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…
You must log in or # to comment.
Yeah. I’m not pro-AI by any stretch but internet searching powered by AI has made it MUCH easier to tinker and troubleshoot. The Linux community can be pretty awful when you’re new to Linux and trying to make things run.
Agreed. The only advice people gave me with issues on Windows as “just use Linux!” OK, I switched…here’s my hundreds of issues, suddenly no help from them. ChatGPT made it possible for me to build a server and switch to Fedora. Not how I wanted to switch, but it worked
The Linux community can be pretty awful when you’re new to Linux and trying to make things run.
My experience, particularly on Lemmy, has been the exact opposite of this. Everyone is more than happy to help, the only unhelpful replies you get usually are memes.
There’s decades of information to shift though and AI knows just enough to shift though the chaff.
Its honestly likely going to slowly become one of the few real use cases for the tech for the avg person. But from a local perspective. Needing a centralized search engine is likely going to become iffy and lower quality even if they shove ai into it.
For how to use bash, you can easily resort to local models with LMStudio. No internet search needed.
Great call out on the irony. So true. Welcome to the future.
Pretty much the same experience here. During my first week of full-time Linux I managed to break KDE Plasma with a widget IIRC and AI was able to tell me which file in .config I needed to delete to restore to default.
I wouldn’t 100% trust ai to blindly copy paste whatever it gave me into my terminal, but one of the beautiful things about Linux is the ability for you to get tech help via cli.
I have older relatives that ask me for their problems with windows and I’m actually hitting dead ends with them more and more where due to lack of vocabulary on their end and suffering through windows GUI you can’t really guide someone through a fix. That and more and more I’m becoming alienated from windows and don’t know what’s going on as much anymore.
If they had Linux I could just message them and give them terminal commands and it would be a lot easier for me to diagnose and give them a handful of terminal commands to copy paste. I’d still end up googling it but I could at least make it soooo much less painless then a face call/meeting app interaction where we both don’t know what windows did on the newest update.
Also unrelated side note windows shouldn’t allow refurbishers to sell old outdated laptops with windows 11 licenses if it breaks every update due to windows shitty hardware restrictions. Its like four times a year their laptop breaks and I forget how we fix it everytime.
I have used AI a little for Linux adaptation but I do want to caution overuse since it’ll sometimes give you really bad advice, like regarding important dependencies and such. Sometimes it cites info for a wrong distro or outdated info, so it’s not so much made up BS, just bad search results essentially.
Drop chats, use a harness. Include somewhere the procedure instructions to always look up documentation before crafting the command. Add instructions somewhere what dependencies you tolerate. Then it’s really good.
Once your tasks get larger, you need additional checks.
The problem tends to be it defaults to the old fashion way of doing thing. Since most training data is that old fashion approach
If you just remember to prompt it to keep things simple or ask it for the easier way after the first step it reduces that problem to effectively zero.
It’s no different then asking some greybeard how to do something then bitching that it’s too complicated.
They always default to “their way”
Welcome to the other side. I highly recommend checking man pages when looking up commands to start getting a feel for how to use them, also I recommend getting tealdeer (TLDR, get it?) It’s a TLDR of man pages that shows you how a package is usually used. I’ve often found that it bridges a syntax gap that is often missed in man pages.
Learning how to navigate and use man pages saved my ass when I was screwing around with my network.
thank you! I’ve been on linux for years but somehow hadn’t heard of these
Man pages are clutch, you’ve been playing on hard mode lol
yeah this explains a lot haha
I feel you. This really resonates with me cuz I have 100% the same story. I had been trying to switch to Linux from Windows pre-AI and it was good, but a really steep learning curve, with everything taking 20+ internet searches to accomplish basic tasks. The thing that finally forced my hand came at just the right time. I had lived the last 10 years of my life using OneNote as my second brain. When I saw Windows 11 and Copilot coming, I knew I had to get out fast. I bit the bullet and paid OpenAI to vibe code my Ubuntu server, which is now self-hosting over 20 different services, including my new Obsidian-based second brain. I’m 100% off Windows, 98% off corporate cloud infrastructure and onto my own self-hosted services, canceled my OpenAI account, and fully on Linux-based PCs. I have a subpar privacy-based AI service (really a fair trade) that enables me to keep it all up and running. I’m no Linux expert and I have to rely on AI a lot, but man, life has just been so much better, and I couldn’t have done it without the AI that both pushed me to it and enabled me to do it.
Man, this makes me very proud of myself. I switched to Linux 10 years ago when it was really rough to maintain. Oooofff the sleepless nights I’d spent hunting for fixes that AI now can fix in mere seconds. I use ChatGPT a ton now to fix issues and my distro has been solid ever since.
Using AI is generally a bad idea
It will bite you if your not careful
Good for you. The only two times I decided to glance at the AI overview of a search cause I wasn’t finding anything, it wasn’t useful at all. So yeah, I’m gonna save the planet a little more.
I still don’t understand where people are findign these useful AI answers. Every single time I try it seems AI is an acronym for artificial idiocy and I wouldn’t even trust it to tell me the time.
(In fact I just resently tried asking that stupid meta AI in sand-boxed Whatsapp (I still have to keep because of some stubborn examples of humanity) about the time in another time zone… It could tell my local time, in which time zone I was, what timezone I was asking about and what the difference between those zones was. Yet it could somehow not answer the question directly before being led there step by step. And then it still did the math wrong… 🤬)
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.
Nothing ironic about that. Thanks to OpenClaw and open weights AI models I started self hosting and figuring stuff out that would have made me frustrated and quit years ago. I have home assistant running on bare metal on a mini PC, a NAS with custom bios, migrated everything away from windows, Kavita for ebooks, jellyfin for music and video, nightscout to ingest my wife’s insulin pump data, and some fun custom sidecars that tie together some nifty automations like automatically diarizing and transcribing voice notes of meetings from my phone without having to pay a subscription fee - latest projects have been a local sync point for logseq, kitchenowl, and nextcloud - super productivity android app and caldav and the to-do lists in home assistant. I never would have had the time to figure all this out with my full time job and parenting but I can cut the cord to all my subscription services and I look at things a new way now. I solve my own problems now when before I would just look for a way to buy a solution. I bought bunk beds for the kids but the bottom bunk didn’t come with slats and I couldn’t find the right size so I went to home Depot and built my own with instructions from my ops agent. I had a fun idea to make an e-ink display sign for my office door that shows what town I’m currently in and what my current MS outlook calendar block is and when it’s over. I never played with Arduino before and now I’m hooked. It gets me over that first execution hump. Sure I break stuff and have to figure out how to put it back together again but that’s part of the fun. I finally found a way to learn stuff that works for me, you know, comes naturally. It’s like I’ve been waiting my whole life for this ever since growing up seeing people using computers via natural language in Star Trek. It extends to my work. The data I need is gated behind ticketing systems of business intelligence professionals who don’t have the time or inclination to give me what I need so hey looks like copilot basic is great and m-code, guess I don’t need BI analysts after all. Sucks for them.
I have Bazzite and couldn’t be happier. Hate that I didn’t switch sooner lol
Took me a week or two to understand the basics. Really isn’t much, tbh.
Bazzite would honestly be my newbie recommendation nowadays. The only immutable distro I didn’t have much issues with.
Hey man, welcome! Enjoy the freedom.
Yeah I recently used duckai to trouble shoot a speaker issue on my laptop running guix and was able to solve the issue. It gave me commands to run and pasted the output back to it to get the next step. I don’t know how long it would have taken me to figure it out if I hadn’t used it.
Was about to say now you should look into self-hosting AI, but you’re already on it. 😄
