Web Development Is Fun Again
Key topics
The notion that web development has become enjoyable again is sparking a lively debate, with many attributing this resurgence to the emergence of Large Language Models (LLMs). While some commenters, like HPsquared, see LLMs as a welcome return to the Renaissance Man ideal, others, such as acedTrex, argue that they rob people of meaningful work and specialization. The discussion is also highlighting the tension between generalists and specialists, with some, like Palomides, claiming that LLMs have made it harder for non-specialists to remain marketable. As the conversation unfolds, it's clear that the impact of LLMs on development and work is a complex, multifaceted issue that elicits strong opinions.
Snapshot generated from the HN discussion
Discussion Activity
Very active discussionFirst comment
26m
Peak period
92
0-6h
Avg / period
17.8
Based on 160 loaded comments
Key moments
- 01Story posted
Jan 4, 2026 at 10:00 AM EST
5d ago
Step 01 - 02First comment
Jan 4, 2026 at 10:26 AM EST
26m after posting
Step 02 - 03Peak activity
92 comments in 0-6h
Hottest window of the conversation
Step 03 - 04Latest activity
Jan 7, 2026 at 2:01 PM EST
2d ago
Step 04
Generating AI Summary...
Analyzing up to 500 comments to identify key contributors and discussion patterns
Want the full context?
Jump to the original sources
Read the primary article or dive into the live Hacker News thread when you're ready.
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.
This is fundamentally what makes them so DAMAGING to humanity. They didn't bail us out, they robbed us of it.
For example, there's a common core to music, art, food, writing, etc that you don't see until you've gotten good at 3+ aesthetic fields. There are common patterns in different academic disciplines and activities that can supercharge your priors and help you make better decisions.
LLMs can "see" these these connections if explicitly prompted with domains and details, but they don't seem to reason with them in mind or lean on them by default. On the other hand, LLMs are being aggressively RL'd by the top 10% of various fields, so single field expertise by some of the best in the world is 100% baked in and the default.
Do you also enjoy hiring a taskrabbit to go hiking for you, taking photos along the way?
Enjoying having is fine too, but let's at least be honest about it.
I enjoy looking at photos people took on hikes, but I don't call it hiking.
If you want to take photos with a drone, that's cool. But does flying a drone from the comfort of your couch really make hiking fun again?
Some folks walk out of their house and start hiking. Some folks drive somewhere and then start walking. Some folks take photos from the car. Some folks take a roadtrip.
All of these things ask for different effort & commitment with different experiences & results as the payoff. At least be honest about that.
I wanted to self-host the links, so I installed Linkding. (I didn't write Linkding.) For the fediverse bot, I installed gotosocial as the service host (I didn't write gotosocial.)
From there, a cronjob running a small program using Linkding and gotosocial APIs could do the trick. Decided to do it in golang, because the standalone binaries are easy to deploy.
Writing that small program didn't seem like fun - I've already played with those APIs and golang. What I wanted, for my enjoyment, was the completed system.
So, I took 10 minutes to write out a quick spec for the program and what I wanted it to do. I loaded that up as context for Claude Code along with some pointers for building CLI apps in golang. I let it rip and, in about 20 minutes, Claude produced a functional tool. It also wrote a decent README based on my original prose.
I reviewed the code, did some testing, made some tweaks, called it done. My bookmarks are now regularly posted to a bot account on the fediverse. This is an enjoyable outcome for me - and I didn't have to type every line of code myself.
For bonus points, I also had Claude Code gin up some GitHub Actions workflows to lint, test, build, and release multi-platform binaries for this tool. I've done these things before, but they're tedious. More enjoyable to have the resulting automations than to build them. And now I have them: I can make tweaks to this tool and get builds just through the GitHub web UI.
I've since repeated this pattern with a handful of other small personal tools. In each case, I wanted the tool and the utility it offered. I didn't care about the process of writing the code. It's working pretty well for me.
but on the other hand, you can 'go oldschool' but with the hot new tools: install ubuntu, launch claude with yolo mode, and just tell it what you want as if it were a sysadmin from the early 2000s/late 90s.
both roads very reasonable, but that the old way of doing things is new again is interesting.
I've been having a great time prompting "vanilla JavaScript, no react" and building neat things that use browser APIs exclusively (including modern stuff like web audio APIs and Web Components and WASM) because I don't need to learn a bunch of boilerplate stuff first anymore.
Feels like coding in the 200xs and I'm enjoying every minute of it.
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.)
Got it.
Whether or not you use my software is up to you.
The person who actually cooked it cooked it. Being the "catalyst" doesn't make you the creator, nor does it mean you get to claim that you did the work.
Otherwise you could say you "cooked a meal" every time you went to MacDonald's.
Now I’m a life coach because I’m responsible for your promotion.
So now that we have tools that promise to offload the work a software developer does, there are more people interested in simply producing software, and skipping all of that "busy work".
The idea that this is the same as software development is akin to thinking that assembling IKEA furniture makes you a carpenter.
And an IC is not "left behind" if those roles don't interest them. What a ridiculous thing to say. A systems analyst or product manager is not a natural progression for someone who enjoys software development.
I bet there are professional carpenters out there who occasionally assemble an IKEA bookshelf because they need something quick and don't want to spend hours building one themselves from scratch.
What I'm pushing back on is the idea that these are equivalent to carpentry and programming. I think we need new terminology to describe this new process. "Vibe coding" is at the extreme end of it, and "LLM-assisted software development" is a mouthful.
Although, the IKEA analogy could be more accurate: the assembly instructions can be wrong; some screws may be missing; you ordered an office chair and got a dining chair; a desk may have five legs; etc. Also, the thing you built is made out of hollow MDF, and will collapse under moderate levels of stress. And if you don't have prior experience building furniture, you end up with no usable skills to modify the end result beyond the manufacturer's original specifications.
So, sure, the seemingly quick and easy process might be convenient when it works. Though I've found that it often requires more time and effort to produce what I want, and I end up with a lackluster product, with no learned skills to show for it. Thus learning the difficult process is a more rewarding long-term investment if you plan to continue building software or furniture in the future. :)
Using a drill doesn’t make you any less of a carpenter, even if you stopped using a screwdriver because your wrists are shot.
Heck, Suno has gotten me to the point where I play so much more piano (the recording -> polished track loop is very rewarding) that not only did I publish an album to Spotify in my favorite genre, of music that I’m really happy with, I’ve also started to produce some polished acoustic recordings with NO AI involvement. That’s just because I’ve been spending so much more time at the piano, because of that reward loop.
My artist name is He & The Machines (yes, it’s a bit on the nose). It’s on Spotify, iTunes, YouTube, and anywhere else you look probably.
The album name is “songs to play at the end of the world”.
Are you willing to go into some more detail about what you do with Suno and how you use it?
I generate a bunch, pick the ones that sound good, extend them if necessary, and save. Eventually once I have 30ish I can just pick the top winners and assemble an album. It’s drop dead simple.
The only reason I published them is because my family started to get worried that the songs would get “lost,” and at the request of friends also. Not doing it for profit or anything.
The recording is the real prompt: the longer of a recording you create, the more Suno adheres to the structure and tone/rhythm/voicings you choose.
I use the v5 model. Way better than the v4/4.5 models.
If keep the change’s focused I can iterate far faster with ideas because it can type faster than I can.
I took time during a holiday to write an Obsidian plugin 4 years ago to scratch a personal itch as it were. I promptly forgot most of the detail, the Obsidian plugin API and ecosystem have naturally changed since then, and Typescript isn't in my day-to-day lingo.
I've been collecting ideas for new plugins since then while dreading the investment needed to get back up to speed on how to implement them.
I took a couple hours over a recent winter holiday with Claude and cranked out two new plugins plus improvements to the 4 year old bit-rotting original. Claude handled much of the accidental complexity of ramping up that would have bogged me down in the past--suggesting appropriate API methods to use, writing idiomatic TS, addressing linter findings, ...
As a father of three with a busy life, this would've simply been impossible a couple of years ago.
Now I can genuinely point Claude Code at them and say "upgrade this to the latest versions" and it will do most of that tedious work for me.
I can even have it fill in some missing tests and gaps in the documentation at the same time.
So instead of refreshing that less used knowledge I just ask the AI to do it for me. The implications of this vs searching MDN Docs is another conversation to have.
They don't think like graphic designers, or like programmers. It's not easy for beginners. It's not aimed at ease of implementation. It's not amenable to automated validation. It's not meant to be generated.
If there is some person for whom CSS layout comes naturally, I have not met them. As far as I can tell their design goal was to confuse everyone, at which they succeeded magnificently.
Before 2017, the web had no page layout ability.
Think about it. Before the advent of Flexbox and CSS Grid, certain layouts were impossible to do. All we had were floats, absolute positioning, negative margin hacks, and using the table element for layout.
> They don't think like graphic designers or like programmers. It's not easy for beginners.
CSS is dramatically easier if you write it in order of specificity: styles that affect large parts of the DOM go at the top; more specific styles come later. Known as Inverted Triangle CSS (ITCSS), it has been around for a long time [1].
> It's not aimed at ease of implementation. It's not amenable to automated validation.
If you mean linting or adhering to coding guidelines, there are several; Stylelint is popular [2]. Any editor that supports Language Server Protocol (LSP), like VS Code and Neovim (among others), can use CSS and CSS Variables LSPs [3], [4] for code completion, diagnostics, formatting, etc.
> It's not meant to be generated. Says who? There have been CSS generators and preprocessors since 2006, not to mention all the tools which turn mockups into CSS. LLMs have no problem generating CSS.
Lots of developers need to relearn CSS; the book Every Layout is a good start [5].
[1]: https://css-tricks.com/dont-fight-the-cascade-control-it/
[2]: https://stylelint.io
[3]: https://github.com/microsoft/vscode-css-languageservice
[4]: https://github.com/vunguyentuan/vscode-css-variables
[5]: https://every-layout.dev
It's not the fault of CSS that most developers don't learn to use it correctly. That's like blaming the bicycle when learning to ride one.
Frankly, it's not a priority for most of them to learn CSS; they don't see it as a "real" programming language; therefore it's not worth their time.
It's not like blaming the bicycle, that's the whole point of my analogy to programming languages. Like I said, learning a new programming language in a few weeks of regular use is a common experience. This also happens with bikes, because you can try a few things, lose balance, make a few intuitive adjustments, and iterate easily.
This just doesn't work with CSS. There are so many pitfalls, corner cases and reasoning is non-compositional and highly contextual. That's the complete opposite of learning to ride a bike or learning a new programming language.
You literally do need to read like, a formal specification of CSS to really understand it, and even then you'll regularly get tripped up. People just learn to stick to a small subset of CSS for which they've managed to build a predictable model for, which is why we got toolkits like Bootstrap.
Edit: this also explains why things like Tailwind are popular: it adds a certain amount of predictability and composition to CSS. Using CSS was way worse in the past when browser compatibility was worse, but it's still not a great experience.
Wade through ads
Skim a treatise on the history of centering content
Skim over the “this question is off topic / duplicate” noise if Stack Overflow
Find some code on the page
Try to map how that code will work in the context of your other layout
Realize it’s plain CSS and you’re looking for Tailwind
Keep searching
Try some stuff until it works
Or…
Ask LLM. Wait 20-30 seconds. Move on to the next thing.
You: Hey ChatGPT, help me center a div.
ChatGPT: Certainly, I'd be glad to help! But first you must drink a verification can to proceed.
Or:
ChatGPT: I'm sorry, you appear to be asking a development-related question, which your current plan does not support. Would you like me to enable "Dev Mode" for an additional $200/month? Drink a verification can to accept charges.
Maybe in 3-5 years this will work on consumer hardware at speed, but not in the immediate term.
DeepSeek-V3.2-Exp has 37B active parameters, GLM-4.7 and Kimi K2 have 32B active parameters.
Lets say we are dealing with Q4_K_S quantization for roughly half the size, we still need to move 16 GB 30 times per second, which requires a memory bandwidth of 480 GB/s, or maybe half that if speculative decoding works really well.
Anything GPU-based won't work for that speed, because PCIe 5 provides only 64 GB/s and $2000 can not afford enough VRAM (~256GB) for a full model.
That leaves CPU-based systems with high memory bandwidth. DDR5 would work (somewhere around 300 GB/s with 8x 4800MHz modules), but that would cost about twice as much for just the RAM alone, disregarding the rest of the system.
Can you get enough memory bandwidth out of DDR4 somehow?
An article about the best open weight models, including Qwen and Kimi K2 [3].
[1]: https://openrouter.ai/models
[2]: https://huggingface.co
[3]: https://simonwillison.net/2025/Jul/30/
Microsoft’s dedication to infusing OpenAI tech into everything seems like a play to cut even those tepid brains out of the loop and capture the vehicles of planning and production. Training your workforce to be dependent on third-party thinking, planning, and advice is an interesting strategy.
Come on!
I did that a lot initially, it’s really only with the advent of Claude Code integrated with VS Code that I’m learning more like I would learn from a code review.
It also depends on the project. Work code gets a lot more scrutiny than side projects, for example.
Given how often people acknowledge that ai slop needs to be verified, it seems like a shitty way to achieve something like this vs just checking it yourself with well known good reference material.
If you haven’t been convinced by pure argument in 2026 then you probably won’t be. But the great thing is you don’t have to take anyone’s word for it.
This isn’t crypto, where everyone using it has a stake in its success. You can just try it, or not.
But there is an interesting looking-glass effect at play, where the truth seems obvious and opposite on either side.
Aaand done. Very first result was a blog post showing all the different ways to do it, old and new, without any preamble.
As a bonus, I pay attention to what the AI did and its results, and I have actually learned quite a bit about how to do this myself even without AI assistance
If I do this a few more times it might even stick in my head.
These days I use display: flex; so much that I wish the initial value of the display property in CSS should be flex instead of inline;
They are not coding either. They steal and plagiarize.
If you'd please review https://news.ycombinator.com/newsguidelines.html and stick to the rules when posting here, we'd appreciate it.
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.
I'm personally more afraid that stupid sales oriented will take my job instead of losing it to solid teams of dedicated expert that invested a lot of skills in making something on their own. it seems like value inversion
The initial creation and generation is indeed much easier now, but testing, identifying, and fixing bugs is still very much a process that takes some investment and effort, even when AI assisted. There is also considerable room for differentiation among user flows and the way people interact with the app. AI is not good at this yet, so the prompter needs to be able to identify and direct these efforts.
I've also noticed in some of my projects, even ones shipped into production in a professional environment, there are lots of hard to fix and mostly annoying bugs that just aren't worth it, or that take so much research and debugging effort that we eventually gave up and accepted the downsides. If you give the AI enough guidance to know what to hunt for, it is getting pretty good at finding these things. Often the suggested fix is a terrible idea, but The AI will usually tell you enough about what is wrong that you can use your existing software engineering skills and experience to figure out a good path forward. At that point you can either fix it yourself, or prompt the AI to do it. My success rate doing this is still only at about 50%, but that's half the bugs that we used to live with that we no longer do, which in my opinion has been a huge positive development.
What opportunities? You aren't going to make any money with anything you vibe coded because, even the people you are targeting don't vibe code it, the minute you have even a risk of gaining traction someone else is going to vibe code it anyway.
And even if that didn't happen you're just reducing the signal/noise ratio; good luck getting your genuinely good product out there when the masses are spammed by vibe-coded alternatives.
When every individual can produce their own software, why do you think that the stuff produced by you is worth paying for?
Vibe-coding something isn't a guarantee the thing is shit. It can be fine. It still takes time and effort, too, but because it can take lot less time to get a "working product", maybe some unique insight the parent commenter had on a problem is what was suddenly worth their time.
Will everyone else who has that insight and the vibe coding skills go right for that problem and compete? Maybe, but, also maybe not. If it's a money-maker, they likely will eventually, but that's just business. Maybe you get out of the business after a year, but for a little while it made you some money.
I'm hearing what you are saying, but the "business as usual" way almost always requires some money or some time (which is the same thing). The ones that don't (performance arts, for example) average a below-minimum-wage pay!
IOW, when the cost of production is almost zero, the market adjusts very quickly to reflect that. What happens then is that a few lottery ticket winners make bank, and everyone else does it for free (or close to it).
You're essentially hoping to be one of those lottery ticket winners.
> How does Glad sell plastic bags when there are thousands of other companies producing plastic bags, often for far, far less?
The cost of production of plastic bags is not near zero, and the requirements for producing plastic bags (i.e. cloning the existing products) include substantial capital.
You're playing in a different market, where the cost of cloning your product is zero.
There's quite a large difference between operating in a market where there is a barrier (capital, time and skill) and operating in a market where there are no capital, time or skill barriers.
The market you are in is not the same as the ones you are comparing your product to. The better comparison is artists, where even though there is a skill and time barrier, the clear majority of the producers do it as a hobby, because it doesn't pay enough for them to do it as a job.
My Glad example was off the cuff but it still feels apt to me for the case I mean: the barrier for an existing plastic product producer who doesn't already to also produce bags is likely very low, but it's still non zero, while the barrier for a random person is quite high. I feel vibe coding made individual projects much cheaper (sometimes zero) for decent programmers, but it hasn't made my mom start producing programming projects -- the barrier still seems quite high for non technical people.
I think a better analogy (i.e. one that we both agree one) is Excel preadsheets.
There are very few "Excel consultants" available that companies hire. You can't make money be providing solutions in Excel because anyone who needs something that can be done in Excel can just do it themselves.
It's like if your mum needed to sum income and expenditures for a little side-business: she won't be hiring an excel consultant to do write the formulas into the 4 - 6 cells that contain calculations, she'll simply do it herself.
I think vibe coding is going to be the same way in a few years (much faster than spreadsheets took off, btw, which occurred over a period of a decade) - someone who needs a little project management applications isn't going to buy one, they can get one in an hour "for free"[1].
Just about anything you can vibe-code, an office worker with minimal training (the average person in 2026, for example) can vibe-code. The skill barrier to vibe-coding little apps like this is less than the skill barrier for creating Excel workbooks, and yet almost every office worker does it.
--------------------------------------------------------------
[1] In much the same way that someone considers creating a new spreadsheet to be free when they already have Excel installed, people are going to regard the output of LLMs "free" because they are already paying the monthly fee for it.
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.
It used recent APIs and patterns that I didn't have to go read extensive docs for or do deep learning on. It has an acceptable test suite. The code was easy to read, and reasonable, and I know no one will ever flip it into ad-serving malware by surprise.
A big thing is just that the idea of creating a non-trivial tool is suddenly a valid answer to the question. Previously, I know would have had to spend a bunch of time reading docs, finding examples, etc., let alone the inevitable farting around with a minor side-quest because something wasn't working, or rethinking+reworking some design decision that on the whole wasn't that important. Instead, something popped into existence, mostly worked, and I could review and tweak it.
It's a little bit like jumping from a problem of "solve a polynomial" to one of "verify a solution for a polynomial".
Just yesterday for example, I used AI to build a GTK app that has a bunch of sports team related sound effects built into them. I could have coded this by hand in 45 minutes, but it only took 10 minutes with AI. That's not the best part though. The best part is that I was able to use AI to get it building into an app image in a container so I can distribute it to myself as a single static file that I can execute on any system I want. Dicking with builds and distribution was always the painful part and something that I never enjoyed, but without it, usage is a pain. I've even gone back to projects I built a decade ago or more and got them building against modern libraries and distributed as RPMs or app images that I can trivially install on all of my systems.
The joy is now in the results rather than the process, but it is joy nonetheless.
There is immense pleasure in a nice piece of code - something that is elegant, clever and simple at the same time.
Grinding out code to get something finished - less fun…
Building the instrument would be electrical engineering.
Playing the instrument would be writing software.
Is it necessary to pay $200/mo to actually ship things or will $20/mo do it? Obviously I could just try it myself and see how far I get bit I'm curious to hear from someone a bit further down the path.
Which means that a sensible way to go about those things is to start with a $20 subscription to get access to the best models, and then look at your extra per-token expenses and whether they justify that $200 monthly.
You can vibe code, i.e. no code review, but this builds up technical debt. Think of it as a junior who is doing one sprint's worth of work every 24 hours of wall-clock time when considering how much debt and how fast it will build up.
I'll use it for a few hours at a time, a couple days a week, often while watching TV or whatever. I do side projects more on long rainy weekends, and maybe not even every week during the summer. I'll hit the limit if I'm stuck inside on a boring Sunday and have an idea in my head I really wanted to try out and not stop until I'm done, but usually I never hit the limit. I don't think I've hit the limit since I switched my default to Haiku FWIW.
The stat's say I've generated 182,661 output tokens in the last month (across 16 days), and total usage if via API would cost $39.67.
I started on the $20 plans for a bit of an experiment, needing to see about this whole AI thing. And for the first month or two that was enough to get the flavor. It let me see how to work. I was still copy/pasting mostly, thinking about what to do.
As i got more confident i moved to the agents and the integrated editors. Then i realised i could open more than one editor or agent at a time while each AI instance was doing its work.
I discovered that when I'm getting the AI agents to summarise, write reports, investigate issues, make plans, implement changes, run builds, organise git, etc, now I can alt-tab and drive anywhere between 2-6 projects at once, and I don't have to do any of the boring boiler plate or administrivia, because the AI does that, it's what its great for.
What used to be unthinkable and annoying context switching now lets me focus in on different parts of the project that actually matter, firing off instructions, providing instructions to the next agent, ushering them out the door and then checking on the next intern in the queue. Give them feedback on their work, usher them on, next intern. The main task now is kind of managing the scope and context-window of each AI, and how to structure big projects to take advantage of that. Honestly though, i don't view it as too much more than functional decomposition. You've still got a big problem, now how do you break it down.
At this rate I can sustain the $100 claude plan, but honestly I don't need to go further than that, and that's basically me working full time in parallel streams, although i might be using it at relatively cheap times, so it or the $200 plan seems about right for full time work.
I can see how theoretically you could go even above that, going into full auto-pilot mode, but I feel i'm already at a place of diminishing marginal returns, i don't usually go over the $100 claude code plan, and the AIs can't do the complex work reliably enough to be left alone anyway. So at the moment if you're going full time i feel they're the sweet spot.
The $20 plans are fine for getting a flavor for the first month or two, but once you come up to speed you'll breeze past their limitations quickly.
Me from 9 days ago: https://news.ycombinator.com/item?id=46391392#46398917
452 more comments available on Hacker News