Story

I’m trying to understand where “vibe coding” realistically stands today.

The project I’m currently working on is getting close to 60k lines of code, with fairly complex business logic. From what I’ve heard, at this scale only a few tools (like Claude’s desktop app) are genuinely helpful, so I haven’t experimented much with other AI coding services.

At the same time, I keep seeing posts about people building 20k lines of code and launching a SaaS in a single 40-hour weekend. That’s made me question whether I’m being overly cautious, or just operating under outdated assumptions.

I already rely on AI quite a bit, and one clear benefit is that I now understand parts of the codebase that I previously wrote without fully grasping. Still, at my current pace, it feels like I’ll need several more months of development, followed by several more months of testing, before this can become a real production service. And that testing doesn’t feel optional.

Meanwhile, products that are described as being “vibe coded” don’t seem to be getting particularly negative evaluations.

So I’m wondering how people here think about this now. Is “you don’t really understand the code, so it’ll hurt you later” still a meaningful criticism? Or are we reaching a point where the default approach to building software itself needs to change?

I’d especially appreciate perspectives from people working on larger or more complex systems.