Yeah, they’ve done this on this one particular site that I like to read, one old (hilarious) celebrity blogger who made a new home on [redacted]. [redacted] is pure shit. I dunno exactly what they’re doing but the ads they serve up are largely local rather than third party - and they’re served up so aggressively the site is all but unreadable on my phone. So ads are crazy in-your-face despite having adblock on the phone itself and a Pi-Hole! Just to keep reading the guy I like I had to set up a shortcut that loads it in reader view to bypass all the bullshit and fuck knows how long that will last before they somehow figure out how to block reader view.

Edit: I probably shouldn’t be giving them ideas, lol.

Yes, well, my use for Ollama is solely as a plugin for Home Assistant. But you can wrap llama.cpp with whatever you want or use the half-dozen semi-popular competitors! My point is just that there are no tools that are exclusive to Windows, they’re all on Linux.

Now I have a leftover Windows micro-PC running a local LLM model, so I can be less dependent on GPT, as long as time isn’t a factor…

Might as well go all in. LM Studio, Stability Matrix, Comfy UI, Ollama - everything’s native on Linux.