Niall McCormack

Codex @OpenAI. @titlesxyz, @BleepBleeps, @WeAreROLI, @BeatsMusic (@AppleMusic) and @RGA alumni. Views my own.

[Niall McCormack @ndmccormack]

@LizhouW53073 @thsottiaux @JustinBleuel Hey Leo, I work at @OpenAI on the Browser and Computer Use teams - can you go into more detail about the Windows Computer Use and Browser (Chrome?) plugin problems you’ve been seeing?

[Niall McCormack @ndmccormack]

Being part of the @OpenAI Windows Computer Use team has been an amazing experience - so happy to see this launch!

[OpenAI @OpenAI]

Windows users, this one’s for you.

Computer use now works on Windows, so Codex can take action on your Windows computer.

And with Windows support for Codex in the ChatGPT mobile app, you can start, review, and steer tasks on the go while work continues on your Windows machine.

An early experience, but we’re working on more ways to keep your work moving, wherever you are.

[Niall McCormack @ndmccormack]

@thsottiaux 6 months is a lifetime in AI!

[Niall McCormack @ndmccormack]

@thsottiaux I prefer to think of it as Thursday++

[Kol Tregaskes @koltregaskes]

Many developers have suspected for months that GPT-5.5 outperforms Claude Sonnet for coding. But SWE-Bench reported near-parity, and it made people question what they’d been seeing in practice.

DeepSWE aligns more closely with that day-to-day experience: GPT-5.5 scores 70% versus Claude Sonnet at 32%. That difference is substantial.

DeepSWE focuses on what tends to matter in real workflows: whether an agent can take a short behavioral prompt, locate the correct area of the codebase, and implement the change cleanly - without needing you to enumerate files, modules, and functions. SWE-Bench often fails to capture that, due to dataset contamination and weaker verification.
https://t.co/C3s80xfDkk

[DHH @dhh]

For complicated agent work, it's amazing how much GPT5.5 has improved. I found 5.2 to be very far behind Opus. Now using Opus 4.7 after 5.5 feels like a big step backwards. Gotta love this level of competion! Strong comeback for OpenAI.

[Niall McCormack @ndmccormack]

Another week, another ridiculously good launch by the @OpenAI Codex team!

Now you can control your computer from your phone - get codex to operate your computer whilst you're away from your desk, spin up tasks, grab files from your desktop, you name it, you can do it...

[OpenAI @OpenAI]

You've been asking for this one...

Now in preview: Codex in the ChatGPT mobile app.

Start new work, review outputs, steer execution, and approve next steps, all from the ChatGPT mobile app. Codex will keep running on your laptop, Mac mini, or devbox.

[dominik kundel @dkundel]

One of the coolest things with Codex for Chrome is combining it with subagents so you can test things like multiplayer games!

Available for both macOS and Windows.

Happy Codexing

[Evan Bacon 🥓 @Baconbrix]

You can now 'inspect element' for any iOS app directly in Codex or the browser!

~ / npx serve-sim

S/O @rounak for the contribution 🚀

[James Sun @JamesZmSun]

Today, we launched browser use inside Codex to further close the build & verify loop for local development!

Now, you can ask Codex to build your front end, and test it like a user would by clicking through the app.

Codex sees everything a user sees through vision & checks the network/console logs to help debug & fix any issues that it finds.

This change brings us closer to fully autonomous coding agents that delivers high quality and tested changes.

Watch Codex test my app in the browser, catch & fix a real bug, and doing that loop again with a brand new feature.

[Tibo @thsottiaux]

Stop tweeting for a hot minute and update your Codex App to find full browser use, global dictation, non-dev mode, a new auto-review mode that is much safer than yolo, in-app docs and PDF viewer, and ... GPT-5.5.

[Tibo @thsottiaux]

Codex just got a lot more powerful.

Computer use, in-app browser, image generation and editing, 90+ new plugins to connect to everything, multi-terminal, SSH into devboxes, thread automations, rich document editing. Learns from experience and proactively suggestions work. And a ton more.

[OpenAI @OpenAI]

Codex for (almost) everything.

It can now use apps on your Mac, connect to more of your tools, create images, learn from previous actions, remember how you like to work, and take on ongoing and repeatable tasks.

[Niall McCormack @ndmccormack]

@OpenAI have just released an incredible Codex release, launching on its first anniversary!

It now helps me with (almost) everything - coding and non-coding - and I honestly don’t know how I’d live without it.

Check the blog post, download and let me know what you think!

https://t.co/q35dxB1HWq

[Tibo @thsottiaux]

Feeling codexy today

[Steve Ruiz @steveruizok]

I was curious about how design apps differ in their edge / corner / rotate hit areas, so I wrote a script to move my mouse in a 50x50 grid and track what the cursor was.

[Thomas Ricouard @Dimillian]

Ohhh look at this Codex plugin, it has some nice skills 😉

[Adam Fry @adamhfry]

Another week, another ChatGPT Atlas release!

You can now sign in to multiple ChatGPT accounts (personal, work, school) with separate profiles.

We've heard from our users that this was one of the biggest blockers to using Atlas everywhere in their life.

Hit “update” in the top right to get the latest, or download at https://t.co/MlSRZjHPWB

[Niall McCormack @ndmccormack]

@sorenwrenn Super excited to see what you’ve been brewing!

[Niall McCormack @ndmccormack]

The new @openai Codex app launched yesterday! I’ve been using it for the past month, and it’s easily the most compelling agentic coding experience I’ve tried.

Running multiple agents in parallel, combined with Skills and Automations, makes it feel less like an IDE and more like a programmable collaborator. A genuinely new way to code.

Give it a whirl and let me know what you think!

https://t.co/euhXh240ct