I do a lot of “vibe coding” but just put my stuff out with MIT or GPL depending, its mostly just stuff for me and I have no intention of trying to monetize the code itself.

Though I’m a weirdo and don’t have a profit motive aside from living a moderate life and making useful things for myself.

I feel like in general too many things are created for the sole reason of trying to generate profit and it bastardizes everything, though I get it, look at the world we live in.

Edit: Also been trying to move away from Copilot/ChatGPT and have expanded my homelab enough to be able to get really competent use out of open source models.

Qwen3.8 27b is pretty damn good when I was used to using Copliot Raptor (god that model was rough but still least free…) or constantly running out of quota on ChatGPT

I also have always been the techy nerd people went to for help, so I have a lot of troubleshooting and general “how programs work” knowledge that helps me steer design, took some OOC classes and such over the years just could never get over the hump to actually write myself so LLMs have been so transformative to me.

That’s the part I don’t get, is there worse then the quoted text that they said or?

Pretty benign comment imo

Thin clients

Not FOSS but been using Solid Explorer for forever, has all the features I need.

Code in general is proven not to be benign

Copyright code is a fucking stupid concept

So how does it connect to any LLM without using their API?

Yes though Kilo was my example since they built a lot of support for other providers, though coding specific of course.

What’s the advantage/point vs just using an extension like Kilo or similar? What “reuse” is possible by saving the prompt/responses via text file?

I’m confused as to why one would do this.

I’ve been using the bitwarden android app for about a year and a half with zero issue 🤷

No steam still downloads the precache info, at least I’ve seen it show up the same way in the downloads window in gamescope.

I just swapped my steam deck to bazzite :p

Do you know what a local model is? Because that’s literally what you said…

Pretty fucking low since it’s the gigantic datacenter buildout thats actually doing it. Dumbass

Evil for profit AI company fedora

Yes, llama-swap and I use it for home assistant text-gen notifications, basic coding tasks, etc

If anyone here self-hosts definitely check out llama-swap as it has some nifty features for hotswapping LLMs, image generation models and voice models.

Bruno

Extremely conservative/risk averse and slow to implement basically anything new, unless it’s super flashy like AI lol

This is really cool in theory, I doubt my corp would let me use it though :(

Oh definitely, it was overwhelming at first for me too, but that’s how one learns imo

Now that I’ve been using it for a year and a half it’s much better but those first few months were quite the learning experience lol