AI coding has 5 levels. Which one are you at? This framework comes from Glowforge CEO Dan Shapiro, inspired by the levels of autonomous driving (see diagram). The recently popular Clawdbot (now renamed Moltbot) creator says he's at L5. With 60,000 stars on GitHub in 10 days, his approach includes: • Opening 4 Claude windows simultaneously to develop different features in parallel • "I don't design the code structure for myself, I design it for AI" • Never rolling back when issues occur, letting AI change direction core shift: from "code review" to "reviewing requirements + looking at test results". I am currently between L3 and L4: AI writes most of the code, I make architecture decisions and reviews. Some practical habits in use: 1. When problems occur, let AI fix them, don't do it yourself. If you change it, it loses context and may make the same mistake again next time. 2. Open multiple windows at the same time. One for fixing bugs, another for writing new features, without interference. 3. Think of yourself as a product manager. Clearly describing "what is needed" is more important than "how to write". Which level are you at?👀