To help you understand the trends surrounding AI and other new technologies and what we expect to happen in the future, our highly experienced Kiplinger Letter team will keep you abreast of the latest developments and forecasts. (Get a free issue of The Kiplinger Letter or subscribe.) You'll get all the latest news first by subscribing, but we will publish many (but not all) of the forecasts a few days afterward online. Here’s the latest…
It’s not easy to make sense of the artificial intelligence arms race. Astronomical sums are being spent on building AI data centers, with circular financing deals stoking bubble fears. It’s not yet clear how AI big spenders will make a return on their massive investment.
At the same time, demand for AI continues to outstrip supply. AI revenue is starting to pour in, as adoption by consumers and businesses rises swiftly. Meanwhile, Big Tech companies have mountains of cash and profitable business lines.
What gives? Generative AI is a true breakthrough, but risks related to overspending are on the rise. Meanwhile, a very large portion of recent U.S. economic growth and stock market gains comes from this AI spending.
The major worry is that today’s vast spending on AI data centers is nowhere near economically sustainable. To meet the expected demand for data centers, it will require $500 billion in annual global capex spending on new data centers, according to an analysis by Bain & Company, the management consulting giant.
AI companies will have to find $2 trillion in new yearly revenue by 2030 to arrive at an economically sustainable model. There could be an $800 billion shortfall if firms don’t find new and better ways to boost sales. Don’t mistake Bain as pessimistic, though, says David Crawford, a partner at Bain and chairman of its global Technology, Media & Telecommunications practice.
“We actually believe those things will happen,” Crawford says of finding new revenue. “We're extremely bullish on this trend.” He calls generative AI more significant than anything he’s seen working at Bain for 25 years. “We’re in for an extraordinary period of innovation.”
Of course, there are plenty of others who see the growing chasm between AI spending and revenue as the telltale sign of a bubble forming. That includes many people who agree that AI is a breakthrough technology with huge potential but worry that the hype is outpacing reality.
To drill down on the looming economic challenges, look no further than OpenAI, where sales are surging, but costs are rising faster. OpenAI reportedly will see sales of roughly $10 billion in 2025, a huge feat, since ChatGPT launched in 2022. It aims to make $100 billion by 2029, but it has plans to spend hundreds of billions over the next few years.
The start-up has a complex web of deals that includes a five-year contract to buy $300 billion in computing power from Oracle, and a deal for Nvidia to invest $100 billion in OpenAI. Nvidia’s financing the purchase of its own chips, along with other circular financing deals, has stoked bubble fears. OpenAI also has tie-ups with AMD and Broadcom for chips. Amid the massive future outlays, OpenAI has a private valuation of $500 billion, more than Samsung, Johnson & Johnson or Costco. And Alphabet, Amazon, Meta, Microsoft and others keep spending heavily in an arms race that requires ever more computing power to build leading AI tech.
Consider a few of the major risks we see:
