DEV Community

Cover image for How has AI changed your approach to development?
Ben Halpern
Ben Halpern Subscriber

Posted on

How has AI changed your approach to development?

August 2023 check-in — what is different in your approach in the ChatGPT, Copilot, etc. era of development?

If not much has changed, speak to that.

Top comments (33)

Collapse
 
jason_espin profile image
Jason Espin

It hasn't. I've seen a lot of developers leaning on chat GPT as a crutch. Their first instinct as soon as they get stuck rather than figuring something out is to go on ChatGPT and have it answer the solution for them. The problem is a lot of the time the answers it gives are incorrect or error prone and the very same Devs using it as a crutch don't know how to tweak the answers to actually get a working and useable solution. I tried GitHub co-pilot but didn't end up paying after the trial as I found as a .Net developer the tooling and auto complete within Visual Studio and Visual Studio code made development a lot more efficient than using any AI linked tools. I'd agree with a lot of the sentiment on here that AI ik general is overhyped at the moment and not all that it's cracked up to be.

Collapse
 
droidmakk profile image
Afroze Kabeer Khan. M

I feel auto-pilot is giving more mistaken auto completetions than what i actually need. It has caused me again review the code again rather than go with flow that i actually already had in mind.

Collapse
 
chukshon profile image
Honour

you’re right on this

Thread Thread
 
chukshon profile image
Honour

👍

Collapse
 
greggcbs profile image
GreggHume

I cant tell you how many times gpt has given me incorrect code or answers. I have realized that it is over-hyped and still needs a lot of work before it becomes a useful tool for my development. I do look forward to a time where I can give AI a system spec and it will build it out for me and then I can work on it and ask the AI to build out new features. I am so tired of writing the same code over and over again, its boring now, i cant wait for advancements.

Collapse
 
theplebdev profile image
Tristan Elliott
  • ChatGPT: has saved me hours of googling and searching stack overflow. Initially I was very hesitant to use it. However, its ability to allow me to keep asking why and drilling further and further down on a problem is really revolutionary. I am 100% on board the AI coding hype train. Its like a more personal google search and its awesome
Collapse
 
nwarwick profile image
Nicholas Warwick

Seconded. Being able to drill down and keep asking why efficiently is a game changer for me.

Collapse
 
jovialcore profile image
Chidiebere Chukwudi

Being able to ask why Is it for me too

Collapse
 
leandro_nnz profile image
Leandro Nuñez

+1. The keep asking why did it for me too.

Collapse
 
themikaelson profile image
themikaelson

Did u use chatgpt 3 or 4?

Collapse
 
theplebdev profile image
Tristan Elliott

I use chatgpt 3.5, which is the included under the free tier

Thread Thread
 
joemulligan profile image
Sean Ablett

If you have the wherewithal to get 4, give it a try. It’s hallucinations are much less common and it’s error rates in coding discussions are much less frequent.

Collapse
 
ben profile image
Ben Halpern

I'll start the conversation with my experience:

  • AI autocomplete isn't that big a deal for me, but I could see that changing with iterative improvements to this type of tech.
  • ChatGPT is most helpful in exploring a paradigm I'm not as familiar with and having a really fast "no stupid questions" loop. I can be a bit more adventurous than I had been.
  • Latency is still more than I want. It's easy to genuinely be slowed down by this tech on that issue alone.
  • I write a lot of boilerplate with GPT.
Collapse
 
raddevus profile image
raddevus

I'm very curious by your last statement.

  1. Which software dev language are you using GPT to generate? (Ruby? I see you are a Rubyist)
  2. If it's just "boilerplate" then why not simply have your own "library" of code snippets to get your projects started? Thanks
Collapse
 
mistval profile image
Randall • Edited

I feel GitHub Copilot accelerates me a lot and it does change how I go about coding. I will often pause and wait for it to auto-complete something, where I wouldn't have before. Sometimes it generates code that isn't quite what I would write, but as long as it's good code I will leave it alone. I never accept bad code from it, or code I don't understand.

I don't use ChatGPT very often, but it's in my toolbox now as a method of last resort. If I look at documentation and use my noggin and I still can't figure something out, I'll ask ChatGPT and sometimes as if by magic it understands my question and knows a great solution. So it's just one more resource for me, but it can be a pretty powerful one sometimes.

Collapse
 
deozza profile image
Edenn Touitou

It's been 4 months since I started using github copilot. I use it mainly to develop a personal design system in sveltekit (html, css, typescript).

It helped me a lot when doing repetitive tasks. Like for example, I started writing css variables like :

:root{
    --primary: rgb(59 130 246);
    --primary-dark: rgb(37 99 235);
}
Enter fullscreen mode Exit fullscreen mode

And the prompt automatically completed for me the secondary, success, danger, warning and info.

When I started doing a btn class :

.btn.btn-primary {
    background-color: var(--primary-bg-button, var(--primary));
    color: var(--primary-text-button, var(--white));
    border: 1px solid var(--primary-border-button, var(--primary));
}
Enter fullscreen mode Exit fullscreen mode

It took the template and used it for all the other variables.

I also used it for a small symfony (PHP) project. I started writing the controllers. When I moved on to the tests, copilot wrote lots of basic tests (some with dataProvider). I only had to tweak them a bit or to add edge cases tests.

In the end, I find it very useful for redundant tasks. And as an autocomplete on steroids. I don't think I used it in other use cases.

I don't use chatGPT, and I use very lighlty Google Bard to sometime get a help writing documentation or when I don't want to Lorem Ipsum my interfaces.

Collapse
 
aiden_oliver profile image
Aiden Oliver

AI has dramatically impacted the way I troubleshoot and transform API responses in the Integration space. Although it is far from being able to develop scalable and efficient technical solutions on it's own, it assists me in minor tasks such as script development and enhancements.

Collapse
 
cheetah100 profile image
Peter Harrison

Have included it in my workflow for some time. Useful so long as you understand its limits and respect that it lies like a weasel when it reaches the limit of its abilities. Always double check generated code, and learn from it rather than cut and paste. May not be replacing developers yet, but is pretty impressive.

Collapse
 
maggierm88 profile image
Maggie Martin

I've started out mostly using it for refactoring smaller chunks of code - first explaining what I want to do, then pasting my current code. From there, I test it and review it to see if it actually does what I want, and if it is, in fact, a better written/more condensed version of my original. I may ask them to rewrite it and see some additional options. I probably use their suggestions about 1/3rd of the time.

Collapse
 
adriens profile image
adriens

🤓 Personal side projects

I use chat-GPT on free tiers for dummy questions that help me save a lot of time

🤵‍♂️ Pro

We use GH Copilot, for now mostly for programmers and data-science & engineering.
As we use it, we tend to make better comments to get better results... and the question on maintaning documentation started to raise, especially this one :

"Why writing and maintaining documentation on a code that will probably change over time while we can get the doc just on time ?"

Also, reading this book brought me a lot of inspiration around this topic, which helped imagine the future of programmers work at the AGI era:

Collapse
 
karishmashukla profile image
Karishma

I primarily use it for

  • doing mundane and repetitive coding tasks
  • getting a quick overview of concepts I am not familiar with

It really helps me to wrap up work faster and close my laptop sooner

Collapse
 
dreama profile image
Dream

I'm a fan of the new custom instructions in chatgpt. I wish the text were longer and I could paste huge instructions there.

Collapse
 
deathroll profile image
deathroll • Edited

I don't use AIs at all. It's a lot faster and less error prone to rtfm and do things my own way than prompt an AI.

Collapse
 
deathroll profile image
deathroll

Also really tired of all this hype and huge amounts of AI-generated content.

Collapse
 
fyodorio profile image
Fyodor

AI fatigue is real 😅

Collapse
 
duncan_true profile image
Dun

It's taken a lot of boring tasks off my plate, but I still have to oversee it pretty tightly — which isn't that much better. I can't say I'm actually more productive, but I don't want to dismiss what the next gen will bring.

Collapse
 
ujjwall-r profile image
Ujjwal Raj

To be honest, it really saves a lot of time for me. The only thing is that I have to keep in mind that the code writing techniques is aligned with the project I am contributing to or building. I basically look into the crux idea how AI solves the issue I want to solve and get idea from their code. Other than that I have to write my own code. But anyways, this only saves a lot of time for me. At least 3 times faster development.

Collapse
 
a5okol profile image
5okol

Despite being an experienced developer, my life has been affected. I use both ChatGPT and Copilot. In some cases ChatGPT helps a lot, for example, when integrating third-party services. You can read less documentation, just feed ChatGPT documentation and write where you want to integrate, for example NextJs.

Capailot impressed me a lot in the beginning, now it doesn't provide many solutions, mostly it helps to add some trivial things like imports.