Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Vibe coding and agentic engineering are getting closer than I'd like

simonwillison.net

Post reply on HN
Print view View original

381–390 of 958 posts

Re: Vibe coding and agentic engineering are getting closer than I'd like

#381

Post by jwpapi »

devin wrote: post #39

> If you can go from producing 200 lines of code a day to 2,000 lines of code a day, what else breaks? The entire software development lifecycle was, it turns out, designed around the idea that it takes a day to produce a few hundred lines of code. And now it doesn’t. It is so embarrassing that LOC is being used as a metric for engineering output.

I deleted 75000 lines of code of my codebase in the last 2 months and that was tremendously more useful to by business than the 75000 AI has written the 2 months before...

Re: Vibe coding and agentic engineering are getting closer than I'd like

#382

Post by tempaccount5050 »

rvz wrote: post #312
keeda wrote: post #246

I think all coding will become vibe coding, but it will be no less an engineering discipline. Note: I still review pretty much every line of code that I own, regardless of who generates it, and I see the problems with agents very clearly... but I can also see the trends. My take: Instead of crafting code, engineering will shift to crafting bespoke, comprehensive validation mechanisms for the results of the agents' wo…

This is complete insanity for anyone that actually works on production-grade, hundred billion dollar systems that are critical to the function of the global economy. Other than for your own pet projects, almost all of what you said has no place for "vibe engineering" / or "vibe coding" on serious software engineering products that are needed in life and death situations.

Almost no one works on stuff like that, so congrats on finding a corner case I guess.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#383

Post by transcriptase »

Aurornis wrote: post #202
peterbell_nyc wrote: post #179

For me the distinction is the quality and rigor of your pipeline. Vibe coding: one shot or few shot, smoke test the output, use it until it breaks (or doesn't). Ideal for lightweight PoC and low stakes individual, family or small team apps. Agentic engineering: - You care about a larger subset of concerns such as functional correctness, performance, infrastructure, resilience/availability, scalability and maintainabi…

If your slider only goes between vibe coding or agentic engineering you're missing an entire range of engineering where the human is more involved. I've been using Opus, GPT-5.5, and some lesser models on a daily basis, but not having them handle entire tasks for me. Even when I go to significant effort to define and refine specs, they still do a lot of dumb things that I wouldn't allow through human PR review. It wo…

Next time give it the context required for the task, eg an explanation of why you have those hand coded simplifications, and be amazed at how proper use of a tool works better than just assuming your drill knows what size bit to pick.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#384

Post by eddiewithzato »

turtlebits wrote: post #228

The scary part is that codebases are getting layers of AI complexity, that it's going to cost $$$ to have the latest model decipher and make changes as no human can understand the code anymore. Pretty soon there is no code reuse and we're burning money reinventing the wheel over and over.

The models today will happily slop over a single 1k loc react index component on a brand new project.

They really are bad for creating a healthy codebase

Re: Vibe coding and agentic engineering are getting closer than I'd like

#385

Post by jwpapi »

wg0 wrote: post #365

Here's for the AI supremacists: Let's assume AI is 10x perfect than humnas in accuracy and produces 10x less bugs and increases the speed by 1000x compared to a very capable software engineer. Now imagine this: A car travels at a road that has 10x more bumps but it is traveling 1000x slower pace so even though there are 10x bumps, your ride will feel less bumpy because you're encountering them at far lower pace. Now…

You are speaking out of my soul. Thank you. Great example. I have grinded AI extensively 14 hours a day on my own project for months. I’ve been using AI since GPT-2.

I maxxed out Claude Max $200 subscription and before I justified spending $100/day.

And it was worth it, but not because it wrote me so good code, but because I learnt the lessons of software engineering fast. I had the exact ride you are describing. My software was incredible broken.

Now I see all the cracks, lies and "barking the wrong tree" issues clearly.

NOW i treat it as an untrustworyth search engine for domains I’m behind at. I also use predict next edit and auto-complete, but I don’t let AI do any edit on my codebase anymore.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#386

Post by eddiewithzato »

kushalpatil07 wrote: post #149

Every time I do deep work, and think of solutions to a complex problem. I always have the opportunity to ask claude to implement a sub-par AI slop solution. Do this enough times, and I will have forgotten how to think.

That’s why I like the term “mind virus” for AI. Humans always go for shortest path

Re: Vibe coding and agentic engineering are getting closer than I'd like

#387

Post by rgbrenner »

jmalicki wrote: post #225
rgbrenner wrote: post #218

Earlier quoted context omitted.

300k-400k isn’t the current limit if you create modules and/or organize the code reasonably.. for the same reason we do this for humans: it allows us to interact with a component without loading the internals into out context. you can also execute larger tasks than this using subagents to divide the work so each segment doesn’t exceed the usable context window. i regular execute tasks that require hundreds of subagen…

That makes it not a context window. How to organize code like you said, and how agents interact with it, to keep the actual context window small is the fundamental challenge.

ok "series of context windows spread across many agents".. sure much clearer.

Doesn't change my point: the amount of code the agent can operate on is very large, if not unlimited, as long as you put even a little bit of thought into structuring things so it can be divided along a boundary.

If you let the codebase degrade into spaghetti, then the LLM is going to have the same problem any engineer would have with that. The rules for good code didn't disappear.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#388

Post by gck1 »

deadbabe wrote: post #196
dataviz1000 wrote: post #52

Have you noticed that the coding agents get really close to the solution on the first one shot and then require tons of work to get that last 10% or 5%? If we shift the paradigm of how we approach a coding problem, the coding agents can close that gap. Ten years ago every 10 or 15 minutes I would stop coding and start refactoring, testing, and analyzing making sure everything is perfect before proceeding because a bu…

That will not work as cleanly as you described once a lot of code has been committed to the code base. You cannot just blow away an entire working code base and start over just because an LLM is struggling to make a feature work with existing architecture.

This happened on every single greeenfield project that I've started with AI, no matter how rigorous process I've had defined.

And it's not just easier because it's cheap, it's easier because you're not emotionally attached to that code. Just let it produce slop, log what worked, what didn't, nuke the project and start over.

It just gets incredibly boring.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#389

Post by pydry »

layoric wrote: post #374
etothet wrote: post #33

Vibe Coding (and LLMs) did not create undisciplined engineering organizations or engineers. They exposed and accelerated them. Plenty of engineers have loose (or no!) standards and practices over how they write coee. Similarly, plenty of engineering teams have weak and loose standards over how code gets pushed to production. This concept isn't new, it's just a lot easier for individuals and teams who have never reall…

This is very true, I've found these tools that I am highly encouraged to use very hit and miss, which they are by nature. After using Matt Pocock's skills, I've come around to the idea that LLM's main utility is to act as the ultimate rubber ducky. The `grill-me` feature is honestly the most useful, not for guiding the follow up writing of code, but to make me write down and explore the idea I have more quickly. It's…

The first time i used LLMs it was to try and refactor behind a solid body of tests i trusted.

I figure if it cant code when it has all of the necessary context available and when obscure failures are easily detected then why would i trust it when building features and fixing bugs?

It never did get good enough at refactoring.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#390

Post by jwpapi »

_doctor_love wrote: post #256

Repeat after me: most software spends the majority of its lifetime in the maintenance phase. Repeat after me: it follows that most of the money the software makes occurs during the maintenance phase. Repeat after me: our industry still does not understand this after almost 100 years of being in existence. Alan Kay was 100% right when he said that the computer revolution hasn't occurred yet. For all of our current adv…

I hate code and I want as little of it as possible in my codebase.
Post reply on HN