Anders Gerner

@JuanPa @JuanPa I will be happy to share more thoughts on this workflow and the reasons I don’t use the CLI more, if you like ✌️

@Anders_Gerner @Dimillian @mattpocockuk @shadcn interesting! have you used the CodeRabbit CLI to get the feedback before the agent makes a commit?

Are you a loop person or a non-loop person? Even with unlimited tokens, I've been really shy about using anything that is doing work unintentionally on my behalf. I feel like it’s just creating more work for me to review...

@thsottiaux Sun is not shining in Denmark😔

Good morning ☀️

@JuanPa @Dimillian @mattpocockuk @shadcn Yes, I do 1 run of CodeRabbit locally before PR sub. It often takes quite some time and to avoid rate limits, I only do the one CR session. Also, I sometimes see CodeRabbit be happy locally and then on the PR still have other comments, so I tend to use the PR feedback as truth

@Dimillian @mattpocockuk @shadcn Oh, sorry - proper shout out to @coderabbitai ✌️

@Dimillian I am a loop person, but I agree with you in regards to the the steering. I use the “improve codebase architecture” and “grill me with docs” skills from @mattpocockuk together with the “improve” skill from @shadcn for planning and executing. Loop: Work, PR with CodeRabbit .. ✌️

@Dimillian With FaceID ✌️

Do you lock your Codex Remote with FaceID or not?

Introducing a limited preview of GPT-5.6 Sol, our next generation frontier model, as well as GPT-5.6 Terra, a balanced model for efficient, everyday work, and GPT-5.6 Luna, a fast and affordable model for high-volume work. openai.com/index/previewi…

@Baconbrix YES🙌🏼💪🏻

Accessibility tree is shockingly slow. Going to explore how the Accessibility Inspector app works and see if I can get it to be instant and reactive in serve-sim

@Adam__Allcock Awesome!

I got tired of copy-pasting between Codex and ChatGPT to use GPT-5.5 Pro. Codex is where my coding happens. ChatGPT is where I do deeper planning, online research, and strategic planning with Pro and long context. So I built a visible bridge between them. [1/n]

@thsottiaux @steipete @thsottiaux awesome!

I have a new kind of big button that I can press for Codex. Over the next 100 days, we will select one person per day who does impressive or incredibly useful work with Codex and give them 10X usage limits for a month to see what they can do with it. First one tomorrow.

@rezoundous I think I will stay, but I would upgrade my Cursor subscription for more Composer 2.5 usage. It does feel like a lot to pay, for half the usage on Pro 😑

If you're on $100 Codex plan, will you be staying / downgrading / upgrading / canceling the plan when the 2x promo ends?

@simpsoka Computer use and Chrome extension in EU 🤩 Would be awesome to multiple sessions open at the same time without having to open multiple windows or for subagents work. Able to change reasoning after plan mode is done, so you don’t have to escape and change before implementation.

What other Codex papercuts should we fix?

@thsottiaux Yeees! Was already down to 38% yesterday and there is a long time until the 19th. Thank you!🤩

Codex usage limits have now been reset across all paid plans. Enjoy the weekend!

@steipete YES PLEASE!

All I want is codex automatically entering /review mode after it's done and just looping until it stops finding booboos. (Yah I'm gonna build that)

@rezoundous I am on 47% on pro 😅 there is a loooong time until the 12th😑 - just wishing on @thsottiaux resetting again 🤩😍 With both Symphony running and /goal in CLI, then it goes damn fast 😵

Codex Pro weekly limit at 68%. Refreshes on May 12. I am sad.

@michelleefang Oh yes please! I am using my dev time to support my wifes project, that is helping women to know their rights in regards to birth and hope to prepare them as best as possible with their partner ✌️

if you're vibe coding or building over the holidays, i want to gift one of you a 6 month subscription of claude pro to support <3 just drop a comment below. merry christmas!

@NoahEpstein_ Composer

cursor just made every $200/month copilot subscription look like a scam dropped today with their own coding model what took 8 hours of manual coding now takes 30 seconds and it runs 8 versions of itself in parallel to pick the best solution while github's charging $20/month for autocomplete, cursor built an entire autonomous dev team composer model: → 4x faster than gpt/claude → completes full features in <30 seconds → tests its own code automatically → built with reinforcement learning on real codebases here's what's actually wild: most companies paying $150k/year for junior devs to do work this does for $20/month just saved a client $253k/month migrating their dev work to cursor's multi-agent system the intelligence gap between "we hired 3 developers" and "we deployed cursor" is getting stupid comment "COMPOSER" and ill send the full breakdown of how to replace your dev costs with this

@Baconbrix Really like Posthog ✌️ @posthog

What’s the best analytics library for an Expo app?

@saulsharma @expo 😱

🚀I built Voltra, an npm package that lets you: ship custom Live Activities, Widgets, Dynamic Island + more with React. No Swift, Xcode, or extra JS runtime needed. ⚡ Hot reload ⛽ Server push ✻ AI coding agent-friendly 𝝠 @Expo + React Native ready Demo + must-read Thread⬇️

@Baconbrix @expo Thanks for sharing! 🤩🙌🏼

This is the CLAUDE md file I use for new @Expo apps.