Thomas Ricouard

I'm joining @OpenAI at the end of the month, and I can't wait to get started! I'll be working on everything related to Codex, bringing what I learned building Codex Monitor, and working with the developer experience team with @romainhuet!

@manabiSRS Yes will get much faster for long thread in the next update

@Dimillian Nice read Can you please make the iOS app fast? It's so slow (iPhone 14 Pro Max) that on long threads, I must wait 10 seconds between key presses when typing. And that's immediately after force quitting and reopening, too. Long ChatGPT threads are similarly slow. Codex Mac too.

@krzyzanowskim sir, this is all useful state of the arts tokens.

@Dimillian dude, you get paid to inflate the sats 😆🎤🫳

I crossed 50 billion! Also still didn't break the streak for now.

@ggg78g89 same tbh

@Dimillian My aim in life is to Join Openai to get unlimited codex tokens.

I can't wait for the EU to read the AI news in September!

@krzyzanowskim I’m talking about over engineered good code tho

@Dimillian it was NEVER problem to output bad code.

Outputting code is not a problem anymore at all. Most of my time is now spent on getting simpler and dumber code. It's crazy to think about that.

@GergelyOrosz @antirez @matteocollina I’m very French don’t bother me 😂😂

@antirez @matteocollina My own impression is they are Very French with a Don’t Bother Us type of energy unless you’re a Traditional Company who is happy to go thru layers of buerocracy Either that or they truly don’t want to talk to devs

Btw anybody with some Mistral insider info is understanding WTF the company is doing? They are under delivering so much that there must be a hard reason, either politics, terrible management, total lack of GPU compared to Chinese players, or what?

@cmaciasjimenez @thsottiaux No this is a compaction issue on our side. Usually this should happen automatically and you don’t have to worry about the context. If you can do us a /feedback and send me the id.

@thsottiaux @Dimillian Hey guys this is the first time I'm seeing this while using Codex. Is this expected after a long chat? what does it mean? I already had some compactions, etc so I guess it's not the original context window, right? Any tips? Thank you.

agi wen

@ben_ai_eng Yes fix for that is coming very soon

@Dimillian and idea why codex mobile cashes when opening a long running thread?

I know what I'm doing this weekend

@SIGKITTEN @apanasenko @ajambrosino @callmemabie @OpenAI 👀👀👀👀

@Dimillian @apanasenko @ajambrosino @callmemabie @OpenAI i got PR stacked 4 deep for u lol

@OpenAI @ajambrosino - adding a live activity for codex on mobile - is this on the team’s radar?

Wait til he find out about 5.5

@SIGKITTEN @apanasenko @ajambrosino @callmemabie @OpenAI I just woke up and I see more work but it seems to be cool work

@apanasenko @ajambrosino @callmemabie @OpenAI @Dimillian doing doing

This has @kagigz all over it 🫶 Such a helpful ship!

@bonitadreama Wow

@Dimillian I win 😅 This was a lighter week, which is kinda funny.

That’s a lot of dogfooding

Thursday Codex updates: - Developer Mode for Browser use with controlled CDP access - deeper debugging for network, console, runtime errors, perf, and page state - /init in the app composer - customizable macOS Dock icons - Computer Use for more Enterprise users - Windows per-app access controls - Unread chats in the command menu - Browser use up to 2x faster - rate-limit reset banking for Plus and Pro referral invites to earn more resets during the promotion - clearer summaries, plugin management, usage-limit guidance, and lots of fixes across Browser, automations, SSH, Mobile QR pairing, PRs, MFA, and more

@RonPualS also will be back soon :)

@Dimillian but I cannot manage my threads by the thread created from mobile Codex? No toolcall codex_app.*

Do you enjoy being able to make new worktree from Codex Mobile directly? Because I do it a lot!