Skip to content
Source material

Complaints database

29,255 raw documents, unedited and searchable. This is what everything else on the site is built from — nothing here is generated.

  • Hacker News2026-07-11source ↗

    Write code like a human will maintain it

    A couple of notes for anyone reading this comment and thinking of implementing something similar: - You should use skills instead of commands (commands still work, but they've been rolled into skills) https://code.claude.com/docs/en/skills - Hardcoding git diff against main isn't always ideal…

  • Hacker News2026-07-11source ↗

    Muse Spark 1.1

    It’s just inherently a difficult problem to solve, I think (just like with human individual contributors, where there famously also doesn’t exist one universal, automated process). “Good” benchmarks to gauge development skills at the moment seem to be: DeepSWE [0] by Datacurve FrontierCode [1] by Cognition And then th…

  • Hacker News2026-07-11source ↗

    GPT-5.6, Grok 4.5, Claude, and Muse Spark build the same 4 apps

    Claude training should learn that sometimes people use the word "honestly" because they'd otherwise be lying most of the time.

  • Hacker News2026-07-11source ↗

    Ask HN: How do you use Vim in the era of AI?

    neovim + claude code + open terminal is exactly my setup! But all the heavy lifting I used to do simply I’m not doing it anymore. I spend most of the time creating new worktrees and reviewing code, and I guess I’m just not interested about the implementation details that much (not that I don’t look at the code, but mi…

  • Hacker News2026-07-11source ↗

    AI 2040: Plan A

    I wish the authors of the article spent more time studying how LLM works before writing a doomsday scenario. Currently no matter how impressive LLMs are, they are just token auto complete machines. It cannot invent or think anything new which is not in its training dataset.

  • Hacker News2026-07-11source ↗

    Apple sues OpenAI, accuses ex-employees of stealing trade secrets

    > do you think they are just lying Yes. They're constantly lying, and constantly getting caught for it. They have a reputation for it. Why do you think this would be any different? Their standard opt-out agreement frames it as if they won't train on your data, but they do anyway, due to legal loopholes. They essential…

  • Hacker News2026-07-11source ↗

    An update on residential proxies and the scraper situation

    Disclaimer: this works for my very small number of personal services that I run. I have no idea how this would (or probably wouldn't) scale at all. Also, the methodology I describe below is based on what I'm able to do technically, which is pretty much limited to bash scripting. On my external-most device I have a fir…

  • Hacker News2026-07-11source ↗

    The vintage beauty of Soviet control rooms (2018)

    Having worked on SCADA software in the past, I find the evolution of the control room UX fascinating. You can see in these pictures, where every input and output is a real physical thing, just how much density of information was required for Operators to process. As we moved to computer screens representing the same,…

  • Hacker News2026-07-11source ↗

    QuadRF can spot drones and see WiFi through my wall

    Glad I’m not the only one. I’ve been tinkering with sensors, robotics, sdr and similar stuff for 20 years now, but this conversation was way over my head.

  • Hacker News2026-07-11source ↗

    Apple sues OpenAI, accuses ex-employees of stealing trade secrets

    That doesn't sound too heinous. As far as I am aware, employers aren't entitled to exit processes so long as they get their property back. OpenAI possessing an offboarding checklist accessible to any Apple manager doesn't seem like an IP issue. I'm not sure what conclusion to draw from this part other than Apple tryin…

  • Hacker News2026-07-11source ↗

    Ask HN: How do you use Vim in the era of AI?

    I spend more time reading, navigating, reviewing and refining code than generating it and vim is still the fastest tool for that.

  • Hacker News2026-07-11source ↗

    Ask HN: How do you use Vim in the era of AI?

    I switched to Emacs. Whatever AI did to TreeSitter caused it to constantly yell at me about errors because of markdown which I do not have the energy to figure out, while losing syntax highlighting and formatting support entirely whenever that happens. Otherwise though - same as usual, although I do keep my AI agent a…

  • Hacker News2026-07-11source ↗

    Spiel: Chrome extension that reads articles/PDFs aloud with local TTS

    Sounds like a very cool project. I often use the ElevenLabs app/extension to listen to articles, but I would love to have a local option to do this. I'm on Windows though, so I look forward to your future updates.

  • Hacker News2026-07-11source ↗

    Successful companies go blind

    When I was in a large org, it was a common failure that a manager would come in from a smaller firm - and assume that our design practices etc. were meaningless overhead. Inevitably they'd try to do a "rapid prototype" of a feature that had been tried a hundred times before and declared "too hard/unworkable/…

  • Hacker News2026-07-11source ↗

    I've been building this alone for months. Roast it before I lose any more time

    well it took 10s of second to load very little. tapping on the muesli vs corn flakes comparison gave me no visual feedback to indicate it was ever going to do anything. then it died. when it came back I tried tapping on Visual Studio Code, expecting a page to come up but nothing happened. after enough time to flip bac…

  • Hacker News2026-07-11source ↗

    Write code like a human will maintain it

    > You know what it constantly does? Commits without permissions You know what solves this? A deny rule. That’s right, you can solve it committing without permissions by.. not giving it permissions. > it's quietly messing up on a lot of that list. If only there was some way to know. But alas, code review won’t be inven…

  • Hacker News2026-07-11source ↗

    Write code like a human will maintain it

    This technique incrementally codifies the subset of my personal definition of code quality that can be codified. I’ve found a discovery based approach is better than anticipatory, because it forces everything you spend tokens to prove its worth. I still do code review - how else would I know what to codify! But since…

  • Hacker News2026-07-11source ↗

    Apple sues OpenAI, accuses ex-employees of stealing trade secrets

    Absolutely, but just as it's not ok to enter someone's home just because they forgot to lock the door, it's not ok to exploit access at your old employer because their offboarding process missed something. I do the same as GP does; I don't want there to be any chance that my former employer has forgotten to revoke acc…

  • Hacker News2026-07-11source ↗

    Postgres rewritten in Rust, now passing 100% of the Postgres regression tests

    I've always played the game that tests are only as useful as you have resources to attribute to them. Mostly all modern development is a compromise between new features and stuff that supports those new features (tests included, but also reviews, code maintenance, docs, etc.). If LLMs can be utilized to quickly make d…

  • Hacker News2026-07-11source ↗

    Show HN: Getting GLM 5.2 running on my slow computer

    I must say, this is incredible, nice work! I've been tinkering with local LLMs for a while now and experimenting with different tech, and I'd never thought it'd be possible to run such a large model on consumer-grade compute. It still feels like these days, you need to buy a $10K DGX Spark or something crazy expensive…

  • Hacker News2026-07-11source ↗

    GPT-5.6 Sol Ultra produces proof of the Cycle Double Cover Conjecture [pdf]

    if you get the same session that wrote the code to review it the poor results are entirely deserved. and if you get a different instance to review the code then you would know that it works rather well.

  • Hacker News2026-07-10source ↗

    GPT-5.6 Sol Ultra produces proof of the Cycle Double Cover Conjecture [pdf]

    It's in the training data! Long conversations between humans result in humans getting tired and going to bed. I have this reality baked into my workflow: 1. Start by hyping the task at the beginning, mentioning that there's no rush, I've cleared your schedule, and I'm jealous that you get dedicated time really focus a…

  • Hacker News2026-07-10source ↗

    AI 2040: Plan A

    One of the authors talks about this here: https://www.astralcodexten.com/p/introducing-plan-a > It’s increasingly clear that nobody has a plan for if this AI thing turns out to be real. > ... > Plan A isn’t another prediction. It’s a wish list, a positive vision, a road map for navigating the futur…

  • Hacker News2026-07-10source ↗

    GPT-5.6 Sol Ultra produces proof of the Cycle Double Cover Conjecture [pdf]

    If you'd ever tried to get an LLM to review its own code, you'd know.

  • Hacker News2026-07-10source ↗

    QuadRF can spot drones and see WiFi through my wall

    > I have heard claims of devices (mostly TVs) supposedly coming with secret 5G cell uplinks built This is occasionally mentioned on HN, but I have not yet seen a specific instance of this. Please share if you know something about secret 5G cell modems used to spy on people.

  • Hacker News2026-07-10source ↗

    Write code like a human will maintain it

    If I’m going to be responsible for the code that Claude writes on my behalf, I’m also going to take full responsibility for the moment that it is added to the project history, so I’m going to at least review every line before I allow that to happen. The automatic coauthor line is also just a pet peeve. It’s a tool, no…

  • Hacker News2026-07-10source ↗

    An update on residential proxies and the scraper situation

    What really confuses me is ... people always say, it's because companies are gathering data for AI training. Then why would they need to scrape the same page thousands of times per day? Edit: the article says millions of times per hour? (!?) The article is also astonished by this, and speculates it might be some kind…

  • Hacker News2026-07-10source ↗

    Please don't discontinue Gemini 2.5 Flash

    If you paid a one-time fee for an offline model, and then you were revoked access to it, that would apply. If you are paying an ongoing subscription for a service, I'd advise you not to rely on it too much or keep a list of alternatives.

  • Hacker News2026-07-10source ↗

    GPT-5.6 Sol Ultra produces proof of the Cycle Double Cover Conjecture [pdf]

    Interesting take! I feel like 2 of them are maybe overstated: > - extent to which correctness of solution be easily specified and checked I don't think most software is like solving a math problem or series of math problems. Algorithmic problems are very narrow and might be more like this though, where an oracle that…

  • Hacker News2026-07-10source ↗

    Show HN: Reviving my 2001 college band with AI

    A and B examples are convincingly "human". It is complete nonsense to say otherwise. The AI versions are simply giving the music a kind of commercial streamline production treatment; treatment that many listeners need to accept the music as viable. Some will fight brutally to hide this need here. No offense, but both…