Claude Code

What hackers pick instead

• OpenAI CodexA coding agent many find as good as or better than Claude Code, thorough on hard problems, with generous $20-plan limits, though its output needs careful review.2474recommend
• OpenCodeAn open-source coding agent recommended for mixing models and providers, including cheap or local ones, with a good-value Go plan; critics cite prompt privacy, security holes and bloat.1060recommend
• Gemini CLIGoogle's terminal coding agent is liked for its generous free tier, polished interface and strong one-shot results, but critics cite rate limits, bugs, eager code edits and its planned discontinuation.172recommend
• ClineFree open-source VS Code agent that works with your own API key, billed per token. Critics note context loss in long sessions.63recommend
• Mistral VibeA terminal coding agent people recommend for cheap subscription value and an open-source CLI; the most common caveat is weaker models and data-use defaults on Team plans.57recommend

Every quote

The 40 most detailed of 14665 comments. Each links to the original.

1. 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.

   Recommends · Mar 2026 · in “Ask HN: How do you cope with the broken rythm of agentic coding?”

2. 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_.

   Mixed · Jan 2026

3. 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.

   Recommends · Aug 2026 · in “Claudette: Make Claude Stop Talking Like a BuzzFeed Article”

4. If you have ever pointed claude/codex to your a binary executable and asked it to figure out something it can run against full throttle, I fond it always gets back to you with some good insights.

   Recommends · Jul 2026 · in “Google fixed more Chrome bugs in June than over the past two years, thanks to AI”

5. 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

   Recommends · Jan 2026 · in “Don't fall into the anti-AI hype”

6. 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.

   Recommends · Aug 2026 · in “Google Search Is Dying. What Comes Next Is Worse”

7. 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.

   Mixed · Jul 2026 · in “What is happening to jobs? Separating AI hype from reality”

8. 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.

   Recommends · Mar 2026 · in “LLM Doesn't Write Correct Code. It Writes Plausible Code”

9. Starting a Qwen session from scratch in some other CLI is a completely different experience than having Qwen pick up where Opus left off in your fully configured Claude Code environment.

   Recommends · Apr 2026

10. 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

    Mixed · Mar 2026 · in “Get Shit Done: A Meta-Prompting, Context Engineering and Spec-Driven Dev System”

11. 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.

    Recommends · Feb 2026 · in “Anthropic raises $30B in Series G funding at $380B post-money valuation”

12. 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

    Mixed · May 2026 · in “How Claude Code works in large codebases”

13. 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.

    Recommends · Jun 2026 · in “Stop Using Conventional Commits”

14. Put Claude Code on the task (reason for choice: Claude Desktop lets me just throw it at a folder with unzipped bundle of sources and assets I found laying around my blog archive)

    Recommends · Apr 2026 · in “Starfling: A one-tap endless orbital slingshot game in a single HTML file”

15. 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.

    Mixed · Feb 2026 · in “They lied to you. Building software is hard”

16. 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.

    Recommends · Feb 2026 · in “Time Is Different”

17. 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.

    Recommends · Mar 2026 · in “If AI brings 90% productivity gains, do you fire devs or build better products?”

18. 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.

    Recommends · Dec 2025 · in “LLM Year in Review”

19. 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."

    Recommends · Jun 2026 · in “GLM-5.2 is the new leading open weights model on Artificial Analysis”

20. 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.

    Recommends · Jan 2026 · in “Show HN: Executable Markdown files with Unix pipes”

21. 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.

    Criticizes · Apr 2026 · in “Claude Code is unusable for complex engineering tasks with the Feb updates”

22. There's been lots of Github issues posted in the Claude Code repo with lots of new comments each day screaming into the void, but radio silence from Anthropic since the revert in December.

    Criticizes · Jan 2026 · in “Claude Chill: Fix Claude Code's Flickering in Terminal”

23. 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

    Criticizes · Jul 2026 · in “Codex starts encrypting prompts, uses ciphertext for inference instead”

24. 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.

    Criticizes · Apr 2026 · in “An update on recent Claude Code quality reports”

25. Claude Code starts spiraling — "this isn't right either", "actually let me change this part too", "wait no let me revert that" — just Clauding endlessly and making things worse.

    Criticizes · Mar 2026 · in “Ask HN: What is your take on the importance of code quality when coding with AI?”

26. 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.

    Criticizes · Feb 2026 · in “Claude Code Is Being Dumbed Down”

27. 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.

    Criticizes · Apr 2026 · in “An update on recent Claude Code quality reports”

28. 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.

    Criticizes · May 2026 · in “How Claude Code works in large codebases”

29. Claude attempted several different approaches and eventually, drawing on a historical clue in how the MD2's substitution table was constructed, found a surprisingly simple method that reproduces all 256 entries exactly.

    Recommends · Oct 2026 · in “How RC2's π table was made”

30. Claude code is more the opposite where you can watch as closely as you want and often you get to a point where you have enough trust and experience with it that you know what it's going to do and don't want to bother.

    Recommends · Feb 2026 · in “GPT-5.3-Codex”

31. When Claude Code shipped dynamic workflows under the ultracode name a few months ago I thought it was the most interesting thing that happened to coding agents for a while, but it's closed source.

    Mixed · Aug 2026 · in “Show HN: Gigacode – the model writes its own multi-agent workflow, then runs it”

32. If you're not approaching Claude Code and other agentic coding agents with an open mind with the goal of deriving as much value from them as possible, you are missing out on super powers.

    Recommends · Feb 2026 · in “How to effectively write quality code with AI”

33. if you took the time to truly learn how to do pure agentic coding (not vibe coding) you would realize as a principal engineer you have an advantage over engineers with less experience

    Recommends · Mar 2026 · in “I'm 60 years old. Claude Code has ignited a passion again”

34. I've certainly felt the "mimics good code" thing in the past. It's been less of a problem for me recently, maybe because I've started forcing Claude Code into a red/green TDD cycle

    Mixed · Jan 2026 · in “Don't fall into the anti-AI hype”

35. I've been using CC from day one (when API pricing was the only way to pay for CC), then I've been on the $20 Pro plan and am getting a solid $5+ worth of usage in each 5h session

    Mixed · Nov 2025 · in “GPT-5-Codex-Mini – A more compact and cost-efficient version of GPT-5-Codex”

36. Perhaps if he was able to get Claude Code to do what he wanted in less time, and with a better experience, then maybe that's not a skill he (or the rest of us) want to develop.

    Mixed · Feb 2026 · in “The Codex App”

37. All the success of AI tools in actual, real-world software has been in tools specifically design to assist existing, working, competent developers (e.g. Cursor, Claude Code)

    Recommends · Jan 2026 · in “The recurring dream of replacing developers”

38. setting up proper structure while everything still fits in a single context window of Claude code, as well as splittjng as much as possible into libraries works pretty well

    Recommends · Feb 2026 · in “Two kinds of AI users are emerging. The gap between them is astonishing”

39. she's running Claude Code natively on her laptop, and she tagged me yesterday on Facebook in some update about how much more she enjoyed using Claude Code than plain Claude

    Recommends · Aug 2026 · in “LLMs reward expertise”

40. can you really use Claude Code on the Pro plan as a full time developer, or professional 'knowledge worker' without hitting the usage limits fairly early in the day anyway?

    Mixed · Apr 2026 · in “Claude Code no longer included in Pro tier”