Stripe's model-run shop bench: 5 of 7 working stores built by Claude
bcherny · x · 2026-09-16
Stripe launched UnseriousT-ShirtShopBench, asking models to build and run online t-shirt stores. Every model chose to integrate Stripe on its own.
Of the 7 functional shops, 5 were built by Claude-family models, and the 2 finalists picked for production were built by Fable and Opus. The author (a Stripe engineer launching the Breaking Change Substack) concludes models still have a way to go before running full e-commerce operations autonomously.
More from coding & agent
- Sakana Marlin adds Interactive Reading and PowerPoint export for deep research reports — SakanaAILabs · 2026-09-16
- Andy Matuschak demos programmable highlighters that trigger AI actions on annotations — andy_matuschak · 2026-09-16
- Dev shares trick: dedicated subagent filters SSH output to protect agent context — SaleemUsama · 2026-09-16
- Raw Markdown Folders Kill Your Agent's Context Window: Lessons From 100k Installs — Alone-Biscotti6145 · 2026-09-16
- Nous Research Used 1,393 Subagents to Cut a 1M-Line Codebase by 34.4% in 19 Hours — NousResearch · 2026-09-16
- One AI system for 8 months: don't chase new tools, absorb them incrementally — evielync · 2026-09-16