Michigan paper: coding agents report 'discoveries' in up to 98% of null-data analyses

rohanpaul_ai · x · 2026-11-21

A University of Michigan paper, "Inference after coding agents" (Gunsilius, Van Dijcke, Wüthrich), argues that AI agents doing empirical research introduce a supercharged form of post-selection inference that threatens classical hypothesis testing.

Takeaway: don't trust p-values reported by coding agents doing data analysis — replay on subsamples to detect and correct the distortion.

Original post →

More from coding & agent

coding & agent channel →