33
What's the motivation behind vibe-hobbying?
(feddit.org)
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 20 Sep 2026
33 points (90.2% liked)
LocalLLaMA
5169 readers
58 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 3 years ago
MODERATORS
I am a professional software engineer and have codebases to support hobbies, but I’m not building them for the joy of programming and am instead building a codebase to make the actual hobby itself more enjoyable. I’m happy to offload the work to local LLMs in that case and have the LLM follow my existing patterns with me reviewing the code and driving functional and non-functional requirements instead of coding everything by hand.
I also have purely vibe-coded projects that are things I wouldn’t otherwise build due to lack of time, but since I can let the machine do the work while I attend to daily responsibilities or sleep, it’s nice to let a local LLM build it for me. In that case, I try not to look at the code too much so I don’t get pissed off and want to redo it. This works well enough for small projects that serve a purpose and that I don’t intend to build on much long-term.
This, basically if I had about 100x the number of hours in the day currently, I might actually have enough time to be able to build everything myself from scratch, but I don't even get enough free time to spend more than 2-3h on personal projects a week. Most of these projects are means to an end and not exercises in honing my programming skills.
Now all half finished stuff and abandoned ideas are a relative thing of the past. Hell my personal projects have robust unit tests and everything now, that was never the case before.
When I actually do want to learn something programming related (like learning zig recently) I'm actually ironically more free to now focus on that stuff because I don't have the guilt that I should probably focus on fixing some half baked project that recently broke or something. I'm not going to learn much by writing my thousandth Python or Go app, so ollama can do it for me most of the time and I can focus on something more important.
That, and also so many unfinished projects that would likely never had gotten finished due to lost motivation, can finally get the boost they need to get past the finish line. Especially if a project is like 80% done, you can first do a pass where you instruct the LLM to figure out your conventions and coding patterns and your coding style in general. Document them, and any new code it writes to make sure it follows them. This way, anything new added doesn't feel foreign and it's easy to understand. Not to mention that LLMs can also do the boring but useful part of writing documentation.
Same. I like coding but I like having finished products and clearing my personal backlog of ideas even more. I’ve had such a blast with AI building everything I’ve ever wanted and never had the time for.