llm/0c2f997f-ee88-4da1-8587-79dca97bbc3f/batch-2-1f6af8ac-a111-40ba-8a9e-79c175624d60-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. 24/7 Work Culture Concerns
2. Labor Union Organization
3. Work-Life Balance Boundaries
4. Alternative Mobile Coding Setups
5. Git Worktrees Parallel Development
6. Push Notification Systems
7. Tailscale VPN Security
8. LLM Productivity Claims Skepticism
9. Capitalism and Worker Exploitation
10. Code Quality Without Review
11. Terminal Apps for Mobile
12. Session Persistence with Tmux
13. Anthropic Marketing Suspicions
14. Cloud VM Cost Efficiency
15. Cognitive Effects of LLM Use
16. Vibe Coding Quality Concerns
17. Open vs Proprietary AI Models
18. Future of Software Engineering Jobs
19. Multi-Agent Orchestration Tools
20. Voice Input for Mobile Coding
COMMENTS TO CLASSIFY:
[
{
"id": "46492453",
"text": "You can just say no."
}
,
{
"id": "46492667",
"text": "In many countries, these and other jobs show you cannot. If you don't, others will and so you won't have a job very soon. Especially if these types of jobs lose their shine/prestige and are basically call center quality/pay like jobs in 5-10 years."
}
,
{
"id": "46492509",
"text": "I'd love to believe that, but unless our timeline is disrupted (world war / climate change / regulation re: power generation and consumption), I unfortunately can't imagine a future different to the one I described - and I've tried!"
}
,
{
"id": "46492633",
"text": "Join a union."
}
,
{
"id": "46492707",
"text": "Move somewhere with strong worker rights/laws even if you are not in a union. Here no with a normal job (not freelancers / contractors etc) is looking at their work phone/email outside 9-5/4-5 days a week; this frustrates US companies who merge/acquire companies here greatly but they cannot do much (firing for no cause is very expensive) except slowly move the operation to the US and wind down here, which is expected; everyone is already looking for new jobs as no one wants the 'performance reviews' with the broken records like 'you are not a teamplayer because your colleague was trying to reach you at 22:00 Friday night'."
}
,
{
"id": "46492557",
"text": "This was the end game with or without AI. It was always going to result in a zero-sum game because the factories that are open around the clock can output more products - which is exactly why a lot of manufacturing has non stop shift work. If you don’t, you’re leaving money on the table and a competitor will gladly take it.\n\nWhen you saw 996 being talked about it should have set a few alarm bells off, because it started a countdown timer until such a work culture surpasses the rather leisurely attitude of the West in terms of output and velocity. West cannot compete against that no matter how many “work smarter, not harder” / “work to live don’t live to work” aphorisms it espouses. This should be obvious by now (in hindsight).\n\nYou can blame LLM or capitalism or communism but the hard matter is, it’s a money world and people want to have as much of it as they possibly can, and you and your children can’t live without it, and every day someone is looking to have more of it than you are."
}
,
{
"id": "46493205",
"text": "The Chinese are not doing 996 as much these days. It is illegal for starters."
}
,
{
"id": "46493473",
"text": "Chinese are way past 996 and onto 007"
}
,
{
"id": "46495383",
"text": "This has been like this forever. Change is that software engineers, historically spoiled and expensive is going to have a brutal reality check - aka we will work just everyone else."
}
,
{
"id": "46493104",
"text": "You have a profound amount of certainty about such an absurdly dystopian vision.\n\nWhy is that?"
}
,
{
"id": "46493465",
"text": "Experience."
}
,
{
"id": "46492148",
"text": "This is a pretty sophisticated setup. I particularly like how it uses Tailscale.\n\nI've been using the simpler but not as flexible alternative: I'm running Claude Code for web (Anthropic's version of Codex Cloud) via the Claude iPhone app, with an environment I created called \"Everything\" which allows all network access.\n\n(This is moderately unsafe if you're working with private source code or environment variables containing API keys and other secrets, but most of my stuff is either open source or personal such that I don't care if the source code leaks.)\n\nAnthropic run multiple ~21GB VMs for me on-demand to handle sessions that I start via the app. They don't charge anything extra for VM time which is nice.\n\nI frequently have 2-3 separate Claude Code for web sessions running at once, often prompted from my phone, some of them started while I'm out walking the dog. Works really well!"
}
,
{
"id": "46492255",
"text": "I don't like claude code web due to its lack of planning mode. I found the result is often lackluster compare to claude code cli.\n\nMy current setup: Tailscale + Terminus(ipad) + home machine(code base)\n\nNeed to look into how to work on multiple features at the same time next."
}
,
{
"id": "46492288",
"text": "I've been using git worktrees with Claude and it's pretty awesome:\n\nhttps://www.youtube.com/watch?v=up91rbPEdVc\n\nPair worktrees with the ralph-wiggum plugin and I can have Claude work for hours without needing any input:\n\nhttps://looking4offswitch.github.io/blog/2026/01/04/ralph-wi..."
}
,
{
"id": "46492661",
"text": "Worktrees took way too much setup and hand-holding for me, but https://conductor.build made it easy!"
}
,
{
"id": "46494155",
"text": "I delayed adopting conductor because I had my own worktree + pr wrappers around cc but I tried it over the holidays and wow. The combination of claude + codex + conductor + cc on the web and claude in github can be so insanely productive.\n\nI spend most of my time updating the memory files and reviewing code and just letting a ton of tasks run in parallel"
}
,
{
"id": "46494763",
"text": "software is all about wrappers, isn't it? :)\n\nconductor -> multiple claude codes/codexes -> multiple agents -> multiple tools/skills/sub-agents -> LLMs"
}
,
{
"id": "46492381",
"text": "I haven't missed planning mode myself. I tend to tell it \"write a detailed plan first in a file called spec.md for me to review\", then use that as the ongoing plan.\n\nI like that it ends up in the repo as it means it survives compaction or lets me start a fresh session entirely."
}
,
{
"id": "46493285",
"text": "I was doing the same, but recently I noticed that Claude now writes its plans to a markdown file somewhere nested in the ~/.claude/plans directory. It will carry a reference to it through compaction. Basically mimicking my own workflow!\n\nThis can be customized via a shell env variable that I cannot remember ATM.\n\nThe downside (upside?) is that the plan will not end up in your repo. Which sometimes I want. I love the native plan mode though."
}
,
{
"id": "46493542",
"text": "I've been really impressed with https://github.com/BloopAI/vibe-kanban to do this. Really really impressed."
}
,
{
"id": "46492315",
"text": "Can you not use PAL MCP for this? Have one top agent as controller etc? It's not ideal but it feels like the space of multi agent stuff is evolving ... I notice that there are a lot of posts on hn about these things so we are trying to do the same thing really."
}
,
{
"id": "46492712",
"text": "I'm surprised to see people getting value from \"web sandbox\"-type setups, where you don't actually have access to the source code. Are folks really _that_ confident in LLMs as to entirely give up the ability to inspect the source code, or to interact with a running local instance of the service? Certainly that would be the ideal, but I'm surprised that confidence is currently running that high."
}
,
{
"id": "46492895",
"text": "I still get the full source code back at the end, I tell it to include code it wrote in the PR.\n\nI also wrote my own tool to extract and format the complete transcript, it gives me back things like this where I can see everything it did including files and scripts it didn't commit. Here's an example: https://gistpreview.github.io/?3a76a868095c989d159c226b7622b..."
}
,
{
"id": "46492922",
"text": "Oh fascinating - so you're reviewing \"your own\" code in-PR, rather than reviewing it before PR submission? I can see that working! Feels weird, but I can see it being a reasonable adaptation to these tools - thanks!\n\nWhat about running services locally for manual testing/poking? Do you open ports on the Anthropic VM to serve the endpoints, or is manual testing not part of your workflow?"
}
,
{
"id": "46492948",
"text": "Yeah, I generally use PRs for anything a coding agent writes for me.\n\nIf something is too fiddly to test within the boundaries of a cloud coding agent I switch to my laptop. Claude Code for web has a \"claude --teleport\" command for this, or I'll sometimes just do a \"gh pr checkout X\" to get the branch locally."
}
,
{
"id": "46493078",
"text": "Much obliged, thank you!"
}
,
{
"id": "46492879",
"text": "The output from Jules is a PR. And then it's a toss-up between \"spot on, let's merge\" and \"nah, needs more work, I will check out the branch and fix it properly when I am the keyboard\". And you see the current diff on the webpage while the agent is working."
}
,
{
"id": "46493643",
"text": "Claude Code on the web, ChatGPT Codex and Google Jules are not the same as Claude, ChatGPT and Gemini. They are entire apps where you authorize Github access and they work via PRs.\n\nThey'll include screenshots on your PRs etc.\n\nI like using them a lot when I can."
}
,
{
"id": "46493811",
"text": "Right, yes, that was precisely my point - it was weird to me that people were comfortable operating on a codebase that they don't have locally, that they can't directly interact with."
}
,
{
"id": "46493919",
"text": "> it was weird to me that people were comfortable operating on a codebase that they don't have locally, that they can't directly interact with.\n\nI have a project where I've made a rule that no code is written by humans. It's been fun! It's a good experience to learn how far even pre-Opus 4.5 agents can be pushed.\n\nIt's pretty clear to me that in 12 months time looking at the code will be the exception, not the rule."
}
,
{
"id": "46493908",
"text": "when the agent pushes the PR, in a branch, you can switch to that branch locally on your machine and do whatever, review it, change it, and ask for extra modifications on top, squash it, rebase it"
}
,
{
"id": "46492700",
"text": "Check out superconductor.dev (I’m building it), if you want live app previews, docker-in-docker functionality, multiple agents in one mobile app, and more."
}
,
{
"id": "46493912",
"text": "I have my very fast macbook pro at my desk in my office, and I use tmux and tailscale and git worktrees and I’ve built a notification setup like this author.\n\nThanks to tailscale and ssh I can vibecode on the go from my phone with this setup.\n\nWhile it’s great to leave a task running, no matter what I do I can’t achieve the type of high quality work on the go that I can when I’m sitting at my desk.\n\nFor me working on a full SaaS.. I just can’t do quality work on my phone.\n\nThe only way I can do quality work is to sit at my desk where I’m focused on the work. To play with the result of a prompt, take copious notes, feed them back to the agent, not ship until the thing is polished to a shine. To feature flag the changes, review all code in excruciating detail as though it was written by a dyslexic intern, add all the metrics and logs one can think of (VictoriaMetrics), add user-behavior logging (Amplitude/Posthog) and monitor the thing like your livelihood depends on it. Because it’s a p"
}
,
{
"id": "46497182",
"text": "Same here, I’m vibecoding a toy project where I never looked at the code from my phone, but I always seat for work. I’m using happy app and that’s good enough for now, I have the desktop in tailscale but I access it that way just for testing"
}
,
{
"id": "46492618",
"text": "I don't like typing long messages on my phone so this workflow, as cool as it sounds, wouldn't work for me. My current setup is that I have a Claude Code hook that runs whenever CC needs my input and it uses my Home Assistant instance to send a push notification to my phone. I then return back to the computer and continue on the work.\n\nThis works reasonably well, but there is a gap for small messages or review comments. I am waiting for Anthropic to shop a feature where the Claude mobile app is able to mirror Claude Code (not the Claude desktop app) and lets me see the diffs of the changes it made and send commands. I'd use this to steer the conversation while on the go with short commands or prompts so that when I'm back at the computer I can focus on the important feedback that I can jot down quickly on the computer keyboard."
}
,
{
"id": "46497012",
"text": "I use the same setup myself, download WisprFlow for IOS and over time just add to its dictionary the unusual words you often use during development\n\nworks perfectly, i just say what i want coded, press enter, and Claude Code just does it in my server over Termius app"
}
,
{
"id": "46493215",
"text": "I also don't like typing long messages on my phone that's why I use this keyboard that will do high quality transcriptions via whatever AI provider you want. Much better than siri/google speech to text on device.\n\nhttps://github.com/DevEmperor/Dictate"
}
,
{
"id": "46497820",
"text": "I used to use Wispr Flow but did not like the non-local aspect, and having yet another subscription, so I switched to VoiceInk (one-time payment around $30 I think), and with a locally running Parakeet v3 model on my\nMacBook, transcription is basically instant. I was previously using it with the local Whisper Turbo 3 which is slightly more accurate and it had a 3-4 second lag, so I was absolutely shocked how fast parakeet v3. The slight drop in accuracy is totally fine when talking to AIs, and I also have a line in my CLAUDE.md that says I am usually dictating and that it should take that into account when interpreting my messages."
}
,
{
"id": "46493646",
"text": "I concur that phones aren't great as they are today, but perhaps this exact scenario will prompt the return of PDAs with proper keyboards etc? Or, alternatively, subcompact laptops like the stuff that https://gpdstore.net makes - they are still small enough to be pocketable (needs fairly large pockets but...), and yet you get a keyboard that is actually usable, and they even have one device with fold-out dual screen."
}
,
{
"id": "46492822",
"text": "I was looking for a similar scheme, and though far from perfect I found you can run tmux+ttyd. ttyd lets you share your terminal over http. That lets you use your phone's browser (and speech-2-text)."
}
,
{
"id": "46494817",
"text": "There has been a sustained campaign over the last few days to push \"I use Claude from my phone\". I saw multiple posts on LinkedIn already, and now this.\n\nThis blog is super sus too. All the posts are about Claude. I suspect it's run by Anthropic, just read the About page: https://granda.org/en/about/"
}
,
{
"id": "46495159",
"text": "I think your statement \"I use Claude from my phone\" is quite a large set of folks - the iOS app alone likely has several millions of installs."
}
,
{
"id": "46496659",
"text": "How hard is it to build a marketing agent these days?"
}
,
{
"id": "46495125",
"text": "Not everything is a conspiracy or content marketing by some bullshit company.\n\nI'm increasingly using Claude from my phone because the models are now good enough to use unsupervised.\n\nThere's nothing suspicious to me on that About page."
}
,
{
"id": "46497091",
"text": "7 USD/day? That's ~200/month -- isn't that just very expensive? I am probably missing something.\n\nE.g. a Terragonlabs subscription is 25/month for 3 concurrent tasks and 50/month for 10."
}
,
{
"id": "46497561",
"text": "You can optimize things. I have a github action that starts stops a fast google cloud vm for our builds. It only gets used about 3 minutes per build. We maybe have a few dozen builds per month. So that's a few hours of run time. The rest of the time the vm is stopped and not billed (except for storage, which is cents per month at most). It's a simple debian vm so it boots in about 20 seconds.\n\nVMs are expensive if you leave them running 24/7 but the logic to start/stop them is pretty easy. There's no need.\n\nAnyway, you need to balance this against the payoff. Agentic coding is useful enough that it beats spending your own time. And that includes waiting time for the relatively slow/underpowered containerized environments that some tools would use by default. I use codex web and codex cli (with a qemu vm so I can use the --yolo flag). Codex web is a bit limited with memory and CPU. Some of my slower builds are taking forever there. To the point where most of the time it consumes is just"
}
,
{
"id": "46497139",
"text": "If you are already paying $200-500/m… and you are doing the work of 10 people… I can totally see the value.\n\nI’ll check the Terragonlabs option.\n\nLots of options for startups right now, selling pickaxes! I’m waiting for a better terminal experience, personally. I can’t deal with 30+ poorly named windows. I need to be able to search for that one thread I was working on yesterday…"
}
,
{
"id": "46497220",
"text": "> I’m waiting for a better terminal experience, personally.\n\nSame! Even colored tabs would go a long way for me."
}
,
{
"id": "46493529",
"text": "I've been working on something similar: https://github.com/shepherdjerred/monorepo/tree/main/package...\n\nEssentially you run a server on some machine. Sessions are created in Docker containers, K8s pods, or via Zellij (an app similar to tmux). You can:\n\n- Directly attach to sessions via Docker attach (built-in via a TUI). You get a normal Claude Code experience, but multiplexed. The switcher/UI shows you the status of Claude and the PR (pushed, merge conflicts, CI status, review status, etc.)\n\n- Manage sessions via a web UI. Connect to Claude Code directly via your browser. You have access to the usual Claude Code terminal or a native chat view.\n\n- Manage sessions via an app. You have access to a native chat view.\n\nIt achieves isolation via Git worktrees + a proxy so that containers have access to zero credentials (there aren't even any Claude code creds in the container), which allows you to more safely use bypass all permissions mode.\n\nThis works better for me that Claude Code on Web"
}
,
{
"id": "46494107",
"text": "Looks super nice, will take it for a spin."
}
]
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