Perhaps, but even as someone who uses LLMs I don’t like them being allowed to run amok on my machine. I don’t trust them.

They’re also a crutch that shouldn’t be necessary for tasks so commonplace and simple as adding a network interface.

They're the next step in UI for computers. Telling codex to add a network interface is easier than a GUI which is easier than a terminal program which is easier than manually editing a config file. None of those are a crutch. They are increasingly useful tools.

I'm curious how you get codex to do anything when you don't have a working network?

Frankly I find terminal applications considerably easier than most GUIs for most purposes, but I agree that natural language is generally an easier interface layer than either, and that an interface layer to the functions of a computer in general seems to be LLMs' destiny as a technology

I’ve been using command lines for over 25 years now and the thing that rubs me the wrong way about them is that nobody can agree on conventions with regard to how a CLI utility should work, which limits the amount of knowledge that’s transferable between them. Each effectively has to be learned individually which gets old fast.

I mean I think there's about as much convention and overlap as there seems to be for GUIs at least, and with much more discoverable clarification to boot

The issue with manpages is that they need to be pulled up independent of the program, they’re overly verbose, and often don’t include practical usage examples or if they do, bury them under miles of flags I’ll never use.

Sometimes CLI utility help commands fill the gap, but often they’re too spartan or don’t even exist.

In no way is a stochastic system that has zero ability to understand anything "the next step in UI". That's a recipe for disaster and even greater frustration.

fwiw, I haven't had this issue on Fedora on GNOME. Ubuntu/Debian have always been a pain for me, but Fedora has been great.

I see this as IBM/RedHat is a better steward/maintainer than other projects.

Yeah, the install was originally a GNOME one, but I added KDE after because it handles some things better. For example, GNOME tray item extensions will crash some tray-item-spawning programs running under WINE/Proton, which isn’t a problem under KDE.

I think GNOME gets some things more correct (it has a much better grip on design for instance), but I don’t agree with its strictly-minimalist philosophy that makes the macOS desktop look full-featured in comparison.

XFCE and Cinnamon are probably the closest to striking the right balance as far as I’m concerned (and are boring in a good way) but sadly they don’t get a fraction of the development resources that the big guys get.

But what if you switched to Linux to avoid having to use AI?

This is a genuinely incomprehensible take to me. You damn well better learn to use the tool, or you will be obviated by those that do (at least, as long as your job depends on it). Linux or no Linux.

Also, you are now using the tool that is best suited to "use AI". You will hit those rough patches, and it's good to know how to work through them. But sometimes there is just no time for such bullshit, and you now have a tool at your disposal that can just sweep these problems away. It is not without its downsides, but this is a clear "dumping the baby out with the bathwater" scenario.

Your post has the same energy of the old codgers who won't "learn computers" and impotently swim against the tide. It's fine if you want to do that (you do you), but you are swimming in the wrong direction IMO.

(If you don't work in tech, the magnitude of my recommendations would soften towards you in particular, but the velocity would remain the same.)

> "You damn well better learn to use the tool, or you will be obviated by those that do"

These vaguely threatening LLM promoter comments are almost like cultish "believe in $DEITY or you'll go to $PERDITION" preaching. It's just freaky.

I'm genuinely wondering what goes through their minds when they post this.

What goes through my mind is some combination of "Holy shit, this technology is incredible." and "Holy shit, this technology is retarded." and "If I don't stay on top of this shit, I'm going to lose my fucking job.".

On the other side of the fence, the aversion to using the tool seems equally cultish, like not working on the Sabbath.

If it makes you feel any better, I don't think this tech is "AGI" and that it seems to have some fundamental limitations that make it perform worse than a 3-year-old can perform on many tasks. But it's foolish to avoid something that could cause you to be replaced by some idiot that can do untold damage with just a few prompts, all because you didn't (assuming you work in tech) want to stay on top of the tools available to you.

This is actually a great point. I've taken some esoteric issue with my Debian Linux install and gotten exactly the needed fix. Especially when the error is extremely misleading ("/dev/root: Can't open blockdev" was that I forgot to install the actual kernel image itself...) Distros could ship open-weight LLMs that sure, might take a minute to come up with the answer, but they could be preset with the privileges to actually execute the solution.

However, those only exist because real people talk about problems on forums. If we fully integrate an LLM into the desktop and nobody discusses the issues they run into anymore, will LLMs continue to be able to solve the problems?

Agents aren't a panacea: The sharp edges shouldn't be there to begin with.

IE, the ethernet port shouldn't just disappear from the OS; it doesn't matter that now it's a little easier to fix the problem.

Should is a four-letter word, my friend. The sharp edges are there whether you want them to be or not.

If you don't have ethernet the agent isn't going to get a lot done

I had a local model help me to revert a bad kernel last year. I think it was Qwen-3-Coder, and I had no GUI and no network.

Yes but we should not need an AI chatbot to solve problems which should be trivial for us to solve ourselves. Linux should just not have these issues, period.

OK, good luck with that attitude. Until the fabled Year of the Linux Desktop finally arrives, you can use the available technology to solve the problem in a practical manner.

> "These sharp edges are a lot less annoying with agents to help solve the problem."

That applies just as much to Windows and MacOS as it does to Linux.

-1 because why would someone who is annoyed with AI features in macOS migrate to Linux, where they would then be “forced” (in order to not waste their own time) to use agents to fix breaking OS-level functionality..

I've been a Linux user since at least 2013, I don't think I've ever been forced to use agents to fix anything?