I’ve had several occasions in my life where I’ve tried to switch to Linux only to run into hardware incompatibilities that would have taken me man-months to solve. Thanks to GPT my primary personal PC, home media and project server is now running Linux and fully functional. I’ve got Jellyfin, NextCloud, Navidrome and Joplin all happy. I’ve also been able to wipe an obsolete MacOS off my 2017-era Macbook Pro and it’s happily running Mint.
There’s a deep irony in Windows being enshittified by AI, while the same AI makes Linux about a billion times more usable. 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…
I use LMMs daily, but I never even had the idea to use the stupid AI button in WhatsApp. And I had a buddy mentioning last week how hilarious bad the google search AI is.
You’re here in selfhosted. Do a minimum of research, fire up opencode and create an agents.md with something like „Never guess, if you don’t know something do an online search first!“. This will get rid of 99 percent of hallucinations. Then just use one of the free models opencode provides.
No, thanks. My “research” is testing AI from time to time. And it is indeed artificial idiocy most of the time.
And when basically all answers I ever get from AI proponents is either “Those local models are just not powerful enough so it’s on you that you don’t get sane results” or “Those models just need some tuning so it’s on you for not running a local one you can optimise for your usecase” you start to realize there might be an entirely different problem…
I get perfectly good search results by avoiding AI, so there is really no need for me to tune anything but the settings on my searxng instance…
Gotcha! You do you.