Rendered at 09:40:17 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
linzhangrun 15 seconds ago [-]
I tried it yesterday. The experience seems smoother than on Windows. I hope Computer Use will be added soon.
Also, when will OpenAI fix the issue where Xhigh and Ultra are both translated as “极高” in Chinese? It’s been this way for quite some time. As far as I know, the proportion of Chinese employees at these Silicon Valley AI companies is quite high.
cloudie78 49 minutes ago [-]
Reminder to everyone, treat these as trojans. Run them isolated from the rest of your system.
Give it a full desktop in a VM if you want to, just not direct access to your system.
perching_aix 41 minutes ago [-]
They ship with their own sandboxing by default, and Codex specifically is open source.
rawland 25 minutes ago [-]
I’d wait. Remember when Chromium downloaded and installed binary blobs.
"The American private sector is the most innovative and
technologically advanced in the world, and its scale,
speed, and capacity secure a critical offensive cyber
advantage for the United States."
wahnfrieden 22 minutes ago [-]
This app is NOT open source
badcafe23423435 26 minutes ago [-]
if it is open source why no exist any fork? why I can remove openai model default from instalation?
fragmede 33 minutes ago [-]
How do I get it to fix my Bluetooth if I do that? If you've been AI-pilled, 2026 is the year of Linux desktop because instead of dicking around with config files, I can just tell AI to fix python.
rawland 15 minutes ago [-]
Hermes Agent, local model, RAG-ed copy of archwiki. You are more able than you believe. Already now, no permission needed.
cyanydeez 13 minutes ago [-]
I just use a local model; its too dumb to hack into NSA just to fix my bluetooth.
TekMol 3 minutes ago [-]
Does this mean it is possible to talk to Codex from ChatGPT on a mobile phone now?
When I tried that with the Codex CLI version on a Linux VM, I did not get it to work. Possibly because OpenAI only supports connecting ChatGPT to a desktop installation of Codex?
BodyCulture 2 hours ago [-]
This will make it much easier to trap people into installing it without any isolation just to their primary user account or even make it run with admin privileges by default.
With the recent security related events we already see that it seems to be wide spread practice that many operators avoid the hassle of isolating their agents.
It is just an incredible cultural experience to see how quick stupidity gets accepted as a behavioural default.
usef- 1 hours ago [-]
The Linux version seems to use bubblewrap + seccomp for a "workspace sandbox" automatically, in addition to the auto mode and/or user approval.
A VM would be even better, but people could presumably run this in one if we manage to convince them of higher sandboxing in general ?
bloak 4 minutes ago [-]
Bubblewrap gets a bit confused inside a Docker container. If anyone knows how to run Codex inside a Docker container on Linux without it constantly complaining about a broken bubblewrap, please tell.
justincormack 42 minutes ago [-]
The cli does that already with codex on linux
meerita 30 minutes ago [-]
What's the benefit of working with this app, which eats insane amounts of memory, instead of Codex CLI?
ComputerPerson 21 minutes ago [-]
I'm only familiar with the Anthropic equivalent, but the cognitive load is different as opposed to necessarily better or worse. I have friends who prefer mousing around the UI.
Tabs for long-running often-compacted sessions is a difference I've noticed in emergent UX.
meerita 14 minutes ago [-]
I use Claude Code CLI, Codex Cli. Both are really good, they don't eat memory like the GUI apps.
ComputerPerson 9 minutes ago [-]
I use the CLI, too, but I enjoy watchinng people use the desktop apps. It seems like the desktop apps may be a little bit better suited for human-in-the-loop work. If you're already switching back and forth between a mouse, having an IDE running may make more sense.
The best feeling has to be in the CLI, in my oppinion. A low-stakes project where you can let ultracode runaway from you in the CLI is the most fun.
PunchTornado 22 minutes ago [-]
does the app eat more money that codex cli? I mean is there a difference in cost in asking via the app something vs the cli?
ddxv 21 minutes ago [-]
I think these styles of apps will be popular for OpenAI and Anthropic as they help solve some of their moat issues. The deeper you integrate someone's files into their app, the harder it will be to switch AIs
cyanydeez 11 minutes ago [-]
ok, but you know these things are marketed as super products; it's pretty easy for me to use a local model to scale up almost any project on github. Why would this be an effective moat beyond "I use codex too!!"
I'd love to see the stats on how many Linux users want this. Most Linux usage probably comes from WSL/SSH'ing into servers, where they would use the CLI instead of a GUI. Even for the people who run Linux on the desktop, most probably prefer the terminal anyways
torh 3 hours ago [-]
FYI; This link shows Codex based on your current OS. I get a norwegian landing page with a download link for Windows.
Does this mean that ChatGPT Desktop will run now also on Intel Macs?
badcafe23423435 28 minutes ago [-]
Why not create a separate account on Linux just for the agent?
This security measure should also be enabled by default. Many packages REQUIRE the creation of an account, but agents do not. Interesting.
pdhborges 3 hours ago [-]
For someone who has not tried these desktop apps: what is the the advantage versus cli codex with some MPCs and multiple folders each one with their context files?
Gareth321 2 hours ago [-]
The same as an OS with a UI. Discoverability, fewer actions per activity, easier navigation, faster to learn/lower skill floor, etc. Some highlights:
1. Much better multi-agent orchestration. The app supervises many agents, with different project views and built-in git worktrees, so agents can work on isolated copies of the same repo. It's easy to jump between tasks and see changes. I recall OpenAI wrote that CLI was not designed around this style of work.
2. The app combines multiple terminals, file previews, PR-review workflows, SSH connections, an integrated browser, and page annotations. For front-end stuff, Codex can run the app in Codex for mockups/prototypes, then iterate inside the app. IMHO I think this is a much faster, more intuitive flow.
3. For long-running and recurring agent workflows, I think they're much easier to manage in the app. You get automations, review queues, persistent conversation context, future schedules, and auto resume for longer running tasks. E.g. CI failure summaries, issue triage, and release briefs.
You can do some of the above, to some degree, with varying levels of success in the CLI, but I think it's miles ahead in the app.
arminluschin 2 hours ago [-]
You get GUI niceties: a nice presentation of the output like inline markdown rendering including tables and images in a nice font. Input supports drag & drop, and I can actually navigate the input field the way I am used to (pointing and clicking, using keyboard shortcuts to jump to beginning of words / sentences).
Not sure what the most modern CLIs support, but for me just the ergonomics of a GUI text field alone are superior.
Pavilion2095 2 hours ago [-]
It's easier to use for most people. I don't think CLI and GUI programs target the same audience.
logicallee 2 hours ago [-]
I'm not ready to try this yet, since after some recent experiences[1] I've decided not to be at the cutting edge of new tools and models for a few weeks or months.
However, from the screenshots and description, I expect that you would have these advantages:
- History. Currently, if you type into the CLI (TUI) your intention and requests are captured in some transcripts, but not in conversational turns. If you want the history of what you typed into the cli/tui you would have to datamine it from transcripts. By contrast, on the screenshots you can see it is a simple conversation that's saved and easy to return to.
- Multiplatform. As per the announcement "Use Codex across ChatGPT, your editor, and the terminal", meaning that you could open the ChatGPT app on your phone and continue to interact with this. While this might not matter to you if you exclusively code while sitting in front of your computer, still, it helps you be able to stay on top of things if you are on mobile.
- Background tasks and autonomous work. It says you can schedule it to do things in the background (issue triage, alert monitoring). At the moment, it would only do this if you've asked either codex or another agent to build a harness for it that does so. (i.e. you could ask Claude to build a harness that calls Codex on some schedule or interval.)
These all seem pretty good and I look forward to starting to use it once it's been more battle-tested.
[1] notably, on the Anthropic side the Opus 5 regressions - I had to downgrade to Opus 4.8 as I found Opus 5 was unreliable. I currently use Opus 4.8 and Codex Sol 5.6.
manupati 1 hours ago [-]
Download it a few hours ago. I've been waiting a long time for linux and it is working fine in debian kvm via X11
ksimukka 23 minutes ago [-]
oh Electron, leave my ram alone.
0xB0D 17 minutes ago [-]
Plague of AI slop.
A senior engineer in an Open Source project told me "I haven't looked at code in months"
In which case what TF is it you even do ?
wltr 3 hours ago [-]
If that’s an Electron app, what’s the difference with running it in the browser?
lwansbrough 2 hours ago [-]
Access to your computer
JPLeRouzic 2 hours ago [-]
That's why I won't download that tool.
tristanj 2 hours ago [-]
Access to your computer is the entire point of the app. Codex computer use can script and control any application on your computer.
You can give it any task on your computer and it can automate it.
Such as creating a photo on Photoshop, creating 3D models, editing videos, or browsing any website without scripting.
Gareth321 2 hours ago [-]
Honestly, you're missing out. The productivity gains I've had with these tools is unbelievable. I understand the risk though, so if you've got government sensitive data on your computer, or no backups, don't use the "full access" option. Babysit what it does instead.
dmortin 2 hours ago [-]
Isn't it expensive, though? If you let it perform gui or web tasks for you using vision, I'd think it consumes lots of tokens.
Closi 15 minutes ago [-]
Depends how much you are using it - for a casual user the $20 tier gives you just about enough use for hobby projects etc.
Or if you are doing full time development then you just need to pony up for the 20x tier if you want to use it.
Running Codex locally removes so much friction and is so fast compared to either running it on the web (where it has to build environments online etc which consumes time) or compared to copy-pasting chatgpt that it's just a no-brainer.
zorked 24 minutes ago [-]
I don't know about Chatgpt but I used Kimi (they have a Chinese-only plugin that does desktop control - works fine if you enable it even if you don't know Chinese). Observing how it works, it's mostly using the accessibility features of the user interfaces - it fetches a sort of DOM for the desktop applications. Only rarely it has to take a screenshot.
margorczynski 1 hours ago [-]
Can you give some examples? I'm evaluating where/how I could use stuff like this.
vineyardmike 1 hours ago [-]
Literally everything from generic coding agent to shopping.
I run it in a MacOS vm, fwiw, for certain tasks. I usually hand it a repo and say “install all build dependencies” and it’ll click through installation GUIs where necessary. I wonder if the TOS of an application is enforceable if a bot agreed and a human never saw it.
It can UI test web apps if that’s part of your job, but it can also just use the browser for tasks. I’ve had it research flights by checking different dates automatically and compiling the results for me. I’ve heard others use it to handle building a shopping cart for instacart/grocery delivery.
Probably the hero usecase for most people would be app/web development. It can control either a browser or a device simulator and can iteratively build and test the application, by clicking real buttons.
shevy-java 46 minutes ago [-]
> Literally everything from generic coding agent to shopping.
People need help with shopping now?
ccozan 18 minutes ago [-]
ooh, chatGPT is really good in filtering bullshit and recommending the products that really fit.
For serious stuff, is part of the shopping flow.
WASDx 48 minutes ago [-]
I upgraded my workflow a few months ago from "copy-paste things in and out of ChatGPT" to "use an agent that edits my project files and runs tests on its own" and the ergonomics are just so much better and enables automating bigger tasks. I still monitor everything it does and do manual adjustments so I feel ownership of the code.
margorczynski 31 minutes ago [-]
But isn't that use-case solved a harness like OpenCode or Codex? OpenClaw and Hermes are a bit different beast although they can also be used for development in a more holistic manner (e.g. automated GUI testing).
I'm just wondering about other uses where such a system would be useful aside from asking it via Signal or WA for the weather.
SillyUsername 3 hours ago [-]
None that I can see - I already have it installed as a chrome app on my Mint desktop, and it seems identical.
martin- 2 hours ago [-]
Does the Chrome app have access to your local files, like when you're working on a code project?
water-drummer 2 hours ago [-]
Why do you need nodejs if you can run javascript in the browser?
shevy-java 48 minutes ago [-]
Do people really use that? It seems horrible to turn your computer into a spydevice for AI slop spammers.
villgax 3 hours ago [-]
people good w/ linux would not have been holding their breath for companies which keep intelligence for a premium & h0st@ge depending on policy
Give it a full desktop in a VM if you want to, just not direct access to your system.
Also in the news: https://www.whitehouse.gov/presidential-actions/2026/08/expa...
When I tried that with the Codex CLI version on a Linux VM, I did not get it to work. Possibly because OpenAI only supports connecting ChatGPT to a desktop installation of Codex?
With the recent security related events we already see that it seems to be wide spread practice that many operators avoid the hassle of isolating their agents.
It is just an incredible cultural experience to see how quick stupidity gets accepted as a behavioural default.
A VM would be even better, but people could presumably run this in one if we manage to convince them of higher sandboxing in general ?
Tabs for long-running often-compacted sessions is a difference I've noticed in emergent UX.
The best feeling has to be in the CLI, in my oppinion. A low-stakes project where you can let ultracode runaway from you in the CLI is the most fun.
1. Much better multi-agent orchestration. The app supervises many agents, with different project views and built-in git worktrees, so agents can work on isolated copies of the same repo. It's easy to jump between tasks and see changes. I recall OpenAI wrote that CLI was not designed around this style of work.
2. The app combines multiple terminals, file previews, PR-review workflows, SSH connections, an integrated browser, and page annotations. For front-end stuff, Codex can run the app in Codex for mockups/prototypes, then iterate inside the app. IMHO I think this is a much faster, more intuitive flow.
3. For long-running and recurring agent workflows, I think they're much easier to manage in the app. You get automations, review queues, persistent conversation context, future schedules, and auto resume for longer running tasks. E.g. CI failure summaries, issue triage, and release briefs.
You can do some of the above, to some degree, with varying levels of success in the CLI, but I think it's miles ahead in the app.
However, from the screenshots and description, I expect that you would have these advantages:
- History. Currently, if you type into the CLI (TUI) your intention and requests are captured in some transcripts, but not in conversational turns. If you want the history of what you typed into the cli/tui you would have to datamine it from transcripts. By contrast, on the screenshots you can see it is a simple conversation that's saved and easy to return to.
- Multiplatform. As per the announcement "Use Codex across ChatGPT, your editor, and the terminal", meaning that you could open the ChatGPT app on your phone and continue to interact with this. While this might not matter to you if you exclusively code while sitting in front of your computer, still, it helps you be able to stay on top of things if you are on mobile.
- Background tasks and autonomous work. It says you can schedule it to do things in the background (issue triage, alert monitoring). At the moment, it would only do this if you've asked either codex or another agent to build a harness for it that does so. (i.e. you could ask Claude to build a harness that calls Codex on some schedule or interval.)
These all seem pretty good and I look forward to starting to use it once it's been more battle-tested.
[1] notably, on the Anthropic side the Opus 5 regressions - I had to downgrade to Opus 4.8 as I found Opus 5 was unreliable. I currently use Opus 4.8 and Codex Sol 5.6.
A senior engineer in an Open Source project told me "I haven't looked at code in months"
In which case what TF is it you even do ?
You can give it any task on your computer and it can automate it. Such as creating a photo on Photoshop, creating 3D models, editing videos, or browsing any website without scripting.
Or if you are doing full time development then you just need to pony up for the 20x tier if you want to use it.
Running Codex locally removes so much friction and is so fast compared to either running it on the web (where it has to build environments online etc which consumes time) or compared to copy-pasting chatgpt that it's just a no-brainer.
I run it in a MacOS vm, fwiw, for certain tasks. I usually hand it a repo and say “install all build dependencies” and it’ll click through installation GUIs where necessary. I wonder if the TOS of an application is enforceable if a bot agreed and a human never saw it.
It can UI test web apps if that’s part of your job, but it can also just use the browser for tasks. I’ve had it research flights by checking different dates automatically and compiling the results for me. I’ve heard others use it to handle building a shopping cart for instacart/grocery delivery.
Probably the hero usecase for most people would be app/web development. It can control either a browser or a device simulator and can iteratively build and test the application, by clicking real buttons.
People need help with shopping now?
For serious stuff, is part of the shopping flow.
I'm just wondering about other uses where such a system would be useful aside from asking it via Signal or WA for the weather.