My question to Grok: “Extrapolating from the past three years how long before running LLMs consumes more power than the entire Sun generates?”
Extrapolating from the growth in global AI data center power demand over the past three years (2022–2025), which serves as a proxy for LLM power consumption given that LLMs drive much of the recent AI surge, we can estimate the timeline. Data from SemiAnalysis (as cited in a RAND report) shows the following facility power demand for AI data centers:
- 2022: 1.451 GW
- 2023: 4.28 GW
- 2024: 10.6 GW
- 2025: 19.9 GW
To arrive at the extrapolation:
- Fit an exponential growth model to these data points. Using linear regression on the natural log of power vs. year (with 2022 as t=0), the slope is approximately 0.876, corresponding to an annual growth factor of e^0.876 ≈ 2.401 (i.e., power multiplies by about 2.4 each year on average).
- The Sun generates 3.826 × 10^26 watts of power, equivalent to 3.826 × 10^17 GW.
- Starting from 19.9 GW in 2025, the factor needed to exceed the Sun’s output is (3.826 × 10^17) / 19.9 ≈ 1.924 × 10^16.
- Solve for years n: 2.401^n = 1.924 × 10^16, so n = log(1.924 × 10^16) / log(2.401) ≈ 43.
Thus, it would take approximately 43 years from 2025 (i.e., by around 2068). This assumes the exponential growth rate from the past three years continues indefinitely, though in reality, physical, technological, and economic constraints would likely slow or halt such growth long before reaching solar scales.
Note that ChatGPT 5 failed to answer this question, identically worded. It used data center power consumption growth, not LLM- or AI-specific power consumption growth.
When does the exponential growth stop? We can power a human brain with an Egg McMuffin. Is the answer an analog chip with a digital interface? IEEE has a 2024 article on a Chinese design using optical computing that supposedly cuts power consumption by 99%. But if these improvements were real would the AI companies be signing 20 year leases for nuclear power?
I’m not really a Muskovite, however his brain chip implant idea could offer a solution. Instead of hastily designed, inefficient, silicon ANNs, we could use HNN (human neural nets), evolved over millions of years, directly connected to the ‘Net. Suspension in a saline-solution tank optional. Or scrap AI, go back to keyboards, video, and mice, as well as jobs, and use the surplus GPUs to play games.
This reminds me of extrapolations from the 1990’s about processor heat approaching that of the surface of the sun. Nicely done.