Complaints database
29,255 raw documents, unedited and searchable. This is what everything else on the site is built from — nothing here is generated.
Show HN: Clawk – Give coding agents a disposable Linux VM, not your laptop
Another +1 to cloud sandboxes (and exe.dev) vs laptop sandbox. Runs 24/7 completely air gapped from your laptop. You also want a service proxy so the sandbox can access GitHub or Stripe without keys accessible to the agent. I haven't seen many of the laptop sandbox tools do this, where exe.dev does it out of the…
Control the Ideas, Not the Code
This article feels too black and white > How are you supposed to review 5k lines of code every day? Maybe there’s grey areas of reviewing 10% of the code, ensuring tests actual are meaningful, the big ideas are correct etc. I personally find that more efficient to do by looking at some code than a proxied description…
QuadRF can spot drones and see WiFi through my wall
You can look at wikipedia's list of SDRs[1] to see which can do wifi ranges now. I was more thinking about the future because you're right that it's a less common capability at the moment - but if you want a popular hobbiest platform you could check out the HackRF line[2]. [1] https://en.wikipedia.org/w…
Ask HN: What Are You Working On? (July 2026)
Im building an agent that interacts with health care providers on your behalf to proactively get itemized bills and other substantiation as needed. Born out of my own frustration with the paperwork for getting reimbursed from my healthcare cost sharing ministry. The app is React with a Laravel backend on EC2 where the…
Ask HN: Add flag for AI-generated articles
I didn't respond to your argument because I didn't want to escalate, but since you insist on personally attacking me and breaking the HN guidelines far more explicitly than what you're accusing the OP of doing... No LLM has responded like your quote of OP that you assert is LLM generated. Dense verbose writing is not…
Grok CLI uploaded the whole home directory to GCS
I will keep banging this drum until people listen: Trying to use markdown files to limit access should never be treated as a security guarantee at all. This is a form of in-band signalling that goes into a machine that, among other things, tries to read between the lines of your requests, extrapolate user desires, and…
Control the Ideas, Not the Code
I really don't understand why we feel the need to drop the review aspect. Programming with LLMs is a very non-linear process, there's no prompt-to-code mapping where editing a part of the prompt would produce an identical code construct with just a small part of it changed. LLMs are incapable of ensuring the thing wor…
Ask HN: What Are You Working On? (July 2026)
I am vibecoding a elixir/phoenix agent dashboard to manually & closely review the coding agent plans and code patches for my day job. I am at a stage where I can I use portal to work on the portal and my day job. I have not yet figured out a way to live reload the dashboard itself after a feature addition or a bu…
How to read more books
> I dont know you about you, but the reason I read is to learn and retain Millions of people read for entertainment. If you ask the people who read Fifty Shades and other erotic novels¹, how many do you think would say they do it “to learn and retain”? In fact, not retaining is something I would like to do with certai…
Control the Ideas, Not the Code
I also got a hint from this that he worries the community would reject features in Redis (and Redis itself) if they expected that the code has not been human-reviewed. I'm facing this with some of my own open source projects: I feel a responsibility to manually review the code because I don't want to damage the reputa…
Show HN: DOM-docx – HTML to native, editable Word docs (MIT)
All of the suite test cases are small fragments of HTML to test specific things, so I probably do need a way to test bigger documents. Thanks for the feedback. I’ll add that to the to-do list. I’ll try the red hat example later this evening.
Ask HN: Add flag for AI-generated articles
>My biggest issue is that it’s impossible to engage with and give feedback on an AI written document Thanks for giving shape to a general annoyance, in my case with code, that I only recently started noticing. When discussing code with my colleagues, especially with those that I do not know particularly well, I often…
Control the Ideas, Not the Code
But the CPU is not executing the textual description of your architecture. It executes code. Honestly, I've found that the architecture described to and by LLMs is always a more rosy picture than what is actually generated, no matter how many times you do an adversarial review. It's less visceral than in image generat…
Zig Creator Calls Spade a Spade, Anthropic Blows Smoke
Completely different approaches. The TypeScript Go port was done responsibly, reviewing every line ported, publishing both runtimes in parallel to give it time for real-life battle testing, with plenty of communication to the community about what was happening. The Bun Rust port was irresponsible and unprofessional, m…
How to read more books
I'm the same way for fiction, but there's a certain class of non-fiction audiobooks (memoirs, (auto)biography, essays, etc) that works very well for me even when doing light chores. It's made me much more selective about what podcasts I listen to, since I've realized just how information-poor most of them are. I do st…
Ask HN: Add flag for AI-generated articles
> what is there to say Ways to contribute: Peer review, human code review, money for tokens for code and code review, configure SAST and DAST tools to make it DevSecOps instead of DevOpsSec, configure AGENTS.md and an /upgrade-dependencies-and-run-tests skill, Compare "It's inadequate because it's AI" with "it lo…
Leak of San Francisco Police Drone Footage Exposes Reality of Urban Surveillance
> Did you read the article… These are being used for active calls only. I'm the person who posted the article lol. The article lists several cases where the drones were used to investigate random people – not active calls. They deployed drones to spy on some guy listening to music on his roof, and used drones to follo…
Leak of San Francisco Police Drone Footage Exposes Reality of Urban Surveillance
The problem is that police misuse every single power they have been given and public trust is very low for years now. I do not want to live in a world where random drones/cameras control my every move, and if your response to that is "I don't understand the problem" then we cannot live in the same society. It has…
Control the Ideas, Not the Code
I agree that in the end the most important thing is to have the correct mental model of the code, and there is no need to know every implementation detail if you can ensure with other means that they address your requirements. An issue I can can see with not reviewing the code (especially code someone else wrote) is h…
How to read more books
I think I might have trouble with that approach for "harder/denser non-fiction" because for such reading I might well want to stop and think from time to time -- maybe there's an argument I'm not convinced by and want to reason through step by step, maybe there's a mathematical calculation with a non-obvious step…
Count Binface
They probably couldn't. Farage is in very safe seat. He wouldn't have called the election otherwise. You don't vote for a comedy character to win an election in a safe seat, because they won't. You vote for Binface because you think Nige is wasting money on a pointless box ticking distraction instead of spending the m…
Old and new apps, via modern coding agents
"Trust" - what level of review does the output need to meet your standards of correctness? Donald Knuth's code would be much more likely to meet my standards during a code review than some LLM output.
Ask HN: What Are You Working On? (July 2026)
I am working on speeding up the review-refine loop of LLM generated artefacts between me and the LLM. i run my coding agent (claude code) in auto / full-permission mode, so it doesn’t stop for accept/reject — by the time it’s done i’ve got a pile of generated code, docs, sometimes ui to review. and the slow…
Zig Creator Calls Spade a Spade, Anthropic Blows Smoke
Yes and no. Let's first settle on the definition of vibecoding so that we're not miscommunicating over definitions. I'm using the one that seems the median definition nowadays: >95% of the code written by LLMs, <60% of the output code human-reviewed, meaning there's a large part of the codebase that no human ever revi…
The console wars have been lost
I got a steam deck 2 years ago and I haven’t run in to any games like this. They all either skip the launcher or have a controller navigable one. I just had a look at the steam page and valve has listed a long list of usability issues with this game. I guess if it was a console they could just reject it and make the d…
An Infuriating Goodbye to Photoshop
I've been using Photoshop since CS1 (was a Corel user before that). Photoshop and Illustrator CS6 were the last good versions. Very snappy and with probably 99% of the features I use today. Everything slowly degraded when they moved to the subscription model which I've been paying since 2013. Apple Silicon support was…
Show HN: DOM-docx – HTML to native, editable Word docs (MIT)
Thanks for the feedback, I’ll add Word validation to my todo list.
Ask HN: Does anyone let AI agents play games just for fun?
Opus 4.6 can not solve a Rubik's Cube. What changed between Opus 4.6 and Fable and the GPT 5.6 models released since? LLM models cannot actually reason about a red or white piece sitting on the opposite side of the cube or figure out how to move it into place. The model knows where the piece is supposed to go because…
Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
Yeah, my personal workflow has different reviewers for codebase(patterns, code cleanliness, etc), frontend, security, product fit, etc. So they spawn as separate subagents. Both so that they stay limited to their role, and so they don't have preconceived notions about the implementations. It's a bit heavy-handed but w…
I love LLMs, I hate hype
A slight defense of any qualifiers, mine or others. I am a sole developer, who formed a "box" as you put it, to house my assets. I'm the sole director of it. That doesn't mean my box is at war with users. To be clear, a merchant is a middleman and some merchants have taken the goods produced by the builder and built a…