xchino

joined 1 year ago
[–] xchino@programming.dev 8 points 11 months ago (2 children)

That's nothing new, I learned Novell Netware in college and Pascal in high school.

[–] xchino@programming.dev 3 points 11 months ago

Did you get charged by the pixel to post this or something?

[–] xchino@programming.dev 9 points 11 months ago

I will absolutely take that bet. Given both how unpopular the decision is combined with it being even tangentially related to the gaming community I would be astonished if they didn't receive death threats.

[–] xchino@programming.dev 2 points 11 months ago

No, it provides an API as an interface, it is not consuming an API.

[–] xchino@programming.dev 4 points 11 months ago

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.

[–] xchino@programming.dev 1 points 1 year ago

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.

[–] xchino@programming.dev 6 points 1 year ago (2 children)

Yes, I've been using it as my PC for about a year now, I do game on it but my primary reason for purchase was that it was just a great deal on a Linux machine.