I’ve tried coding and every one I’ve tried fails unless really, really basic small functions like what you learn as a newbie compared to say 4o mini that can spit out more sensible stuff that works.

I’ve tried explanations and they just regurgitate sentences that can be irrelevant, wrong, or get stuck in a loop.

So. what can I actually use a small LLM for? Which ones? I ask because I have an old laptop and the GPU can’t really handle anything above 4B in a timely manner. 8B is about 1 t/s!

  • catty@lemmy.worldOPEnglish
    2·
    13 小时前

    Doesn’t Twitch own all data that is written and their TOS will state something like you can’t store data yourself locally.

    • CrayonDevourer@lemmy.worldEnglish
      11·
      6 小时前

      I’m not storing their data. I’m feeding it to an LLM which infers things and storing that data.

        • CrayonDevourer@lemmy.worldEnglish
          1·
          25 分钟前

          There’s not actually that much code. It’s like 8 lines for an AI ‘agent’, and maybe another 16 lines for ‘tools’, and I’m using Streamlink for grabbing the audio stream, and pulseaudio has a ‘monitor’ device you can use to listen to what’s playing on the speakers. Throw it on a very minimal linux distro on a VM, and that’s it.

          I don’t do ‘vibe coding’, but that IS where I got the idea from. People who are doing ‘vibe coding’ nowadays aren’t just plugging things into a generic AI, they’re spinning up ‘agents’ and making tools via MCP and then those agents are tasked with specific things, and use the tools to directly write to files, search the internet, read documents, etc