> "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.

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.

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

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.

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.

-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..