Complaints database
29,255 raw documents, unedited and searchable. This is what everything else on the site is built from — nothing here is generated.
Write code like a human will maintain it
> shipping 10x as many features and bugfixes sounds better I understand you're excited about the tool, but for the sake of earnest discussion here, maybe commenters like yourself can tone the hype down to plausibility? Claims like this are just nonsense. It's not how product development works. How do you even have so…
A road to Lisp: Why Lisp
I don't quite understand what you mean by generic collections in this case. Do you want to restrict a list to only contain one specific type?
Good Tools Are Invisible
Obsessive hacker tools like Emacs are not a productivity enhancer. But If you find them fun go for it. You are allowed to have fun. You are allowed to enjoy your environment. If tinkering with Emacs is fun for you go for it. It's prob not replacing mental cycles for "productive" work. It's replacing zoning out with so…
Write code like a human will maintain it
I run various forms of workflows to run dedicated QA, code review (of various flavors) simplification and text simplification agents. Especially the simplification goes a long way to remove dumb padding, duplication and efficiency. Dedicated docs/comment simplification is also becoming more and more necessary on…
How do you use Vim in the era of AI?
Codex has /diff to review the code, or you can look when it’s a Pull Request
Write code like a human will maintain it
Write yourself a /review command. That is an empty markdown file at `.claude/commands/review.md`. In it, put a checklist of things the agent should look for. When you’re ready to have your agent review the code, type `/review`. The checklist will be examined and it’ll plan out some findings to ask…
Ask HN: How do you use Vim in the era of AI?
I wrote my own neovim AI harness https://github.com/dlants/magenta.nvim And wrote about my thoughts on the relevance of nvim here https://dlants.me/ai-whiplash.html It's been many months, and I thoroughly prefer my harness inside of nvim as my day to day development environment. Usin…
Ask HN: Do we need a support group for developers alienated by LLMs?
It's very good for bug fixes. I paste the log into the agent, and it has a good chance of suggesting the fix. I have to review it, but it has been a big time saver. For new code, I treat it like a very knowledgeable mid level engineer who has a lot of patience to search the code base. We make changes a step at a time…
How do you use Vim in the era of AI?
My Neovim + AI workflow is running Neovim (LazyVim) and Claude Code side by side in a terminal split. As the agent makes changes, I review them in Neogit. I don't really make edits by hand much anymore, but the keyboard is still how I navigate the code when doing reviews. I can jump to references, open files, read thr…
Late Bronze Age Collapse
Patrick Wyman—of the Tides of History podcast—just put out a new book, Lost Worlds , which is worth a read if this is your bag. The basic premise is that the way ancient history is typically taught, "that we moved linearly from foraging to farming, and then from country farmers to city-dwelling, tax-paying subjects of…
How do you use Vim in the era of AI?
Usually I keep terminal split open with the agent side by side and make edits by hand where needed or for reviewing the code. Inside the vim itself I have a small plugin that you can feed a block of text with the comment instructing LLM what to do. It then replaces the text with the result of execution. Super useful f…
Good Tools Are Invisible
The things about multiple cursors is that you think about the processing while doing it, while most people using macros looks at the structure of the text first and then devise the macro. I wouldn’t say the latter is faster, but it’s a different mindset. And the other thing is that vim has the “dot” command to repeat…
Ask HN: How do you use Vim in the era of AI?
^G in Claude and Codex will drop you into $EDITOR to edit your prompt. I use that all the time. "vimdiff" is a really great way to review code changes side-by-side.
Write code like a human will maintain it
It's interesting that the author didn't mention considering updating their agentic code review prompt to keep an eye out for repetitive/duplicate code.
How do you use Vim in the era of AI?
I switched from using Vim as my primary editor to using Zed's Vim Mode. When you have a second process editing your project in the background you need an editor that can display those changes immediately without clunky buffer reloads. I've also customized Zed's UI to optimize for reading and reviewing code, and mostly…
In Emacs, everything looks like a service
It sounds like you think emacs is some sort of basic text editor, I dunno, like Notepad on Windows, that has an adjoined Lisp interpreter? Admittedly, it doesn't help that there are some sibling comments that implicitly seem to be speaking that way. However, Emacs is a 42-year-old software program that has been in con…
Ask HN: How do you use Vim in the era of AI?
Use it to write and edit code when that makes sense for you to do so. Just like you always have. It's an extremely useful skill to have even still. I've had much more success with agents reviewing my code and offering inline autocomplete over LSP than I have with letting the agents write the code, which I then try to…
Girls just wanna have fast MPMC queues with bounded waiting
> Most people use short review prompt, with yes/no answers I don't. I review code by hand, like I have for 20 years. I think you might have some sample bias.
GPT-5.6
GPT-5.6 is the first model where I’ve actually frustrated to use it. I’m explicitly telling it to do something extremely specific and it’s just not listening to me. Eg, I gave it an image to update. The image is sized 400x200 pixels. It then generates a new image at 300x300. I explicitly state to be 400x200 in size an…
Building a real-time AI tutor for 5-year-olds
> At some point, you need to watch out for cynical/nasty series. In fact, all of the books we purchase are ranked against peers they have read in the past, or those we know to actively avoid buying due to cynicism, sarcasm, or open disdain towards adults (Wimpy Kid). yeah how do you "know" this? our kid is obsess…
Building a real-time AI tutor for 5-year-olds
I'm not seeing the issue with e.g. Treasure Mountain or Treasure Mathstorm. They can do little math, reading, and logic puzzles while listening to Bach and Beethoven. It's engaging enough to get them to practice addition/subtraction but unengaging enough that they don't sit at it for more than 5-10 minutes at onc…
ChatGPT Work
Wow, this is the worst update I've ever seen. Highly confusing and atrocious UX. Where are my chats? Where are my projects? Why do I get a window inside the ChatGPT app for new chats now? Why does switching between Work and Codex not do anything? Are both the same? How can a company like OpenAI mess up so badly? Unles…
Building a real-time AI tutor for 5-year-olds
This isn't a new thing though, nobody likes having to sit around all day and listen to someone talk and kids are the worst at that. They're young and have so much energy so a teacher has always needed to adjust the learning to make it something that the kids can learn from while paying attention and not disrupting the…
A road to Lisp: Why Lisp
You sweet, summer child, just so you know, I have existed for nearly half a century in this world where the larger part of it I have spent dealing in computing. I have seen and dealt with more programming languages (including Ruby) than you can count with your fingers and toes and that number keeps growing still. I'm…
Harman and Dr. Sean Olive are reshaping headphone sound (2025)
Great insight; I was going to theorize something about objective vs subjective experiences, in that you can't trust a human to make an objective observation about e.g. sound quality. Best thing you can do with human listening tests is gather data and make it about statistics. But it's never about just what's objective…
Show HN: Microcosm Industries – Simulation toys and software microcosms
I’ve been obsessed with simulation toys (software that allows you to play with a complex miniature world) ever since I was young and playing with SimCity and cellular automata. This kind of software exists at the delightful and weird intersection of simulation, complexity science, education, and gaming. And I want mor…
Ask HN: Who wants to be hired? (July 2026)
Location: EU, overlap with US East+West Time Zones Remote: Yes Relocation: No Technologies: Claude Code, Rust, C++, Python, Go, Zig, Haskell, TypeScript, JS, Nix, K8s, Terraform Email: damianjobsites+hn@gmail.com CV: on request 長 Senior engineer / tech lead (20+ YOE). Former IC → EM → Director → CTO. 宝 Mul…
Ask HN: Do we need a support group for developers alienated by LLMs?
I'm sure a lot of engineers feel the same way, especially those who love programming and aren't just in it for the money. I have mixed feelings on the topic - on the one hand i'm quite happy not to write boilerplate code again and again, AI is good at that especially with the right instructions/skills so i'm not…
A road to Lisp: Why Lisp
I'll paraphrase someone who commented on HN once (about dynamic vs static typing, IIRC): permissive languages are enablers for solo programmers, but you need more restrictive languages for team programming. This matches my experience because you don't chose who you work with. Skill level is uneven among the team. Less…
Launch HN: Context.dev (YC S26) – API to get structured data from any website
> Websites can opt out of our service, and we respect these requests and add them to our block list. I.e: "robots.txt already exists and is commonplace but if we actually followed it our solution wouldn't work so all websites on the planet need to do something specific to opt-out our ddos." lmao