Ask Lemmy
A Fediverse community for open-ended, thought provoking questions
Rules: (interactive)
1) Be nice and; have fun
Doxxing, trolling, sealioning, racism, and toxicity are not welcomed in AskLemmy. Remember what your mother said: if you can't say something nice, don't say anything at all. In addition, the site-wide Lemmy.world terms of service also apply here. Please familiarize yourself with them
2) All posts must end with a '?'
This is sort of like Jeopardy. Please phrase all post titles in the form of a proper question ending with ?
3) No spam
Please do not flood the community with nonsense. Actual suspected spammers will be banned on site. No astroturfing.
4) NSFW is okay, within reason
Just remember to tag posts with either a content warning or a [NSFW] tag. Overtly sexual posts are not allowed, please direct them to either !asklemmyafterdark@lemmy.world or !asklemmynsfw@lemmynsfw.com.
NSFW comments should be restricted to posts tagged [NSFW].
5) This is not a support community.
It is not a place for 'how do I?', type questions.
If you have any questions regarding the site itself or would like to report a community, please direct them to Lemmy.world Support or email info@lemmy.world. For other questions check our partnered communities list, or use the search function.
6) No US Politics.
Please don't post about current US Politics. If you need to do this, try !politicaldiscussion@lemmy.world or !askusa@discuss.online
Reminder: The terms of service apply here too.
Partnered Communities:
Logo design credit goes to: tubbadu
view the rest of the comments
Honestly, very little. Unless you're in a "not designed here" environment. There's a lot of open source applications/libraries out there that can be added to your project to get what you need.
But I do agree, vibe coding can be great as long as it's just for one off small projects. Need to do a quick computation or a quick POC and don't want to spend the time setting everything up? Great!
But if you want to build an application that's used by 1000 or even millions and receives regular updates? Please follow best practices / design patterns, etc... otherwise you'll be rewiring the entire codebase every time you want to add a new feature.
I dunno, my experience is teams of people grinding away designing systems that are likely 95% the same as what several other companies already constructed, if not hundreds. It’s great if they use (much less contribute to) some open library for the functionality, so the wheel doesn’t get re-invented, but how often is that the case?
Of course one doesn’t want to distribute slop. I’m talking more theoretical, especially if more formal code verification becomes standard.
Mind you, a lot of this reimplementation is because those 1000 other implementations that came before all haven't had their source code released to the public. No amount of vibecoding is going to help there because those LLMs were never trained on code that was never publicly released.
They're trained on plenty that's similar enough, as long as its Python or something in the dataset.
It's also been shown that LLMs are good at 'abstracting' languages to another, like training on (as an example) Chinese martial arts storytelling and translating that ability to english, despite having not seen a single english character in the finetune. That specific example I'm thinking of is:
https://huggingface.co/TriadParty/Deepsword-34B-Base
Same with code. If you're, say, working with a language it doesn't know well, you can finetune it on a relatively small subset, combine with with a framework to verify it, and get good results, like with this:
https://huggingface.co/cognition-ai/Kevin-32B
Someone did this with GDScript too (the Godot Game Engine scripting language, fairly obscure), but I can't find it atm.
Not that they can be trusted for whole implementations or anything, but for banging out tedious blocks? Oh yeah. Especially if its something local/open one can tailor, and not a corporate API.
Auto-writing boilerplate code doesn't change the fact that you still have to reimplement the business logic, which is what we're talking about. If you want to address the "reinventing the wheel" problem, LLMs would have to be able to spit out complete architectures for concrete problems.
Nobody complains about reinventing the wheel on problems like "how do I test a method", they're complaining about reinventing the wheel on problems like "how can I refinance loans across multiple countries in the SEPA area while being in accord with all relevant laws".