Codex is now in the ChatGPT mobile app

(openai.com)

228 points | by mikeevans 7 hours ago

36 comments

  • Alifatisk 6 hours ago
    Whats crazier is that Codex is free. I thought I had to pay to even try it out but nope, you can use the desktop app or cli for free, its apparently included in the free plan. You just have to sign in to your ChatGPT account.

    Of course I am aware that the caveat here is that all my interaction is part of training, but I’m fine with that. Even Qwen Cli discontinued the free plan.

    • orionsbelt 2 hours ago
      First hit is free… got to get you hooked.
    • beering 2 hours ago
      Can’t you just turn off training on your data in the settings?
    • firesteelrain 2 hours ago
      How much better is it than Claude? I have both but Claude sucks up so many tokens.
      • stldev 1 hour ago
        I switched some time after Anthropic bricked their models with adaptive thinking. It's a legit mystery to me how people are still using CC professionally.

        Codex is far less frustrating and manages context better. It's also costing me about 1/3rd as much as Opus 4.7 on CC.

        • ggsp 53 minutes ago
          The only way to keep using CC for me has been to stick to 4.6 1M
      • bobbylarrybobby 2 hours ago
        5.5 is absolutely comparable to opus 4.7 (both on highest effort), maybe even better. It generally seems less lazy, faster, and writes code closer to what I'd write. The only downside is that for very very long tasks, it can kind of lose track of the goal. For tasks under ten minutes I'll go with codex every time.
      • yieldcrv 2 hours ago
        Less gibliterrating and more doing

        Very fast

    • thorum 4 hours ago
      I was really unimpressed by the free Codex (for nodejs/react dev). I think it must be using a less powerful model or they’re limiting it in some other way.
      • jwilliams 4 hours ago
        Are you specifically pointing at a different experience between free + paid? Or just that the free version is unimpressive?

        I'm using paid on TypeScript and it's genuinely terrific. Subjectively I think it has the edge over Opus.

        I'd be surprised if OpenAI is hamstringing the free version. That would seem crazy from a GTM PoV. If anything the labs seem to throttle the heavy paid users.

        • fragmede 3 hours ago
          Yes, the free version doesn't have access to the same models that the paid does.
          • debian3 3 hours ago
            You have access to 5.5 xhigh on free. Which model is missing except the 5.3 that run on cerebras?
          • wahnfrieden 3 hours ago
            It's only missing the trash models. Likely a user skill issue.
      • throw03172019 2 hours ago
        The free version of ChatGPT is definitely worse as well. My SO uses the free version and I can tell a significant downgrade.
      • wahnfrieden 4 hours ago
        Post your chat session
        • ssl-3 3 hours ago
          Can Codex chats be shared? (This is a genuine question; so far, I've only used Codex in CLI on Linux.)
      • dakolli 2 hours ago
        I'm unimpressed by all LLMs, and especially unimpressed by the people claiming to be impressed by them.
    • Rover222 6 hours ago
      I think it's free for about 2 useful requests and then you have to upgrade or wait?
      • melagonster 3 hours ago
        Switching to GPT 5.4-mini can increase the number of requests we can use freely.
      • osiris970 4 hours ago
        So basically a 20$ Claude plan lmao
        • sidrag22 52 minutes ago
          the current state of that 20$ claude plan, despite twice this week them stating better usage. first for "double 5 hour usage", then for 50% overall more usage a week.

          MAYBE the 50% overall is true, but the double usage during a 5 hour window i just dont see it at all. I've maxed 3 5 hour windows since this happened, 0% chance it was double as much as normal, i ate up about 4-5% of my weekly total each time(this was ~10% each time pre announcements). wish i could give token numbers but its obscured i just know it was around 120k 4.6 with some delegation to sonnet subagents.

          So SURE its almost certainly more allotted weekly, but if those totals are consistent for 5 hour blocks, you gotta split your daily usage into at least 3 sessions with 5 hours between them to even hit that weekly limit. its unreal how much they have burned their good reputation in a 2 month stretch, i am positive its also being astroturfed with bots more than happy to advance the narrative.

          the internet is annoying, these tools are overall cool, just wish anthropic would go back to being semi predictable.

        • replwoacause 4 hours ago
          I stopped using my Claude subscription because it became so prohibitive. Back to ChatGPT and Codex full time and been pretty happy. I miss the tone/writing style of Claude, but don't miss the frustration of being told I've reached my plan limits in a comically short amount of time.
          • dmd 3 hours ago
            Using these prompts/steering[0], setting Base style to Friendly, Warm to More, Enthusiastic to Default, Headers, Lists, and Emoji to Less, I have found I can get gpt-5.5 about ... 80% of the way there to writing as non-annoyingly as Claude. And it's so much faster and has such higher limits that that's worth it for me.

            I also put together this ridiculous thing[1] because I missed the font and color scheme of Claude.

            [0] https://gist.githubusercontent.com/dmd/91e9ca98b2c252a185e8e...

            [1] https://github.com/dmd/aimpostor

            • firesteelrain 2 hours ago
              How do you fit that entire prompt in the customized instructions ?
              • dmd 2 hours ago
                Some of it is in my customized instructions, some of it I fed pieces in at a time saying "remember this please:" so it goes into Memories.

                I'm not entirely clear on the mechanism by which memories make it into context, so it's possible some of it isn't all the time, but it does seem to be working reasonably.

                Again, it's not as good as Claude when it comes to writing "not like an AI". But it's significantly better than it was.

            • replwoacause 3 hours ago
              Thanks, I’ll give those a try!
              • dmd 3 hours ago
                FYI I'm actively working on aimpostor, so check back in a couple days for some quality improvements. (I'm definitely not going to bother with a Sparkle updater or anything like that.)
          • Razengan 4 hours ago
            on Codex I ran into limits maybe like 2 times in 3 months, after doing several "upgrade this experimental game to my latest shared framework" passes on 5.5 Extra High
            • ssl-3 2 hours ago
              On which plan?

              I can go through a 5-hour limit with a $20/mo Plus subscription in a few minutes with 5.5 Extra High. This causes me to reserve the latest/best rev for the harder problems.

              5.5 really does seem to be very superior to 5.4, but it's also very expensive to run: The gas gauge moves fast. It's not very clearly defined whether 5.5 will cost less to get a problem solved quickly, or if a bunch of automatic iterations of 5.4 will solve it less-expensively. Both are often frustrating to me on the $20 plan.

              (Also: Are you sure you're seeing it right? 5.5 has been in the wild for less than a month, so far. https://openai.com/index/introducing-gpt-5-5/ )

    • throwaway613746 6 hours ago
      [dead]
  • charlie90 14 minutes ago
    Nice. Next step is giving codex/Claude Code local device control...problem is the current ios/android are so locked down that agents can't do much ...but the space is so ripe for disruption that I bet we'll see AI-native devices coming out within the next few years that allow agents to interact with everything. I would be nervous if I were apple right now.
    • adithyassekhar 12 minutes ago
      Android can allow an app to control the device using accessibility permissions.
  • jumploops 5 hours ago
    I’ve been using Codex from my phone for the past couple of months (through a tunnel, not this app).

    I was initially quite excited, but I’ve found the results are less than great compared to being at a keyboard.

    Something about the smaller screen size and/or lack of keyboard causes me to direct the agent less, which in turn creates more tech debt/code churn/etc.

    Maybe I’m just showing my age, and I should practice voice dictation or something more, but my thoughts flow faster and more clearly on a keyboard (less ums).

    • keyle 3 hours ago
      I'm not sure I follow, you develop code on a remote machine by speaking to your phone and are unimpressed by the result?
      • jumploops 1 hour ago
        It's not that I'm unimpressed by the results, it's that I think I'm saving time by pushing the agent along remotely, but the reality is that my messages to the agent(s) end up being a lot shorter, which inevitably leaves more up for interpretation.

        Don't get me wrong, I still use Codex (and sometimes Claude Code) remotely every day, and am overall excited for this release, it's just that the benefit wasn't as high as I had initially hoped.

        Part of this is due to the models getting better (no need to prod along with "continue"), and part of this is the nature of how I use my phone (short bursts of attention).

        But again, maybe I'm just old and prefer big screens with a keyboard.

      • selcuka 3 hours ago
        They are unimpressed by their (current) ability to use it, not the technology.
    • aiscoming 4 hours ago
      the ums are exactly the sign that you speak much faster than you type, so you need a pause for your thoughts to catch up
    • fowlie 5 hours ago
      I've been trying voxtype (using whisper models) lately, and to my surprise all my ums are filtered out. It's really good now actually!
      • esperent 3 hours ago
        I don't see any way to use that on a phone.
    • cm2012 2 hours ago
      Wispr flow cuts out ums. I love it
    • redanddead 1 hour ago
      the main thing is functionality, you can always work around the ergonomics
  • reassess_blind 4 hours ago
    Is there a native way to work remotely with Claude/Codex on a local folder or git repo on your main machine without having to connect it to GitHub? For creating apps for personal use I’d rather just keep the files local.

    Edit: Running into issues setting it up on Windows. There's no "/remote-control" command in the CLI, so I installed the Windows Codex app. Then I updated the iOS app which now has the "Codex" feature in the sidebar, which should allow remote access to the Windows machine's instance - except it doesn't connect. The iOS app shows my desktop's hostname, so it knows there's an instance there, but refuses to connect. Issues like this would persuade a lot of folks to switch back to Claude.

    • barrkel 4 hours ago
      This is what /remote-control does in Claude Code, once it's running on your main machine. You can open it up in the phone app.
      • vardalab 1 hour ago
        It flakes out in less than 24 hrs. I tried leaving a session open on remote control mode in a VM but it inevitably stopped with some token auth error.
    • wolfoftheweb 1 hour ago
      You can run Codex and Claude on mobile from https://github.com/happier-dev/happier
    • wahnfrieden 4 hours ago
      That’s this announcement.
      • reassess_blind 3 hours ago
        I ask because I tried the other week to use /remote-control in Claude, and it prompted to connect a Github repo with no local alternative. Things may have changed since then.

        My experience today with the new Codex remote control has been that it doesn't connect at all.

    • iamjs 4 hours ago
      I think the `/remote-control` feature does this, if I understand you correctly.
      • DonsDiscountGas 4 hours ago
        It's supposed to. I've always found it buggy and unreliable but maybe that's just me. (This command exists in Claude btw not sure about Codex)
      • maille 4 hours ago
        Does it work on windows? And how do you then remote in?
    • Salgat 4 hours ago
      I wish codex supported this, I use it all the time for claude.
    • nsonha 1 hour ago
      I tried apps that do this workflow (happy coder being one), but the workflow itself is rather clunky. You have to first start the session inside the remote machine. I now only do ssh, I can start or resume on whatever device suits at the time. The only downside is latency and connection drops, mosh solves it.
    • Razengan 4 hours ago
      [dead]
  • vohk 6 hours ago
    Dang, I thought this was going to be integration for Codex Cloud, not the (still not available for Linux) Codex App. Not even Codex CLI, alas. You can still access the Cloud option from a mobile browser well enough but I prefer an app UI for poking at the things on the go.
    • tekacs 6 hours ago
      You can do this from the CLI - `codex remote-control` works on Linux (I have no affiliation, just something I noticed).

      They might just not have cut a new build yet, today. It 'works' on master, but the mobile app thinks that your build is outdated (v0.0.0) if you build from master without overriding version, so probably easiest to wait until they cut a build if they haven't.

      • embedding-shape 5 hours ago
        > You can do this from the CLI - `codex remote-control` works on Linux (I have no affiliation, just something I noticed).

        Woah, hadn't seen this before!

        Off-topic, how long compile times do people have for codex-rs in openai/codex? Even my very beefy computer takes like 30 minutes to compile in release mode, makes me wonder why it's so slow and how this TUI got so large. But then I remember, agents like to write a lot of code, compilers get slower when they have to compile a lot of code :)

        • tekacs 4 hours ago
          Try turning off LTO. Their default codex-rs/Cargo.toml uses `lto = "fat"`, which is... expensive and slow and... you really really don't need it for a local build that you're not distributing.

          In my experience, although the build is a little slow, it's that LTO step that takes a million years.

      • vohk 5 hours ago
        Oh, that's promising, thanks! I've just been using the npm version.
      • asadm 6 hours ago
        thanks. i dont use the app and so this is cool
    • beering 1 hour ago
      Codex Cloud has been in the chatgpt app for quite some time now. If you click out of the new dialogs then you can access your cloud threads
  • breatheoften 2 hours ago
    This is extremely what Ive been wanting -- I had previously thought about using one of the hackish apps that try to deliver this experience - or spinning up something for this myself ... - but integrating this directly is definitely the right way to provide the best system and product experience -- and this seems to work out of the box exactly as I would want!
  • Jimidesuu 42 minutes ago
    So Codex is also heading towards 'portability' and I can see that here but I bet this will take time before it's cleanly optimized for mobile hard use
  • throwatdem12311 1 hour ago
    > Stay connected to active work from anywhere

    And here I thought AI was gonna automate the world and we were gonna work less.

    Turns out you’re gonna work 24/7 no matter where you are!

    • mifydev 1 hour ago
      This is a very myopic and unnecessary cynical sentiment. It's not about you - agents just need to run without your computer being on all the time. Coding is a background task that needs to run unattended now.
      • throwatdem12311 1 hour ago
        This is absolutely not true. I run dozens of Opus agents all day and they need so much constant attention and babysitting (lest everything turn to sh*t) that I would not qualify it anywhere close to “background”. And I’m sure as hell not wrangling these things from my *phone*.
        • EGreg 50 minutes ago
          What would it take to remove yourself from the loop so your agents can go parabolic and kick off the singularity?

          (Have them cover their own token costs, hehe).

          • someguy101010 35 minutes ago
            if i didn't have to prompt it to learn from its mistakes and it just "intuitively" knew to do that
      • nullsanity 51 minutes ago
        [dead]
    • teaspoon 1 hour ago
      Why not work the same amount and be at your desk less?
      • throwatdem12311 1 hour ago
        The same reason I don’t have social media apps on my phone.
      • sheept 1 hour ago
        your boss will probably prefer the colleague that can now work more, and isn't occasionally absent from their desk
  • miohtama 3 hours ago
    I have been using Omnara now some months, on desktop and mobile. It's web/mobile remote for Claude and Codex.

    I can do some tasks on mobile, especially if they are follow up and steering only, greatly increasing productivity as you can keep working whilst in transit, etc.

  • boodleboodle 1 hour ago
    Could Codex CLI get this support also? I am sure a lot of us are running remote linux machines with Nvidia GPUs, with codex CLI running
    • beering 1 hour ago
      I think this is a thing, maybe need to upgrade your codex cli.
  • iridione 5 hours ago
    This is neat! Now I'm curious, what's left to innovate in the coding agent space? Sure there are the usual suspects like maintenance, security, reliability and other scalability improvements and looks like they will be addressed in the next year or two.
    • thornewolf 5 hours ago
      there is something "wrong" with the ux that is hard to pin down. these things generate even text summaries more rapidly than i can read them. i need a better method for dumping info into my brain + dynamic control (if necessary)
      • jpalomaki 3 hours ago
        Tell it to create html summaries with diagrams and sidebar for navigation.

        Or ask Codex to create image that explains xyz.

      • ssl-3 4 hours ago
        When I take time to read all of the output, I often find that it's mostly noise. I don't like noise so I usually don't bother.

        But a person can use subagents, if they want, to filter that down. This burns tokens in a big hurry, but I think subagents can be arbitrary local commands (eg, a local LLM).

        Or, you know: Just slow down. :) It doesn't always have to be a race, does it?

    • deadbabe 3 hours ago
      Agent farms. Have agents make tons of random high fidelity variations around the clock of the same app or feature from some vague ideas, and you use each of them to see which one you like best and can productize, and you skip the need to do iterative prompts.
      • helsinki 1 hour ago
        Some of us pay by the token.
    • ukuina 4 hours ago
      [dead]
  • asadm 6 hours ago
    I use Termius on my phone to remote and make agent do stuff while i chill or am on road. This seems useful too.
  • m3kw9 37 minutes ago
    Buggy af though
  • impulser_ 4 hours ago
    Say what you want about OpenAI, but their software is actually pretty dam good especially compared to Anthropic and Google. Anthropic is just sloppy, and Google just doesn't live on this planet.

    Both of the Codex apps are very good.

    I tried this out and it works significantly better than Claude's remote control in fact the first few times I tried Claude's remote control it didn't even work and to this day is very buggy.

    • haint_ 1 hour ago
      I use remote-control every day and haven't had many issues with it, aside from the fact that the mobile app being pretty limited, e.g there are no prompt suggestions like slash commands and skills, everything in the textbox is just a raw string. You also can’t start a new session directly from the app (have to SSH into the host manually to do that)

      Other than those limitations, the connection has been very stable for me, definitely more reliable than alternatives like happy.engineering or Omnara. What’s been buggy for you specifically?

  • jsemrau 2 hours ago
    I don't understand OpenAI's product strategy.
    • hello8402 1 hour ago
      > I don't understand OpenAI's product strategy.

      Neither does OpenAI.

  • ahmadyan 4 hours ago
    i'm not sure if i'm hallucinating, but i swear i had codex in the chatGPT app from long time ago (like the original codex on the web).

    they added some new stuff, like remote control to wherever the desktop codex app is running, but these companies need to work much more on their press releases.

    • wahnfrieden 4 hours ago
      That was cloud codex. Not comparable
  • breatheoften 2 hours ago
    This is super nice!!!!!!
  • schnitzelstoat 6 hours ago
    This is really useful for when you just need to approve plans or make small decisions.
  • Loranubi 2 hours ago
    macOS only so far. "Windows is coming soon"
  • tekacs 6 hours ago
    It's refreshing that unlike Anthropic's Remote Control, this actually... works.

    Feels like a testament to the value in taking time and doing it properly.

    Now if only codex got its 1M token context window back.

    ---

    Edit: Hmmm. Maybe I spoke too soon. Sigh. Definitely _more_ reliable by far overall, but still have queued messages with responses on my phone that don't show up on my computer, and responses that don't show up on my phone.

    Edit 2: New threads created from my phone seem to have a little stall-out, but ones that are underway are behaving reasonably well.

    • 20kleagues 6 hours ago
      Out of curiosity, what issues did you face with remote control on claude? I use it daily and it seems to work pretty well (bar the issues when my Mac would sleep and then the session would disconnect, but that's an issue on my end).
      • RayVR 6 hours ago
        My own experience has been that it works for about five minutes before it just disconnects or hangs. I’ve never been able to use it successfully.
      • hamza_q_ 2 hours ago
        Made a menu bar app you may find useful for MacBook sleep prevention, even when the lid is closed:

        https://github.com/narcotic-sh/modafinil

      • tekacs 6 hours ago
        Myriad, to be honest. I find it to just constantly be in a 'torn' state, the UI is very mushy on mobile with a lot of the affordances from desktop missing, and... it's distinctly less useful when you can't... edit, rewind, start a new thread, etc.
  • Razengan 4 hours ago
    Codex has been great in the last 3-4 months I've been using it, almost exclusively to review existing GDScript code, and this was the feature I wanted most, because with gamedev you get the best ideas when you're out and about or in bed :)

    Claude on the other hand has been jank all around from the UX to the UI to the AI itself that it's baffling how it's more popular here on HN: https://i.imgur.com/jYawPDY.png

    Sadly this remote control feature doesn't seem to be for Mac to Mac yet? I love the MacBook Neo as a "thin client" for AI and keep the MacBook Pro at home/hotel, and it would be nice to share Codex desktop sessions (without SSH → resume link)

  • sbinnee 3 hours ago
    I don't like this direction. For accessibility aspect, sure it is good. But Codex is a coding product. I am increasingly concerned of lack of reviewing practice. I doubt that a mobile app is good for reviewing code changes.

    > Stay connected to active work from anywhere

    ... (and anytime because it's on your phone). No thanks.

  • fHr 5 hours ago
    rust and opensource W
  • cyanydeez 4 hours ago
    opencode behind a nginx proxy with a standard user/password is sufficiently powerful. You can also upgrade to https://docs.linuxserver.io/images/docker-code-server/ and run any vscode plugins; opencode's plugin is pretty rudimentry but cline has been making a lot of strides.

    You can run your local LLM and just connect the docker containers. I'm paranoid of being disconnected from the LLM, so I never run any of this on the same machine, so orchestrating a docker-compose file that provides the necessary services is important.

    I'm still trying to find a good remote file system to loop into the setup for improved switching between cli and these web containers.

  • Squab 5 hours ago
    friends, you don’t have to always be productive. leave the agent on the computer and take care of yourself.
    • jorl17 5 hours ago
      For many people, that's exactly why this is useful: less time on the computer, more time doing other things and occasionally checking in.

      In those scenarios, the goal is not "work at any time" but to "be anywhere at any time", or, rather, to "be able to work from anywhere, doing anything".

      Sort of....I guess.

      • yhgyy 15 minutes ago
        I love how all these software engineers are willingly walking into a productivity trap where they will be exploited.

        I’m not a swe but damn, I’d hate to be one.

  • andrew_kwak 1 hour ago
    [dead]
  • samcooper 2 hours ago
    [flagged]
  • comment0r 5 hours ago
    [dead]
  • AIMC 5 hours ago
    [flagged]
  • randomsimon 3 hours ago
    [dead]
  • stavros 6 hours ago
    The best way I've found to work with LLMs is another OpenAI project, Symphony (which I implemented for Linear/GitHub and OpenCode[0]).

    It integrates with your issue tracker and makes the tracker the UI for the LLM. It also clones the repo for every ticket, and can set up fixtures/etc. I can work on multiple items at a time, which is fantastic because otherwise you have to wait for the LLMs a lot.

    [0] https://github.com/skorokithakis/symphony

  • fa3ax 2 hours ago
    They needed to announce something after the Anthropic slop rewrite of Bun.

    In an ideal world the would allocate 50% of compute to find errors in that rewrite and publish how bad Claude is, but that would undermine confidence in slop in general so that is not going to happen.

  • mv4 5 hours ago
    Can someone recommend an IDE that can be used with a self-hosted model (via OpenAI or similar)?
    • aiscoming 4 hours ago
      vs code supports local models (bring your own key/model)

      you need a model server - ollama/llama.cpp/lm studio

      • no-name-here 3 hours ago
        > bring your own key

        Do you mean supporting oai-compatible api URLs in copilot? If so then you need either VS Code Insiders, or a VS Code extension I believe?

    • suyash 3 hours ago
      Look up OpenCode