Why is there no analog to napster/bittorent/bitcoin with LLMs?

Is there a technical reason that there is not some kind of open source LLM that we can all install on our local host which contributes computing power to answering prompts, and rewards those who contribute computing power by allowing them to enter more prompts?

Obviously, there must be a technical reason which prevents distributed LLMs or else it would have already been created by now.

    • JackRumford@alien.topB
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      It’s terribly inefficient in many ways. Data centers with best GPUs are the most efficient hardware and energy wise. They are often built in places with access to cheap/green energy and subsidies. Also for research/development cash is cheap, so there’s little incentive to play with some decentralized stuff which adds a level of technical abstraction + needing a community. Opportunity cost wayyy outweighs running this in a data center for the vast majority of use cases.

      • Prudent-Artichoke-19@alien.topB
        link
        fedilink
        English
        arrow-up
        1
        ·
        1 year ago

        Distributed inference IS indeed slower BUT its definitely not too slow for production use. I’ve used it and it’s still faster than GPT4 with the proper cluster.

      • ColorlessCrowfeet@alien.topB
        link
        fedilink
        English
        arrow-up
        1
        ·
        1 year ago

        some niche community uses where the budget is none and people will just distribute the electricity/GPU cost

        Aren’t there a lot of people who don’t run their GPUs 24/7? That would put the marginal cost of equipment at zero, and electricity costs what, something around $1/W-yr?

    • ExTrainMe@alien.topB
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      Bad marketing. I only seen it recently.

      Plus you get one model no loras (unless something changed recently).

      • lordpuddingcup@alien.topB
        link
        fedilink
        English
        arrow-up
        1
        ·
        1 year ago

        It runs a few models and if others decide to run models it runs with em just try the chat we app or the dashboard to see what’s currently running issue is not enough people donating compute

    • ortegaalfredo@alien.topB
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      Because LLama2-70B is similar or better in most metrics, and it small enough to not need distributed inference.