llm/c92d54db-e3c8-419f-931f-0c3a686c0e4d/batch-3-75234737-f61f-4dcc-bdf6-0c98bed18510-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 coding vs results
3. Parent/manager time constraints
4. Vibe coding criticism
5. Web development complexity
6. Learning with AI assistance
7. Code review burden
8. Frontend framework criticism
9. Solo developer challenges
10. AI as skill crutch
11. Hobby project completion
12. Cost of AI tools
13. Pattern recognition experience
14. Management skills transfer
15. Identity crisis for developers
16. Local vs cloud AI models
17. Unnecessary toolchain complexity
18. Code quality concerns
19. Generalist vs specialist debate
20. Mental model building
COMMENTS TO CLASSIFY:
[
{
"id": "46491562",
"text": "That IKEA analogy is pretty good, because plenty of people use IKEA furniture to solve the \"I need a bookshelf\" problem - and often enjoy the process - without feeling like they should call themselves a carpenter. 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."
}
,
{
"id": "46493248",
"text": "Definitely. I'm not disparaging the process of assembling IKEA furniture, nor the process of producing software using LLMs. I've done both, and they have their time and place. 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 fo"
}
,
{
"id": "46492964",
"text": "Little bit of a sweeping generalization there. There are a huge range of ways in which LLMs are being leveraged for software development. Using a drill doesn’t make you any less of a carpenter, even if you stopped using a screwdriver because your wrists are shot."
}
,
{
"id": "46491327",
"text": "It's called being a systems analyst or product manager. Upskill into these roles (while still accepting individual contributor pay) or get left behind."
}
,
{
"id": "46491518",
"text": "I'm sorry, \"upskill\"? The roles you mentioned don't require any more advanced skills than those required for software development—just a different set of skills. 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."
}
,
{
"id": "46489115",
"text": "I was just getting pretty sick and tired of programming, instead now AI can write the code down while I do the fun things of figuring out how shit works and general device hacking + home projects"
}
,
{
"id": "46491983",
"text": "What do LLM's have to do returning to coding? Just... ...write the code. Stop being lazy."
}
,
{
"id": "46490981",
"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. You only have those things if you choose to use them. I've been building websites for 25 years. I use the same core technologies today that I did when I started. Sure, I make use of modern improvements to the languages themselves, but I have never permanently adopted any of the \"hot new trends\" and feel I am better - or at least saner - for it. No, your marketing or e-commerce website almost certainly doesn't need a JS bundling toolchain. It almost certainly doesn't need a CSS preprocessor or even a CSS boilerplate/framework. It almost certainly doesn't need an enterprise-class PHP framework; or a dependency manager; or a CI/CD pipeline."
}
,
{
"id": "46491165",
"text": "Those technologies don't just solve tech issues, they solve organizational issues. If one or two people manage a website, going without fancy tooling is completely fine. When 1000 people are managing a product with complex business logic across multiple platforms, you need fancy tooling to ensure everyone can work at a reasonable level of productivity."
}
,
{
"id": "46494327",
"text": "> you need fancy tooling to ensure everyone can work at a reasonable level of productivity. If you have a thousand people working on a single product, yes, but you also have the resources to have dedicated tool support teams at that level. In my experience, if you’re under multiple dozens of developers or not everyone works on all of your projects, the tools fragment because people aren’t combining or configuring them the same way and there’s enough churn in the front-end tool space that you’ll hit various compatibility issues which lower the effectiveness of sharing across projects. This is especially true if you’ve hired people who self-identify as, say, Next or Tailwind developers rather than web developers and lack the understanding of the underlying technology to fix complex problems."
}
,
{
"id": "46493435",
"text": "> build pipelines, bundlers, CSS frameworks with their own toolchains, progressive web apps, Core Web Vitals, SEO, layout shifts, srcset/responsive images Build pipelines are purely a technical decision. Bundlers are purely a technical decision (TBH, a non-brainer if you decide to have a build pipeline, but it's not an organizational helper). Those help one do some things, not several people to organize. I'm still waiting for any person to claim they made CSS maintainable by adopting a framework. It's an almost purely organizational decision with no upsides at all. PWAs are a product decision, not technical or organizational. The same applies to Core Web Vitals, SEO, layout shifts and srcset, those are all product decisions. You can escape the technical and organizational decisions. You can't escape the product ones."
}
,
{
"id": "46491854",
"text": "The article is about developing as a solo developer."
}
,
{
"id": "46491029",
"text": "What are you using? If you don't mind me asking."
}
,
{
"id": "46491136",
"text": "It's so weird to see this take repeated over and over. I have to assume you have never written a large scale project for the web? The only part where I agree is that you don't need PHP or server-side rendering in general."
}
,
{
"id": "46492209",
"text": "Nowhere he talked about large scale projects and the article neither btw. I am sure his choices are different when working on a large scale project."
}
,
{
"id": "46491361",
"text": "I used to think the same about server-side rendering until I more closely looked at React SSR. I think it makes a lot of sense and allows for faster initial rendering of the page while automatically setting up the JS and interactivity in the background."
}
,
{
"id": "46491566",
"text": "Couldn't you just static render the parts that you're using SSR for? I am not trying to be dismissive, but a common strict requirement is static hosting from a CDN, embedded environments, etc."
}
,
{
"id": "46492574",
"text": "If you static render, it won't be an interactive application. With React SSR you get the best of both: stream static HTML chunks immediately, and rehydrate with JS later, prioritizing components the user interacts with. It should load quicker compared to traditional React apps where the browser loads the HTML, then loads the JS bundle, and only then renders a loading skeleton while likely triggering more requests for data."
}
,
{
"id": "46494275",
"text": "> It should load quicker compared to traditional React apps where the browser loads the HTML, then loads the JS bundle, and only then renders a loading skeleton while likely triggering more requests for data. Then your JS bundle is broken. Promises exist. Modules exist. HTTP/2+ exists. You can load data while you are loading a small amount of JS required to render that data while you are loading other parts of your JS. If everything is sequential: load giant JS bundle -> fetch -> render, that's because someone architected it like that. Browsers give you all the tools you need to load in parallel, if you don't use them then it's not the browser's fault. You do not need SSR or rehydration. That's just Vercel propaganda. They saw that people are doing a stupid thing and decided to push a complex solution to it. Why? It makes them money."
}
,
{
"id": "46493308",
"text": "You seem to be confused about your terms, both SSR and SSG can rehydrate and become interactive, you only need SSR if you have personalized content that must be fetched on an actual user request, and with frameworks like astro introducing island concept it even let's you mix SSG and SSR content on a single page."
}
,
{
"id": "46492855",
"text": "Static rendering has nothing to do with interactivity in a web app. I guess if you're already so deeply entrenched in writing all your application logic on the server side you need React SSR, but that sounds miserable."
}
,
{
"id": "46493910",
"text": "I enjoy when: Things are simple. Things are a complicated, but I can learn something useful. I do not enjoy when: Things are arbitrarily complicated. Things are a complicated, but I'm just using AI to blindly get something done instead of learning. Things are arbitrarily complicated and not incentivized to improve because now \"everyone can just use AI\" It feels like instead of all stepping back and saying \"we need to simplify things\" we've doubled down on abstraction _again_"
}
,
{
"id": "46494523",
"text": "Fun is the way, not the destiny"
}
,
{
"id": "46489004",
"text": "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, phpMyAd"
}
,
{
"id": "46490902",
"text": "> Even with refinement and back-and-forth prompting, I’m easily 10x more productive Developers notoriously overestimate the productivity gains of AI, especially because it's akin to gambling every time you make a prompt, hoping for the AI's output to work. I'd be shocked if the developer wasn't actually less productive."
}
,
{
"id": "46490979",
"text": "I accept there are productivity gains, but it's hard to take \"10x\" seriously. It's such a tired trope. Is no one humble enough to be a meager 2.5x engineer?"
}
,
{
"id": "46491027",
"text": "Even 2.5x is absurd. If they said 1.5x I might believe them."
}
,
{
"id": "46491149",
"text": "I'm building an AI agent for Godot, and in paid user testing we found the median speed up time to complete a variety of tasks[0] was 2x. This number was closer to 10x for less experienced engineers [0] tasks included making games from scratch and resolving bugs we put into template projects. There's no perfect tasks to test on, but this seemed sufficient"
}
,
{
"id": "46491281",
"text": "That sounds reasonable to me. AI is best at generating super basic and common code, it will have plenty of training on game templates and simple games. Obviously you cannot generalize that to all software development though."
}
,
{
"id": "46494034",
"text": "> That sounds reasonable to me. AI is best at generating super basic and common code I'm currently using AI (Claude Code) to write a new Lojban parser in Haskell from scratch, which is hardly something \"super basic and common\". It works pretty well in practice, so I don't think that assertion is valid anymore. There are certainly differences between different tasks in terms of what works better with coding agents, but it's not as simple as \"super basic\"."
}
,
{
"id": "46494192",
"text": "I'm sure there is plenty of language parsers written in Haskell in the training data. Regardless, the question isn't if LLMs can generate code (they clearly can), it's if agentic workflows are superior to writing code by hand."
}
,
{
"id": "46494248",
"text": "There's no shortage of parsers in Haskell, but parsing a human language is very different from parsing a programming language. The grammar is much, much more complex, and this means that e.g. simple approaches that adequate error messages don't really work here because failures are non-actionable."
}
,
{
"id": "46491818",
"text": "As you get deeper beyond the starter and bootstrap code it definitely takes a different approach to get value. This is in part because context limits of large code bases and because the knowledge becomes more specialized and the LLM has no training on that kind of code. But people are making it work, it just isn't as black and white."
}
,
{
"id": "46491396",
"text": "One concern is those less experienced engineers might never become experienced if they’re using AI from the start. Not that everyone needs to be good at coding. But I wonder what new grads are like these days. I suspect few people can fight the temptation to make their lives a little easier and skip learning some lessons."
}
,
{
"id": "46491192",
"text": "I recently used AI to help build the majority of a small project (database-driven website with search and admin capabilities) and I'd confidently say I was able to build it 3 to 5 times faster with AI. For context, I'm an experienced developer and know how to tweak the AI code when it's wonky and the AI can't be coerced into fixing its mistakes."
}
,
{
"id": "46491328",
"text": "What's the link?"
}
,
{
"id": "46491398",
"text": "The site is password protected because it's intended for scholarly researchers, and ironically the client doesn't want LLMs scraping it."
}
,
{
"id": "46491161",
"text": "Numbers don't matter if it makes you \"feel\" more productive. I've started and finished way more small projects i was too lazy to start without AI. So infinitely more productive? Though I've definitely wasted some time not liking what AI generated and started a new chat."
}
,
{
"id": "46491242",
"text": "> Numbers don't matter Yes that's already been well established."
}
,
{
"id": "46493737",
"text": "From one personal project, Last month: 128 files changed, 39663 insertions(+), 4439 deletions(-) Range: 8eb4f6a..HEAD Non-merge commits: 174 Date range (non-merge): 2025-12-04 → 2026-01-04 (UTC) Active days (non-merge): 30 Last 7 days: 59 files changed, 19412 insertions(+), 857 deletions(-) Range: c8df64e..HEAD Non-merge commits: 67 Date range (non-merge): 2025-12-28 → 2026-01-04 (UTC) Active days (non-merge): 8 This has a lot of non-trivial stuff in it. In fact, I'm just about done with all of the difficult features that had built up over the past couple years."
}
,
{
"id": "46492928",
"text": "Don't worry, it's an LLM that wrote it based on the patterns in the text, e.g. \"Starting a new project once felt insurmountable. Now, it feels realistic again.\""
}
,
{
"id": "46493080",
"text": "That is a normal, run of the mill sentence."
}
,
{
"id": "46493114",
"text": "I can't prove it of course but I stand by it."
}
,
{
"id": "46494051",
"text": "Claiming that use of more complicated words and sentences is evidence of LLM use is just paranoia. Plenty of folk write like OP does, myself included."
}
,
{
"id": "46494232",
"text": "One of my favorite engineers calls AI a \"wish fulfillment slot machine.\""
}
,
{
"id": "46490973",
"text": "Just as a personal data point, are you a developer? Do you use AI?"
}
,
{
"id": "46491011",
"text": "Yes and yes."
}
,
{
"id": "46491054",
"text": "And you find yourself less productive?"
}
,
{
"id": "46491099",
"text": "No but I don't use it to generate code usually. I gave agents a solid go and I didn't feel more productive, just became more stupid."
}
,
{
"id": "46491376",
"text": "A year or so ago I was seriously thinking of making a series of videos showing how coding agents were just plain bad at producing code. This was based on my experience trying to get them to do very simple things (e.g. a five-pointed star, or text flowing around the edge of circle, in HTML/CSS). They still tend to fail at things like this, but I've come to realize that there are whole classes of adjacent problems they're good at, and I'm starting to leverage their strengths rather than get hung up on their weaknesses. Perhaps you're not playing to their strengths, or just haven't cracked the code for how to prompt them effectively? Prompt engineering is an art, and slight changes to prompts can make a big difference in the resulting code."
}
]
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