• Hacker News
  • new|
  • comments|
  • show|
  • ask|
  • jobs|
  • grapefruitsoda 5 minutes

    We use capn crunch (for cerealization)

    For crypto/stock transfers we ofc use chips n dips

  • zane_shu 2 days

    [flagged]

  • rgbrgb 37 minutes

    looks cool. what is latency like? I haven't used qmd before and it looks like it runs 3 local models.

  • cyanydeez 2 days

    if this were localai, you could just figure out how to update the memore if the fill changes.

    verdverm 21 minutes

    yup, one of the reasons I built gmd to replace qmd, also that I wanted to use Typesense and incorporate llm-wiki concepts. Updating memory does depend on the nature of the change and may impact multiple memories or indexed files, and why llm-wiki concepts are needed too.

    Right now, imo, the main reason to build something like this or a harness is to understand the quirks son you can evaluate production grade implementations as the space matures. We are all still very early in the curve.

    https://github.com/verdverm/gmd