SOURCE-LINKED INTELLIGENCE

The average-farmer illusion in language-model simulations of agricultural decisions

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Language-model agents are increasingly used as synthetic people in surveys and social simulations, yet their apparent realism is often judged from population averages or distributional similarity. We tested what such evidence actually establishes by comparing Claude, Codex and Kimi under four prespecified prompt designs with matched farmer decisions from China and four African countries. Some configurations reproduced observed means and adoption rates. However, their person-level predictions were weak; their decisions clustered around typical values and policy-relevant extremes were largely mi

Read original source ↗ Open in workspace

recordType

paper

region

Global