llm/122b8d72-a8a3-4fcf-8eca-6a52786d1a8b/batch-3-e4a73837-f244-4668-9df9-fbc1955442c1-input.json
The following is content for you to classify. Do not respond to the comments—classify them.
<topics>
1. Lack of Concrete Evidence
Related: Commenters repeatedly criticize the article for providing no examples, code, projects, costs, or specifics about what was actually built, calling it empty hype and platitudes without substance or proof of claims
2. Author Credibility Concerns
Related: Multiple commenters point to the author's previous blog post praising the Rabbit R1 as evidence of poor technical judgment and tendency toward unfounded enthusiasm for new technology
3. AI Coding Tool Limitations
Related: Discussion of how AI tools work well for simple, repetitive, or locally-scoped tasks but fail with complex systems, large codebases, and non-trivial problems requiring significant human guidance
4. Greenfield vs Legacy Projects
Related: Observations that AI coding excels at new projects under 10,000 lines of code but struggles maintaining consistency and avoiding regressions in larger, established codebases
5. Astroturfing Suspicions
Related: Multiple commenters suspect pro-AI posts are marketing campaigns or astroturfing given the billions invested in AI, with some noting suspicious voting patterns and repetitive promotional content
6. AI-Generated Content Detection
Related: Many suspect the blog post itself was written by AI, citing lack of specifics, excessive em-dashes, and generic promotional language characteristic of LLM-generated slop
7. Manager Fantasy Critique
Related: Skepticism about the desire to become a 'super manager' rather than hands-on developer, with some viewing it as CEO cosplay or escapism from actual technical work
8. Productivity Illusion
Related: Discussion of whether AI tools create actual productivity gains or merely the feeling of productivity, with some noting impressive-looking output that lacks substance or quality
9. Security Concerns
Related: Significant worry about OpenClaw's security vulnerabilities, prompt injection risks, and the danger of giving AI agents access to production systems, emails, and sensitive data
10. Skills and Learning Curve
Related: Debate over whether effective AI tool usage requires significant skill development, with some arguing poor results indicate user skill issues while others see fundamental tool limitations
11. Real World Use Cases
Related: Commenters share legitimate use cases including utility scripts, exploring unfamiliar codebases, setup automation, and learning new tools, distinguishing these from transformative claims
12. Cost and Accessibility
Related: Discussion of the financial barriers including expensive subscriptions, Mac Mini hardware, and token costs that contradict claims of democratizing technology
13. AI Hype Cycle
Related: Observations that we're at the apex of AI hype, with predictions the bubble will pop and more realistic assessments will emerge over time
14. Context Window Problems
Related: Technical discussion of how AI agents lose coherence as context grows, with compaction causing confusion and requiring human redirection
15. Testing and Verification
Related: Emphasis on the need for humans to verify AI output, run tests, and maintain quality control since AI cannot reliably check its own work
16. Language-Specific Performance
Related: Observations that AI performs better with some programming languages like Python and JavaScript compared to Java, Scala, or enterprise frameworks
17. Engineering vs Management
Related: Philosophical debate about why engineers want to become managers, whether it's about power, career progression, avoiding obsolescence, or building bigger things
18. Model Selection Matters
Related: Discussion of significant quality differences between AI models, with frontier models like Opus and GPT-5.2 performing notably better than cheaper alternatives
19. Workflow Integration Tips
Related: Practical advice including using AGENTS.md files, breaking tasks into smaller chunks, brainstorming with agents, and having separate contexts for review and implementation
20. Vibe Coding Skepticism
Related: Criticism of fully autonomous AI coding without understanding the output, with warnings about technical debt, logical errors, and unmaintainable code accumulation
0. Does not fit well in any category
</topics>
<comments_to_classify>
[
{
"id": "46936416",
"text": "> only for the first ~10kloc. After that the AI, no matter how well you try to prompt it, will start to destroy existing features accidentally\n\nI am using them in projects with >100kloc, this is not my experience.\n\nat the moment, I am babysitting for any kloc, but I am sure they will get better and better."
}
,
{
"id": "46936802",
"text": "It's fine at adding features on a non-vibecoded 100kloc codebase that you somewhat understand. It's when you're vibecoding from scratch that things tend to spin out at a certain point.\n\nI am sure there are ways to get around this sort of wall, but I do think it's currently a thing."
}
,
{
"id": "46940272",
"text": "You just have another agent/session/context refactor as you go.\n\nI built a skribbl.io clone to use at work. We like to play eod on Friday as a happy hour and when we would play skribbl.io we would try to get screencaps of the stupid images we were drawing but sometimes we would forget. So I said I'd use claude to build our own skribbl.io that would save the images.\n\nI was definitely surprised that claude threaded the needle on the task pretty easily, pretty much single shot. Then I continued adding features until I had near parity. Then I added the replay feature. After all that I looked at the codebase... pretty much a single big file. It worked though, so we played it for the time being.\n\nI wanted to fix some bugs and add more features, so I checked out a branch and had an agent refactor first. I'd have a couple context/sessions open and I'd one just review, the other refactored, and sometimes I'd throw a third context/session in there that would just write and run tests.\n\nThe LLM will build things poorly if you let it, but it's easy to prompt it another way and even if you fail that and back yourself into a corner, it's easy to get the agents to refactor.\n\nIt's just like writing tests, the llms are great at writing shitty useless tests, but you can be specific with your prompt and in addition use another agent/context/session to review and find shitty tests and tell you why they're shitty or look for missing tests, basically keep doing a review, then feed the review into the agent writing the tests."
}
,
{
"id": "46939400",
"text": "Meanwhile, in the grandparent comment:\n\n> Somehow 90% of these posts don't actually link to the amazing projects that their author is supposedly building with AI.\n\nYou are in the 90%."
}
,
{
"id": "46939560",
"text": "I’m using it in a >200kloc codebase successfully, too. I think a key is to work in a properly modular codebase so it can focus on the correct changes and ignore unrelated stuff.\n\nThat said, I do catch it doing some of the stuff the OP mentioned— particularly leaving “backwards compatibility” stuff in place. But really, all of the stuff he mentions, I’ve experienced if I’ve given it an overly broad mandate."
}
,
{
"id": "46936880",
"text": "Yes, this is my experience as well. I've found the key is having the AI create and maintain clear documentation from the beginning. It helps me understand what it's building, and it helps the model maintain context when it comes time to add or change something.\n\nYou also need a reasonably modular architecture which isn't incredibly interdependent, because that's hard to reason about, even for humans.\n\nYou also need lots and lots (and LOTS) of unit tests to prevent regressions."
}
,
{
"id": "46938106",
"text": "Where are you getting the 10kloc threshold from? Nice round number...\n\nSurely it depends on the design. If you have 10 10kloc modular modules with good abstractions, and then a 10k shell gluing them together, you could build much bigger things, no?"
}
,
{
"id": "46936816",
"text": "I wonder if you can up the 10kloc if you have a good static analysis of your tool (I vibecoded one in Python) and good tests. Sometimes good tests aren't possible since there are too many different cases but with other forms of codes you can cover all the cases with like 50 to 100 tests or so"
}
,
{
"id": "46938393",
"text": "Could you elaborate on the static analysis?"
}
,
{
"id": "46935082",
"text": "I agree with you in part, but I think the market is going to shift so that you won’t so many need “mega projects”. More and more, projects will be small and bespoke, built around what the team needs or answering a single question rather than forcing teams to work around an established, dominant solution."
}
,
{
"id": "46935236",
"text": "How much are you willing to bet on this outcome and what metrics are you going to measure it with when we come to collect in 3 years?"
}
,
{
"id": "46935610",
"text": "This is the way: make every one of these people with their wild ass claims put their money where their mouths are."
}
,
{
"id": "46935947",
"text": "Hold up. This is a funny comment but thinking should be free. It’s when they are trying to sell you something (looking at you “all the AI CEOs”) that unsubstantiated claims are problematic.\n\nThen again the problem is that the public has learned nothing from the theranos and WeWorks and even more of a problem is that the vc funding works out for most of these hype trains even if they never develop a real business.\n\nThe incentives are fucked up. I’d not blame tech enthusiasts for being too enthusiastic"
}
,
{
"id": "46936417",
"text": "It's not the public, the general public would like to see tech ceo heads on spikes (first politician to jail Zuckerberg will win re-election for the rest of their short lives) but the general attitude in DC is to capitulate because they believe the lies + the election slush fund money doesn't hurt."
}
,
{
"id": "46936302",
"text": "I'm fine with free thinking, but a lot of these are just so repetitive and exausting because there's absolutely no backing from any of those claims or a thread of logic.\n\nMight as well talk about how AI will invent sentient lizards which will replace our computers with chocolate cake."
}
,
{
"id": "46936670",
"text": "> Hold up. This is a funny comment but thinking should be free.\n\nThinking usually happens inside your head."
}
,
{
"id": "46937005",
"text": "“Holy tautology Batman.”\n\nWhat is your point?\n\nIf you’re trying to say that they should have kept their opinion to themselves, why don’t you do the same?\n\nEdit: tone down the snark"
}
,
{
"id": "46937108",
"text": "> What is your point?\n\nHoly Spiderman what is your point? That if someone says something dumb I can never challenge them nor ask them to substantiate/commit?\n\n> tone down the snark\n\nIt's amazing to me that the neutral observation \"thinking happens in your head\" is snarky. Have you ever heard the phrase \"tone police\"?"
}
,
{
"id": "46940860",
"text": "No. Sorry. I meant my own snark."
}
,
{
"id": "46932218",
"text": "You’re right, but on the other hand once you have a basic understanding security, architecture, etc you can prompt around these issues. You need a couple of years of experience but that’s far less then the 10-15 years of experience you needed in the past.\n\nIf you spend a couple of years with an LLM really watching and understanding what it’s doing and learning from mistakes, then you can get up the ladder very quickly."
}
,
{
"id": "46932304",
"text": "I find that security, architecture, etc is exactly the kind of skill that takes 10-15 years to hone. Every boot camp, training provider, educational foundation, etc has an incentive to find a shortcut and we're yet to see one.\n\nA \"basic\" understanding in critical domains is extremely dangerous and an LLM will often give you a false sense of security that things are going fine while overlooking potential massive security issues."
}
,
{
"id": "46934319",
"text": "Somewhere on an HN thread I saw someone claiming that they \"solved\" security problems in their vibe-coded app by adding a \"security expert\" agent to their workflow.\n\nAll I could think was, \"good luck\" and I certainly hope their app never processes anything important..."
}
,
{
"id": "46935882",
"text": "Found a problem? Slap another agent on top to fix it. It’s hilarious to see how the pendulum’s swung away from “thinking from first principles as a buzzword”. Just engineer, dammit…"
}
,
{
"id": "46938399",
"text": "But if you are not saving \"privileged\" information who cares? I mean think of all the WordPress sites out there. Surely vibecoding is not SO much worse than some plugin monstrosity.... At the end of the day if you are not saving user info, or special sauce for your company, it's no issue. And I bet a huge portion of apps fall into this category..."
}
,
{
"id": "46934558",
"text": "> If you spend a couple of years with an LLM really watching and understanding what it’s doing and learning from mistakes, then you can get up the ladder very quickly.\n\nI don't feel like most providers keep a model for more than 2 years. GPT-4o got deprecated in 1.5 years. Are we expecting coding models to stay stable for longer time horizons?"
}
,
{
"id": "46936264",
"text": "This is the funniest thing I've read all week."
}
,
{
"id": "46936270",
"text": "Don't you think it has gotten an order of magnitude better in the last 1-2 years? If it only requires another an order of magnitude improvement to full-on replace coders, how long do you think that will take?"
}
,
{
"id": "46936465",
"text": "Who is liable for the runtime behavior of the system, when handling users’ sensitive information?\n\nIf the person who is liable for the system behavior cannot read/write code (as “all coders have been replaced”), does Anthropic et al become responsible for damages to end users for systems its tools/models build? I assume not.\n\nHow do you reconcile this? We have tools that help engineers design and build bridges, but I still wouldn’t want to drive on an “autonomously-generated bridge may contain errors. Use at own risk” because all human structural engineering experts have been replaced.\n\nAfter asking this question many times in similar threads, I’ve received no substantial response except that “something” will probably resolve this, maybe AI will figure it out"
}
,
{
"id": "46937148",
"text": "If you look at his github you can see he is in the first week of giving into the vibes. The first week always leads to the person making absurd claims about productivity."
}
,
{
"id": "46940453",
"text": "Here’s mine\n\nhttps://apps.apple.com/us/app/snortfolio/id6755617457\n\n30kloc client and server combined. I built this as an experiment in building an app without reading any of the code. Even ops is done by claude code. It has some minor bugs but I’ve been using it for months and it gets the job done. It would not have existed at all if I had to write it by hand."
}
,
{
"id": "46936456",
"text": "To be fair, AI probably wrote the blog post from a short prompt, which would explain the lack of detail."
}
,
{
"id": "46941300",
"text": "This is 100% the case."
}
,
{
"id": "46932198",
"text": "Specifics on the setup. Specifics on the projects.\n\nSHOW ME THE MONEY!!!"
}
,
{
"id": "46936196",
"text": "exactly. so much text with so little actionable or notable content... actually 0"
}
,
{
"id": "46932297",
"text": ">Somehow 90% of these posts don't actually link to the amazing projects that their author is supposedly building with AI.\n\nMaybe they don't feel like sharing yet another half working Javascript Sudoku Solver or yet another half working AI tool no one will ever use?\n\nProbably they feel amazed about what they accomplished but they feel the public won't feel the same."
}
,
{
"id": "46935600",
"text": "Then, in my opinion, there's nothing revolutionary about it (unless you learned something, which... no one does when they use LLMs to code)"
}
,
{
"id": "46936293",
"text": "I am an old school c++ programmer and actually I have learned modern c++ just by using LLMs."
}
,
{
"id": "46935717",
"text": "The article made it seem that the tool made them into the manager of a successful company, rather than the author of a half finished pet project"
}
,
{
"id": "46940663",
"text": "Grifters gotta grift.\nThere is so much money on the line and everyone is trying to be an influencer/“thought leader” in the area.\n\nNobody is actually using AI for anything useful or THEY WOULDNT BE TALKING ABOUT IT. They’d be disrupting everything and making billions of dollars.\n\nInstead this whole AI grift reads like “how to be a millionaire in 10 days” grifts by people that aren’t, in fact, millionaires."
}
,
{
"id": "46933711",
"text": "AI is great, harness don't matter (I just use codex). Use state of the art models.\n\nGPT-5.2 fixed my hanging WiFi driver: https://gist.github.com/lostmsu/a0cdd213676223fc7669726b3a24..."
}
,
{
"id": "46936019",
"text": "Fixing mediatek drivers is not the flex you think it is."
}
,
{
"id": "46936157",
"text": "It is if it's something they couldn't do on their own before.\n\nIt's a magical moment when someone is able to AI code a solution to a problem that they couldn't fix on their own before.\n\nIt doesn't matter whether there are other people who could have fixed this without AI tools, what matters is they were able to get it fixed, and they didn't have to just accept it was broken until someone else fixed it."
}
,
{
"id": "46938430",
"text": "Right!? It's like me all the sudden being able to fix my car's engine. I mean, sure, there are mechanics, and it surely isn't rocket science, but I couldn't do it before and now I can!!! A miracle!\n\nCue the folks saying \"well you could DIE!!!\" Not if I don't fix brakes, etc ..."
}
,
{
"id": "46938099",
"text": "It was an easy fix for someone who already knows how WiFi drivers work and functions provided to them by Linux kernel. I am not one of these people though. I could have fixed it myself, but it would take a week just to get accustomed to the necessary tools."
}
,
{
"id": "46936321",
"text": "This was incredibly vague and a waste of time.\n\nWhat type of code? What types of tools? What sort of configuration? What messaging app? What projects?\n\nIt answers none of these questions."
}
,
{
"id": "46937535",
"text": "Yeah, i’ve gone to the point where I will just stop reading AI posts after a paragraph or two if there are no specifics. The “it works!” / “no it doesn’t” genre is saturated with generality. Show, don’t tell, or I will default to believing you don’t have anything to show at all."
}
,
{
"id": "46937779",
"text": "That was very vague, but I kinda get where they're coming from.\n\nI'm now using pi (the thing openclaw is built on) and within a few days i build a tmux plugin and semaphore plugin^1, and it has automated the way _I_ used to use Claude.\n\nThe things I disagree with OP is: The usefulness of persistent memory beyond a single line in AGENTS.md \"If the user says 'next time' update your AGENTS.md\", the use of long-running loops, or the idea that everything can be resolved via chat - might be true for simple projects, but any original work needs me to design the 'right' approach ~5% of the time.\n\nThat's not a lot, but AI lets you create load-bearing tech-debt within hours, at which point you're stuck with a lot of shit and you dont know how far it got smeared.\n\n[1]: https://github.com/offline-ant"
}
,
{
"id": "46939876",
"text": "Would you describe your Claude workflow?"
}
,
{
"id": "46940417",
"text": "They're not coming from anywhere. It's an LLM-written article, and given how non-specific it is, I imagine the prompt wasn't much more than \"write an article about how OpenClaw is changing my life\".\n\nAnd the fact this post has 300+ comments, just like countless LLM-generated articles we get here pretty much daily... I guess proves the point in a way?"
}
,
{
"id": "46937117",
"text": "Well, note that the previous post was about how great the Rabbit R1 is…"
}
]
</comments_to_classify>
Based on the comments above, assign each to up to 3 relevant topics.
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
]
}
,
{
"id": "comment_id_3",
"topics": [
0
]
}
,
...
]
Rules:
- Each comment can have 0 to 3 topics
- Use 1-based topic indices for matches
- Use index 0 if the comment does not fit well in any category
- Only assign topics that are genuinely relevant to the comment
Remember: Output ONLY the JSON array, no other text.
50