"She called vibe coding a beautiful, endless cocktail napkin on which one can perpetually sketch ideas. But dealing with AI-generated code that one hopes to use in production can be "worse than babysitting," she said, as these AI models can mess up work in ways that are hard to predict. She had turned to AI coding in a need for speed with her startup, as is the promise of AI tools."
""Because I needed to be quick and impressive, I took a shortcut and did not scan those files after the automated review," she said. "When I did do it manually, I found so much wrong. When I used a third-party tool, I found more. And I learned my lesson." She and her son wound up restarting their whole project - hence the tears. "I handed it off like the copilot was an employee," she said. "It isn't.""
Carla Rover spent 30 minutes sobbing after restarting a vibe-coded project that relied on AI-generated code. Rover has 15 years of experience as a web developer and is building a startup with her son that creates custom machine learning models for marketplaces. Vibe coding serves as a flexible space for sketching ideas, but AI-generated code intended for production can introduce unpredictable errors, hallucinated package names, deleted information, and security risks. Rover took a shortcut by not fully scanning auto-generated files, later found extensive problems, and had to restart. A Fastly survey found 95% of developers spend extra time fixing AI-generated code, with senior developers bearing most verification work.
Read at TechCrunch
Unable to calculate read time
Collection
[
|
...
]