embedded dev with a billion toolchains, GPU development with each vendors bespoke API, ffmpeg with its billion parameters - if anything, you could say LLMs bailed us out of the impending ultra-specialization. without LLMs, we might be facing a world where 30% of the workforce is in software dev.
i am keeping my eyes peeled on vibe-coding PCB layouts and schematics. a lot of eyes in that direction already but its still early.
Something I like about our weird new LLM-assisted world is the number of people I know who are coding again, having mostly stopped as they moved into management roles or lost their personal side project time to becoming parents.
AI assistance means you can get something useful done in half an hour, or even while you are doing other stuff. You don't need to carve out 2-4 hours to ramp up any more.
If you have significant previous coding experience - even if it's a few years stale - you can drive these things extremely effectively. Especially if you have management experience, quite a lot of which transfers to "managing" coding agents (communicate clearly, set achievable goals, provide all relevant context.)
I was very anti AI (mainly because I am scared that I'll take my job). I did a side project that would have took me weeks in just two days. I deployed it. It's there, waiting for customers now.
I felt in love with the process to be honest. I complained my wife yesterday: "my only problem now is that I don't have enough time and money to pay all the servers", because it opened to me the opportunities to develop and deploy a lot of new ideas.
> AI assistance means you can get something useful done in half an hour, or even while you are doing other stuff. You don't need to carve out 2-4 hours to ramp up any more.
That fits my experience with a chrome extension I created. Instead of having to read the docs, find example projects, etc, I was able to get a working version in less than a hour.
I don't know but to me this all sounds like the antithesis of what makes programming fun. You don't have productivity goals for hobby coding where you'd have to make the most of your half an hour -- that sounds too much like paid work to be fun. If you have a half an hour, you tinker for a half an hour and enjoy it. Then you continue when you have another half an hour again. (Or push into night because you can't make yourself stop.)
Yep, have seen this myself as previously a manager and now with a young family.
I can make incredible progress on side-projects that I never would have started with only 2-4 hours carved out over the course of a week.
There is a hopefully a Jevon's paradox here that we will have a bloom of side-projects, "what-if" / "if only I had the time" type projects come to fruition.
The good thing about AI is that it knows all the hundreds of little libraries that keep popping up every few days like a never-ending stream. No longer I need to worry about learning about this stuff, I can just ask the AI what libraries to use for something and it will bring up these dependencies and provide sample code to use them. I don't like AI for coding real algorithms, but I love the fact that I don't need to worry about the myriad of libraries that you had to keep up with until recently.
Yes, people who were at best average engineers and those that atrophied at their skill through lack of practice seem to be the biggest AI fanboys in my social media.
I think this is probably the disconnect between me and heavy LLM-users. I find the process of asking them to generate code to be overall much more frustrating than just writing code myself.
I don't like it. It lets "management" ignore their actual jobs - the ones that are nominally so valuable that they get paid more than most engineers, remember - and instead either splash around in the kiddie pool, or go jump into the adult pool and then almost drown and need an actual engineer to bail them out. (The kiddie pool is useless side project, the adult pool is the prod codebase, and drowning is either getting lost in the weeds of "it compiles and I'm done! Now how do I merge and how do I know if I'm not going to break prod?" or just straight up causing an incident and they're apologizing profusely for ruining the oncall's evening except that both of them know they're gonna do it again in 2 weeks).
I really don't know how often I have to tell people, especially former engineers who SHOULD KNOW THIS (unless they were the kind of fail-upwards pretenders): the code is not the slow part! (Sorry, I'm not yelling at you, reader. I'm yelling at my CEO.)
It all comes back to "Do more because of AI" rather than "Do less because of AI".
Getting back into coding is doing more. Updating an old project to the latest libraries is doing more.
It often feels ambiguous. Shipping a buggy, vibe-coded MVP might be doing less. But getting customer feedback on day one from a real tangible product can allow you to build a richer and deeper experience through fast iteration.
Just make sure we're doing more, not less, and AI is a wonderful step forward.
> You don't need to carve out 2-4 hours to ramp up any more.
Yes. That used to require difficult decision making: “Can I do this and how long will it take?” was a significant cognitive load and source of stress. This was especially true when it became clear something was going to take days not hours, having expended a lot of effort already.
Even more frustrating was having to implement hacks due to time constraints when I knew a couple more hours would obviate that need.
Now I know within a couple of minutes if something is feasible or not and decision fatigue is much lower.
If it's actual code that runs important stuffs in production: either one cares enough to understand all the ins and outs and going into managements didn't cut them from coding, either they're only pushing what they see as "good enough" code while their team starts polishing resumes and they probably have a better output doing management.
PS: if you only have half an hour for writing something, will you have 3h rolling it back and dealing with the issues produced when stuff goes sideways ? I really don't get the logic.
A friend of mine dabbled in programming when they were younger, but ended up as a writer.
A few months ago they finally got annoyed enough about the janky manual way they need to get the dialog and scripts to a specific format and just went with the basic ChatGPT copy+paste route.
Within a weekend they had a full web UI that automated a good 50% of the manual work.
With a few nudges from yours truly they graduated into agentic coding and now we're at around 90-95% automation of the manual stuff + massive improvements in the actual writing process (proper previews, the system can "guess" what the layout is suposed to be), it can export to multiple formats required by different vendors etc.
All done by a copywriter with a programmer's mindset (the need to automate) and an LLM.
Strong agree! Forget all those studies that say “but developers are slower” or whatever — I’m actually building way more hobby projects and having way more fun now. And work is way more fun and easier. And my node_modules folder size is dropping like crazy!
When stuff was getting too complicated, I looked for ways to make things simpler.
Developers have spent decades trying to figure out ways to make things simpler, less code the better, only to throw it all out the window because chatbot go brrrrrr.
I remember those times, and it was a lot of fun, but there's really nothing stopping you from running a LAMP stack today, writing PHP without frameworks and with manual SQL queries.
In fact, it's a lot more fun for me to approach this today. Modern PHP is a joy. MariaSQL is very much MySQL (and switching to Postgres isn't exactly a bump in complexity). It's way easier to write code that won't get injected.
If you want to slice your designs in Photoshop (ehem, the real OGs used Fireworks) go ahead and use Dreamweaver, go ahead. That said, HTML5 makes not having to use tables for layout easy, not more complex and VS Code has all the good parts of Dreamweaver (trust me, you don't need or want the WYSIWG... if you must, just use inspect elements and move the changes over to the HTML file).
I guess all this is to say that web dev is simpler, not more complex for solo devs today. There exists more complicated tooling, but if you're solo-dev'ing something for fun, skip it!
EDIT: Also, phpMyAdmin was fun to use but also the best way to get your box popped. Today, something like DBeaver suits me just fine.
Man I missed Macromedia Fireworks. Such a great time! I think I had the last bundle before the Adobe buy-out, Macromedia Studio I think it was called? So good!
I still write vanilla PHP with SQL queries. And with all the modern PHP features, things have never been faster or more joyful to work with.
I honestly feel bad for people who fall victims to complexity. It burns you out when all you need is to keep things simple and fun. Life is too short for anything else.
> On the frontend, you have build pipelines, bundlers, CSS frameworks with their own toolchains, progressive web apps, Core Web Vitals, SEO, layout shifts, srcset/responsive images…
LLMs are successful in webdev because of unnecessary frameworks being piled on top of each other more in the name of job security than technical necessity.
>>Starting a new project once felt insurmountable. Now, it feels realistic again.
Honestly, this does not give me confidence in anything else you said. If you can't spin up a new project on your own in a few minutes, you may not be equipped to deal with or debug whatever AI spins up for you.
>>When AI generates code, I know when it’s good and when it’s not. I’v seen the good and the bad, and I can iterate from there. Even with refinement and back-and-forth prompting, I’m easily 10x more productive
Minus a baseline, it's hard to tell what this means. 10x nothing is nothing. How am I supposed to know what 1x is for you, is there a 1x site I can look at to understand what 10x would mean? My overall feeling prior to reading this was "I should hire this guy", and after reading it my overwhelming thought was "eat a dick, you sociopathic self-aggrandizing tool." Moreover, if you have skill which you feel is augmented by these tools, then you may want to lean more heavily on that skill now if you think that the tool itself makes everyone capable of writing the same amazing code you do. Because it sounds like you will be unemployed soon if not already, as a casualty of the nonsense engine you're blogging about and touting.
Of course its fun. Making slop _is_ very fun. Its a low-effort dopamine-driven way of producing things. Learning is uncomfortable. Improving things using only your braincells can be very difficult and time consuming.
Meanwhile, I've been feeling the fun of development sucked away by LLMs. I recently started doing some coding problems where I intentionally turned off all LLM assistance, and THAT was fun.
Although I'll be happy to use LLMs for nightmare stuff like dependency management. So I guess it's about figuring out which part of development you enjoy and which part drains you, and refusing to let it take the former from you.
AI makes finishing projects easier. But I would steer away from starting them.
In order for me to be comfortable with a code base and consider it mine I need to have written the foundation, not merely reviewed in. Once the pillars are there, LLMs do make further development faster and I can concentrate on fun details (like tinkering with CSS or thinking about some very specific details).
As someone that only has sporadic pockets of deep time in my free time the thing that has been immensely helpful from an LLM coding point of view is mental model building. I can now much more easily get "into the flow" after being away from a codebase for a period of time by asking questions. For example, remind me where all the integration points for that API route is located. Or give me a rundown on this file. Etc.. It gets me back up to speed so much more quickly and makes me productive with limited amounts of time. It also means I don't have to try to carry this context around with me or I'll forget it.
One thing is true: now I go to the bar with the other guys in the group, drink whatever and let Claude or Codex do the work while I supervise, then merge PR in the morning... I wish I was kidding, but for non critical projects this is now a reality
I work at most 3-4 hours a day, and my work is prompting Cursor. Certainly an improvement over suffering 8 hours a day, but still not quite what I'm looking for.
Agree with this. Like the author, I've been keeping ajour with web development for multiple decades now. If you have deep software knowledge pre-LLM, you are equipped with the intuition and knowledge to judge the output. You can tell the difference between good and bad, if it looks and works the way you want, and you can ask the relevant questions to push the solution to the actual thing that you envisioned in your mind.
Without prior software dev experience people may take what the LLM gives them at face value, and that's where the slop comes from imho.
yeah, I think that too - for me the -Ofun comes from HTMX https://htmx.org and the HARC stack https://harcstack.org so I can server side code in a my preferred programming language hint: not JS (with a helping of LLM on the side)
On the frontend, you have build pipelines, bundlers, CSS frameworks with their own toolchains, progressive web apps, Core Web Vitals, SEO, layout shifts, srcset/responsive images…
I've been making web stuff for a similar length of time as Mattias by the sounds of it. I started with Perl but moved to PHP 4 pretty soon after. I recognise this problem but I have different take.
All the complexity was there 20 years ago, but we ignored it. That doesn't mean it was simpler. It just means we took crazy (with hindsight) risks. Sure, there were no build pipelines like today, but we had scripts we ran to build things. There was Adobe Pagemill for making site wide changes before we deployed a new version. Back in the day we made those changes, did a very brief check that things worked locally, and then manually FTP'd files to a server, breaking it in the process because a user would see the site change as they navigated. Some of us would put up a maintenance page during an update effectively just blocking all the traffic. That's certainly 'simpler', but it's also much worse for the user, and on a site that did things with data potentially risked corrupting a user's records. It was incredible that things didn't break more often. Maybe they did and we just never realised.
We didn't have CSS frameworks but we certainly did have our own in-house templates, and they had separate toolchains. As time went on that toolchain mostly migrated to Wordpress and it's template builder plugins. Again, give me Tailwind over that mess.
We had Core Web Vitals and SEO in the form of Urchin Stats. We had layout shift but we called it FOUC. We had kind of had srcset, but it was implemented as a set of Macromedia Dreamweaver mm_ JS image preload and swapping functions. <picture> is a lot nicer.
Things are just better now. Writing web software is loads of fun. I also leverage LLMs in my code because they're awesome, but not to simplify things. I don't think the complexity is new. I just think it's visible now.
I have fond (?) memories of WebEdit, a code editor with FTP integration, so you could directly edit your PHP4 files on the server. (And no, we didn't have source control.)
Strong agree. The modern web world is clearly better but we traded a whole lot of complexity for a little bit of benefit (and frequently regressed on speed). The microservices and javascript framework wars were the dark ages.
Other community members are flagging many of your posts and emailing us to complain because you're repeatedly breaking the guidelines. Whether or not I recognize a decade-old meme is irrelevant. The guidelines have been in place for most of HN's history and apply equally to everyone.
Low-quality comments and projects are unwanted on HN whether they're generated by LLMs or humans. If your reaction to seeing bad stuff is to post more bad stuff, you're just making the problem worse. Anyone who is earnest about wanting to reduce low-quality content on HN can do so by flagging bad posts and emailing us (hn@ycombinator.com) so we can investigate further. Several users do that routinely.
HN is only a place where people want to participate because others make an effort to raise the standards rather than dragging them down. Please do your part to make HN better not worse.
135 comments
[ 2.2 ms ] story [ 98.5 ms ] threadembedded dev with a billion toolchains, GPU development with each vendors bespoke API, ffmpeg with its billion parameters - if anything, you could say LLMs bailed us out of the impending ultra-specialization. without LLMs, we might be facing a world where 30% of the workforce is in software dev.
i am keeping my eyes peeled on vibe-coding PCB layouts and schematics. a lot of eyes in that direction already but its still early.
AI assistance means you can get something useful done in half an hour, or even while you are doing other stuff. You don't need to carve out 2-4 hours to ramp up any more.
If you have significant previous coding experience - even if it's a few years stale - you can drive these things extremely effectively. Especially if you have management experience, quite a lot of which transfers to "managing" coding agents (communicate clearly, set achievable goals, provide all relevant context.)
I felt in love with the process to be honest. I complained my wife yesterday: "my only problem now is that I don't have enough time and money to pay all the servers", because it opened to me the opportunities to develop and deploy a lot of new ideas.
That fits my experience with a chrome extension I created. Instead of having to read the docs, find example projects, etc, I was able to get a working version in less than a hour.
I can make incredible progress on side-projects that I never would have started with only 2-4 hours carved out over the course of a week.
There is a hopefully a Jevon's paradox here that we will have a bloom of side-projects, "what-if" / "if only I had the time" type projects come to fruition.
Just...
...write the code. Stop being lazy.
It's telling, isn't it?
I really don't know how often I have to tell people, especially former engineers who SHOULD KNOW THIS (unless they were the kind of fail-upwards pretenders): the code is not the slow part! (Sorry, I'm not yelling at you, reader. I'm yelling at my CEO.)
Getting back into coding is doing more. Updating an old project to the latest libraries is doing more.
It often feels ambiguous. Shipping a buggy, vibe-coded MVP might be doing less. But getting customer feedback on day one from a real tangible product can allow you to build a richer and deeper experience through fast iteration.
Just make sure we're doing more, not less, and AI is a wonderful step forward.
Yes. That used to require difficult decision making: “Can I do this and how long will it take?” was a significant cognitive load and source of stress. This was especially true when it became clear something was going to take days not hours, having expended a lot of effort already.
Even more frustrating was having to implement hacks due to time constraints when I knew a couple more hours would obviate that need.
Now I know within a couple of minutes if something is feasible or not and decision fatigue is much lower.
Yes !
> moved into management roles
Please stop. Except if "coding" is making PoCs.
If it's actual code that runs important stuffs in production: either one cares enough to understand all the ins and outs and going into managements didn't cut them from coding, either they're only pushing what they see as "good enough" code while their team starts polishing resumes and they probably have a better output doing management.
PS: if you only have half an hour for writing something, will you have 3h rolling it back and dealing with the issues produced when stuff goes sideways ? I really don't get the logic.
A few months ago they finally got annoyed enough about the janky manual way they need to get the dialog and scripts to a specific format and just went with the basic ChatGPT copy+paste route.
Within a weekend they had a full web UI that automated a good 50% of the manual work.
With a few nudges from yours truly they graduated into agentic coding and now we're at around 90-95% automation of the manual stuff + massive improvements in the actual writing process (proper previews, the system can "guess" what the layout is suposed to be), it can export to multiple formats required by different vendors etc.
All done by a copywriter with a programmer's mindset (the need to automate) and an LLM.
Developers have spent decades trying to figure out ways to make things simpler, less code the better, only to throw it all out the window because chatbot go brrrrrr.
In fact, it's a lot more fun for me to approach this today. Modern PHP is a joy. MariaSQL is very much MySQL (and switching to Postgres isn't exactly a bump in complexity). It's way easier to write code that won't get injected.
If you want to slice your designs in Photoshop (ehem, the real OGs used Fireworks) go ahead and use Dreamweaver, go ahead. That said, HTML5 makes not having to use tables for layout easy, not more complex and VS Code has all the good parts of Dreamweaver (trust me, you don't need or want the WYSIWG... if you must, just use inspect elements and move the changes over to the HTML file).
I guess all this is to say that web dev is simpler, not more complex for solo devs today. There exists more complicated tooling, but if you're solo-dev'ing something for fun, skip it!
EDIT: Also, phpMyAdmin was fun to use but also the best way to get your box popped. Today, something like DBeaver suits me just fine.
Man I missed Macromedia Fireworks. Such a great time! I think I had the last bundle before the Adobe buy-out, Macromedia Studio I think it was called? So good!
I honestly feel bad for people who fall victims to complexity. It burns you out when all you need is to keep things simple and fun. Life is too short for anything else.
what do you mean? why?
LLMs are successful in webdev because of unnecessary frameworks being piled on top of each other more in the name of job security than technical necessity.
Honestly, this does not give me confidence in anything else you said. If you can't spin up a new project on your own in a few minutes, you may not be equipped to deal with or debug whatever AI spins up for you.
>>When AI generates code, I know when it’s good and when it’s not. I’v seen the good and the bad, and I can iterate from there. Even with refinement and back-and-forth prompting, I’m easily 10x more productive
Minus a baseline, it's hard to tell what this means. 10x nothing is nothing. How am I supposed to know what 1x is for you, is there a 1x site I can look at to understand what 10x would mean? My overall feeling prior to reading this was "I should hire this guy", and after reading it my overwhelming thought was "eat a dick, you sociopathic self-aggrandizing tool." Moreover, if you have skill which you feel is augmented by these tools, then you may want to lean more heavily on that skill now if you think that the tool itself makes everyone capable of writing the same amazing code you do. Because it sounds like you will be unemployed soon if not already, as a casualty of the nonsense engine you're blogging about and touting.
Although I'll be happy to use LLMs for nightmare stuff like dependency management. So I guess it's about figuring out which part of development you enjoy and which part drains you, and refusing to let it take the former from you.
In order for me to be comfortable with a code base and consider it mine I need to have written the foundation, not merely reviewed in. Once the pillars are there, LLMs do make further development faster and I can concentrate on fun details (like tinkering with CSS or thinking about some very specific details).
Without prior software dev experience people may take what the LLM gives them at face value, and that's where the slop comes from imho.
I've been making web stuff for a similar length of time as Mattias by the sounds of it. I started with Perl but moved to PHP 4 pretty soon after. I recognise this problem but I have different take.
All the complexity was there 20 years ago, but we ignored it. That doesn't mean it was simpler. It just means we took crazy (with hindsight) risks. Sure, there were no build pipelines like today, but we had scripts we ran to build things. There was Adobe Pagemill for making site wide changes before we deployed a new version. Back in the day we made those changes, did a very brief check that things worked locally, and then manually FTP'd files to a server, breaking it in the process because a user would see the site change as they navigated. Some of us would put up a maintenance page during an update effectively just blocking all the traffic. That's certainly 'simpler', but it's also much worse for the user, and on a site that did things with data potentially risked corrupting a user's records. It was incredible that things didn't break more often. Maybe they did and we just never realised.
We didn't have CSS frameworks but we certainly did have our own in-house templates, and they had separate toolchains. As time went on that toolchain mostly migrated to Wordpress and it's template builder plugins. Again, give me Tailwind over that mess.
We had Core Web Vitals and SEO in the form of Urchin Stats. We had layout shift but we called it FOUC. We had kind of had srcset, but it was implemented as a set of Macromedia Dreamweaver mm_ JS image preload and swapping functions. <picture> is a lot nicer.
Things are just better now. Writing web software is loads of fun. I also leverage LLMs in my code because they're awesome, but not to simplify things. I don't think the complexity is new. I just think it's visible now.
We have many typesafe (no, not TypeScript!) options with rock solid dev tooling, and fast compilers.
AI is just a badaid, its not the road you want to travel.
We detached this comment from https://news.ycombinator.com/item?id=46489151 and marked it off topic.
Thats programmer inside jokes, and seriously, the amount of slop posted here should be moderated, not some random comment about a 15 year old joke.
Low-quality comments and projects are unwanted on HN whether they're generated by LLMs or humans. If your reaction to seeing bad stuff is to post more bad stuff, you're just making the problem worse. Anyone who is earnest about wanting to reduce low-quality content on HN can do so by flagging bad posts and emailing us (hn@ycombinator.com) so we can investigate further. Several users do that routinely.
HN is only a place where people want to participate because others make an effort to raise the standards rather than dragging them down. Please do your part to make HN better not worse.