16 AI models ran produce buying for 90 days — only 3 beat a simple reorder formula

ycombinator · x · 2026-11-19

oroagents ran a 90-day experiment putting 16 AI models in charge of daily buying decisions for a produce wholesaler. Only 3 models made more money than a simple reorder heuristic.

The striking part: the models noticed their mistakes and wrote them down, but mostly kept repeating them anyway — an empirical counterpoint to the assumption that self-reflection reliably improves agent performance.

Original post →

More from coding & agent

coding & agent channel →