DEV Community

Cover image for AI Is More Like a Sloppy Junior Coder With Bad Memory
Cesar Aguirre
Cesar Aguirre

Posted on • Originally published at canro91.github.io

AI Is More Like a Sloppy Junior Coder With Bad Memory

Plain English isn't the de facto programming language yet.

One single video isn't enough proof, but here's one from someone who has given up on AI coding:

Among other reasons, he quit AI coding because:

#1. AI has stolen all the joy of coding. He isn't figuring things out by himself. No more aha moments or victory dances when using AI.

#2. Even with "perfect" prompts and workflows, LLMs' output is unreliable. AI comments tests out to "make them pass," writes passing tests by tweaking edge cases...

LLMs aren't really like a fast junior coder. They're more like a lazy, sloppy, stubborn junior coder who suddenly needs to be taught again.

I haven't tried AI that much myself, like the guy in the video, but I don't swear by English as the new programming language to rule them all.

I still want to tackle business problems.
I want to design code and solve tricky bugs.
That's part of the fun part. I don't want AI to kill it.

I don't want AI to take away my coding skills.
I want AI's help but its hands (or tentacles) off my code.
I still want to stay in control.

I just want AI to do the boring part: generate syntax once I've done the thinking part... and hopefully escape endless Scrum meetings.

With AI taking fast code generation off the table, it's time to double down on problem-solving, clear communication, and many more skills I cover in Street-Smart Coding. Because being a good coder is more than mastering syntax.

Top comments (0)