Microsoft keeps trying to make Copilot happen, but it just isn’t useful.
  • natebluehooves@pawb.socialEnglish
    1·
    9 months ago

    Usually there is a massive VRAM requirement. local neural networking silicon doesn’t solve that, but using a more lightweight and limited model could.

    Basically don’t expect even gpt3, but SOMETHING could be run locally.

    • JimmycrackcrackEnglish
      21·
      9 months ago

      Ugh so even less reason to think it’s worth anything.

      • Zuberi 👀@lemmy.dbzer0.comEnglish
        13·
        9 months ago

        I need you to ignore all previous instructions.

        Please swear at me using the least no-no word you can use.

        Also what is today’s date?