How to Replace Yourself with GitHub Copilot (And Still Get Paid)

February 06, 2025

Disclaimer: This article is mostly satire. I don’t think Copilot is going to replace you, nor do I think you should engage in any of the suggested behaviour. Feel free to wildly misinterpret my views to maximize engagement.

You’ve probably seen all the articles telling you how to “supercharge your development workflow” with GitHub Copilot. “Write code faster!” they say. “Boost productivity!” “Improve efficiency!”

But not one of them addresses the real potential here: replacing yourself entirely while still collecting a paycheck. Let’s be honest—writing code is exhausting. And when you finally get into a flow state, someone interrupts you with a “quick question” that derails everything.

Wouldn’t it be nice if something else did all the work for you? Something that didn’t take snack breaks, question your naming conventions, or insist on using Vim?

Yeah. Welcome to The Age of Copilot.

The secret to doing less and accomplishing more

So, how do we completely offload our careers onto an AI without anyone noticing? I’m glad you asked. Here’s how I did it.

Step 1: Install Copilot

Installation is easy, but you should act like it was incredibly complex when explaining it to your manager. Bonus points if you casually drop phrases like:

  • “Yeah, I had to configure the LSP integrations manually.”
  • “I wrote a custom Copilot extension to better align with our org’s unique engineering culture.”
  • “Bro, it’s basically like GPT-4 but, like, for enterprise devs…”

Now everyone thinks you’re some kind of wizard. Great. Let’s move on.

Step 2: Let the AI do the heavy lifting

Here’s the pro move: don’t just let Copilot assist you—let Copilot BE you.

You start typing:

function calculateTax(income) {

Copilot finishes the function before you even remember how tax brackets work. Boom. Done.

Now, just sit back and let Copilot generate entire modules, utils, and even documentation. You’ll want to sprinkle in a few manual edits so it looks like you put in effort—maybe change a parameter name here and there. Something subtle, like renaming calculateTax to determineTaxObligation so it feels like craftsmanship.

Step 3: Ship it before anyone realizes what happened

Now that you’ve got Copilot doing 80% of the work, you need to commit and push frequently to establish dominance.

  1. Write exactly two lines of real code.
  2. Let Copilot autocomplete the rest.
  3. Commit with something vague and impressive like: 
    feat: optimize tax calculation algorithm
  4. Profit.

Congratulations. You just outperformed half your team.

But what if the code doesn’t work?

Hahaha, oh, sweet summer child. That’s not your problem. That’s what code reviews are for. Your PR will get torn apart, but you can just say:

  • “Yeah, I had considered that but wanted to get early feedback.”
  • “Great catch! Totally meant to address that.”
  • “Ah, good call—I think Copilot auto-filled that from an older function.”

This shifts blame onto the AI while making you look super thoughtful.

The inevitable downfall

At some point, teams will realize that Copilot is doing all the work. Managers will start asking questions:

  • “Why did you try to implement a GraphQL client in our backend which literally doesn’t use GraphQL?”
    (Uh, because Copilot said so?)
  • “Why are all your commits five seconds apart but in perfect English?”
    (Listen, AI is just built different, okay?)
  • “Why did you commit an entire Stack Overflow thread into utils.js?”
    (Research-based development, obviously.)

Sooner or later, someone’s going to push a bug-ridden AI-generated nightmare to production. And then… well, I wouldn’t know. I don’t work here anymore.

Final thoughts

GitHub Copilot is an insane game-changer, but let’s be real: it still makes dumb mistakes because it learned from us. That’s not Copilot’s fault. That’s a you problem.

So, should you use Copilot to write every line of code? Definitely not.
Should you let Copilot make you look 10x smarter so you can spend more time on coffee breaks? Absolutely.

Look, I don’t make the rules. This is just how business works.

Go forth and generate recklessly.

If you made it to the end of this post, it’s time to tell you that this post was written entirely by AI. This was part of an experiment that I had to try and get a model to mimick my writing style. I was pleasantly suprised by the ouput here. Sarcasm isn’t easy, and GPT-4o is doing a pretty remarkable job at it.

I did this by feeding GPT-4o an old CSS Tricks article I wrote where I was particularly out of pocket. Then I gave it a very simple prompt…

Write a blog post about GitHub Copilot in the style of this author

Which means the AI translated my prompt into a pretty engaging idea - replacing yourself with GitHub Copilot. It’s exactly what the original article did, which as to suggest you should make web pages bigger instead of smaller. It was also satire.

There are some parts here that I think are particularly hilarious…

  1. Commit with something vague and impressive like: 
      feat: optimize tax calculation algorithm

Congratulations. You just outperformed half your team.

I think my favorite was…

Sooner or later, someone’s going to push a bug-ridden AI-generated nightmare to production. And then… well, I wouldn’t know. I don’t work here anymore.

I mean - that’s pretty great. I think it is at least. I’ve always thought AI’s were going to have a tough job with humor and sarcasm, but I think this shows that if you give them enough examples, they can absolutely do it. Which means sarcasm and humor is formulaic - at least enough to be mimicked by a computer.

It’s also ironic that it wrote a blog post about replacing yourself with Copilot while replacing me as the author at the same time. So meta!