@OpenAI Finally! Thank you. Hopefully it’s not as buggy and feature incomplete as Claude’s.
English
Daniel Laberge
1K posts
Daniel Laberge
@LabergeDev
Proud father of a little girl. Technology Enthusiast; Chief Software Architect at https://t.co/YG06mBZSJo
Canada Katılım Ağustos 2009
357 Takip Edilen91 Takipçiler
The master becomes the mentee. At last, Claude is now copying Codex.
But you cannot out-accelerate GPT-5.5.
Daniel San@dani_avila7
Claude Code 2.1.139 added /goal You set a completion condition and Claude keeps working across turns until it's met Works in interactive, -p, and Remote Control 👏
English
@exec_sum This will get stolen immediately if it’s installed outside.
English
BREAKING: Nvidia and PulteGroup are partnering with startup Span to install mini data centers on the walls of new homes
Each unit packs 16 Nvidia Blackwell GPUs, 4 AMD EPYC CPUs, and 3TB of RAM - and taps unused home electrical capacity to run AI inference workloads
English
@thsottiaux That’s awesome. Is it also better at front end design?
English
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.
OpenAI Developers@OpenAIDevs
With GPT-5.5, Codex now gets more of the job done across the browser, files, docs, and your computer. We've expanded browser use so Codex can interact with web apps, and test flows, click through pages, capture screenshots, and iterate on what it sees until it completes the task.
English
@thsottiaux @nickbaumann_ I will drop my Anthropic sub when Codex is as good or better at design than Opus is. Until then, need both.
English
I don't know what they are doing over there, but Codex will continue to be available both in the FREE and PLUS ($20) plans. We have the compute and efficient models to support it. For important changes, we will engage with the community well ahead of making them.
Transparency and trust are two principles we will not break, even if it means momentarily earning less. A reminder that you vote with your subscription for the values you want to see in this world.
Amol Avasare@TheAmolAvasare
For clarity, we're running a small test on ~2% of new prosumer signups. Existing Pro and Max subscribers aren't affected.
English
@thsottiaux Copy pasting to/from the embedded terminal in Codex is SO PAINFUL! 1: the normal shortcuts don’t work, 2: selecting text doesn’t automatically copy it, 3: copying from agent responses and pasting in console often includes garbled control characters.
English
codex for proactively suggesting what it can do for you:
Anthony Kroeger@kr0der
every couple of hours i just get mind blown by the Codex app, it's actually insane i opened a new chat and noticed that there was a list of suggested tasks this might sound normal, but i hovered one and it was suggested based off some bug reports in Slack threads that it read through the Codex <> Slack plugin all this time AI has mostly been reactive to what you prompt or dependent on the automations you set up, but this feels like one of the first real proactive uses of AI
English
We are barely getting started with Codex.
Good engineering and clear product thinking has never been more important and I’m proud of the team for deeply thinking about the primitives that will stand the test of time. Things will continue to accelerate from here.
English
@thsottiaux Copy pasting to/from the embedded terminal in Codex is SO PAINFUL! 1: the normal shortcuts don’t work, 2: selecting text doesn’t automatically copy it, 3: copying from agent responses and pasting in console often includes garbled control characters.
English
@felixrieseberg Copy pasting to/from the embedded terminal is SO PAINFUL! 1: the normal shortcuts don’t work, 2: selecting text doesn’t automatically copy it, 3: copying from Claude responses and pasting in console often includes garbled control characters. @thsottiaux CODEX has the same bugs.
English
Today is a big day! We're launching a ~ new ~ version of Claude Code in the desktop app. It's been redesigned from the ground up for parallel work and is a lot faster.
It's been my main way to use Claude Code for the last few weeks.
English
@thsottiaux Spot pricing during off peak might be a good enough incentive to move some workloads there. Increasing cost during peak is awful for people that HAVE to work during peak hours.
English
With Codex the there is quite the gulf in load between peak and off-peak times, and we would like to achieve more of a smoother traffic pattern as that would be a more optimal use of our compute.
We have ideas, but curious what you all think we should do? Would more usage during off-peak and surge multiplier during peak times make sense?
English
Matt Maher tested frontier models in Cursor v. other harnesses. Cursor boosted model performance by 11% on average:
Gemini: 52% → 57%
GPT-5.4: 82% → 88%
Opus: 77% → 93%
His benchmark measures how well models implement a 100-feature PRD. @cursor_ai consistently outperformed.
English
@edwinarbus @logonx2421 @cursor_ai Same boat here. I’d love for my dev team to give a try to cursor but we can’t afford to pay per token.
English
Daniel Laberge retweetledi
I built a new plugin! You can now trigger Codex from Claude Code!
Use the Codex plugin for Claude Code to delegate tasks to Codex or have Codex review your changes using your ChatGPT subscription.
Start by installing the plugin:
github.com/openai/codex-p…
English
Daniel Laberge retweetledi
I wanted to share a bunch of my favorite hidden and under-utilized features in Claude Code. I'll focus on the ones I use the most.
Here goes.
English
@thsottiaux Codex app for Linux-- any chance this launches soon? @embirico
English