia sommersa? A lot better? Hmm!

PS. As you know (but seemingly turn a blind eye to), Italy’s debt, even though it cannot print euros on its own, has, independent of credit ratings, been assigned by EU regulators, a 0% risk weight.

Are our productivity, real salary, unemployment, and GDP figures up to date?

John Authers writes, “If ever there was a good place to take a deep breath and gain context on our unnecessarily complex world, it would be Jackson Hole, Wyoming” “Powell avoids foreign complications in the winds of Wyoming” August 25.

In a recent post in Bank of England’s blog “bankunderground” I read: “With the rise of smartphones in particular, the amount of stimuli competing for our attention throughout the day has exploded... we are more distracted than ever as a result of the battle for our attention. One study, for example, finds that we are distracted nearly 50% of the time.”

So, one interesting way for central bankers to get an understanding of our ever more complex world would be to ask them: If you deliver the same at work as a decade ago, but now you spend 50% of your working hours consuming distractions, on your cell or similar, how much has your productivity, your real salary, your voluntary unemployment increased? And what about GDP?

PS. Sir, as you well know, before initiating the Jackson Hole proceedings, I would love for all central bankers there to assist a seminar on the meaning “conditional probabilities.” Had they known about it before imposing their risk weighted capital requirements for banks it would have saved the world from a lot of problems.

@PerKurowski

If it now takes researchers much more time to come up with ideas, how much of that is caused by their consumption of distractions?

Sir, Diane Coyle writes that current productivity data does not consider what’s achieved through outsourcing since GDP excludes all the intermediate links in the chain and the additional value is netted out. If included “economic output would look somewhat better than the current statistics suggest. “Conventional measures pose the wrong productivity question” August 16.

But when Coyle refers to “a recent paper a group of economists from Stanford University and the Massachusetts Institute of Technology…calculate that it now takes more than 20 times the number of researchers to generate the same economic growth as it did in the 1930s.” I would have to ask: Does that calculation take due consideration of the ever-growing time researchers spend, not working, but consuming distraction on the cell phones or laptops?

Some months ago, in Bank of England’s “bankunderground” blog, we read a post by Dan Nixon titled “Is the economy suffering from the crisis of attention?” It said, “With the rise of smartphones in particular, the amount of stimuli competing for our attention throughout the day has exploded... we are more distracted than ever as a result of the battle for our attention. One study, for example, finds that we are distracted nearly 50% of the time.”

If those distractioninterruptions were recorded for what they really are, we would probably see a dramatic increase in productivity, in real salaries, in voluntary unemployment and in GDP.

In other words our current economic compasses might not be working properly, risking taking us in the wrong direction.

@PerKurowski

If we want real productivity data, we need consider real working conditions

Sir, I refer to my former colleague at the World Bank Kurt Bayer’s letter of August 16, “Real productivity is an efficiency measure”. I fully agree with what he argues, though, unfortunately, lately, life has become more complicated, even for statisticians. 

Some months ago, in Bank of England’s “bankunderground” blog, we read a post by Dan Nixon titled “Is the economy suffering from the crisis of attention?”. It said, “With the rise of smartphones in particular, the amount of stimuli competing for our attention throughout the day has exploded... we are more distracted than ever as a result of the battle for our attention. One study, for example, finds that we are distracted nearly 50% of the time.”

And so these interruptions should have to be recorded for what they are, meaning a consumption of distractions during working hours. If so, we would perhaps see a dramatic increase in productivity, in real salaries, in voluntary unemployment and in GDP.

In other words our current economic compasses might not be working properly, risking taking us in the wrong direction.

@PerKurowski

We need to rethink productivity data, in light of so many “working hours” spent consuming distractions.

Sir, referencing Chris Giles’ and Gavin Jackson’s “Surge in low-value jobs magnifies UK productivity problem” of August 13, I believe that whenstating “increases in low-wage jobs in bars, social work and warehouses have served to hold back UK productivity growth” it hints at sort of causation that might not really be there.

I say so because we have entered a new era that requires redefining entirely the ways we measure productivity. 

Some months ago, in Bank of England’s “bankunderground” blog, we read a post by Dan Nixon titled “Is the economy suffering from the crisis of attention?”. It said, “With the rise of smartphones in particular, the amount of stimuli competing for our attention throughout the day has exploded... we are more distracted than ever as a result of the battle for our attention. One study, for example, finds that we are distracted nearly 50% of the time.”

Nixon, answering the question posed in the title wrote, “The most obvious place to look would be in productivity growth, which has been persistently weak across advanced economies over the past decade.”

But, what if instead of being recorded as distractions during working hours, these were to be recorded as a private consumption that reduces the effective working hours? Would that not increase GDP and reduce working hours, and thereby point instead to a dramatic increase in productivity?

In the same vein, would then not real-salaries, instead of stagnating, have been increasing a lot?

And what about our employment and unemployment data if the time used to consume distractions during working hours would not be counted as work? 

Sir, it behooves us to make certain how we measure the economy gets updated to reflect underlying realities. 

Perhaps then we are able to understand better the growing need for worthy and decent unemployments.

Perhaps then we are able to better understand the need for a Universal Basic Income, not as to allow some to stay in bed, but to allow everyone a better opportunity to reach up to whatever gainful employments might be left, like those “low-wage jobs” that it behooves us all, not to consider as “low value jobs”

@PerKurowski

Productivity, real salaries, employment rates, GDP should consider the increased consumption of distractions during work hours

Sir, Erik Brynjolfsson (and Andrew McAfee) writes: “If machine learning is already superhuman, why did we not see it in productivity statistics earlier? The answer is that its breakthroughs haven’t yet had time to deeply change how work gets done” “Machine learning will be the engine of global growth” July 27.

That is true, but we also need to realize that we have not done yet measured the effect of all the increased consumption of distractions during working hours.

In Bank of England’s “bankunderground" blog we recently read: “With the rise of smartphones in particular, the amount of stimuli competing for our attention throughout the day has exploded... we are more distracted than ever as a result of the battle for our attention. One study, for example, finds that we are distracted nearly 50% of the time.”

And on a recent visit to a major shop in the Washington area, thinking about it, I noticed that 8 out of the 11 attendants I saw were busy with some type of activity on their cellphones, and I seriously suspect they were not just checking inventories.

The impact of that on productivity, with less effective working time is being put into production, could be huge.

Also, going from for instance a 10% to a 50% distraction signifies de facto that full time or paid by the hour employee’s real salaries have increased fabulously.

And what about the real employment rate if we deduct the hours engaged in distractions? A statistical nightmare? Will we ever be able to compare apples with apples again?

And how should all these working hours consumed with distractions be considered in the GDP figures?

@PerKurowski

What does going from a 10% to a 50% level of distraction signify for full-time employees’ real salaries?

Sir, Sarah O’Connor writes “Males in well-paid full-time employment, earning 2.5 times the median wage, are now working slightly longer hours on average than two decades ago, according to the Resolution Foundation, a think-tank.” “Robots will drive us to rethink the way we distribute work” November 29.

In Bank of England’s “bankunderground" blog we recently read: “With the rise of smartphones in particular, the amount of stimuli competing for our attention throughout the day has exploded... we are more distracted than ever as a result of the battle for our attention. One study, for example, finds that we are distracted nearly 50% of the time.”

So if 50% of the time is now spend being distracted, and since those not employed full time are not equally remunerated for distractions, that of “earning 2.5 times the median wage”, could de facto be a serious understatement.

Sir, just think about what going from for instance a 10% to a 50% distraction signifies to full time employees’ real salaries. Fabulous increases!

PS. And what is its impact on productivity in terms that less effective working time is being put into production?

PS. Or what would the real employment rate be if we deduct the hours engaged in distractions? A statistical nightmare? Will we ever be able to compare apples with apples again?

PS. And how should all these working hours consumed with distractions be considered in GDP figures?

PS. Robots will not only drive us to rethink the way we distribute work. It also forces us to think about how to create decent and worthy unemployments.

@PerKurowski

Martin Wolf, forget for a while the usual numbers. The society needs all men on deck for much more important tasks.

Sir, when you don’t know what to do, you might spend sometime putting a drawer in order, or sharpening some pencils. That’s the impression I get from Martin Wolf’s “British business is starting to look more Italian” March 10.

There are too many new challenges building up fast and on steroids, and those numbers Wolf so insistently feeds his readers with, might also risk chaining us to no longer valid economic realities or models.

How are we to best manage (and measure) the effect of all those salaries paid to humans that are disappearing because of robots and automation?

How are we to get the decent and worthy unemployments, which a structural lack of jobs indicates we will need more and more?

If we go for something like a Universal Basic Income, do we have the tools needed to measure their adequate levels? A correct dose UBI dose could be magical, but an excessive one, extremely poisonous.

What would happen to Britain and Italy, if their robots do not measure up in capacity to for instance Germany’s?

With risk weighted capital requirements for banks our most important risk takers are told not to take risks, while, without a blinking of an eye, we allow our young to take on debt to study what we all suspect will not generate them any repayment capacity.

Regulators allow a low 20% risk weight for what is so dangerous to banks as what’s rated AAA, while imposing a 150% risk weight on the so innocuous below BB-… and tenured economist or finance professors do not even question that.

Where are the societal debates on all these issues? For instance were there any mention of robots in the recent Brexit and US president election processes?

Martin Wolf, at least for a while forget numbers which importance might have been superseded by events. We need all men (good and bad) on deck.

PS. Of course, just in case “all men” includes all women too.

@PerKurowski

A Universal Basic Income, a Societal Dividend, needs always to be slightly small, so as never risk being too large.

Sir Ralph Atkins and Gemma Tetlow report that “Swiss vote against basic income provision” “Welfare systems” June 6.

I support Universal Basic Income, for me it is a Societal Dividend, but I would have voted NO in the referendum. 2.500 Swiss Francs, about US$3.500 monthly, about 50 percent of the Swiss GDP per capita is way too large for a “Basic”. In Switzerland, something like $1.000, perhaps expressed as a percentage of GDP or of average or median salaries, would be a much more reasonable level at which to start this social experiment.

And of course the idea of those working not getting the UBI plays directly into the hands of those arguing that UBI could cause people to work less.

So what is a Societal Dividend or a Citizen's Dividend of that kind proposed by Thomas Paine? Here is my personal take on it.

It is a basic amount transferred to anyone independent of having been able to capitalize on society’s strengths and accumulated assets, like having been able to get a good job.

It could be seen as an effort to grease the real economy by combating the natural concentrations of wealth.

It could be seen as a substitute for many those redistribution efforts that because of their complexity, is bound to attract the profiteers.

It is a well-funded transfer, no funny money, from citizens to citizens, or from natural resources inherited by an Act of God, but not depending on government favors. It could therefore be seen as an effort by citizens to become more independent of that populism and demagoguery that often lies behind all societal redistribution.

Also the way it is funded, can help to align the incentives for other societal causes, for instance if with carbon taxes, with the efforts for a better environment.

But a Societal Dividend should never ever be so large so as to risk de-capitalizing the Society or induce generalized lazyness.

@PerKurowski ©

PS. In other words the Swiss UBI referendum was set up to fail... probably by some anxious redistribution profiteers L

But be careful of not adding to the confusion

Sir it sounds so utmost reasonable what Joseph Stiglitz mentions in “Towards a better measure of well-being” September 14 that I guess no one would, in principle, argue anything different. That said, there is clearly room for a warning, especially with the recent evidence provided by the crisis, on what can happen when someone arbitrarily plays around with the numbers.

The regulators fed up with adding AAapples with Bbbananas as fruits decided to give the first a risk-weight of 20 percent and the latter one of 100 percent when calculating the capital requirements of the banks and we ended up with such a confused world that most experts, FT, included had no idea of what bank leverages they were talking about, in fact most still don’t know.

And so whatever we do to measure what we want better, and a lot of improvements are indeed needed in this area, let us see that we just do not add to that confusion the politicians love to hide behind.