this post was submitted on 24 May 2026
32 points (76.7% liked)
Programming
27035 readers
160 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
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Is that meant to say reviewing? Either way, I can't see how this would lead to good results, even with a comprehensive test suite. Security? Scalability? Maintainability?
I use LLMs to automate boring tasks or generate starting points, but in my experience, i can't trust them to generate code that I'd be proud to share. If I use the code they spit out, I'm always adapting or rewriting it to meet my standards. I find they better at explaining code than generating it.. Anyway...
How will these students evaluate if the code they have generated is up to scratch?
You kind of have to have been a good coder to know what good code looks like.
I know, I know, another AI will be used to review the code...
Something feels a bit off here to me.
I'm sure I will be flamed.
Yeah, at most you can let them manage a 1k loc python script (the free tiers or Gemini Pro at least), but more than that and it starts to really eat your tokens without achieving what you asked or breaking functional behavior.
I extremely doubt that Coding Agents will see a future like promised. LLMs are still so expensive to run, and the useful larger models will probably never be affordable (if they charged for them what they cost). Apart from the fact that even their output can be utter garbage (and mediocre at best). You can already see it everywhere. Websites break in weird ways, ways in which it’s clear that either a complete beginner wrote that or an LLM did. Look at Shazam a few weeks ago. UI design? Horrific. Extremely inconsistent. Ugly. There are many other examples. It just shows that it doesn’t work. And no, the next model will not solve those issues. LLMs are flawed for this task from the ground up, the approach is outright wrong, we can make up so many bandaids and they will still suck, forever.
Inconsistency kills me. I've a colleague at work who insists on putting every doc through an llm to make it look nice then dumps it on the wiki. Now the wiki is a clusterfuck of assumptions and inconsistent styling.
Our documentation on some tedious process does not need to look like a magazine article nor does it help me find the salient code snippets that will help me understand why this awkward bit of code is the way it is.
Meanwhile he thinks he's achieved something.
Yeah, honestly if I notice something has AI in it, I don’t use it anymore. Open source projects with a CLAUDE.md or whatever in them? No, thanks.
The amount of assumptions they make are really one big issue what makes them suck so bad. In the end you just have more work. Instead of getting done 80% of the work in 20% of the time, now you get 30% of the work done in 1% of the time, but good luck getting the remaining stuff done at all.