• RandomLegend [He/Him]@lemmy.dbzer0.com
    link
    fedilink
    arrow-up
    1
    ·
    9 hours ago

    I did make it use getTime every time but when I tell it to make a calendar entry for the “next Tuesday” for example it would be off by at least a week. Sometimes even making the entry in the past.

    I’d agree with you on it being overkill, but I wrote SK many scripts and automations involving LLM tasks that rely on a capable model to determine the flow of a task that I heavily prefer the 27ban models

    currently running gemma4 and for my use case it performs much better than qwen3.8

    • ☆ Yσɠƚԋσʂ ☆@lemmy.mlOP
      link
      fedilink
      arrow-up
      3
      ·
      9 hours ago

      I find what the model was RL trained on is really important. It looks like Qwen 3.8 is mainly focused on agentic coding, so it does really well there. But once you throw it at tasks outside the training then things start to fall apart fast.

      • RandomLegend [He/Him]@lemmy.dbzer0.com
        link
        fedilink
        English
        arrow-up
        2
        ·
        7 hours ago

        yeah the training data is super important, i just hoped that i would fare well inside the home assistant MCP setting :D

        Taking your comment about it being overkill as food for thought, i just pulled the 12b version of gemma4 and run that now. I’ll observe if it works just as good for my usecase and that way i just saved like 10GB of VRAM :D