工程师谈AI编程时代的经验价值

Learn Python. ⠀ Learn JavaScript. ⠀ Learn React. ⠀ Learn Docker. ⠀ Learn AWS. ⠀ Learn Kubernetes. ⠀ Finally, you start feeling confident. ⠀ Then someone says, “I built the whole app with a prompt.” ⠀ Welcome to being a developer. ⠀ After 16+ years in engineering, I understand why this feels exhausting. Every time you get comfortable, the industry gives you more homework. ⠀ But I’d redraw the last part of this curve. ⠀ Your engineering knowledge still matters when you have to explain why: ⠀ • The app works locally but fails in production. ⠀ • One database query takes down the API. ⠀ • A retry charges the customer twice. ⠀ • An AI-generated endpoint lets users access someone else’s data. ⠀ Knowing how to investigate those problems takes experience. Every layer you learned gives you somewhere to start. ⠀ That knowledge helps while you’re prompting, too. ⠀ You can spot a missing requirement, question a design choice, and catch a dangerous assumption before it spreads across twenty files. ⠀ I want AI to handle more of the repetitive work. I also want to understand what I’m putting into production. ⠀ If you’re feeling behind, try this: ⠀ Take one small feature you already know how to build. Ask an AI coding tool to implement it. Then review the result like a teammate’s pull request. ⠀ 1. Read the diff. ⠀ 2. Check the dependencies. ⠀ 3. Test the failure cases. ⠀ 4. Find something you would change and explain why. ⠀ You’ll learn the tool while exercising the judgment you’ve spent years developing. ⠀ And if you’re just starting, follow the generated code all the way through: from the button, to the API, to the database, and back. ⠀ You don’t have to restart your career every time the tools change. ⠀ You do have to keep learning. That part of the picture has always been accurate. ⠀ Which skill on this chart took you the longest to learn?