Shouting into the void
Shouting into the void
Copilot on teams Android keeps turning itself on. I looked through docs & found I was doing things correctly. So I opened it up out of frustration.
I know it means nothing, but I had to say (type?) it out loud. I have really come to hate Windows since 11 was forced on us at work.
Ironically, it'll just ape back what you want to hear by being sympathetic towards my concerns, addressing nothing.
Don't know who's more pathetic, the chatbot or me đ„Č
Unironically AI is pretty good at helping linux noobs.
It figured out the issue with my front panel 3.5 audio jack not working when I plugged in headphones in my Mint desktop pc.
AI is decent at combing through all that documentation and forum posts and getting to a sensible approach.
Even people who've been at it for years. I am skeptical of the AI hype bubble as much as anyone here, but it's been very useful for fixing things in Linux. Just in the past years it helped me (among others):
I doubt anyone here hates AI other than for the big companies pushing it constantly. ML and language models have been a thing since the last decade but we only hate them now cause of how desperate the corpos are about it and oh the data scraping too but that's expected.
For me it helped with:
Albeit I could do these myself by looking at docs but it's not worth the time. Now it just works instead of "maintaining my arch setup".
It's a great tool for the right tasks. What's annoying is that it's marketed as being a great tool for tasks it can barely do.
It has really sped up the process of writing things in languages I'm unfamiliar with. All the stupid little mistakes it will find much faster than trying to google them. As long as you're critical of the answers I also found it pretty good at explaining how to do things. It will often get some details wrong but as long as you have general programming ability and access to documentation you can usually figure those out somewhat easily.
I felt the same way regarding AI. I always felt like it was too unreliable, and while you obviously shouldn't trust it blindly, it has been doing a pretty good job explaining things to me. I've been using a local model with ollama, i think it's called qwen2.5 coder or something, and it has been helpfull explaining some NixOS stuff to me, where i couldn't find it myself (cause NixOS documentation is all over the place). I also use it for explaining some bash stuff to me sometimes when i'm writing a script. Usually i don't just care about the answer but i also want to learn why something works if it isn't clear to me, and so far it also has done a good job explaining how it works when i ask it a follow up question.
Indeed, it helped me a lot when I didn't know when to start. Searching on the web can yield very old results, and you simply don't know what is outdated and what's not.
Ultimately thatâs what most agenic âAIâ is doing these days. Literally just hitting the top few results of Google or Bing and plopping it into the text context.
In other words, if web search is returning very bad results then the LLM will too, if that web search option is enabled. You have to be careful.
True, there's endless data of how to use linux, just not organized in a way new users would want, and LLM can help reword them that way.
Honestly it's really helped me with spreadsheet formulae and more complex regex search and replace terms. And it's so pleasant and patient about all of it. So many of those spaces are DEEPLY toxic to noobs and when I paste the error back to it it's like oh it looks like the regex you're using doesn't support that! Let's try...
it helped me to remove kde, gnome, unity environment when i installed them all, just for testing and after its advices os stopped to launch