Vibe coding and agentic engineering are getting closer than I'd like • Hacker News Board

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

#801

Post by parliament32 » Thu, May 07, 2026, 1:44 PM UTC

pllbnk wrote: post #166

QuantumNomad_ wrote: post #7

People in the future are going to wonder what the hell we were thinking, when 30 years down the line everything is a hot mess of billions of lines of code generated by LLMs that no human has read almost any of it and is no longer possible for anyone to maintain neither with nor without LLMs. And the LLM generated garbage will have drowned out all of the good quality code that ever existed and no one will be able to f…

I think it’s a mistake to think that we will be blindly going in this direction for many years and then suddenly collectively wake up and realize what have we done. It’s a great filter and a great opportunity. If LLMs stop improving at the pace of the last few years (I believe they already are slowing down) then they will still manage to crank out billions lines of code which they themselves won’t be able to grep and…

> I believe they already are slowing down

They certainly have. The only impactful improvement in the last year is "just run it in a loop until it gets it right" lmao

Which, of course, only works as long as the costs are subsidized by the companies vying for market share.

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

#802

Post by dpoloncsak » Thu, May 07, 2026, 1:54 PM UTC

u8 wrote: post #440

The disconnect for AI is that it is a jagged frontier and it only really shines when one of its jagged frontiers extends counter to one of your valleys. If you've been writing Perl for 30 years, you might not want to learn JavaScript just to make a little fun idea in your head to show your wife. Vibe code that shit man. Who cares? Your wife does not care about LOC or those internal design decisions you made. If you'r…

Just here to say I love the line 'A hammer is a really great tool that has thousands of purpose-designed uses. I still prefer my key to get into my car.'

Been saying the 'Hammer is a great tool but you need to know when to use it, just like AI.' to coworkers, and i'm ̶s̶t̶e̶a̶l̶i̶n̶g̶ borrowing your quote instead, now

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

#803

Post by sanderjd » Thu, May 07, 2026, 2:02 PM UTC

LtWorf wrote: post #626

sanderjd wrote: post #348

Earlier quoted context omitted.

Aren't they more likely to leave?

Depends. If they have a good salary, nice coworkers, WFH. If they manage to tolerate having to produce crap they might stick around if other factors are above average. For someone with 3-4 kids who lives far from the city, WFH and time flexibility can be important motivators.

Yep!

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

#804

Post by gchamonlive » Thu, May 07, 2026, 2:03 PM UTC

latexr wrote: post #780

gchamonlive wrote: post #768

Earlier quoted context omitted.

Fair enough. It's always tricky to generalize like this, so I wont defend that position. However, for those who know, I don't think this is blaming the victim. I think victim blaming is a form of debate simplification in this case, just like "this is life" or "shit happens". Sure there are billions of dollars invested in attention stealing mechanisms, just as there are billions of dollars invested in gambling sites,…

> gambling sites, in alcohol, tobacco and highly processed foods, or in the scamming industry Those are great examples because they show that leaving it all up to the individual is not enough. All of those are regulated by the state because we as a society recognised they were doing their damnest to screw everyone else for their own gain. Social media is going the same route, with several countries already introducin…

Exactly, but I still think those are two slightly different conversations. If we are talking about harmful habits at a more general level, I'll defend that we need to be very restrictive in those examples. Online gambling, alcohol use and such shouldn't be allowed to advertise, it should pay almost prohibitively expensive taxes etc...

But if we are talking about the individual, the one inserted in the society, which is temporally bound, the conversation changes. We have to admit that it isn't enough to wait for laws and culture to change in order for the individual to be able to protect him/herself. To be a functional adult is to recognize what's around us that is harmful and do our best to protect ourselves. This is why if people recognize the harm social media is doing to their attention and to their ability to be bored they only have themselves to blame if you don't take action, because only blaming the multi-billion dollar industry for the habits they exploit won't do much for the individual.

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

#805

Post by IshKebab » Thu, May 07, 2026, 2:06 PM UTC

hnuser123456 wrote: post #399

jwpapi wrote: post #398

Earlier quoted context omitted.

I don’t want every verb implemented, I also dont want an IETF standard. I want as little as possible, so I have to worry about as little as possible in the future. Use-cases differ, you described a complete REST API, which can be as much of a problem as a too little.

I see you haven't encountered an API where a GET command can modify the database.

I have not either. What's your point? AI isn't perfect.

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

#806

Post by sanderjd » Thu, May 07, 2026, 2:09 PM UTC

skydhash wrote: post #575

sanderjd wrote: post #342

Earlier quoted context omitted.

This is true. But I find AI tools to be a huge help for all of this. Not to do any of it faster , but to remove a bunch of the tedium from the process of testing ideas and iterating on them. Instead of "I wonder if the problem is..." requiring half an hour of research, now I can do an initial check of that theory in less than a minute, and then dig further, or move onto the next one. Or say I estimate it's gonna take…

Have you ever wonder how people do it without it being a tedium for them? For things that have a visual elements like UI and UX, you can start with sketches (analog or digital) and eliminate the bad ideas, refine the good ones with higher quality rendering. Then choose one concept and inplement it. By that time, the code is trivial. What I found with LLM usage is that people will settle on the first one, declaring it…

I've been doing this for a couple decades. I don't wonder how people did it before AI, I did it for years and years before any of this existed...

> What I found with LLM usage is that people will settle on the first one, declaring it good enough, and not exploring further (because that is tedious for them).

I don't relate to this at all. It's so much easier (and less tedious) to experiment and iterate now. I see people doing a lot more of it, not less.

AI tools are also excellent aids to all the other types of problems you elucidated. You're doing theorycraft, and I might even agree with you if I just sat down and theorycrafted out how I thought this would work for each type of problem as you're doing here. (Indeed, you can probably find HN comments I made in 2022 and 2023 that say very similar things as you're saying!)

But in practice, I find all your theories here about why AI tools are not useful in this or that case to just be totally wrong.

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

#807

Post by cableshaft » Thu, May 07, 2026, 2:09 PM UTC

strken wrote: post #799

Kiro wrote: post #653

Earlier quoted context omitted.

My experience is the opposite: AI takes too many edge cases into account and guard against even the most unlikely thing. The upside is that it often handles edge cases that I either didn't think about or was too lazy to implement. I can with full confidence say that the code AI writes is more robust and safe than if I would have done it myself. The code definitely becomes more bloated though.

My experience has been that it wraps all the obvious things, and even some obscure things, in error handling. In this sense it is safer. It also fails to write abstractions unless they're carbon copies of a well established pattern, and when abstractions already exist, it needs babysitting to ensure it will use them appropriately. It won't introspect about its current direction unless forced to by the user or by an e…

I've definitely had a lot of these same experiences (in fact I've been fighting it on one particular issue the past couple of days and I'm pretty much just giving up and going back to solving it manually now).

But it still seems to get it right (or at least close enough to right that I keep using it) more often than it gets into these traps.

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

#808

Post by sanderjd » Thu, May 07, 2026, 2:10 PM UTC

andai wrote: post #719

sanderjd wrote: post #337

Earlier quoted context omitted.

Yep, validation is key. The smartest thing I've heard on this, which has reoriented how I think about this is that the objective function of a piece of software is now more important to get right than the implementation.

Turns out what was being rewarded all along is "the code looks all right" and "it looks like it works".

No, what is rewarded is "the code has been shown to conform to the given objective function" and especially "that objective function is a good representation of what we are trying to accomplish with this code".

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

#809

Post by 0gs » Thu, May 07, 2026, 2:13 PM UTC

simonw wrote: post #776

0gs wrote: post #742

Earlier quoted context omitted.

https://x.com/karpathy/status/2019137879310836075

Yeah, Andrej thinks "agentic engineering" is a good candidate too. Note that he's not claiming to have coined it there: > Many people have tried to come up with a better name for this to differentiate it from vibe coding, personally my current favorite "agentic engineering" Andrej posted that on 4th of February. I first saw the term "agentic engineering" used by OpenClaw creator Peter Steinberger in October 2025 (a m…

aha! got it

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

#810

Post by theshrike79 » Thu, May 07, 2026, 2:22 PM UTC

eloisius wrote: post #706

vlunkr wrote: post #520

Earlier quoted context omitted.

It’s simple but contains all the necessary info. You can say “build an endpoint to get user data” and it will absolutely do something, but it might be stupid, and when you compound 1000 stupid prompts like that you get spaghetti.

It doesn’t contain any information at all about the structure of the JSON output. Is this a greenfield endpoint and anything will work is does it need to conform to an existing API? What about response codes for different failure modes? What about logging? Your comment exemplifies what a lot of people complain about vibe coding: it works great for greenfielding CRUD apps, but it’s a bitch to use in a real code base.

If it's not a greenfield project, the Agent will go and look at the other endpoints and mimic the style as much as possible. Just like a human would.

"But we have documentati..." then give the Agent access to the same docs as humans and it'll use them.