all 15 comments

sorted by: hot top controversial new old
[–] 2 points 5 hours ago (1 child)

I just want to rent them for my life. I love being a modern serf.

Seriously though, go local or go home. Never paid a single cent for renting a LLM. Any PC that can play video games is fully sufficient to generate text with LLMs.

  • source
  • hideshow 1 child comment
  • [–] 1 point 1 hour ago

    Any PC that can play video games is fully sufficient to generate text with LLMs.

    I am all for local inference, but that is a super ignorant and uninformed take. I hope you are not running around complaining about the hallucinations and bad quality of LLM generated stuff, if your baseline are models that fit in 8 GB of VRAM or something. And no, 16 or even 24 GB wouldn’t bring you close to what the big models can do.

  • source
  • parent
  • [–] 14 points 16 hours ago (5 children)

    Honestly whoever designs how to plumb all the local/edge inference together for a proof of work “token” to exchange for use of that inference or sale is gonna be the crypto that’s actually useful lmfao

    I understand why big ai wants to control the compute but that’s gotta be on the foss radar right?

  • source
  • hideshow 5 child comments
  • [–] 2 points 3 hours ago (1 child)

    Is it cheap for peers on the network to verify that the work has been performed?

  • source
  • parent
  • hideshow 1 child comment
  • [–] 1 point 2 hours ago

    Kinda the opposite. Openrouter exist and you can host any model, but even within the model there are bunch of params that affect how good is the output you get.

    And while most hosts list these upfront, & you just gotta be smart enough to request with specific requirements, I've heard there are still good reasons to just stick to a list of trusted hosts sometimes, I don't really remember what was the issue, quantinizastion level that they aren't honest upfront maybe.

  • source
  • parent
  • [–] 8 points 11 hours ago (2 children)

    Mesh LLM? SETI but for tokens. I can half see it.

    Most of the value in openai now isn't the model, it's the prompts and process. That's where FOSS could shine.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 10 points 16 hours ago (4 children)
  • [–] [S] 36 points 15 hours ago* (3 children)

    Out of the loop?

    That quote is from the CEO of OpenAI. He basically said the AI chips are too scarce for people to use at home. The reason they are scarce at all is because AI companies are hoarding them using investor money.

  • source
  • parent
  • hideshow 3 child comments
  • [+] 1 point 11 hours ago* (last edited 2 hours ago)
    [–] 1 point 13 hours ago

    It is not, provided that you rent your local compute capacity out when you are not using it.

  • source