llm/5888b8dc-b96e-4444-9c3c-465dde409e92/batch-9-b3b3cf40-eb14-416f-ba22-0cd3fa449f24-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": "46494148",
"text": "Have they? I assume you are talking about PHP, which is not that kind of framework, because you would still have to write JavaScript. It lacks type safety too."
}
,
{
"id": "46494234",
"text": "I'm talking about stuff like GWT from 2006."
}
,
{
"id": "46494337",
"text": "Wow, I had no idea that existed. It looks like it is a Java library that abstracts over the web, and generates JavaScript under the hood? I never touched GWT, but it does sound like there would be issues if you wanted to do something that's not supported by the framework. But still, I don't think this is the same as modern full stack frameworks."
}
,
{
"id": "46494539",
"text": "If I remember correctly, it was the first whatever-to-JS transpiler. But it opened the floodgates and \"do everything in one language, bridge the gap transparently\" has been tried several times since then.\n\nAnd even before that, actually! Before web apps were even a thing, we had DCOM and CORBA and some other similar but less-known frameworks that tried to make OOP in general network-transparent. It worked in principle - you could have distributed object graphs in pretty much arbitrary configurations, going back and forth as needed to capture the semantics. It failed in practice because every time you have a network gap you get a slew of potential issues that just don't exist without it (simply put, your connection and/or the other party may suddenly go away).\n\nFWIW I'm not saying that single-language specifically is a bad idea. It's specifically the notion that you can treat a distributed app as a monolithic thing without clearly marked internal boundaries where the network gap is, that fails in real world. But if you expose the gap then you still need to deal with impedance mismatch - e.g. nice your object oriented API no longer works because the object graph can't span the gap, so you need a more procedural (read: REST-style) API with serialization etc.\n\nSo, this is the point where you basically want a language designed from grounds up with message passing in mind. Blazor, but for something like Erlang or Elixir, perhaps?"
}
,
{
"id": "46492566",
"text": "Exactly. AI freed me from the boring character by character toiling"
}
,
{
"id": "46494523",
"text": "Fun is the way, not the destiny"
}
,
{
"id": "46497266",
"text": "I hate the fact that modern webdev has become to unnecessarily complex that developers unironically turn to LLMs instead of realising that it doesn't have to be like this."
}
,
{
"id": "46494649",
"text": "> I’m easily 10x more productive with AI than without it.\n\nSo you've shipped 10x the products? Can you list them?"
}
,
{
"id": "46496990",
"text": "I'm starting to resent the feeling of reading a cool article and for the conclusion to always be AI."
}
,
{
"id": "46496442",
"text": "> I remember when PHP 4 was a thing. jQuery was new and shiny. Sites were built with tables, not divs. Dreamweaver felt like a life hack. Designs were sliced in Photoshop. Databases lived in phpMyAdmin.\n\n> It probably didn’t feel like it at the time, but looking back, those were simpler days.\n\njQuery was bloat, there were others like MooTools. People idealize tables but it was not just grid, it was often used as hacks as well, like weird offsets, etc. Dreamweaver produced mess. Sliced designs? \"This site is optimized for 800x600\"\n\nNot saying current state is good. I just find interesting how nostalgia can distort memories even in tech."
}
,
{
"id": "46489123",
"text": "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."
}
,
{
"id": "46490737",
"text": "I have learned more - not just about my daily driver languages, but about other languages I wouldn't have even cracked the seal on, as well as layers of hardware and maker skills - in the past two years than I did in the 30 years leading up to them.\n\nI truly don't understand how anyone creative wouldn't find their productivity soar using these tools. If computers are bicycles for the mind, LLMs are powered exoskeletons with neural-controlled turret cannons."
}
,
{
"id": "46492559",
"text": "To extend the metaphor, which provides better exercise for your body? A bicycle or a powered exoskeleton with turret cannons?"
}
,
{
"id": "46492624",
"text": "I don't bike for exercise. I bike to get where I'm going with the least amount of friction. Different tools for different jobs.\n\nAlso: I think we can agree that Ripley was getting a good workout."
}
,
{
"id": "46489146",
"text": "The rate at which I'm learning new skills has accelerated thanks to LLMs.\n\nNot learning anything while you use them is a choice. You can choose differently!"
}
,
{
"id": "46490887",
"text": "How are you using AI to learn? I see a lot of people say this but simply reading AI generated overviews or asking it questions isn't really learning."
}
,
{
"id": "46491454",
"text": "I'm using it to build things.\n\nHere's an example from the other day. I've always been curious about writing custom Python C extensions but I've never been brave enough to really try and do it.\n\nI decided it would be interesting to dig into that by having Codex build a C extension for Python that exposed simple SQLite queries with a timeout.\n\nIt wrote me this: https://github.com/simonw/research/blob/main/sqlite-time-lim... - here's the shared transcript: https://chatgpt.com/s/cd_6958a2f131a081918ed810832f7437a2\n\nI read the code it produced and ran it on my computer to see it work.\n\nWhat did I learn?\n\n- Codex can write, compile and test C extensions for Python now\n\n- The sqlite3_progress_handler mechanism I've been hooking into for SQLite time limits in my Python code works in C too, and appears to be the recommended way to solve this\n\n- How to use PyTuple_New(size) in C and then populate that tuple\n\n- What the SQLite C API for running a query and then iterating though the results looks like, including the various SQLITE_INTEGER style constants for column types\n\n- The \"goto cleanup;\" pattern for cleaning up on errors, including releasing resources and calling DECREF for the Python reference counter\n\n- That a simple Python extension can be done with ~150 lines of readable and surprisingly non-threatening C\n\n- How to use a setup.py and pyproject.toml function together to configure a Python package that compiles an extension\n\nWould I have learned more if I had spent realistically a couple of days figuring out enough C and CPython and SQLite and setup.py trivia to do this without LLM help? Yes. But I don't have two days to spend on this flight of curiosity, so actually I would have learned nothing.\n\nThe LLM project took me ~1 minutes to prompt and then 15 minutes to consume the lessons at the end. And I can do dozens of this kind of thing a day, in between my other work!"
}
,
{
"id": "46491837",
"text": "With all due respect you were reading, not learning. It's like when people watch educational YouTube videos as entertainment, it feels like they're learning but they aren't.\n\nIt's fine to use the LLMs in the same way that people watch science YouTube content, but maybe don't frame it like it's for learning. It can be great entertainment tho."
}
,
{
"id": "46493026",
"text": "Disagree, it can be learning as long as you build out your mental model while reading. Having educational reading material for the exact thing you're working on is amazing at least for those with interest-driven brains.\n\nScience YouTube is no comparison at all: while one can choose what to watcha, it's a limited menu that's produced for a mass audience.\n\nI agree though that reading LLM-produced blog posts (which many of the recent top submissions here seem to be) is boring."
}
,
{
"id": "46493631",
"text": "The YouTube analogy doesn't completely hold.\n\nIt's more like jumping on a Zoom screen sharing session with someone who knows what they're doing, asking for a tailored example and then bouncing as many questions as you like off them to help understand what they did.\n\nThere's an interesting relevant concept in pedagogy called the \"Worked example effect\", https://en.wikipedia.org/wiki/Worked-example_effect - it suggests that showing people \"worked examples\" can be more effective than making them solve the problem themselves."
}
,
{
"id": "46493692",
"text": "Ok but you didn't ask any questions in the transcript you provided. Maybe that one was an outlier?\n\nIn order to learn you generally need to actually do the thing, and usually multiple times. My point is that it's easy to use an AI to shortcut that part, with a healthy dose of sycophancy to make you feel like you learned so well."
}
,
{
"id": "46494783",
"text": "Yeah in this particular case I didn't ask any follow-up questions directly to Claude Code - I pasted a few things into Claude chat though, here's one of those conversations: https://claude.ai/share/9c404b38-efed-4789-bea1-06bca5f5d6e4"
}
,
{
"id": "46489253",
"text": "The OP is not talking about making slop, he's talking about using AI to write good code."
}
,
{
"id": "46491082",
"text": "You were never able to stop using the techniques you learned, and you were always able to keep up with minimal effort - you didn’t need to learn any frameworks.\n\nI’m glad you’re having fun, but you didn’t need AI to overcome some laborious hurdle. The only hurdle that existed was your own laziness."
}
,
{
"id": "46495750",
"text": "Laziness, or job search, or parenting, or health issues, or caregiving, or something else. It's not a binary stay-current-or-you're-lazy situation, it's that the entire industry is moving to shorter timelines, smaller teams, and more technical complexity for web projects simultaneously. LLMs are a huge dopamine hit for short term gains when you're spinning plates day after day. The question is what the ecosystem will look like when everybody's been using LLMs as a stopgap for an extended period of time."
}
,
{
"id": "46496109",
"text": "For other people you may have a good point - I chose laziness for this person specifically because they mentioned not having to do it for so long that they didn’t know where to start. I do think of laziness a lot less negatively than other people do, though - indolence is not a sin, just a part of life.\n\nI do share your interest in the answer to that question, though."
}
,
{
"id": "46488981",
"text": "Not the first time I can't access a link posted here due being blocked in Spain."
}
,
{
"id": "46489090",
"text": "Are you using your ISP DNS? I’m in Spain as well and I can access the link just fine."
}
,
{
"id": "46489309",
"text": "I'm using Cloudflare's.\n\nI don't know how this blocking works. A couple minutes ago I could access this link but now I can't. It's happening with another website too. It's like an intermittent blocking today."
}
,
{
"id": "46489468",
"text": "Real Madrid's on today, so it must be LaLiga's bullshit once again.\n\nIf it helps, 8.8.8.8 is not giving me issues, not sure if it's something other than DNS breaking on your side though."
}
,
{
"id": "46489120",
"text": "Reading this from Tenerife airport and worked fine."
}
,
{
"id": "46493743",
"text": "> As a solo developer, you could manage everything. From idea to execution. Or at least, it felt that way\n\nIt's still that way with Rails. Probably other stacks. Sad that the default nowadays is so unproductive that solo devs don't think they can do things."
}
,
{
"id": "46492862",
"text": "Web development may be fun again but you aren’t developing.\nYou order and became a customer.\n\nMaybe you can distinguish good code from bad code but how long will you check it? Auditing wasn’t the fun part ever.\n\nAnd I bet at some point you will recognize a missing feeling of accomplishment because you didn’t figure out the how, you just ordered the what.\n\nWe wouldn’t call someone a painter who let AI do the painting."
}
,
{
"id": "46492531",
"text": "To me it seems like for OP development was a means towards an end. The act to developing software as a craft does not seem to be of importance to him while the output is. His post is full of references to productivity and lacking references of improving his skills (as opposed to using LLMs as a crutch) or getting better at writing software. I bet OP would be equally happy if he had AGI that would write everything for him.\n\nFor many in HN, programming is an end in itself and they would not be happy giving that up just because it makes you finish quicker."
}
,
{
"id": "46492446",
"text": "This is probably the best post i've seen about the whole LLM / vibe coding space at least in relation to web dev. Indeed, as the author states, the code / agent often needs some coralling, but if you know all the gotchyas / things to look for, you can focus 100% on the creativity part! Been loving it as well."
}
,
{
"id": "46500334",
"text": "Even with AI, web development is not fun. Web development was fun while the web was the wild west, and the rent-seekers hadn't gotten their hooks into it. These days you're likely to be delisted from Google because your site isn't responsive, or there's a 500 on a page or two. And then, for your patience and dedication, you get sued by a scummy lawyer who looks for sites with poor WCAG conformance. Congratulations!"
}
,
{
"id": "46491274",
"text": "Couldn’t agree more.\n\nChanging anything in oUR react Bootstrap frontend was a visit to the dentist.\n\nBut Llms really lowered the pain."
}
,
{
"id": "46490651",
"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... I remember when the biggest challenge was IE6 compatibility.\n\nIt is not necessary to do this. Server-side rendering is still a thing.\n\nI still do a lot of my side projects in ruby on rails, which is maybe not fashionable these days but:\n\n- no heavy js means speedy first paint\n\n- I just use normal minified css, no sass or other junk\n\n- partials means navigation is snappy\n\nPlus it containerizes nicely."
}
,
{
"id": "46492761",
"text": "Build pipelines, bundlers, CSS frameworks with their own toolchains, progressive web apps, Core Web Vitals, SEO, layout shifts, and srcset/responsive images have nothing to do with client/server rendering."
}
,
{
"id": "46492975",
"text": "With server-side rendering you don't need a frontend framework at all, is my point.\n\nYou also don't need a css tool chain at all, irrespective of whether or not you render on the frontend"
}
,
{
"id": "46489421",
"text": "Turbo C++ Vibe"
}
,
{
"id": "46488913",
"text": "AI is doing the chores while we paint."
}
,
{
"id": "46489007",
"text": "Except to me it feels more like AI is painting while I have to do the chores"
}
,
{
"id": "46489205",
"text": "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.\n\nWithout prior software dev experience people may take what the LLM gives them at face value, and that's where the slop comes from imho."
}
,
{
"id": "46492210",
"text": "> Clicks, expecting some new spec or framework that actually made web dev fun again\n\n> Looks inside\n\n> \"AI has entered the chat\"\n\nWhat did I even expect. I wonder how many clickbait posts of this type are gonna make the HN front page."
}
,
{
"id": "46493077",
"text": "Agreed. It almost feels like the majority of the top articles reek of LLM writing in bad ways."
}
,
{
"id": "46492045",
"text": "I feel u!"
}
,
{
"id": "46491814",
"text": "Web development is perhaps \"fun\" again if you consider PHP 4 and jQuery as \"fun\". A \"problem\" arises for those of us who prefer Ruby, Rails, and HotWire.\n\nI'm not gonna lie, I use AI every day (in the form of Grammarly). But LLMs and so-called \"agents\" are less valuable to me, even if they would help me to produce more \"output\".\n\nIt will be interesting to me to discover the outcome of this bifurcation!"
}
,
{
"id": "46488989",
"text": "When stuff was getting too complicated, I looked for ways to make things simpler.\n\nDevelopers 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."
}
,
{
"id": "46490659",
"text": "In a very real sense, developers efforts to make web development simpler have clearly failed. This is true regardless of the existence of LLMs and/or your opinion of their utility."
}
]
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