• BB84@mander.xyz
    link
    fedilink
    English
    arrow-up
    59
    arrow-down
    1
    ·
    13 days ago

    Stop depending on these proprietary LLMs. Go to !localllama@sh.itjust.works.

    There are open-source LLMs you can run on your own computer if you have a powerful GPU. Models like OLMo and Falcon are made by true non-profits and universities, and they reach GPT-3.5 level of capability.

    There are also open-weight models that you can run locally and fine-tune to your liking (although these don’t have open-source training data or code). The best of these (Alibaba’s Qwen, Meta’s llama, Mistral, Deepseek, etc.) match and sometimes exceed GPT 4o capabilities.

    • ArchRecord@lemm.ee
      link
      fedilink
      English
      arrow-up
      12
      arrow-down
      1
      ·
      13 days ago

      And there are also free, online hosted instances of those same LLMs in a (relatively speaking) privacy-protecting format from DuckDuckGo, for anyone who doesn’t have a powerful GPU :)

      • BB84@mander.xyz
        link
        fedilink
        English
        arrow-up
        9
        ·
        13 days ago

        Interesting. So they mix the requests between all DDG users before sending them to “underlying model providers”. The providers like OAI and Anthropic will likely log the requests, but mixing is still a big step forward. My question is what do they do with the open-weight models? Do they also use some external inference provider that may log the requests? Or does DDG control the inference process?

        • ArchRecord@lemm.ee
          link
          fedilink
          English
          arrow-up
          6
          arrow-down
          1
          ·
          13 days ago

          All requests are proxied through DuckDuckGo, and all personalized user metadata is removed. (e.g. IPs, any sort of user/session ID, etc)

          They have direct agreements to not train on or store user data, (the training part is specifically relevant to OpenAI & Anthropic) with a requirement they delete all information once no longer necessary (specifically for providing responses) within 30 days.

          For the Llama & Mixtral models, they host them on together.ai (an LLM-focused cloud platform) but that has the same data privacy requirements as OpenAI and Anthropic.

          Recent chats that are saved for later are stored locally (instead of on their servers) and after 30 conversations, the last chat before that is automatically purged from your device.

          Obviously there’s less technical privacy guarantees than a local model, but for when it’s not practical or possible, I’ve found it’s a good option.

          • BB84@mander.xyz
            link
            fedilink
            English
            arrow-up
            2
            ·
            12 days ago

            Okay that sounds like the best one could get without self-hosting. Shame they don’t have the latest open-weight models, but I’ll try it out nonetheless.

    • Kbobabob@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      13 days ago

      There are open-source LLMs you can run on your own computer if you have a powerful GPU.

      What defines powerful? What if you don’t have the necessary hardware?