llm/5888b8dc-b96e-4444-9c3c-465dde409e92/batch-7-9a3e220c-1dd9-41d2-b95e-b50402864776-input.json
You are a comment classifier. Given a list of topics and a batch of comments, assign each comment to up to 3 of the most relevant topics.
TOPICS (use these 1-based indices):
1. AI productivity claims skepticism
2. Joy of programming vs shipping products
3. Skill atrophy concerns with AI
4. Experienced vs inexperienced developer AI gains
5. Web development complexity is optional
6. Code review burden with AI
7. Vibe coding quality concerns
8. Learning while using LLMs
9. Time-constrained developers benefiting
10. AI for boilerplate and scaffolding
11. Frontend framework fatigue
12. Managing AI like junior developers
13. Return to simpler web stacks
14. AI as autocomplete evolution
15. Side project enablement
16. Technical debt from AI code
17. Cost and pricing of AI tools
18. Pattern recognition and code quality
19. Parenting and hobby coding time
20. AI hallucinations and reliability
COMMENTS TO CLASSIFY:
[
{
"id": "46497311",
"text": "I think you’re destined to being bored then, because AI is here to stay. And as its capabilities improve, so will praise for it."
}
,
{
"id": "46501020",
"text": "This author simultaneously admits, he cannot hold the system in his head, but then also claims he’s not vibecoding, and I assert that these are two conflicting positions and you cannot simultaneously hold both positions\n\nI am also doing my pattern recognition. It seems that a common pattern is people claiming it sped me up by x! (and then there’s no AB test, n=1)"
}
,
{
"id": "46489396",
"text": "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…\n\nI'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.\n\nAll 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.\n\nWe 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.\n\nWe 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.\n\nThings 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."
}
,
{
"id": "46493789",
"text": "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.)"
}
,
{
"id": "46489772",
"text": "> I feel like I can manage the entire stack again - with confidence.\n\nBy not managing anything? Ignorance is bliss, I guess.\n\nI understand it. I've found myself looking at new stacks and tech, not knowing what I didn't know, and wondering where to start. But if you skip these fundamentals of the modern dev cycle, what happens when the LLM fails?"
}
,
{
"id": "46491481",
"text": "Then it fails and the world doesn't end. You fix it or delegate it and move on. Most people aren't working on code for power grids and fighter jets. There's room for failure.\nThis same argument was used by the old timers when younger programmers couldn't code assembly or C on bare metal systems."
}
,
{
"id": "46492211",
"text": "In the context of \"fun again\", debugging slop, finding imaginary dependencies, and discovering unimaginably fragile code isn't fun , even if it's not important.\n\nBut past bad output, I worry for our creative fulfillment. The old timers are right. That feeling of accomplishment, a keystone of happiness is a product of work. Probably beyond the scope of the thread."
}
,
{
"id": "46497195",
"text": "This isn't supposed to be a slam on LLMs. They're genuinely useful for automating a lot of menial things... It's just there's a point where we end up automating ourselves out of the equation, where we lose opportunity to learn, and earn personal fulfilment.\n\nWeb dev is a soft target. It is very complex in parts, and what feels like a lot of menial boilerplate worth abstracting, but not understanding messy topics like CSS fundamentals, browser differences, form handling and accessibility means you don't know to ask your LLM for them.\n\nYou have to know what you don't know before you can consciously tell an LLM to do it for you.\n\nLLMs will get better, but does that improve things or just relegated the human experience further and further away from accomplishment?"
}
,
{
"id": "46489044",
"text": "> 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…\n\nLLMs 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."
}
,
{
"id": "46490447",
"text": "You're completely free to write software targeting the browser platform without a framework, build pipeline, and bundler. Those things exist for a reason though and running a large project without them quickly runs into worse problems."
}
,
{
"id": "46490806",
"text": "They exist for reasons, yes. Worse problems? Nah."
}
,
{
"id": "46491109",
"text": "Those things exist because of eachother. If you’re not using a reactive framework, you probably have no need for a bundler and if you’re not using a bundler, you probably have no need for a build pipeline."
}
,
{
"id": "46496763",
"text": "And also a build pipeline doesn't have to be difficult to write. You can do it in like 50 lines of code and esbuild. And then you get to bundle your CSS, use React or whatever, Typescript, etc."
}
,
{
"id": "46499145",
"text": "<Here is a joke for you>\n\nFactory work began when people could use other people as machines. For example, mechanized looms could weave cloth but each cloth weaving machine needed a machine to run it. So use people. Children, real slaves anyone. Slave labor. Thus began the Factory Age.\n\nNow AI can replace people for repetitive labor. AI Can run the machines, it is the new Slave Labor. The problem now is what to do with all the freed slaves? If AI can make us the things that are needed, then how are we needed? We are not. As freed slaves, suddenly we are out of work. We are obsolete.\n\nUnfortunately, for corporations that are now rushing to free themselves from the old, difficult, demanding, contentious slaves, they have missed one gigantic element of the equation. Hmmm. What could it be? Can you guess? What could possibly go wrong here?\n\nFortunately, for us - the freed slaves and factory workers - it turns out we are not just slaves after all. We were just trained to be slaves. So we have a future. If we can adapt to being free. And that is not a joke.\n\n<End joke. I just made this up, nothing about it is true or even remotely serious. />"
}
,
{
"id": "46499423",
"text": "If Bill Bryson is to be trusted, the loom actually replaced a massive amount of labor. Prior to invention of labor-savings devices, Britain made 32x less cotton fibre. The inventions in this space put tens of thousands out of work, in what was already a difficult job market due to automation. I’m not sure your first paragraph makes sense.\n\nPeople were dirt cheap, but machines were vastly more productive (and some inventions were stolen so that no royalties had to be paid)."
}
,
{
"id": "46499266",
"text": "That's not a funny joke."
}
,
{
"id": "46490610",
"text": "It's amazing to be able to try a bunch of ideas with very minimal cost. That being said, AI code assistants don't have eyeballs and they often make things that don't look very good. Craft, polish and judgement still matter."
}
,
{
"id": "46491085",
"text": "I find they can make some things look objectively \"good\", but they just look generic and it feels very easy to spot a site that was made without the vision, polish and judgement.\n\nYou can get LLMs to create some truly unique sites, but it takes a lot more work than a few prompts."
}
,
{
"id": "46495277",
"text": "Last paragraph resonated so deeply with me. Especially this:\n\n```It’s also not the typing of code that I really enjoy, nor is it the syntax or structure or boilerplate that’s required to build anything. It’s the fact you get to build something out of nothing, writing code was just how you got there. And with today’s tooling, that saves a ton of time.```\n\nI never really related with folks that code for beauty or are put off by how AI does the actual coding. The beauty is actually creating something, solving real problems, shipping, and (hopfully) winning. It might be cliche, but it is incredibly true for me to say that using AI feels like a superpower."
}
,
{
"id": "46499303",
"text": "The people who love writing code were the ones who created the languages and frameworks that make it even possible for an LLM to cobble something together for you.\n\nThere is tons of satsifaction in actually creating nuts and bolts frameworks. After you encounter difficulties in creating a real world product you see the need for tools to solve those problems, so crafting those tools and then using them does feel like winning and shipping and solving real problems."
}
,
{
"id": "46500187",
"text": "I'm trying to catch up with AI but it's difficult because most articles I find are kinda vague and there is a lack of clear examples.\n\nIt's always about prompting or how AI \"is great\" yadi yada but hardly any step by step examples.\n\nI can easily ask gemini CLI to produce code for example. But how to work with AI in an existing codebase isn't obvious at all.\n\nIt seems also that for any serious use you need a paid subscription? It seems like the free models just can't handle large codebases."
}
,
{
"id": "46497843",
"text": "“I can reliably reproduce their coding standards, tone of voice, tactics, and processes.”\n\nDoesn’t he mean the “AI tool” can reliably reproduce his friends coding practices? Hilariously ironic if so."
}
,
{
"id": "46499158",
"text": "I think it’s easier to manage full-stack development as a solo developer now even without AI.\n\nNow TypeScript catches a lot of my mistakes before they reach runtime.\n\nNow I have good enough browser automation testing tools to catch regressions in the frontend.\n\nNow it’s quick and easy to run a specific database version for each app I’m working on with docker.\n\nNow I can automate deployment to the cloud instead of having to rely on an entire IT department.\n\nNow I have a scalable way to publish and consume reusable units of code as npm packages.\n\nNone of this was the case in what this author seems to think were the good old days. If web development seemed easy to him back then, I doubt he was working on complex projects"
}
,
{
"id": "46492325",
"text": "Either the projects he's working on are side projects, and in that case I don't see why he would need to use the complex pipelines, just Vanilla JS and PHP still work super fine, even better nowadays actually, or the projects are professional ones and then to ship code written by AI is extremely dangerous and he should have resources (time and people) to do things properly without AI. So, I'm clearly not convinced."
}
,
{
"id": "46496303",
"text": "Maybe it is „very” professional, so he is part of one of hundreds of teams and he is creating micro parts of big system and with such setup he is easily hiding in ocean of very low performing people.\nIn many big setups there are so-called microservices that in reality are picoservices doing function of 1-2 method and 1-2 tables in db.\n\nEither way - the setup looks nice and is one of very few that really shows how to make things work. A lot of people say about 5-10x improvements not showing even the prompts, because probably they made some 2 model CRUD that probably can be already made with 20 lines of code in Django."
}
,
{
"id": "46499815",
"text": "A LOT of what is mentioned for today's frontend and backend developers is really companies dumping more and more responsibility onto developers so they can fire SEOs, Configurations Management specialists, DBAs, etc., so that the company can save more money while burning out more developers."
}
,
{
"id": "46489142",
"text": "AI makes finishing projects easier. But I would steer away from starting them.\n\nIn 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)."
}
,
{
"id": "46489581",
"text": "> But I would steer away from starting them.\n\nI find just the opposite. Before, starting from nothing was a huge impediment. Now you can have a working prototype and start iterating right away. If you figur e out that you've gone down the wrong path, there's little remorse in tossing it out and starting over."
}
,
{
"id": "46493155",
"text": "Setting up build system and prototyping sure. As a replacement for Figma it’s great. But I would throw away all the code and start from scratch if I wanted to be able to maintain the code in the long term."
}
,
{
"id": "46488876",
"text": "Ironically I'm thinking the exact opposite. Now I can build stuff without dealing with the chaos in the frontend frameworks ecosystem..."
}
,
{
"id": "46488914",
"text": "theres a fun \"K-shaped\" optionality with LLMs: on one hand, its possible to deal with otherwise large API surfaces.\n\nbut 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.\n\nboth roads very reasonable, but that the old way of doing things is new again is interesting."
}
,
{
"id": "46489116",
"text": "Yes!\n\nI'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.\n\nFeels like coding in the 200xs and I'm enjoying every minute of it."
}
,
{
"id": "46494072",
"text": "And it's not an either-or. For example, I found that a quick way to get a web frontend for a console app is to prompt it to turn that into a CGI app. But said CGI app can still serve HTML with fancy JS and what not, and use modern frameworks for that if desired."
}
,
{
"id": "46489147",
"text": "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."
}
,
{
"id": "46499093",
"text": "It's good that tools create the OP's positive feeling about being on top of the full Web stack again.\n\nI just wish the tools that provides that feeling was a deterministic front-end code generator built from software technology and software engineering insights and not a neural network utilizing a pseudo-random number generator..."
}
,
{
"id": "46498284",
"text": "> Over the past two decades, I’ve worked with a lot of talented people\n\n> I’ve seen the good and the bad, and I can iterate from there.\n\nA bit of a buried lede, perhaps. Being in the industry for two decades, the definitions and fundamentals can rub off on you, with a little effort. There is a big difference between this and a decidedly non-technical individual without industry experience who sets out to do the same thing. This is not the advertised scenario for LLM vibe-coding."
}
,
{
"id": "46489103",
"text": "I remember missing the fun with webdev, when everything got complex. That's when I tried Rails again, it's truly a joy."
}
,
{
"id": "46494012",
"text": "In particular, and speaking as a backend engineer with zero web design skills, building things with charts/graphs is amazing nowadays! You can literally just operate at the level of \"add another line representing the foo data\", \"add a scatterplot below it\", \"make them line up\", \"actually, make it a more reddish pink\" etc. In the past I've had opinions about d3 and vega-lite and altair and matplotlib etc and learned how to use those ones at a superficial level at least. In my last personal UI with charts I didn't even ask it what framework it had chosen (chart.js is the answer)"
}
,
{
"id": "46493847",
"text": "Maybe it's just me, but the idea that the average web project out there is a complicated mess and thank God we have AI so we can finally think about the things that matter while AI deals with the mess... it makes me sad."
}
,
{
"id": "46497288",
"text": "A product manager here. Thanks to AI, I was able to create my own website on Astro. I was so fascinated by web technologies, that I didn't realize when I created not just a website, but a blazing fast website with extensive amount of metadata generation (Json-LD, OG, microformats, Dublin Core, PRISM, RSL 1.0, Highwire Press, FAIR singposting, MODS generation) and so on. Thanks to this pet project, I'm now quite capable as a software architect of websites. And it is really fun!"
}
,
{
"id": "46495946",
"text": "We can all have fun being homeless I guess"
}
,
{
"id": "46496404",
"text": "Tackling layer of complexity often feels like this. I remember 2010 and my frustration of evergrowing complexity of networking backend programming (C++ mainly), and discovering Go. \"Go made programming fun again\" was a common phrase at the conferences back then.\n\nI feel similar with web-apps development too, except we're not solving complexity here – we just outsorcing it to \"AI-developer\". None of the deficiencies of web stack are solved here. The worst part is that this complexity of web stack is mainly _accidental_ – i.e. coming from the tooling, not from the problem domain."
}
,
{
"id": "46492391",
"text": "> Over the past two decades, I’ve worked with a lot of talented people: backend developers, frontend developers, marketers, leaders, and more. I can lean on those experiences, fall back on how they did things, and implement their methods with AI.\n\nWill that really work? You interacted with the end product, but you don't have the experience and learned lessons that those people had. Are you sure this isn't the LLM reinforcing false confidence? Is the AI providing you with the real thing or a cheap imitation and how can you tell?"
}
,
{
"id": "46490832",
"text": "As someone who always dabbled in code but never was a “real” developer, I’ve found the same thing. I know the concepts, I know good from bad — so all of a sudden I can vibe code things that would have taken me months of studying and debugging and banging my head against the wall.\n\nIf you’ll forgive a bit of self promotion, I also wrote some brief thoughts on my Adventures In AI Prototyping:\n\nhttps://www.andrew-turnbull.com/adventures-in-ai-prototyping..."
}
,
{
"id": "46496420",
"text": "To me, what sucks the most about programming is dealing with ecosystem issues. You want to write a little tool for personal use, but NPM starts acting out. Then you need to do something in java, which you don't use very often, and you get a giant maven error stack trace which you now need to try to understand. All of this frustration is gone since I use AI and I can focus solely on the thing I'm trying to accomplish."
}
,
{
"id": "46496091",
"text": "Maybe its just me but I enjoy learning how all these systems work. Vibe Coding and LLMs basically take that away from me, so I dont think ill ever be as hyped for AI as other coders"
}
,
{
"id": "46489753",
"text": "Tailwind CSS has also been super useful. A vocabulary for style colocated with the elements works far better than an ever growing list of continuously overidden rules."
}
,
{
"id": "46492046",
"text": "My guess is that the amount of total software people use will significantly increase, but the total amount of money made from SaaS will significantly decrease\n\nI've replaced almost all of the App subscriptions with stuff I built for my self. The only subscriptions I pay for are things that are almost impossible to replace like online storage (iCloud) or Spotify"
}
,
{
"id": "46497034",
"text": "This is exactly how I feel about it. The cognitive load of starting a new project is so small now. It's also made it very easy to switch between projects, something that took way too much headspace to do on a whim in the before times."
}
,
{
"id": "46497271",
"text": "You can still build web apps using more basic technologies like PHP, MySQL/Postgres, and just using vanilla JS.\n\nOne of the most frustrating things in my career is how over-engineered everything has become in the last 15 years."
}
]
Return ONLY a JSON array with this exact structure (no other text):
[
{
"id": "comment_id_1",
"topics": [
1,
3,
5
]
}
,
{
"id": "comment_id_2",
"topics": [
2
]
}
,
...
]
Rules:
- Each comment can have 0 to 3 topics
- Use 1-based topic indices
- Only assign topics that are genuinely relevant to the comment
- If no topics match, use an empty array:
{
"id": "...",
"topics": []
}
50