With AI, The Real Edge Is Knowing What to Build
"But... how did you know what to write?" That's what Greg Baugues' daughter asked him after her first encounter with vibe-coding. She was curious if there was a time when we had to type symbols, one by one. It isn't about what symbols to type Coding used to be about the craft: Mastering symbols and perfecting the lines of code. If you knew what to type and could make it work, you could find your…
In the era of artificial intelligence, the critical factor for success is not merely knowing what symbols to type, but rather what to build. Greg Baugues' daughter recently asked him this question after experiencing "vibe-coding." Coding used to be about mastering symbols and perfecting lines of code. However, with AI, coding has become significantly cheaper and accessible. Anyone can generate working code with just a few sentences.
This shift has transformed the job description of a coder. Instead of focusing on typing the right symbols, the new challenge is deciding what to build. The author is currently working on a legacy migration for a hardware shop, where the main page is a tangled mess of over 40,000 lines of outdated Visual Basic code. Refactoring this codebase to a more modern system is a time-consuming process.
Management suggested starting some refactoring work to alleviate the pain of migrating the system. However, the migration process has been dragging on for years, and the progress remains minimal. The author's team debated whether to refactor, migrate, or rewrite the code. The real challenge lies in deciding the right approach.
Ultimately, the edge in coding is knowing how to solve problems and choosing which problems to tackle. To grow beyond mere syntax, it's essential to consult resources like the Street-Smart Coding Manifesto. In an era where coding is cheap, the true value lies outside the IDE.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
