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

811–820 of 958 posts

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

#811

Post by gchamonlive »

kiba wrote: post #787
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,…

We do all what we can as individuals, but it's not enough. The obesity crisis is going unabated except GLP-1 drugs to clean up the mess.

we can also apply regulations but they are also not enough, otherwise people wouldn't OD on controlled substances. At one point the individual needs to start taking responsibility for their actions.

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

#812

Post by dpoloncsak »

0xpgm wrote: post #643
sdevonoes wrote: post #628

Earlier quoted context omitted.

Agree except for this part > If you're at work and they really care about getting something out of the door, do whatever you think is best. If you don’t mind being jobless, sure do whatever you think is best. Not all of us can simply switch companies easily. Folks need to realise that AI in a company setting works for the benefit of the company, not for the individual.

But do companies really know how to use AI? I think most of it is experimentation - throwing things to the wall and seeing what sticks. It's the practitioner who eventually figures out what really works. I see this the same way the agile movement emerged. It was initiated by people who were hands-on programmers and showed enough benefit at minimizing software waste before it took a life of its own and started getting…

> I think most of it is experimentation - throwing things to the wall and seeing what sticks.

This is true in macro, but I think we're specifically referring to LLM-generated /assisted code (vibe-coding). 'Getting something out the door' is not an necessarily in reference to an AI-infused product, just new code written by AI

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

#813

Post by cableshaft »

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've been a software nerd all my life (and there was a time where I worked 60 hours a week at a startup working hard to make mobile games), but there's just been so much extra crap associated with it (especially web development, and especially corporate web development, what currently pays my bills) over the years that it's worn me down and I'm happy to let A.I. churn through the hard or frustrating or endless amounts of boilerplate bits, and let me focus on other things.

Part of me still wishes we were making websites with just HTML, CSS, PHP, and a little Javascript here and there (before AJAX). I'm still not convinced all this extra SPA functionality is really needed for most corporate website needs (something like Google maps or real-time chatting, sure, other things not so much), but I do it because they insist.

I also really like game design, and I had a fairly simple game idea that I prototyped a physical version of and playtested a few times and thought, 'yeah, this is pretty fun'.

But I don't have the energy to code it in my spare time anymore. Was curious how close to a working MVP it could get with me writing up a specification yesterday with the help of ChatGPT (after I brainstormed a few aspects of the design), and dumped that spec into a new repo on GitHub, and about 20 minutes later, it had a fully functional game that worked exactly like my physical prototype.

It was still missing other features, like tutorials and stats and sharing abilities and the like, and I'd like to adjust the presentation some, and the computer opponent A.I. was a bit weak and could have been stronger, but it was fully functional and even looked pretty good, kind of like a Wordle presentation, which was what I was going for anyway.

Something that would have taken me probably 40 hours of dedicated work at least to get everything working and looking as nice as it did.

So yeah, it's kind of like 'well what's the point of me manually coding this anymore'.

What I really like about software was solving puzzles, but now I can focus on the more interesting puzzle of what makes a good game design and 'how best to present this to players' instead of how to get five different libraries and/or APIs to play nice together and learn how it all works.

If coding hadn't become some labyrinthian monstrosity and got out of your way when coding, I probably would want to keep coding more.

Some languages/frameworks get close to that, Lua/Love2D is pretty smooth except when it gets to you wanting to distribute it on platforms other than PC/Mac/Linux, or integrate with external libraries, or for me work with shaders since I'm still pretty weak with shaders.

But even then, it was hard to deny how much faster A.I. could code a feature and I've started getting more hands-off there as well.

That being said, work has gotten less fulfilling, since I'm not doing any actual design work really, just implementing features and making them look according to Figma specifications or fixing bugs, so that's gotten less fulfilling without the busywork of solving coding puzzles (now it's 'how to say this to the A.I. to get it to fix this right, which is still a puzzle but a much weaker one). I'm starting to get tempted to make a go of starting my own business so I can have more autonomy again.

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

#814

Post by gchamonlive »

lvales wrote: post #765
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…

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.

If they don't want to, go for it. I'm all up for the freedom to choose your poison, as long as it doesn't restrict someone else's freedom of choice (like jumping off a building and landing on someone, killing you both). What I'm saying is that if you recognize booze is bad for you, but you don't do anything about it because heck there is a billion dollar industry behind it, everyone drinks and you'll die anyway, IDK it seems to me like it's mostly your fault, because you'd know where yo get help if you really wanted to. That is, of course, assuming where you live has good policies for treating people with such diseases.

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

#815

Post by sanderjd »

vultour wrote: post #667
sanderjd wrote: post #429

Earlier quoted context omitted.

I genuinely don't understand what you're talking about with this comment. Learn how to do what things properly? I've been writing software for two decades... I'm not primarily in a learning phase, I'm in a doing phase. I'll take advantage of tools that save me time and energy in my work (for the right price). Why wouldn't I? What do you mean by "barely working"? I can now put more iterations into getting things worki…

There is simply no chance that LLMs are saving you 30 hours of work a week, especially if they're doing something where you'd have to do the research yourself. Either you're just simply wrong, or you went from understanding the code you were writing to skimming whatever the magic box spits out and either merging it outright or pawning off the effort of review on someone else.

That's why I gave a range. I didn't say it is saving me 30 hours every week, I said 10 to 30 hours a week. So 30 is the max of the range, and I'd say the distribution is pretty heavily left-skewed. It really depends on what I'm doing, but I do think there are weeks where it has save me 75% of the time I would have otherwise spent. I think there are two kinds of weeks where this is the case:

1. A week where I would have otherwise actually spent the majority of my time writing out and doing a ton of refactoring of a lot of implementation code. This is very rare for me, but it does exist. I can remember how it could actually take me a whole week to just "code up" meaningfully sized prototypes or greenfield implementations of some unambiguous thing. Truly, now, for that kind of work, claude code can save me full days of mechanical work.

2. A week where there is something very subtle going on that I have to figure out, probably having to do with some component or system I'm not very familiar with yet. Having an AI tool as a rubber ducky, or like a supercharged stackoverflow, can save me days of reading, debugging, working on minimal repros, etc.

Again, I'm not saying this is the common case at all. And estimating this kind of thing is always wildly inaccurate, so sure, take it with a grain of salt. But I know that a few times now, doing estimates based on my past experience, I've said "that will take me a week" (in case #1) or "gosh, I dunno, that's a tricky one, that might take me a week to figure out" (in case #2), and instead it only took me a day.

But honestly I think people focus too much on the high end of this range. The more valuable thing to me is the large number of weeks where it saves me that 10 to 15 hours, where I can then use that time to research new things, try more ideas, say "yes" to more things, or just not spend that time working.

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

#816

Post by dpoloncsak »

andai wrote: post #333
truncate wrote: post #309

Earlier quoted context omitted.

>> Bad engineers continue being bad, good engineers continue being good. I don't know if good engineers can necessarily continue to be good. There is limit to how much careful consideration one can give if everything is on an accelerated timeline. Regardless good or not, there is limit on how much influence you have on setting those timelines. The whole playing field is changing.

An old comic I like: - I've taken a controversial new pill that accelerates my brain. -- So you're smart now? - I'm stupid faster! That being said, being stupid faster can work if validation is cheap (and exists in the first place). Turns out "eh close enough" for AGI is just stupidity in an "until done" loop. (Technically referred to as Ralphing.)

I say this usually about self-driving cars, but the phrase fits here too. "It doesn't need to be perfect. It just needs to be better than the average human, and humans suck at driving."

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

#817

Post by WhereIsTheTruth »

Keyboards and mouse have always been a bottleneck, the average person only types around 50 words per minute

If you want to build a project, you can never shorten the actual time it takes to write it out, you are stuck at that 50 words per minute limit

LLMs, agents, call it how you want, they allow us to remove that bottleneck

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

#818

Post by sanderjd »

skydhash wrote: post #555
sanderjd wrote: post #429

Earlier quoted context omitted.

I genuinely don't understand what you're talking about with this comment. Learn how to do what things properly? I've been writing software for two decades... I'm not primarily in a learning phase, I'm in a doing phase. I'll take advantage of tools that save me time and energy in my work (for the right price). Why wouldn't I? What do you mean by "barely working"? I can now put more iterations into getting things worki…

My one question for you: What’s your level of editor fluency? Because I would really like to know if there’s a correlation between claiming these kind of time savings and not using advanced features in your editor. My time is spent more on editing code than writing new lines. Because code is so repetitive, I mostly do copy-pasting, using the completion and the snippets engine, reorganize code. If I need a new module,…

High.

My 2023 to early 2025 usage of AI was as "slight improvement to my existing editing and autocomplete capabilities". That was great and I loved it. But sometime over the last 12 months it has switched to "mostly using the editor pane to read rather than edit".

Honestly I experience this as a great loss. All these hours over all these years perfecting the vim editing movements! And now I only spend like 10% of my time directly editing things anymore.

I feel like it would be fun (and also sad and nostalgic) to see a time lapse of the relative size and time spent focused between my editor pane, terminal pane, and AI tool pane. It has changed massively, especially in the last year.

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

#819

Post by allthetime »

XenophileJKO wrote: post #662
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.

This is such a naive take. Most of the nerdiest and most "quality" oriented engineers are hard leaning in to agentic coding. I feel like the most impressive engineers I know have always leaned in to learning how to "sharpen the axe" and AI is really the biggest axe we have seen.

Where did I say they weren’t? We’re all using LLMs now, it would be stupid not to. It’s how we use them and how much care we’re willing to give up for speed that is at issue here.

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

#820

Post by ori_b »

sothatsit wrote: post #606
ori_b wrote: post #545

Earlier quoted context omitted.

How much calculus do you think you could pick up skimming a textbook without doing exercises? We mocked these "architects" from experience. We knew that if you weren't feeling the friction yourself, you wouldn't learn enough to do good design. Maybe you don't care about engineering great systems. Most companies don't. It's good for profit. This isn't new, though AI enables less care.

The entire mistake you are making is comparing using AI to skimming textbooks, or taking shortcuts. Your entire premise is wrong. People who care about craft will care about the quality of what they produce whether they use AI or not. The code I ship now is better tested and better thought through now than before I used AI because I can do a lot more. That extra time goes into additional experiments, jumping down mor…

You can keep telling yourself that. I have seen the results from others making the same arguments. The result is invariably trash.
Post reply on HN