Bending Spoons runs 99% of AI traffic on self-hosted open models, thanks to evals

alex_verem · x · 2026-09-25

Bending Spoons runs 99% of its AI traffic on self-hosted open models. The author notes most CTOs default to frontier models like Claude Opus for agents but can't prove a cheaper model would work. The fix: build an eval set of production cases with expert-signed correct answers, run every candidate model against it, then treat the model as a shoppable line item — cheap models for routine work, frontier models only for hard cases.

Original post →

More from coding & agent

coding & agent channel →