Does thinking about how to offload matter? | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

kovek 3 months ago | parent | context | favorite | on: We decreased our LLM costs with Opus

Does thinking about how to offload matter?

locknitpicker 3 months ago [–]

A discussion on how to avoid paying the price of running an expensive model is not about the expensive model. You can triage things running a cheap model with Ollama. Heck, throw in gpt4.1 which is free.

kovek 3 months ago | [–]

I don’t think triaging is necessarily an easy task

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact