| I'm a non-technical founder who built an entire SaaS frontend using v0 and Cursor over the past year. My experience might be useful here since I'm on the extreme end of "vibe coding" - I genuinely don't understand most of the code I'm shipping. What surprised me: 1. The "you don't understand the code" criticism is real but misses context. I don't understand the implementation details, but I understand the system architecture, user flows, and business logic. That's enough to make good decisions about what to build next. 2. The iteration speed unlocks something new. I can try three different approaches to a feature in the time it would have taken to spec out one. This changes how you think about product development - you learn through building rather than planning. 3. The bottleneck moved from "writing code" to "understanding what you actually want." The conversations I have with the AI force me to be precise about requirements in a way I never had to be when just thinking about features. Where it breaks down: anything that requires deep technical judgment about performance, security, or scale. I can build the feature, but I can't tell you if it will hold up under load or if there's a subtle security issue. I need technical people for that. The "20k LOC weekend" stories are selection bias, but the productivity gains are real for certain types of work. The key is knowing which type you're in. Source: non-technical founder who built a production SaaS frontend this way |