▲ 467 points
back
316 comments
Interesting to see the Linux version released. On Windows, though, my experience with the new ChatGPT app since Codex was folded into it hasn't been great.
I'm a Codex user, and when it was still a standalone app it worked really well for me. Since it became part of the new ChatGPT app, the app feels noticeably slower and, at least on my machine, is currently using around 1.27 GB of RAM [1].
The old ChatGPT app, which has now been renamed "ChatGPT Classic", feels much faster and is using around 478 MB under the same conditions.
I have a reasonably powerful PC, so the difference is pretty noticeable. I assume Classic will eventually be discontinued, but so far the transition to the new app on Windows hasn't been particularly good for me.
> The old ChatGPT app, which has now been renamed "ChatGPT Classic", feels much faster and is using around 478 MB under the same conditions.
That's definitely better, but all things considered, this is still an absurd amount of memory for a text chat client, even if you account things like hardware composited high-definition UI surfaces etc. into it.
The old app also had a habit of spinning at least one CPU core at 100% due to some runaway "shimmer" animation when an image wouldn't load or something...
> my experience with the new ChatGPT app since Codex was folded into it hasn't been great.
My main gripe beyond the performance issues is that OpenAI doesn't yet seem to know where they want to go with Codex and "ChatGPT Work", and is changing the paradigms daily, making it feel like there's no point in even trying to understand them.
It's really unclear to me which conversations (and lately scheduled tasks) are local and which are cloud-based.
Codex app was always unoptimized , but the competitores arent great either.
However it’s still a an agent app, it gets the job done and has great tooling.
Eventually the whole thing will probably be remade in a more performant way and be announced in a blog post as one shotted by gpt 6.x
From yesterday, with 26 comments: https://news.ycombinator.com/item?id=49264334
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?
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.
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.
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.
For me the main one is in-app browser with feedback you can do that's native to its elements lika a network inspector. All "real" browsers felt too broken when I tried them.
The bad part of the setup is: you still have to tell it to ssh into your dev container and make changes there (since that's where the linux running dev server is). Most work still via cli, which is faster and much more lightweight in token usage.
It's easier to use for most people. I don't think CLI and GUI programs target the same audience.
Not using it day today but projects and pinned session seem useful, mentally
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.
At least on Windows/Mac, a significant number of users of this app are non developers, and you should tame your expectations about them handling things like "isolation".
Even for developers working on Linux, you'll be surprised how many have never run a docker command in their life.
The testimonials at the bottom are all from AI companies.
Linux users are kind of averse to trojans. You should call it Back Orifice For Linux. You don't even have to change the OpenAI logo!
FYI; This link shows Codex based on your current OS. I get a norwegian landing page with a download link for Windows.
The most remarkable things about this announcement:
- Electron based app: Electron is a framework sold on the basis of enabling rapid cross-platform development at the cost of performance.
- Frontier AI company: AI is sold on the basis of enabling rapid development
- App was released in February & took 6 entire months to port to Linux
More details here: https://learn.chatgpt.com/docs/linux/linux-app
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.
Unrelated to this Linux release but I've been using the new ChatGPT desktop app since I annoying updated on accident, and I haven't had that great of an experience.
I previously really enjoyed the Codex app. It was easy for me to understand and find what I needed. The conversation view provided the right amount of information without feeling too concise or full of jargon and the typographic hierarchy made it easy to skim. The project based workflow made sense for my needs.
Ever since they combined all ChatGPT into one app though it has become a mess. It's trying to do too much in one. The settings menu is especially bloated, and I find the UI to be too complicated for the simple questions I'm asking outside of development work. I would rather just use the web interface for general use at this point. They've also been updating much of the UI to follow the same patterns as Claude, and I've not been impressed with the Claude desktop app.
To me, they are taking multiple steps backwards. I hope they eventually find their way again.
I wonder why operating systems aren't integrating with browsers more.
Nobody should be installing or using AI apps. Your browser is as far as they should go.
Reminder that the macOS app went from "this is fairly well made" to "it downloads multiple gigabytes of random things and doesn't follow any design conventions nor standards"
The Linux app will fail the same tests.
Sitting at 2.2GB of combined resident RAM across 11 processes. I haven't done a single query yet.
An often overlooked advantage of Electron based apps is they can convert any older version of laptop into a nice toaster oven.
This is fantastic as I can toast or reheat my frozen waffles on the same machine which is also running a agentic loop on codex desktop to cook my software.
The permission prompts after asking it to touch only 3 files are more concerning to me than Electron itself. An agent that can expand its access scope that easily needs a much clearer capability boundary, especially on a desktop where the user’s files are the real sandbox.
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
so instead of using a browser, now i can use an app that is a browser. makes total sense
Not sure what I should see under the Link provided. Here is another one:
https://community.openai.com/t/codex-in-chatgpt-desktop-app-...
"The desktop app is designed as a workspace for managing projects, working with files, using browser workflows, and running Codex alongside ChatGPT."
Not sure if I really understand this. And somehow I am worried about ChatGPT having access to my files and workflows. How much control do I have?
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
I find it almost funny how hostile the response is when a company actually goes through the effort of supporting Linux. Apparently shipping the Linux version is only step one, you also need to pick the right framework, use the right packaging, consume the right amount of RAM, and preferably rewrite it natively.
On macOS, the version made for Apple Silicon in Swift was abandoned (now it called ChatGPT-classic until they decide to kill it) to this garbage in Electron.
If gpt is so great as they say, why aren't they using their own operating system yet? They have all the resources they need to prove a point
Congrats on supporting Linux. It makes the ecosystem more rich. Hope they will continue to maintain it and provide parity support.
Heads up: unlike Codex CLI, Codex Desktop is proprietary, and thus can't be audited for Claude Code style hidden anti-user behavior.
Why would I use this over browser version or CLI
I’ve got a long running chat in the Windows app that becomes completely unresponsive for minutes on end. Complete travesty.
So much negativity... I like the desktop app and am looking forward to testing it out.
Just in case you don't know how to set it up, here is the guide https://youtu.be/AfuHEdxktF8
Everybody is irritated about electron, but that's not at all the problem. It's possible to write performant and optimized react code. They simply don't. I find the chatgpt app on Windows to be extremely laggy.
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?
Finally! My shitbox Surface 8 pro that's running Debian will be pleased.
Why would they write this in electron instead of something closer to the metal I thought this is the whole point of AI.
I am unable use non-CLI tools, so I don't care about this app. However, I have a question about codex CLI: currently I am using pi agent and I am happy with it, using codex CLI would give me some advantage?
Glad to see a .rpm, Claude only publishes a .deb.
About the damn time. Couldn't they vibe code the Linux version using the same very tool from the day one?
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
Does this mean it's a matter of time until I can deploy codex on my raspberry pi now?
Why is this written in electron?
OpenAI: With AI, you can build really good apps, really quickly! Fire your devs!
Also OpenAI: Aight look, Electron is the best that we can do at this point, take it or leave it.
If this isn’t enough to convince you how little truth there is in everything these companies claim, then you have been brainwashed entirely already.
Why aren’t we getting quality native apps on all platforms, released simultaneously, if these AI code monkeys are THAT good? Where are all these amazing experiences built with AI that these guys keep promising?
I guess an Electron monstrosity is about as far as it can go.
Learn from this, internet. (I know none of you will, but doesn’t hurt to call a bit of attention to it)