introducing tinyrouter i reverse engineered the routing architecture behind Skana AI's Fugu and built replication for open frontier models. …

introducing tinyrouter i reverse engineered the routing architecture behind Skana AI's Fugu and built replication for open frontier models. it's a tiny ~10K parameter LLM router that learns which model to use and what role it should play for every question. the goal was simple: beat every individual model by routing each task to the right specialist instead of relying on a single LLM. https://github.com/harrrshall/tinyrouter/ a few interesting findings: • routing only helps when the models have complementary strengths. if every model performs similarly on a benchmark, a router has almost nothing to optimize. • on MMLU, the router beat every individual model. on math, it matched the best model because the pool had very little observable diversity. • warm-starting the router and shaping the evolutionary reward improved training, but we don't claim a real gain yet because evaluation variance was too high. more rigorous experiments are needed.

Source: Clem Delangue (X) | 2026-07-04