The research behind synthetic users: what the studies show, where they disagree, and how much weight a Cast interview can carry.
Researchers have re-run famous human experiments with AI participants. Most results come back. The ones that don’t are just as instructive.
August 8, 2026 · 7 min read
A Stanford-led team tested GPT-4 against 70 real experiments with 119,330 participants. The answer, published in Nature, is a careful yes.
July 26, 2026 · 7 min read
Stanford researchers built AI agents of real people from interviews. The agents answered like their humans almost as reliably as the humans answered like themselves.
July 13, 2026 · 7 min read
An MIT-trained economist rebuilt classic behavioral experiments with AI participants. The results were familiar, and the surprises were useful.
May 21, 2026 · 8 min read
Twenty-five AI characters, one idea seeded in one head, and a party that half the town remembered to attend. Why this playful paper matters for research.
April 25, 2026 · 7 min read
In 2023 a team at Brigham Young asked a language model to vote. What came back changed how social scientists think about AI respondents.
April 12, 2026 · 8 min read
