News for hackers. Stuff that matters.
Re:Vibe coding and agentic engineering are getting closer th... by ativzzz on Wednesday May 06, 2026 @12:02PM (#48037763)
By then, the fix will be easy. Fire up the latest LLM, point it at your codebase and tell it "rewrite this from scratch. do it well. fix the architecture mistakes"
Re:Vibe coding and agentic engineering are getting closer th... by hasbot on Wednesday May 06, 2026 @12:16PM (#48037966)
We can do this today too (but definitely hopefully future LLMs make better architectural decisions). With Claude, I've been working on an application for the last 2 months. I didn't have a great vision of what I wanted when I started but I didn't want that to slow me down. The architecture is terrible - Claude separated some functionality into different classes but did a bad job at it and created a big ball of mud. Now that I finally have my vision locked down and implemented (albeit poorly), it'd be a great time to throw it away and start over. It'd be interesting to see the result and see how long it takes.
Re:Vibe coding and agentic engineering are getting closer th... by ativzzz on Wednesday May 06, 2026 @02:00PM (#48039378)
Just have claude (or gpt maybe) do an architecture review and request a multi-phase refactoring plan. This is probably better to do incrementally as you notice the balls of mud forming but it might not be too late. Either way, if it does something you don't like, `git checkout` and start over
Re:Vibe coding and agentic engineering are getting closer th... by bulbar on Wednesday May 06, 2026 @12:04PM (#48037800)
Will work just as good as today or 20 years ago.
Re:Vibe coding and agentic engineering are getting closer th... by cortesoft on Wednesday May 06, 2026 @12:05PM (#48037817)
Are you suggesting AI coding was as good 20 years ago as it is today?
Re:Vibe coding and agentic engineering are getting closer th... by hrldcpr on Wednesday May 06, 2026 @12:15PM (#48037964)
I think they're being sarcastic, saying that rewrites from scratch have rarely worked well (whether done by AI or humans).
Re:Vibe coding and agentic engineering are getting closer th... by bulbar on Thursday May 07, 2026 @12:16AM (#48045323)
Exactly. Sorry for not being explicit about it. I thought it was clear enough, because 'this code is crap, let's just rewrite the whole thing, doesn't look to hard' is kind of famous for being a bad idea most of the time since forever.
Re:Vibe coding and agentic engineering are getting closer th... by vrganj on Wednesday May 06, 2026 @12:31PM (#48038172)
It sure wrote less crappy code.
Re:Vibe coding and agentic engineering are getting closer th... by fnoef on Wednesday May 06, 2026 @12:03PM (#48037781)
"Make sure to double check everything, and MAKE NO MISTAKES!!!"
Re:Vibe coding and agentic engineering are getting closer th... by bhagyeshsp on Wednesday May 06, 2026 @12:11PM (#48037905)
"YOU'RE A SENIOR SOFTWARE ENGINEER!!!"
Re:Vibe coding and agentic engineering are getting closer th... by ryandrake on Wednesday May 06, 2026 @01:12PM (#48038725)
"Ultrathink!"
Re:Vibe coding and agentic engineering are getting closer th... by unfunco on Wednesday May 06, 2026 @12:21PM (#48038040)
Don't hallucinate!
Re:Vibe coding and agentic engineering are getting closer th... by kurthr on Wednesday May 06, 2026 @12:03PM (#48037779)
"Write me a really cool game, that will make me lots of money, fast!"
Re:Vibe coding and agentic engineering are getting closer th... by estimator7292 on Wednesday May 06, 2026 @12:18PM (#48037997)
I see your point, however: EA sports has been doing this for literally the entire lifetime of gaming as an industry
Re:Vibe coding and agentic engineering are getting closer th... by DonHopkins on Wednesday May 06, 2026 @12:37PM (#48038256)
Electronic Sharts slogans and franchises:

"Shit's in the Game!"

"Chunder Everything"

"Maddening NFL 26"

"FIFiAsco 26"

"UFC 26 (Un Finished Code)"

"The Shits 4"

"Battlefailed"

"Need for Greed"

Re:Vibe coding and agentic engineering are getting closer th... by KumaBear on Wednesday May 06, 2026 @12:06PM (#48037826)
Make me a 1hr episode of my favorite book. Make it as lore accurate as possible. Plot out the script for the next 100 episodes.
Re:Vibe coding and agentic engineering are getting closer th... by faizshah on Wednesday May 06, 2026 @12:40PM (#48038290)
It won't be an LLM that does it, the entire feature of an LLM is it produces generalizable reasonably "correct" text in response to a context.

The system that makes it have an opinion about good vs bad architecture or engineering sensibilities will be something on top of the transformer and probably something more deterministic than a prompt.

Re:Vibe coding and agentic engineering are getting closer th... by orphea on Wednesday May 06, 2026 @12:50PM (#48038429)
Do you think new LLMs are going to write better and better code? When all they are going to have is the slop generated by previous, worse models?
Re:Vibe coding and agentic engineering are getting closer th... by chickensong on Wednesday May 06, 2026 @03:55PM (#48040899)
Yes. The models may have started from indiscriminate scraping, but people are undoubtedly working on refining the training data. Combined with the overall model capabilities, I suspect code quality will continue to go up.

What you're suggesting is a negative flywheel where quality spirals down, but I'm hoping it becomes a positive loop and the quality floor goes up. We had plenty of slop before LLMs, and not all LLM output is slop. Time will tell, but I think LLMs will continue to improve their coding abilities and push overall quality higher.

Re:Vibe coding and agentic engineering are getting closer th... by orphea on Thursday May 07, 2026 @08:48AM (#48048781)
Let's agree to disagree.

What I see is that while LLMs can do real tasks, they often produce overengineered unmaintainable slop (plenty of examples where code can be reduced 10x to do the same). I hope this is not a base to continue training LLMs on.

Re:Vibe coding and agentic engineering are getting closer th... by chickensong on Friday May 08, 2026 @04:34PM (#48068439)
I don't disagree that there's a lot of slop getting churned out, you're not wrong there. I just have hopes that we'll course-correct after some initial adjustment period, but I have no idea how long that might be (guessing several years).

I don't know how long LLMs will hold their position, but in my mind, it makes sense that computers will eventually be the best programmers. Humans will still guide, but rarely write or even read code. I might be dead by then, but that's my prediction for the future.

Re:Vibe coding and agentic engineering are getting closer th... by jcalx on Wednesday May 06, 2026 @01:04PM (#48038639)
There is definitely going to be some Wirth's law-like [0] effect about the asymmetry of software complexity outpacing LLMs' abilities to untangle said software. Claude 9.2 Optimus Prime might be able to wrangle 1M LoC, but somehow YC 2035 will have some Series A startup with 1B+ LoC in prod — we'll always have software companies teetering on the very edge of unmaintainability.

[0] https://en.wikipedia.org/wiki/Wirth%27s_law

Re:Vibe coding and agentic engineering are getting closer th... by AlotOfReading on Wednesday May 06, 2026 @03:50PM (#48040842)
It's the Peter principle for computers. Codebases expand to the limits of the organization's ability to manage them. If you make one person use ed to write code for a bare metal environment, you'll get a comparatively small, laser-focused codebase. If you task a hundred modern developers to solve the same problem, you'll get a Linux box device running a million lines of JavaScript.

Same thing happens in other fields. A rich country and a poor country might build equivalent roads, but they won't pay the same price for them.