The AI wrote 500 lines of code, but I only needed 20

Hi everyone!

I've been experimenting with AI coding assistants recently, and something interesting happened.

I asked an AI agent to make a relatively small change to an existing project. Instead of modifying the necessary section, it generated a completely new implementation with hundreds of lines of code.

It technically worked, but maintaining it would have been another challenge.

A few things I've noticed:

• AI sometimes overcomplicates simple tasks.

• Generated code isn't always consistent with existing architecture.

• Reviewing the output can take longer than writing a small function manually.

I'm curious how other developers handle this.

Do you prefer giving AI very specific instructions or letting it figure out the implementation itself?