Matt Pocock

AI tools perform poorly on messy codebases because they amplify existing problems rather than fixing them. The concept of 'deep modules' — a software design principle about 20 years old — is proposed as the solution to managing complexity, reducing cognitive load, and making codebases more AI-friendly.

If you throw AI at a bad codebase, you're going to get worse results. Garbage in, garbage out.

And holding it together in your head will land you in cognitive debt.

But these problems have a 20-year old solution: deep modules.

Here's how: https://t.co/9zkEDrs2Ef

<p>If you throw AI at a bad codebase, you're going to get worse results. Garbage in, garbage out.

And holding it together in your head will land you in cognitive debt.

But these problems have a 20-year old solution: deep modules.

Here's how: https://t.co/9zkEDrs2Ef</p>