I Made 866 Commits in 5 Weeks. My Understanding Didn't Keep Up.
AI has made me dramatically faster at building software. You can see it on my GitHub: a sudden surge of activity at the start of September, several projects started, and a few of them actually shipped. That part isn't up for debate. I can go from an idea to a working prototype in a day. I can ask questions about an unfamiliar API, generate test scaffolding, trace a bug across a codebase, and get…
The author, who has utilized AI to boost their coding speed, has noticed a growing gap in their understanding of the software they create. In just five weeks, they made 866 commits and completed several projects, with AI writing most of the code. However, the author realized that they were missing key computer science fundamentals, such as data structures like hash maps and indexes.
This gap became apparent when they attempted to solve a common LeetCode problem, Two Sum, and found themselves struggling to explain the underlying concepts. The author then implemented four rules to help bridge this knowledge gap: making predictions before seeking AI assistance, not accepting code they can't understand, asking what test would have caught the error, and reading the code before asking AI to rewrite it.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
