Latest / Logosofia no Dia a Dia
Routing AI Models: When 3 Rules Beat a Trained Router
Daniel wants to stop randomly assigning podcast episodes to AI models and start routing them intelligently. But the routing literature has a trapdoor: the famous "85% cost reduction" headline compares learned routers against always using the most expensive model — a baseline nobody with a budget actually runs. This episode walks through the router toolbox (RouteLLM's matrix factorization, RoRF's random forests, LLMRouter's 16-router harness), digs into personalization research like GMTRouter and Prompt-to-Leaderboard, and lands on an uncomfortable question: at podcast scale, does a learned…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.