The artificial intelligence (AI) age is upon us and, as is the case with every disruptive technology, it is accompanied by doomsayers who fear it will irreparably harm society. "For Some Recent Graduates, the A.I. Job Apocalypse May Already Be Here," The New York Times recently warned in a recent headline. "There Is Now Clearer Evidence AI Is Wrecking Young Americans' Job Prospects," read another headline in The Wall Street Journal. While these pessimistic headlines evoke a Philip K. Dick sci-fi dystopia, emerging data paint a brighter, more nuanced picture.
The Federal Reserve Bank of St. Louis published a report on Tuesday that explores how AI adoption is associated with unemployment, which is up to 4.2 percent according to the Bureau of Labor Statistics' dismal July jobs report.
The authors use two metrics to offer a tentative, noncausal answer: theoretical AI exposure, which measures whether large language models (LLMs) "can reduce task completion time by at least 50%" in various occupations; and actual AI adoption, based on responses to the Real-Time Population Survey created by Adam Blandin, professor of economics at Vanderbilt University, and Alexander Bick, an economic policy advisor at the St. Louis Federal Reserve. According to the study, computational and mathematical occupations had the most exposure (roughly 80 percent), the highest rate of AI adoption (45 percent), and the largest increase in their unemployment rate between 2022 and 2025 (by 1.2 percentage points). Personal services, meanwhile, had the least exposure (about 15 percent), the lowest rate of AI adoption (less than 10 percent), and the smallest increase in its unemployment rate between 2022 and 2025 (by less than 0.1 percentage points).
