# Claude Code 4522 Hacker News commenters recommended Claude Code and 3788 criticized it, November 2025 to November 2026. It was recommended in 13 of 13 months; owners who said how long report a median of 0.5 years (417 owners). **Verdict:** An agentic coding tool that writes, runs and tests code on its own, often replacing hand-coding entirely, though many report quality regressions after updates and broken code on complex work. ## Why people recommend it - Writes and tests working code autonomously (5 comments): "with an agentic system like Claude Code that is able to compile, run and test the code it is generating you can have it iterate until the code meets whatever test or other criteria you have set" ([source](https://news.ycombinator.com/item?id=46583539)) "I was able to tell Claude Code to do something like the example you gave, and it did it and it built, without me asking, and produced a working program on the first try." ([source](https://news.ycombinator.com/item?id=47481976)) "Yes, there is. It's called Claude Code. Point it at the HuggingFace URL and say "Download these weights and build whatever is needed to run them, then test the model."" ([source](https://news.ycombinator.com/item?id=48575724)) - Replaced writing code by hand (3 comments): "They have the best coding agent around. I would say roughly half the industry no longer writes code by hand and claude is/was the only agent that let me drop my editor all together." ([source](https://news.ycombinator.com/item?id=46998956)) "I've been writing all of my code via Claude for a while now, and I don't think I will ever go back to working in an editor writing code the way I did for most of my career." ([source](https://news.ycombinator.com/item?id=47175721)) "I found myself very consistently asking Claude to make the code more elegant and readable. At which point I realized I was being silly and just switched to Claude code." ([source](https://news.ycombinator.com/item?id=46334875)) - Customizable via CLAUDE.md and hooks (5 comments): "CLAUDE.md with workflow rules. CC reads it at session start. Mine includes "never mark a task complete without proving it works" and "after any correction, update lessons.md." This eliminated the cycle of fix break ask fix." ([source](https://news.ycombinator.com/item?id=47382609)) "with Claude Code you can provide custom instructions when compacting, and instruct the LLM that is in charge of compacting the session to prioritize the retention of specific bits. It can help a lot." ([source](https://news.ycombinator.com/item?id=49393493)) "The only way I've found to strictly enforce things on an agent (tests, linting, whatever) is to use a claude pre-command hook that will block git commit if the checks don't pass." ([source](https://news.ycombinator.com/item?id=48415940)) - Handles sysadmin and automation tasks (5 comments): "I've had the opposite experience giving claude code SSH/ADB access to my devices. Not sure if it's the model itself or the harness, but I haven't had to manually do a sysadmin task in months." ([source](https://news.ycombinator.com/item?id=49254548)) "there are ad hoc automation tasks that I've traditionally used Jupyter notebooks to do that I'm finding are easier to get running using markdown files and Claude Code." ([source](https://news.ycombinator.com/item?id=46551630)) "Using Claude Code for sales and operational workflows, having acceptable criteria upfront (along with some manual checks along the way depending on the task) definitely helps the output." ([source](https://news.ycombinator.com/item?id=47318962)) ## What people warn about - Quality regressions after updates (5 comments): "I noticed a regression in review quality. You can try and break the task all you want, when it's crunch time, it takes a file from Gemini's book and silently quits trying and gets all sycophantic." ([source](https://news.ycombinator.com/item?id=47663331)) "These bugs have all of the same symptoms: undocumented model regressions at the application layer, and engineering cost optimizations that resulted in real performance regressions." ([source](https://news.ycombinator.com/item?id=47885144)) "I would MUCH rather pay the cost in tokens than reduced quality. Frankly, it's shocking to me that you would make that trade-off for users without their knowledge or consent." ([source](https://news.ycombinator.com/item?id=47888323)) - Struggles with complex, maintainable code (4 comments): "I code with a mix of antigravity and Claude code depending on the task, but I feel like I'm living in a different reality when the code I get out of these tools _regularly just doesn't work, at all_." ([source](https://news.ycombinator.com/item?id=46611167)) "It is passable to have entire apps written by LLMs (I’ve made several that I otherwise never would have had the time to create by hand), but I wouldn’t say maintainable or easily extendable." ([source](https://news.ycombinator.com/item?id=49055068)) "AI can be alright at creating a Proof of Concept for an app idea, and it's great as a Super Auto-complete, but anything with a modicum of complexity, it simply can't handle." ([source](https://news.ycombinator.com/item?id=46862141)) - Needs explicit guidance and context (3 comments): "Plan mode is handy on the on-off. But if you enter another plan mode, thinking claude would learn from, or build off a previous plan spec, it won't unless you explicitly say something" ([source](https://news.ycombinator.com/item?id=47420791)) "There's a bunch of stuff I include, depending on the project. In theory it should be able to do it without that by looking at the repo style, but I haven't found that to be the case" ([source](https://news.ycombinator.com/item?id=48145934)) "In really large codebases grep and find timeout. If you operate at that scale you quickly come to realize Claude will not use the tools you built to make searching feasible." ([source](https://news.ycombinator.com/item?id=48147775)) - Less visibility into what it does (2 comments): "I really hate this change. I had just given a demo about how Claude Code helped me learn some things by showing exactly what it was doing, and now it doesn't do that any more." ([source](https://news.ycombinator.com/item?id=46981309)) "if Claude Code makes it so it's impossible to inspect what the sub-agents actually received before they started their work, then I'll say it's similarly impossible to rely on Claude Code" ([source](https://news.ycombinator.com/item?id=48905527)) ## Alternatives hackers recommend - [OpenAI Codex](https://hackerapproved.com/p/codex.md): 2474 recommend - [OpenCode](https://hackerapproved.com/p/opencode.md): 1060 recommend - [Gemini CLI](https://hackerapproved.com/p/gemini-cli.md): 172 recommend - [Cline](https://hackerapproved.com/p/cline.md): 63 recommend - [Mistral Vibe](https://hackerapproved.com/p/mistral-vibe.md): 57 recommend ## Where to get it - [Visit the official site](https://claude.com/product/claude-code) ## Cite as Hacker Approved, "Claude Code", https://hackerapproved.com/p/claude-code/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).