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

741–750 of 958 posts

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

#741

Post by coldtea »

rotis wrote: post #722
coldtea wrote: post #689

Earlier quoted context omitted.

>They both stem from the same LLM root and positioning them as significantly different is weird and unconvincing to me. It's the difference between caring and not caring.

Caring about what? I could slap an application and say I vibe coded it or I could equally claim I agentically engineered it. No one could tell the difference(if there is any) without seeing the code. The only thing you could say I used an LLM. And that is what is happening. Most of the code that is "engineered" we don't get to see. So who know what is really going on there and what is the actual result?

>Caring about what? I could slap an application and say I vibe coded it or I could equally claim I agentically engineered it. No one could tell the difference(if there is any) without seeing the code.

Caring about the result, whether one "can tell the difference" or not.

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

#742

Post by 0gs »

simonw wrote: post #220
0gs wrote: post #181

huh. i honestly never thought they were all that different. didn't the same guy coin them both to refer to the same thing?

Not at all. Andrej Karpathy coined vibe coding as: https://twitter.com/karpathy/status/1886192184808149383 > where you fully give in to the vibes, embrace exponentials, and forget that the code even exists [...] It's not too bad for throwaway weekend projects, but still quite amusing. I'm building a project or webapp, but it's not really coding - I just see stuff, say stuff, run stuff, and copy paste stuff, and it mo…

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

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

#744

Post by Kiro »

stephenr wrote: post #621
allthetime wrote: post #490

Earlier quoted context omitted.

AI is just revealing the two types of people in this line of work. Those who don’t actually like software and just do it because it’s lucrative, and the actual nerds who care.

I've posited for a while now that the people who find spicy autocomplete to be exciting are the people who can't really do what it does. I played with Image Playground last year some time. It was really fun. You know why? I can't draw, and I can't paint, to save my life. It's letting me do something I can't do well/at all on my own. Using an LLM to do something I can do, with the caveat that it's pretty mediocre at t…

"I've posited for a while now" and you post the most lukewarm and outdated take like it's an enlightenment. I've been coding for 20 years and can very well do everything the AI does, and so can all devs I know. We use it because it amplifies us, not because we couldn't otherwise. You've chosen a very ridiculous hill to die on.

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

#745

Post by michaelcampbell »

allthetime wrote: post #490
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…

AI is just revealing the two types of people in this line of work. Those who don’t actually like software and just do it because it’s lucrative, and the actual nerds who care.

I think there's a continuum here, too. I've heard it said, in jest, mind, that LLM's square the dev. It turns a 1.5x dev into a 2.25x dev, but it also turns a 0.75x dev into a ~0.56x dev.

I think the exponent of 2 is probably too high, but it's not a bad approximation of a very messy reality.

There is also the division of people who value the thing being produced vs. valuing the actual production of that thing, whether or not its used. I don't see one side here being "right", necessarily, but when a company is behind it one is certainly more valued, and I think not incorrectly.

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

#746

Post by iugtmkbdfil834 »

Turskarama wrote: post #529
ditchfieldcaleb wrote: post #495

Earlier quoted context omitted.

I agree with you on everything you said here except: > when you know how the thing works and have that mental context, you will always be faster than an AI That's just plain false, honestly. No one can type at the speed AI can code, even factoring in the time you need to spend to properly write out the spec & design rules the AI needs to follow when implementing your app/feature/whatever. And that gap will only incre…

In my experience AI can write _something_ from scratch, but often edge cases won't be handled until I go through and read the results or test it. Usually when I'm writing by hand I will naturally find the majority of edge cases as I go. By the time I've read through the results and fixed said edge cases, I usually would have been faster just doing it myself.

This has been my experience thus far. Yes, a complete prototype can be made, but.. you don't really know until you read the code and test it. Just yesterday, small things came up in terms of Qt screen focus that wouldn't have come up otherwise save for initial testing.

I think, and I recognize it is mostly against the 'agentic' push, I will stick with slow iteration.

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

#747

Post by stephenr »

MrScruff wrote: post #740
stephenr wrote: post #736

Earlier quoted context omitted.

There's a reason I call it spicy autocomplete.

Which is what?

.... that an IDE providing a suggestion about what comes next as you type is not new, and the entire basis of how an LLM works is "what word probably comes next".

I'd have thought someone who's so enamoured with the tech would have at least a basic understanding of how it works.

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

#749

Post by iugtmkbdfil834 »

sdevonoes wrote: post #631
eli wrote: post #514

Earlier quoted context omitted.

A much more charitable framing: people who enjoy the process vs people who enjoy the result. (Though, granted, the results are a lot better if you craft it by hand)

But business people always cared only about thr result. My PM (who speaks like a salesman) only cares about the results. My “head of” same. My ceo same. The only ones who ever cared about the process and quality were us the engineers… if we don’t have that care, well, to hell with everything

Assuming it is accurate, the logical conclusion is that the race is over. The management can get their $result and fast. Now, whether it is good or bad, is a separate story, and only time will tell whether they will be forced to learn anything. Right now, the expectation is to push for results and management seems to ascribe current set of failures to: people not embracing AI enough.

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

#750

Post by cpursley »

stephenr wrote: post #735
cpursley wrote: post #720

Earlier quoted context omitted.

While you are dying on a hill, with the help of LLMs, I'm shipping quality software and features to my customers at a pace I haven't been able to before. And no, not some nextjs slop. If you are letting your LLM look at StackOverflow, you are doing it wrong - it needs to be grounding in your stacks official docs and any other style/rules you prefer wired with other tooling like linting/formatting, duplication checkin…

> If you are letting your LLM look at StackOverflow, you are doing it wrong So you've evaluated all the sources that the model was trained on initially have you? How long did that take you? > I'm shipping quality software and features to my customers at a pace I haven't been able to before. I'm sorry are you agreeing with me or not? It sounds like you're agreeing with me.

I’m just saying that you can’t just let it rip based on its training alone, it needs to be grounded and harnessed in stack specific tooling.
Post reply on HN