re: Is "Vibe Coding" Ruining My CS Degree?

22 Dec 2025 #coding

It’s tempting to default to AI for its speed.

If you’re stuck, just write a 2-sentence prompt and after some beep, beep, boop you get an answer. But relying too much on AI hides a serious problem.

I’ve witnessed the over-reliance on AI myself. And it’s worse for CS students. Maame Afua A. P. Fordjour shared in a dev.to post,

[When facing a Data Structures assignment] I type: “Yo, I need a Red-Black Tree implementation in C++. Keep the vibe academic, handle the edge cases for rotation, and add comments that sound like a stressed undergrad wrote them.”

Thirty seconds later. Done.

It compiles. It passes the test cases. It’s beautiful code. And I have absolutely no idea how it works.

It’s not the tool, but how you use it

Like we always say: the problem isn’t the tool, but how we use it.

AI isn’t going anywhere. It’s already changing our job descriptions. But we need strong guidelines to avoid blindly trusting AI and losing our skills.

If you’re a confident coder, write your method signatures, use comments to sketch their bodies, and let AI fill in the blanks.

But if you’re a beginner, my take is radical: don’t use AI to generate code.

Don’t use AI to do your homework. Use it as your teaching assistant instead. To quiz you, generate test cases, explain a tricky code block. Otherwise it’s like sending someone else to the gym and then complaining when you don’t see your muscles growing.

AI is like a powerful calculator. You need strong math skills first before using one.

If you want to strengthen your coding skills, my book Street-Smart Coding covers 30 lessons to help you level up, from Googling to communication to problem-solving.

Grab your copy of Street-Smart Coding here—That’s the roadmap I wish I had on my journey to senior coder.