Hacker News Reader

For model routers, do they have to retrain the routing model every time a new LLM is released?

I really like the idea behind OpenRouter's new auto-beta -- classify by task type, and then just follow what the market is using based on the last 7d. https://openrouter.ai/docs/guides/routing/routers/auto-route...

Maybe a continuous evaluation process, why is there anything to train?