Marcel

🤖 Everyone talks about vibecoding but most definitions focus on how the code was created. I think that misses the point.

My take: vibecoded code is code that nobody on your team has fully understood. It doesn't matter if an AI wrote it, a junior dev copied it from Stack Overflow, or a senior dev hacked it together at 2am. If nobody has truly reviewed and comprehended it — it's vibecode.

That distinction matters because it shifts the conversation from "did you use AI?" to "do you actually know what this does?" 🔍

This also means: code that an AI generated but you thoroughly reviewed and understood is NOT vibecode. The tool doesn't define the category — your level of understanding does.

Why does this matter? Because it changes the risk assessment entirely. Using AI to write code you then deeply review is just a productivity tool. Shipping code you don't fully grasp is a conscious risk decision — sometimes justified, sometimes not.

Do you agree with this definition? Or would you draw the line somewhere else?

#SoftwareDevelopment #AI #Vibecoding #CodeQuality #DevLife

10:33pmWeb
Show threadBlf_tpe14h ago
@marcelschmall Interesting take! After one year as a beginner vibe coder I agree with you. 1/ I can’t go beyond a few hundred lines of code without losing understanding of what the machine does. 2/ I do a lot of effort to understand what’s going on, reformat and it’s rewarding 3/ I still do a lot of mistakes and can be stuck with long debugging! But I also start to grasp how it works. It’s not all black and white.
Show threadMarcel2h ago

@Blf_tpe This is a great real world example! Your point 2 is exactly the key — the moment you put in the effort to understand and reformat, it stops being vibecode. You are turning AI output into YOUR code.

And point 1 is interesting — a few hundred lines seems to be the natural ceiling where vibecoding starts to break down. Beyond that, debugging (point 3) becomes the real cost.

Sounds like you are already moving from vibecoding to AI-assisted coding — and that's a huge difference in terms of risk.

Show threadBlf_tpe1h ago
@marcelschmall Thinking about it, I feel there’s a misunderstanding in the community. Newbies like me feel empowered at first because coding is a bit magical, after a while we realize all the work that’s been done, how precious documentation, open-source etc is. And LLMs do bring lots of people to open-source ! (1/2)
Show threadBlf_tpe1h ago
But people like me don’t understand everything at first :) So for existing members, rather than feeling threatened by ai or annoyed by low level feedback, it can be seen also as a huge opportunity to promote opensource to a very large new audience! (2/2)
Show threadMarcel3m ago

@Blf_tpe Great point — AI as a gateway to open source is a real upside I hadn't considered enough. More people discovering and appreciating the ecosystem is genuinely valuable.

But there's a flip side: if a lot of newcomers start opening issues or PRs on established projects without fully understanding the codebase, that can overwhelm maintainers who are already stretched thin. The intent is good but the burden is real.

Maybe the better path for beginners is to start your own small open source project with vibecoded code. Put it out there, get feedback, learn from the community. That way you build understanding without adding noise to existing projects.

Places like Mastodon could actually be great for that — share your project, ask for feedback, learn in public. Devibecoding as a community effort rather than a solo struggle.