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

761–770 of 958 posts

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

#761

Post by tim-projects »

> Here are some of my highlights, including my disturbing realization that vibe coding and agentic engineering have started to converge in my own work.

Nothing about this should be disturbing unless you want to dig your heels in, cross your arms and refuse to adapt.

AI is a massive opportunity. But if people focus on the issue of the 'change' they simply waste time they could (and should) be spending on integrating it correctly.

I believe that this form of resistance is far more stagnating and dangerous than any of the issues that come with the general onslaught of ai integration.

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

#762

Post by rickdeckard »

gchamonlive wrote: post #732
latexr wrote: post #707

Earlier quoted context omitted.

> Also, when did we stop liking to learn? I suspect it happened when we achieved a level of such constant stimulation (there is a pocket computer always on us with infinite effortless distraction) that we’re never bored and never engage the default mode network. https://en.wikipedia.org/wiki/Default_mode_network https://www.youtube.com/watch?v=orQKfIXMiA8 When you’re bored, your mind goes to places it wouldn’t otherw…

> it happened when we achieved a level of such constant stimulation (...) that we’re never bored and never engage the default mode network. I don't know... I don't disagree, but I think this has been repeated so much that I believe everyone, at least everyone that is actively participating in HN discussions is aware of this. So if we are aware of this and we consciously choose to keep engaging in dopaminergic activit…

> So if we are aware of this and we consciously choose to keep engaging in dopaminergic activities, [..] I think it starts to become a choice.

...or a subtle addiction that also creates the impression of productivity/progress/social interaction...

If so, then all applicable studies on addiction should be taken into consideration as well, but their context probably doesn't even begin to cover the size of the issue here.

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

#763

Post by orphea »

chickensong wrote: post #267
orphea wrote: post #130

Earlier quoted context omitted.

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?

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…

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 than I'd like

#764

Post by user34283 »

xantronix wrote: post #441
user34283 wrote: post #257

Earlier quoted context omitted.

In my opinion you are just wrong. It’s an absolute game changer, and it can now multiply your productivity fivefold if it’s a solo greenfield project. Maybe half a year ago it was as you said. You had to wait for the agent to finish, you had to review carefully, and often the result was not that great. You did not save a lot of time. Now I can spin up 3+ parallel conversations in Codex, each in a git worktree. My wor…

The thing is, I don't care any longer. I sincerely believe velocity without direction is not a good strategy for delivering quality in the long term. And that's the thing about it: How sustainable is this velocity, in terms of socioeconomic concerns, product strategy, and mental health?

Velocity without direction?

I‘m personally directing and QA testing every feature.

I don’t know how socioeconomic concerns, product strategy, and mental health are a concern for me here.

I‘m having a great time with my project and it’s been the most fun I‘ve had in many years of building.

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

#765

Post by lvales »

gchamonlive wrote: post #732
latexr wrote: post #707

Earlier quoted context omitted.

> Also, when did we stop liking to learn? I suspect it happened when we achieved a level of such constant stimulation (there is a pocket computer always on us with infinite effortless distraction) that we’re never bored and never engage the default mode network. https://en.wikipedia.org/wiki/Default_mode_network https://www.youtube.com/watch?v=orQKfIXMiA8 When you’re bored, your mind goes to places it wouldn’t otherw…

> it happened when we achieved a level of such constant stimulation (...) that we’re never bored and never engage the default mode network. I don't know... I don't disagree, but I think this has been repeated so much that I believe everyone, at least everyone that is actively participating in HN discussions is aware of this. So if we are aware of this and we consciously choose to keep engaging in dopaminergic activit…

Why don't addicts chose to stop with their addictive behaviour?

And this isn't an excuse btw, but if you want to understand why, this is a good place to start.

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

#766

Post by phpnode »

batshit_beaver wrote: post #463
phpnode wrote: post #439

Earlier quoted context omitted.

If it's genuinely the case that you can write code faster than you can prompt it into existence then you're not being ambitious enough with your coding agent. Ask it to do more. Tackle bigger problems.

1. It's unclear why creating more code faster is a good thing. Software engineering wisdom for decades has been that code is a cost, not a product. There are great reasons for that, which haven't changed with the appearance of LLMs. 2. There absolutely are cases where modifying code "manually" is unquestionably faster than prompting an LLM. There are trivial examples for this - eg only an insane person would ask an L…

1. More code faster is not the goal. More features / value faster is the goal. Obviously to get there you need to write more code, but it's not writing code for code's sake.

2. Yes, true, but the point is to move up the abstraction hierarchy, so instead of asking the LLM to rename a variable you describe the concrete business goal you're trying to achieve.

It is true that coding agents cannot build fully complete stable systems completely unguided yet. That's why we still have jobs. But it's wrong to suggest that they don't deliver value or that they're destined to produce trash every time. It is a matter of oversight and guidance and setting your codebase up for success. That does require work, but it is not impossible, just a different skillset from the ones we've been used to.

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

#767

Post by MrScruff »

eli wrote: post #514
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.

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)

The results being a lot better crafted by hand I would agree with, if one removes any notion of a time constraint. Sometimes the comparison point is between the LLM authored software or nothing at all.

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

#768

Post by gchamonlive »

latexr wrote: post #759
gchamonlive wrote: post #732

Earlier quoted context omitted.

> it happened when we achieved a level of such constant stimulation (...) that we’re never bored and never engage the default mode network. I don't know... I don't disagree, but I think this has been repeated so much that I believe everyone, at least everyone that is actively participating in HN discussions is aware of this. So if we are aware of this and we consciously choose to keep engaging in dopaminergic activit…

> I think this has been repeated so much that I believe everyone, at least everyone that is actively participating in HN discussions is aware of this. I promise you that is incorrect. People who actively participate on HN are a group more diverse than is often given credit, and I strongly believe there is nothing “everyone knows” here. https://xkcd.com/1053/ Just nine days ago, someone on HN was vaguely aware of the…

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, in alcohol, tobacco and highly processed foods, or in the scamming industry. However, while we need as a society need to discuss mechanisms to control and maybe prohibit these practices, a functional adult human beings should be expected to create safeguards to protect themselves against this. Maybe the phrasing wasn't the best, but my point stands. Once you are aware of things that aren't good for you, you can really only count on yourself to do something about it.

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

#769

Post by bnug »

smugglerFlynn wrote: post #630
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.

You are probably talking about people who just crunch out some half baked solutions for the sake of getting somewhere. But there are other nerds who care, just not about the code quality, but about conversion, testing out business ideas quickly, getting to know their customers better. There are nerds who care about business strategy. There are nerds who care about accounting principles and clean financial reporting.…

This resonates with me. I'm a Mechanical Engineer who loves the process of coding. I did take an intro to business class in undergraduate though, and my professor said one thing that has stuck with me for 30+ years - 'The fundamental goal of a business is to make profit now and in the future'. Vibe coded slop might get some traction and make money now, but high quality code will reduce technical debt and allow it to be made in the future. So, in some ways, both camps are right. The PM/Manager/VP want to make money now, but if they completely disregard the nerdy engineer, they will sabotage their future.

I see a disconnect between these two camps that will probably cause a lot of chaos in the near future. Those that figure it out will thrive.

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

#770

Post by latexr »

therealpygon wrote: post #757
gchamonlive wrote: post #732

Earlier quoted context omitted.

> it happened when we achieved a level of such constant stimulation (...) that we’re never bored and never engage the default mode network. I don't know... I don't disagree, but I think this has been repeated so much that I believe everyone, at least everyone that is actively participating in HN discussions is aware of this. So if we are aware of this and we consciously choose to keep engaging in dopaminergic activit…

Or at least, aware that this argument continues to be made with tenuous evidence and anecdotes. And yet, people are being more productive (actually productive) with AI. Release schedules are increasing, bugs are getting fixed faster, security issues identified and patched sooner, so on and so forth. I’m not denying (at all) that unused skills languish. I take issue with AI being characterized as a magic eraser that m…

> this argument continues to be made with tenuous evidence and anecdotes.

The linked Wikipedia page has plenty of evidence and studies and you can find plenty more with a basic web search. This is not something someone just made up; if you don’t know there are a multitude of studies on the harms of social media, you haven’t looked at all. Which is fine, it’s our prerogative to not search for information, but don’t turn around and say it doesn’t exist or is anecdotal.

> And yet, people are being more productive (actually productive) with AI.

You said, ironically without providing evidence, in the same paragraph that you complained about evidence not being provided for something else which has plenty of it. Furthermore, there are several studies suggesting AI may in fact decrease productivity, but I’m not going to link to those because the more important point is AI has nothing to do with the conversation. The original poster mentioned AI, but this branched thread is exclusively about the “liking to learn” part.

Post reply on HN