Hacker News Reader

Comment by iwontberude | Hacker News Reader

This is certainly not engineering. Maybe I’m finally a curmudgeon after years of chasing everything in this industry and getting burned enough times but vibe coding without manual review and testing is antithetical to contemporary study on software engineering and development. Are we really gluttons for punishment like this? Like writing a novel on a Nokia 6630, it’s a fun oddity but not really a scalable way to create value.

View on HN

Precisely. Unreviewed vibe coding is never going to scale. In the best case, if it works at all, performance issues will persist. In the worst case it could have bugs that will silently destroy data, also create innumerable security vulnerabilities. Future AIs may resolve these limitations, but current AI is not there yet.

To me, coding is a process of learning and discovery, of perpetually preparing me to develop something even better next time. Just as a developer wouldn't be using libraries if they weren't well written, the same logic extends to applications.

I can definitely see poor programmers rely on unreviewed vibe code, and I guess they have nothing to lose, but I don't imagine anyone actually using their output. It's like trying to resell an AI generated image; there is just no market for it after the initial generation.

I actually do recommend reviewing manually - it's just very convenient to see when a person wrote something (then much more scrutiny can be applied) vs. when the work was outsourced to AI. I feel like there is another application though, but didn't mention it for it's not that clear to me yet: you can yet again estimate whether a new programmer can actually code or if they 10x YOLO their way slowly bringing codebase maintainability down.

Reply on news.ycombinator.com