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…
Meta’s recent blockbuster deal with AMD highlighted a key number: Six gigawatts. The dollar figure (up to an estimated $100 billion) and the number of chips (at least a few million) were less important than the staggering amount of electricity required to run the incredibly power-hungry AI chips.
Meta’s not alone. Other tech giants boast about gigawatts as a sign of AI leadership. Advanced AI tech is dependent on large data centers that are huge energy hogs. But why, and will that always be the case?
The underlying reason has to do with a foundational rule of thumb for top AI models. “One of the most reliable and enduring ways you can improve the model is by scaling,” noted David Crawford, a partner at Bain, in a presentation last year. “If you're a competitor in the space and you want to remain in the lead, you invest.”
Leading-edge AI improves by training large language models, the brains behind tools such as ChatGPT, on mountains of data. Three factors need to be scaled up:
