Programming with AI on a short leash to beat Fable
Show notes
After more than a year investigating the use of AIs for critical, high-quality software, an experienced developer proposes the "Short Leash" method. Far from "vibe" approaches that generate inefficient and hard-to-maintain code, this method requires the expert professional to keep the AI on a short leash. This means analyzing each proposed diff, constantly intervening, and denying permissions if the AI "goes off the rails," ensuring you remain in control and understand the codebase. The AI acts as a linter, identifying common errors, but the final review of the PR, especially if AI-assisted, must be done line by line by the human author themselves, who needs to assume responsibility and understanding of the generated code.
Why it matters: This method allows experienced developers to increase their productivity with AI, without sacrificing quality or their own understanding of the code.
Sources:
📬 Enjoyed this? Subscribe to the Vaccari's Code newsletter for the next wave of software & AI trends, straight to your inbox: Subscribe here