Preferences Over Benchmarks: Model Routing — Archana Kamath & Tyler Gillam, DigitalOcean

Per-request routing held quality near a single premium model (90% vs 95%) while cutting a coding session from 25 cents to 8, and the routing model and proxy are open sourced.

• mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
• eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.

• videoBrains vs Hands: How to Run AI Agents Safely in Production — Viren Baraiya
• videoWe Mapped 115 Microservices for Our Coding Agents — Kamalakannan Nandagopal, Postman
• videoTurning Agent Memory Into Skills That Work — Will Lyon, Neo4j
• videoWhy We Deleted Our MCP Server and Rebuilt It — Abhi Arya, Reducto

• videoThe State of Model Routing — NVIDIA, Cognition, OpenRouterAI Engineer
• videoLarge clusters for small models — Daniel Svonava, SuperlinkedAI Engineer
• postOpenRouter's Auto Router now follows real market spend per task typeOpenRouter

Checking sign-in…

Loading comments…