Show HN: Frugon – Find which LLM calls a cheaper model could handle (local, MIT)

(github.com)

11 points | by jarodrh 2 days ago ago

2 comments

  • XUEYANZ an hour ago

    Haha. somehow i just love the naming. it just makes sense :D

  • cyanydeez an hour ago

    this would be more interesting as a local LLM anlysis; throw out all the costs, and figure out primary-subagent model architecture, and maximize token generation and prefill.

    I don't see how anyone can operationalize this information.