Skip to main content

Command Palette

Search for a command to run...

Why GitHub Copilot is not a Threat to your Job

Published
2 min read
Why GitHub Copilot is not a Threat to your Job
M

I’m a senior software engineer loving clean code, and declarative designs. S.O.L.I.D. and agile methodologies fan.

TL;DR: If you are a good software designer Copilot will not help you very much.

What is GitHub Copilot?

GitHub Copilot is an AI pair programmer.

It was trained with a huge coding database of common small routines.

It also can recognize bad comments and create imperative code from them.

GitHub copilot is a text transformer similar to GPT-3.

It was developed by the same company: OpenAI.

How does it work?

The OpenAI Codex engine powers GitHub Copilot.

It was trained with a lot of source code and also natural language.

To use it, we must apply to their waiting list. The approval process is fast.

We add it as a Visual Studio Code Extension that interacts in real-time with GitHub.

Benefits(?)

Autofill

Copilot can predict anemic structures once we describe their accidental data.

They are suitable for implementative and anemic code generation.

Code wizards are a present problem. Copilot is a brand new one.

Bad comments to code

It converts bad comments (those that should never be present in our code) to straightforward algorithms.

We can assume that the training set was filled with bad implementative commented code. We shouldn't rely much on the algorithm's declarative.

Structural tests

CodePilot can generate tests on setters. These tests are coupled to implementation and fragile.

They test our getters, so they don't add much value to validating our system's behavior.

More insights here.

Should we worry about it?

Not now.

If you read the benefits above, most of the Copilot code belongs to the code smell area.

Very soon, transformers like Copilot will replace lazy and implementative programmers.

What should be doing right now?

We need to be cleverer than it.

We need to create great behavioral models far from implementative structural data.

The problem copilot is solving right now tackles software main mistakes. Thinking of programming as just dealing with data instead of behavior.

Once we decide to grow up and build serious software instead of dealing with strings, dates and arrays, we will push our jobs a few years away from this fancy robot.

Please do write me a line below with your thoughts on this.

M

Forget it. Ask anyone who works with neural networks. Then compare what they say to what's in the press and all over the internet. The hype is exceptionally high, while actual AI engineers spend weeks and months trying to get their neural networks to generate something that is at least not complete gibberish.

GPT-3 is amazing on the news, but take a closer look even at the best texts that GPT-3 generate — something seems off and that's the best neural network we have.

The answers are predictable. The long output samples are look good indeed, but when you read them, they turn out to be conceptual gibberish akin to glorified Markov chain output.

Of course, Copilot can make you more productive by automating routine tasks. But Copilot implementing architecture or even coding business logic, the actual ability that distinguishes you from junior developers? Forget it.

3
M

Appreciate very much your insight!!

Copilot can make you more productive by automating routine tasks. But Copilot implementing architecture or even coding business logic, the actual ability that distinguishes you from junior developers? Forget it

E
Edem Gold4y ago

Great article Maxi, personally I feel AI is not yet developed up to the extent of competing with developers

1
M

Yes. It is also not helping us very much since most code it generates are code smells. But in a couple of years we will be obsolete.

10
E
Edem Gold4y ago

I don't think obsolete is the right word. I think we'll evolve AI writing code may make developers evolve into something else.Maxi Contieri

Artificial Intelligence

Part 12 of 13

This series include articles related to - Machine Learning - General Artificial Intelligence - Centaurus Coding - Tools like GPT-3, Codex, Copilot

Up next

I've Recently Learned About GPT3 - This is my Journey

My future project on text transformers applied to code.