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.
More from coding & agent
- Lunch-break demo: ChatGPT + CapCut plugin turns camera roll photos into a GTA 6-style intro video — alifcoder · 2026-11-19
- Tensor launches as an ADE for doing real work with AI, live on Mac, Windows and web — saheedniyi_02 · 2026-11-19
- Ultrafast mode review: great for math proofs, not recommended for coding — gnukeith · 2026-11-19
- Speed up CI for AI-written code: caching, faster runners, test sharding — rseroter · 2026-11-19
- Agentcard raises $8M to let agents buy from 5,000+ stores via Stripe Link — jeff_weinstein · 2026-11-19
- hstack open-sources one-command self-hosting for the Hermes agent — TheMoonMidas · 2026-11-19