Codex for almost everything

Just reading the comments here it's amazing how many people seemingly don't know that Claude Desktop and Cowork basically already does all of this. Codex isn't pioneering these features, it's mostly just catching up.

There seems a fair enthusiasm in the UI of these to hide code from coders. Like the prompt interaction is the true source and the actual code is some sort of annoying intermediate runtime inconvenience to cover up. I get that productivity can be improved with a lot of this for non developers, just not sure using 'code' as the term is the right one or not.

Has anyone figured out how to stop the Codex app from draining my M5 Pro's battery in like 2 hours? I can literally just have it open and my lap turns into a heater. I've tried adjusting all sorts of settings and haven't been able to make a dent. I'm assuming its the garbage renderer.

Lots of scepticism here, but I think this may really take off. After 25 years of heavy CLI use, lately I've found myself using codex (in terminal) for terminal tasks I've previously done by CLI commands.

If someone manages to make a robust GUI version of this for normies, people will lap it up. People don't want to juggle applications, we want computers to do what we want/need them to do.

Do people really want codex to have control over their computer and apps?

I'm still paranoid about keeping things securely sandboxed.

<tin foil hat>

I swear OpenAI has 2-3 unannounced releases ready to go at any time just so they can steal some thunder from their competitors when they announce something

</tin foil hat>

My current expectation is that the Cowork/Codex set of "professional agents" for non-technical users will be one of the most important and fastest growing product categories of all time, so far.

i.e. agents for knowledge workers who are not software engineers

A few thoughts and questions:

1. I expect that this set of products will be extremely disruptive to many software businesses. It's like when a new VP joins a company, they often rip and replace some of the software vendors with their personal favorites. Well, most software was designed for human users. Now, peoples' agents will use software for them. Agents have different needs for software than humans do. Some they'll need more of, much they'll no longer need at all. What will this result in? It feels like a much swifter and more significant version of Google taking excerpts/summaries from webpages and putting it at the top of search results and taking away visits and ad revenue from sites.

2. I've tried dozens of products in this space. For most, onboarding is confusing, then the user gets dropped into a blank space, usage limits are uncompetitive compared to the subsidized tokens offered by OpenAI/Anthropic, etc. It's a tough space to compete in, but also clearly going to be a massive market. I'm expecting big investment from Microsoft, Google etc in this segment.

3. How will startups in this space compete against labs who can train models to fit their products?

4. Eventually will the UI/interface be generated/personalized for the user, by the model? Presumably. Harnesses get eaten by model-generated harnesses?

A few more thoughts collected here: https://chrisbarber.co/professional-agents/

Products I've tried: ai browsers like dia, comet, claude for chrome, atlas, and dex; claw products like openclaw, kimi claw, klaus, viktor, duet, atris; automation things like tasklet and lindy; code agents like devin, claude code, cursor, codex; desktop automation tools like vercept, nox, liminary, logical, and raycast; and email products like shortwave, cora and jace. And of course, Claude Cowork, Codex cli and app, and Claude Code cli and app.

Edit: Notes on trying the new Codex update

1. The permissions workflow is very slick

2. Background browser testing is nice and the shadow cursor is an interesting UI element. It did do some things in the foreground for me / take control of focus, a few times, though.

3. It would be nice if the apps had quick ways to demo their new features. My workflow was to ask an LLM to read the update page and ask it what new things I could test, and then to take those things and ask Codex to demo them to me, but it doesn't quite understand it's own new features well enough to invoke them (without quite a bit of steering)

4. I cannot get it to show me the in app browser

5. Generating image mockups of websites and then building them is nice

Confusingly, Codex their agentic programming thing and codex their GUI which only works on Mac and Windows have the same name.

I think the latter is technically "Codex For Desktop", which is what this article is referring to.

SSH to devboxes is the exact usecase for services like https://shellbox.dev: create a box using ssh... and ssh into it. Now web, no subs. Codex can create it's own boxes via ssh

Does that version of Codex still read sensitive data on your file system without even asking? Just curious.

https://github.com/openai/codex/issues/2847

"Our mission is to ensure that AGI benefits all of humanity. "

They have AGI now?

Just got Computer Use working and honestly it feels really, really good. This is going to enable so many high-quality cross-application workflows in non-browser applications.

They felt the pressure of posting something after Claude 4.7

Maybe they could use Codex to build a Linux app...

"Codex can now operate your computer alongside you" - I really don't want AI to "operate" my computer.

Codex is my favorite UX for anything as it edits the files and I can use the proper tooling to adjust and test stuff, so in my experience it was already able to do everything. However lately the limits seem to have got extremely tight, I keep spending out the daily limits way too quickly. The weekly limits are also often spent out early so I switch to Claude or Gemini or something.

cursor has been doing this for months, welcome to 3 months ago

Well I sure hope there's a toggle to turn those features off, because I don't want to open my entire UI surface to the potential of sandbox escape...

Couple of people in my company have vibe coded some chat interface and they’re passing skills and MCPs that give the model access to all our internal data (multiple databases) and tools (Jira, Confluence etc).

I wonder if there’s something off the shelf that does this?

The first example is tic tac toe. Why would anyone bother? None of those eash things are relevant for people who use AI. They don't care about learning, improving, exploring how things work, creating, being creative to that degree. They want to hit buttons and see the computer do things and get a dopamine rush.

> ... work with more of the tools and apps you use everyday, generate images, remember your preferences ...

Why is OpenAI obsessed with generating imgaes? Do they think "generate image" is a thing that a software engineer do on a daily basis?

Even when I was doing heavy web development, I can count the number of times I needed to generate images, and usually for prototyping only.

Is there anyone that feels that LLMs are wrong for computer use? It's like robotic, if find LLMs alone are really slow for this task

Sherlocking ramps up into IPO

Bunch of startups need to pivot today after this announcement including mine

Is it just me or is the surface area for security issues becoming massive with these tools?

it it doesn't complain about everything being malware maybe i will come back to openai from my adventures with anthropic

> Computer use is initially available on macOS,

Does anyone know of a good option that works on Wayland Linux?

OpenClaw acquisition at work.

First use case I'm putting to work is testing web apps as a user. Although it seems like this could be a token burner. Saving and mostly replaying might be nice to have.

I don't think this one did it. time to for the real release

I'm sorry to be slightly off topic but since it's ChatGPT, anyone else find it annoying to read what the bot is thinking while it thinks? For some reason I don't want to see how the sausage is being made.

Using Claude and Codex side by side now . Would love to just use one eventually

"We’re also releasing more than 90 additional plugins"

but there is no link, why would you not make this a link.

boggles my mind that companies make such little use of hypertext

Tool for everything does nothing really good.

My monthly subscription for Claude is up in a week, is there any compelling reason to switch to Codex (for coding/bug fixing of low/medium difficulty apps)? Or is it pretty much a wash at this point?

>> for the more than 3 million developers who use it every week

It is instructive that they decided to go with weekly active users as a metric, rather than daily active users.

Side note: I really wish there was an expectation that TUI apps implemented accessibility APIs.

Sure we can read the characters in the screen. But accessibility information is structured usually. TUI apps are going to be far less interesting & capable without accessibility built-in.

I can't help but see some things as a solution in search of a problem every time I see these examples illustrating toy projects. Cloud Tic Tac Toe? Seriously?

I'm sure it's been said before, but more and more our development work is encroaching on personal compute space. Even for personal projects. A reminder to me to air gap those to spaces with separate hardware [:cringe:]

Is it OpenAI Cowork?

Am I the only one who sees screen recordings of AI agents as archaic as filming airplane instruments to take measurements?

[dead]

Only on macOS though? This doesn't seem to work on Linux. Neither does Claude Cowork, not officially.

What does "major update to codex" mean? New model? Or just new desktop app? The announcement is vague.

I wish Codex App was open source. I like it, but there are always a bunch of little paper cuts that, if you were using codex cli, you could have easily diagnosed and filed an issue. Now, the issues in the codex repo is slowly becoming claude codish – ie a drawer for people's feelings with nothing concrete to point to.

Man this progress is fast.

Its clear that it will go in this type of direction but Anthropic announced managed agents just a week ago and this again with all the biuld in connections and tools will help so many non computer people to do a lot more faster and better.

I'm waiting for the open source ai ecosystem to catch up :/