Claude

What hackers pick instead

• Google GeminiRecommended for everyday questions, image and handwriting understanding, and coding or scripting help, but many report confidently invented facts and dislike it being pushed into every Google product.2195recommend
• ChatGPTA general-purpose chatbot that people use to research faster, understand health issues, learn topics and draft writing, though it often hallucinates and tells you what you want to hear.2186recommend
• GrokRecommended for fast, concise answers, real-time current events through X, and useful second opinions on code, but critics widely cite Musk-driven political bias and weak safety guardrails.727recommend
• Microsoft CopilotValued for tight Microsoft 365 integration that finds work documents while respecting access permissions; critics dislike Copilot buttons pushed everywhere, confusing branding and made-up links.139recommend
• Claude DesktopPeople recommend it as an approachable home for Claude agents, with connectors, artifacts and parallel sessions; critics call the Electron app slow, buggy and resource-heavy, and dislike its large VM.104recommend

Every quote

The 40 most detailed of 17696 comments. Each links to the original.

1. For bugfinding/incident response in distributed systems - which often involves extensive use of Datadog/Sentry MCPs and poring over heaps of logs in addition to reading tons of code - 4.8 has been significantly better than 4.6.

   Recommends · Jun 2026 · in “Claude Fable 5”

2. Last year I had a friend chatting with me about how Claude had rather quickly transformed their small coding shop, except that they noticed after 3pm it consistently became incredibly dumb.

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

3. For prototypes they're amazing, but when you're just straight vibe coding you get stuck in a hell where you don't want to or can't efficiently really check what's going on under the hood

   Mixed · Nov 2025 · in “Gemini 3”

4. Claude has done an amazing job implementing some tricky algorithms from some difficult academic papers, saving me time overall, but it does require more babysitting than I would like.

   Mixed · Apr 2026 · in “The Peril of Laziness Lost”

5. asked Claude to implement a terminal emulator for Windows that would render everything using DX12 and support modifyOtherKeys plus DA responses, and within a few days it was ready!

   Recommends · Jun 2026 · in “What was your "Oh Shit" moment with GenAI?”

6. Claude absolutely CAN produce moderately complex applications when given detailed, well numbered documentation, but it will "make a mess" on existing codebases with large changes.

   Mixed · Aug 2026 · in “Anthropic IPO valuation hinges on $190-200B 2028 revenue forecast”

7. With a rather short prompt, claude/codex will take your code, write a harness, profile it, build experiments, profile those, and give some pretty solid advice which one to pick.

   Recommends · Aug 2026 · in “Saving 100 terabytes of memory by optimizing 1.1.1.1's DNS cache”

8. Claude is a more "human-like/human-smart" planner than Codex (in a positive way) but is more likely to make mistakes or forget details when implementing major codebase changes.

   Mixed · Mar 2026 · in “GPT-5.4 Thinking System Card”

9. I started using the ReVa/Ghidra MCP server together with Claude since day 1 (Well, since Claude Sonnet 4.0 was released) and I saw Claude get better at it with every update.

   Recommends · Feb 2026 · in “Show HN: Ghidra MCP Server – 110 tools for AI-assisted reverse engineering”

10. the models currently will speculate a (valid, but unlikely/out of our design space/deep edge case) problem, and then cheerfully triple the codebase size and cut speed by 10x

    Mixed · Oct 2026 · in “Redesigning source control at Anthropic”

11. LLMs are great for rapid prototyping, boilerplate, that kind of thing. I myself use them daily. But the amount of mistakes Claude makes is not negligible in my experience.

    Mixed · Mar 2026 · in “We Might All Be AI Engineers Now”

12. I can throw a messy bug report of an intermittent issue at claude, and tell I need issue reproduced and fix developed, and there is a well above 50% chance it'll deliver.

    Recommends · Oct 2026 · in “Pop!_OS bans AI-generated code from much of its codebase”

13. It's been incredible for velocity and the capabilities and accuracy of the models I've been (mostly from Anthropic) have improved immensely over the last few months.

    Recommends · Dec 2025 · in “Vibe coding creates fatigue?”

14. I’ve seen Claude do iterative problem solving, spot bad architectural patterns in human written code, and solve very complex challenges across multiple services.

    Recommends · Mar 2026 · in “I don't use LLMs for programming”

15. All the time i do it. I will often provide claude with read only credentials to the db or api access to the logs and it will nail the problem almost every time

    Recommends · Jan 2026 · in “Coding Is When We're Least Productive”

16. I was able to take down the performance gap on Rust vs C (without Assembly) from 10x to 1.5x through detailed profiling and iterative improvements with Claude.

    Recommends · Apr 2026 · in “Wedeo – a Rust Rewrite of FFmpeg”

17. Imagine my surprise when Claude also provided correct comment references to pages and equation numbers when I asked it to write code to implement diode models.

    Mixed · Oct 2026 · in “Ask HN: How to deal with shipping AI-written code you don't understand?”

18. I find it amazing that without access to profilers or anything Claude is able to respond to “anything I can do to improve the speed” with acceptable results.

    Mixed · Dec 2025 · in “The highest quality codebase”

19. It already makes a difference for me. Instead of going through logfiles, i copy and paste them to claude and it does something and tells me the right answer.

    Recommends · Sep 2026 · in “AI, Tools and Transformation”

20. I'm VERY impressed with Claude 5. I had long ago given up hope that my real-time systems would work without a lot of hacky time-windows and throttle checks.

    Recommends · Jun 2026 · in “Claude Fable is relentlessly proactive”

21. Just maintaining a basic interaction framework, consistent behaviours in chat when starting up, was a daily whack-a-mole where well-tested behaviours shift and alter without rhyme or reason.

    Criticizes · Jan 2026 · in “Compressed Agents.md > Agent Skills”

22. the older Claude models which I genuinely enjoyed writing short stories with have now been deleted, replaced with hypothetically cleverer models which produce text everyone hates

    Criticizes · Aug 2026 · in “Fable and the end of the free lunch”

23. If LLM inference quality is downshifted because of those constraints, that becomes a very real problem for the end users as it effectively amounts to rug-pulling the product.

    Criticizes · Apr 2026 · in “Claude Is Dead”

24. AI can be helpful in development in very limited scenarios but the main thrust of the comment above yours is that it takes longer to read and understand code than to write it

    Criticizes · Apr 2026 · in “I Cancelled Claude: Token Issues, Declining Quality, and Poor Support”

25. i just have the claude scheduled job kinda tool running, but at the grocery store i can spot something and think of a meal, then ask claude if any nearby grocery stores have other key elements to the meal on sale. its pretty handy.

    Recommends · Sep 2026 · in “Amazon blocks Meta’s new Muse AI agent from shopping on amazon.com”

26. It’s worse at CRUD apps and a lot worse at domain specific bits. But it’s more parallelizable, so if I drive it well I can focus my skill on the small subset of problems that actually require it and achieve increased throughput.

    Mixed · Apr 2026 · in “AI Will Be Met with Violence, and Nothing Good Will Come of It”

27. I can ask Claude for "a bilingual German-Russian poem about the side effects of the most common drugs used in anesthesia". I would bet my left shoe that if I asked people on the street, no one will do a better job than Claude.

    Recommends · Mar 2026 · in “Are LLMs not getting better?”

28. If done write it can fix things like code bases that were created by multiple people and groups each with their own conventions. Before I had to know which group did what to know to know the variables. Claude fixed that.

    Recommends · May 2026 · in “Steve Wozniak cheered after telling students they have AI – actual intelligence”

29. I can make Claude design a spreasheet for me, and it will present it beautifully for me, with export to Google Sheets and so on. But then, changes to it don't let me dig up into it interactively.

    Mixed · Jul 2026 · in “Show HN: What should the GUI for AI agents look like?”

30. once you figure out how to swim and have claude running for an hour+ at a time and only bugging you with either high-level taste decisions or 'done, how's it look?' it's pretty low stress

    Recommends · Jul 2026 · in “AI coding is addictive. Engineers are paying the price”

31. As a side effect that boosts precision of the sessions themselves, and buys you the luxury to say things like "do whatever necessary..." and expect to actually understand you.

    Recommends · Aug 2026

32. For Claude subscriptions, subagents still have a 5m TTL and before I discovered that, their constant waits for ~10 min tests or similar tasks would destroy my 5h usage.

    Mixed · Oct 2026 · in “If you don't run your own LLM proxy, how do you know whats going on?”

33. An example being code i wrote for a hypercomplex sedenion based artififial neural network broke claude so bad it start saying it is chatgpt and cant evaluate/run code.

    Mixed · Mar 2026 · in “Claude Struggles to Cope with ChatGPT Exodus”

34. I don't really like the way Claude likes to format slides (too much marketing speak and flowcharts), but it has good ideas often enough that it's still worth it to me.

    Mixed · Apr 2026 · in “ChatGPT for Excel”

35. LLMs are breakthrough technologies. The AI products we have today are SaaS products built by companies doing everything they can to find people who will pay for them.

    Mixed · Apr 2026 · in “The More Young People Use AI, the More They Hate It”

36. Claude is a far superior _model_ to whatever Siri uses, but in terms of the Claude app correctly transcribing speech, in my experience it's as bad or worse than Siri

    Mixed · Jul 2026 · in “Alphabet's cash burn raises alarm for Big Tech as AI spending climbs”

37. It definitely adds a layer of cognitive load, in wrangling/shepherding/accomodating/accepting the unpredictable personalities and stochastic behaviors of the agents.

    Mixed · Mar 2026 · in “Universal Claude.md – cut Claude output tokens by 63%”

38. I like the Claude constitution overall - I hope it becomes something representatives vote on and amend, to avoid the centralized corporate censorship you describe.

    Mixed · Sep 2026 · in “Corporate America is getting hooked on open-source AI”

39. It is much easier and enjoyable to use high level language, where you give pointers to building blocks/ directions/ say hard no when you understand things deviate.

    Recommends · May 2026 · in “Mythical Man Month”

40. it got stuck in "indexing". (Possibly broke the indexer?) But thanks to the CLI integration, it was able to just iteratively grep all the info it needed out of it

    Mixed · Jan 2026 · in “Show HN: I used Claude Code to discover connections between 100 books”