Beyond Vibe Coding

Chapter 3. The 70% Problem: AI-Assisted Workflows That Actually Work

AI-based coding tools are astonishingly good at certain tasks.¹ They excel at producing boilerplate, writing routine functions, and getting projects most of the way to completion. In fact, many developers find that an AI assistant can implement an initial solution that covers roughly 70% of the requirements.

Peter Yang perfectly captured what I’ve been observing in the field in a post on X:

Honest reflections from coding with AI so far as a non-engineer:

It can get you 70% of the way there, but that last 30% is frustrating. It keeps taking one step forward and two steps backward with new bugs, issues, etc.

If I knew how the code worked I could probably fix it myself. But since I don’t, I question if I’m actually learning that much.

Nonengineers using AI for coding find themselves hitting a frustrating wall. They can get 70% of the way there surprisingly quickly, but that final 30% becomes an exercise in diminishing returns.

This “70% problem” reveals something crucial about the current state of AI-assisted development. The initial progress feels magical: you can describe what you want, and AI tools like v0 or Bolt will generate a working prototype that looks impressive. But then reality sets in.

The 70% is often the straightforward, patterned part of the work—the kind of code that follows well-trod paths or common frameworks. As one Hacker News commenter observed, AI is superb at handling the “accidental complexity” ...