this post was submitted on 28 Jun 2026
71 points (92.8% liked)

Programming

27489 readers
385 users here now

Welcome to the main community in programming.dev! Feel free to post anything relating to programming here!

Cross posting is strongly encouraged in the instance. If you feel your post or another person's post makes sense in another community cross post into it.

Hope you enjoy the instance!

Rules

Rules

  • Follow the programming.dev instance rules
  • Keep content related to programming in some way
  • If you're posting long videos try to add in some form of tldr for those who don't want to watch videos

Wormhole

Follow the wormhole through a path of communities !webdev@programming.dev



founded 3 years ago
MODERATORS
 

Support this channel on Patreon ► https://www.patreon.com/zoranhorvatGenerative AI can write code, but it cannot develop software on its own. Here is why the...

you are viewing a single comment's thread
view the rest of the comments
[–] MarckDWN@programming.dev 15 points 1 day ago (3 children)

The problem isn't the tool; it's the lack of engineering foundations. Generalizing all AI-assisted development as 'vibe coding' is a massive oversimplification. There is a vast difference between a beginner blindly copy-pasting LLM output into a codebase they don’t understand, and a senior architect using LLMs as a high-powered assistant to speed up boilerplate, local schema generation, or parsing scripts. When you already know exactly how the underlying system operates, how memory is managed, and how to design clean software architectures, the LLM is just a productivity multiplier. You still design the data flow, audit the tool-use sandboxes, and review every single line of code. It doesn't replace thinking; it replaces tedious typing.

[–] bjornsno@programming.dev 26 points 1 day ago (1 children)

As a senior developer I have serious doubts about the whole thing. Yes, I don't do tedious typing anymore, now I do extremely tedious code review all day, my least favorite part of the job. And I have to be very vigilant because the AI is an idiot more often than not. Then when I finally publish my own code it's time to go review my colleagues' ai code and figure out what they missed in their review.

I don't feel much of a productivity multiplier. I'm not saying we won't get there, but this current iteration ain't it.

[–] peskypry@lemmy.ml 9 points 1 day ago (1 children)

Agree. Using AI as a tool is very productive. On the other hand, letting AI drive everything is insanely time consuming and tiring work due to back & forth prompts.

[–] WolfLink@sh.itjust.works -2 points 21 hours ago (1 children)

I’ve found AI powered autocomplete suggestions is actually quite nice. The time save when it gets it right is sometimes significant, but the time lost when it gets it wrong is usually negligible.

[–] tyler@programming.dev 8 points 15 hours ago (1 children)

good grief, AI powered autocomplete is so bad it slows down my development by an order of magnitude.

[–] Chais@sh.itjust.works 6 points 11 hours ago (1 children)

It's really set up for failure. It can only fall short of a deterministic, type-aware, contextual autocompletion, something IDEs have been supporting for like a decade.

[–] tyler@programming.dev 4 points 4 hours ago

Yeah, as soon as it was added I immediately saw a massive decrease in effectiveness. It starts by showing exactly what I want, then I hit tab and it autocompletes some bullshit that I do not want. I then have to undo and retype everything rather than using tab. It’s a insane failure of dev tooling.