LocalLLaMA

3785 readers

3 users here now

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

Rules:

Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.

Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

founded 2 years ago

MODERATORS

pax@sh.itjust.works

noneabove1182@sh.itjust.works

Smokeydope@lemmy.world

MonsterBug@sh.itjust.works

Best LLMs for PC/Tech Troubleshooting? (lemmy.ml)

submitted 3 weeks ago* (last edited 3 weeks ago) by FrankLaskey@lemmy.ml to c/localllama@sh.itjust.works

22 comments fedilink hide all child comments

I find myself really appreciating what LLMs can do when it comes to help with software and tech support. I am a pretty adept PC power user who is not a programmer and (until recently) has only had a modest amount of experience with GNU/Linux. However, I have started to get into self-hosting my own FOSS apps and servers (started with OpenWebUI, now Jellyfin/Sonarr via Docker compose etc). I’m also reading a book about the Linux command line and trying to decipher the wold of black magic that is networking etc myself.

I have found that LLMs can really help with comprehension and troubleshooting. That said, lately I am struggling to get good troubleshooting advice out of my LLMs. Specifically, for troubleshooting docker container setups and networking issues.

I had been using Qwen3 Coder 480b, but tried out Claude Sonnet 4 recently and both have let me down a bit. They don’t seem to think systematically when offering troubleshooting tips (Qwen at least). I was hoping Claude would be better since it is an order of magnitude more expensive on OpenRouter, but so far it has not seemed so.

So, what LLM do you use for this type of work? Any other tips for using models as a resource for troubleshooting? I have been providing access to full logs etc and being as detailed as possible and still struggling to get good advice lately. I’m not talking full vibe coding here but just trying to figure out why my docker container is throwing errors etc. Thanks!

Note: I did search and found a somewhat similar post from 6 months ago or so but it wasn’t quite as specific and because 6 months is half a lifetime in LLM development, I figured I’d post as well. Here’s the post in question in case anyone is curious to see that one.

you are viewing a single comment's thread
view the rest of the comments

[–] hendrik@palaver.p3x.de 3 points 3 weeks ago* (last edited 3 weeks ago)

I lately tried ChatGPT for some networking stuff. And occasionally I'll use AIstudio (Google) for similar things. And let's say they're all not great. They can do the relatively common (and somewhat easy) Linux stuff, I think they should be able to tell you how to manage your Docker containers and volumes at the command line. But I had GhatGPT massively struggle with networking. And like SystemD service files had problematic stuff in them... So, my local LLMs are way to tiny to try. But there might just not be any properly good AI out there as of today. And their "reasoning" modes aren't like human reasoning or systematic approaches either. They just make up a lot of stuff and that makes them a bit better, it's not logic though. What I end up doing is either fall back to my own brain, learn the stuff and do it myself. Or something alike "vibe-coding"... Ask it 10-20 times, scold it, put in the error messages and eventually I'll get something that runs.

Btw, there's still a human Linux community around. So maybe find your favorite Linux forum and ask there once it gets too complicated for AI.