Skip Navigation
InitialsDiceBearhttps://github.com/dicebear/dicebearhttps://creativecommons.org/publicdomain/zero/1.0/„Initials” (https://github.com/dicebear/dicebear) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)XC
xchino @programming.dev
Posts 0
Comments 17
Want to use some form of ChatGPT but don't want to use the cloud? Run ChatGPT4all locally. It has an API server in the options menus too.
  • I don't think you understand what this is. It is a local model, it runs locally. It provides an API which you can then use in the same manner as you would the ChatGPT API. I'm not super familiar with GPT4all since llama.cpp/kobold.cpp are pretty much the standard in local inferrence, but for example llama-cpp-python provides an OpenAI compatible API.

  • Which hardware do you use and why?
  • I'm using a SteamDeck as my desktop environment while docked, I think it's the only "Linux first" machine I've ever bought. All of my other systems I either built from scratch, a mish-mash of secondhand parts and purchased upgrades, or have been provided with through work.

  • Steam Deck is at sale: 10% to 20% off
  • It's cost:performance ratio at the time was crazy, it is widely assumed Valve is selling it as a loss leader or at mfr cost. The only thing they've said is that it's pricing was "painful". It's hardware isn't that niche, it's just a PC in a handheld form factor.