OpenAI Codex

What hackers pick instead

• Claude CodeAn 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.4522recommend
• 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 6432 comments. Each links to the original.

1. Most often with medium to high complexity problems, if the AI comes up with a working solution it has enough problems that an attentive human reviewer would have rejected it at best.

   Mixed · May 2026 · in “God Damn AI is making me dumb”

2. 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”

3. Codex is good now. I'm undecided which is better, but they're definitely close enough that I feel comfortable recommending Claude-exclusive people in my circle to try codex.

   Recommends · May 2026 · in “DeepSeek V4: The Open-Source Model Frontier Labs Feared”

4. The agent model sounds powerful, but in practice it's still a lot of supervision, retries, and quiet hope it doesn't hallucinate itself into a refactor I didn't ask for.

   Mixed · Feb 2026 · in “The Codex App”

5. I use Codex CLI in my daily usage since just with my $20/month subscription to ChatGPT, I never gets close to the quota. But it trips up over itself every now and then.

   Mixed · Feb 2026 · in “What Claude Code Chooses”

6. codex's remote session integration is better, so outside of some "ultracode" orchestration bells/whistles where Claude Code is ahead, I think Codex is a better tool

   Recommends · Jul 2026 · in “GPT-5.6”

7. Claude Code/Codex are useful for doing certain laborious tasks like bookkeeping errors/reconciliation issues but they don't replace a professional accountant.

   Mixed · May 2026 · in “Claude for Small Business”

8. Codex has had none of these problems. I still don't trust anything it produces, but it's not like everything it produces is completely and utterly useless.

   Mixed · Apr 2026 · in “Claude Opus 4.7”

9. codex is currently a much better model, and it also seems to be technically stronger on the type of applied math and theory heavy programming I like to do

   Recommends · Jul 2026 · in “Claude Is Down”

10. codex did my taxes this year (well it actually implemented a normalization pipeline and a tax computing engine which then did the taxes, but close enough)

    Recommends · Apr 2026 · in “Codex for Almost Everything”

11. Codex did a vertical slice of a feature for me (well defined and well planned). It contained functionality that has historically plagued us developers

    Mixed · Jul 2026 · in “Claude Sonnet 5”

12. Codex has been more consistent and helpful, but it too is still not quite at the point where you can blindly trust it without verifying the output.

    Mixed · Apr 2026 · in “Codex for Almost Everything”

13. The Codex plan for the $20 ChatGPT plan goes much further than Claude's $20 plan, but it's still not enough if you plan to work full-time with it.

    Mixed · Mar 2026 · in “$500 GPU outperforms Claude Sonnet on coding benchmarks”

14. Then I got codex to whip up a script that sends each sheet to a fairly low parameter locally running LLM and I have the yaml in a couple seconds.

    Recommends · May 2026 · in “Local AI needs to be the norm”

15. I've been running them in parallel and I've been let down by Opus 4.6 with maximum thinking way more than I've been let down with OpenAI models.

    Recommends · Mar 2026 · in “No, it doesn't cost Anthropic $5k per Claude Code user”

16. Codex is better at this because it keeps going at hard problems. But then it compacts so many times over that it forgets the todo instructions.

    Mixed · Feb 2026 · in “Automatic Programming”

17. Codex reviewed my immich setup and recommended I change things the clip model, came up with a better backup strat and found holes in my system.

    Recommends · Sep 2026 · in “Saving money on Google Photos with Immich: Your own personal photo storage”

18. it's been so freaking awesome. I don't think it's as good at UI, but man is it thorough and able to gather the right context to find solutions.

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

19. Thanks to Claude Code and Codex I've been able to make several non-trivial internal tools and libraries without writing much in terms of code

    Recommends · Aug 2026 · in “The August 17 outage, and the work ahead”

20. I'm switching because of the higher usage limits, 2x speed mode that isn't billed as extra usage, and much more stable and polished Mac app.

    Recommends · Apr 2026 · in “Codex for Almost Everything”

21. The fact there is no way to disable auto-compaction and no way to go back in the conversation history to before a compact makes codex a no-go for me on any codebase > 5kloc.

    Criticizes · Jul 2026 · in “OpenAI reduces Codex Model Context Size from 372k to 272k”

22. What bothers me about these cuts is the assumption that because the models are supposedly getting better and cheaper, less usage is somehow equivalent value.

    Criticizes · Sep 2026 · in “Changing the difference between Codex plans to be Plus=1x Pro 100=5x Pro 200=10x”

23. This 'getting stuck once every ten-fifteen minues' is very much the experience trying to develop complex software with codex or Claude code right now.

    Criticizes · Jun 2026 · in “Codex just found a "workaround" of not having sudo on my PC”

24. I figured I'd just have Codex do it. I realized after about 3 days of various back and forth in between other work things that we were somehow stuck.

    Criticizes · Aug 2026 · in “Tech leaders say AI means less work – staff say they work up to 90 hours a week”

25. if I tell codex to do that with a specific stack and using specific paradigms to keep the code performant and maintainable, it's still a win over coding it by hand

    Recommends · May 2026 · in “AI sticker shock hits corporate America”

26. Codex feels much faster. For a while after the rewrite it was bad because you couldn't copy anything from the terminal but since then it's gotten much much better.

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

27. They definitely can make some things better and you can do somethings faster, but all the efficiency is gonna get sucked up by companies trying to drop more slop.

    Mixed · Jan 2026 · in “Cursor's latest "browser experiment" implied success without evidence”

28. Claude Code and Codex save you the computation, while every single instinct and 2 second "intuition", which is what you build with experience, is still online.

    Recommends · May 2026 · in “Software engineering may no longer be a lifetime career”

29. I still haven't experienced a local model that fits on my 64GB MacBook Pro and can run a coding agent like Codex CLI or Claude code well enough to be useful.

    Mixed · Feb 2026 · in “Qwen3-Coder-Next”

30. Or are you suggesting there were hundreds of researchers who just happened to be close to solving hundreds of these long standing open problems using Codex

    Mixed · Oct 2026 · in “Sharing AI progress in mathematics”

31. I use a codex subagent in Claude Code, so at arbitrary moments I can tell it "throw this over to gpt-5 to cross-check" and that often yields good insights

    Recommends · Nov 2025 · in “FAWK: LLMs can write a language interpreter”

32. If I run Codex against a project that includes a private API key, is there a chance a future user of ChatGPT could ask for an API key and get back mine?

    Mixed · Sep 2026 · in “On the Navier–Stokes Millennium Prize Problem”

33. Spending even a few days with Claude Code/Codex (using opus 4.6 or GPT 5.4) should convince anyone that the demand for tokens will be vast and infinite.

    Recommends · Mar 2026 · in “Will the AI data centre boom become a $9T bust?”

34. It is not a silver bullet but if you are not the one paying for it, there is no downside to throw a problem at it and see if it can come up with a fix.

    Recommends · Jun 2026 · in “AI Is Slowing Down”

35. Codex has me absolutely stoked again. I can finally have fun with the youngsters, knowing that the latest new hotness no longer has a learning curve.

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

36. harnesses created by the model providers (OpenAI/Codex CLI, Anthropic/Claude Code, Google/Gemini CLI) tend to be better than generalist harnesses

    Recommends · Jan 2026 · in “Karpathy: A few random notes from Claude coding quite a bit last few weeks”

37. this is why the workflow of consulting Gemini/Codex for architecture and overall plan, and then have Claude implement the changes is so powerful

    Recommends · Dec 2025 · in “GPT-5.2-Codex”

38. What bothers me with codex cli is that it feels like it should be more observable, more open and verbose about what the model is doing per step

    Mixed · Apr 2026 · in “Claude Opus 4.7”

39. Codex CLI paired with `emacs --batch` is perfectly capable of setting up, developing, and testing just about any kind of extension you'd want.

    Recommends · Sep 2026 · in “Malleable software: Restoring user agency in a world of locked-down apps (2025)”

40. I use a qemu vm for running codex cli in yolo mode and use simple ssh based git operations for getting code in and out of there. Works great.

    Recommends · Jan 2026 · in “2025: The Year in LLMs”