Danil

@thsottiaux THANKS!

Some of you noticed limits drained faster in Codex, we root caused it to an optimization that we rolled back that had an impact on cache hit rates when compacting across long running sessions. We fixed this and have now reset usage limits for all accounts. Enjoy the weekend.

@nicdunz They're lowering the limits here, and you're talking about...

fast mode should be the standard mode in codex and use the standard modes limits not 1.5x

@argofowl @thsottiaux The limits have also been cut

codex with gpt 5.5 has been making some really weird/dumb mistakes the past 2 days something is off @thsottiaux, please investigate

@OpenAI Chrome codex extension

@OpenAI Computer use, memory in eu

Highlights from today’s Codex Thursday launches: 1️⃣ Codex can now securely use apps on your Mac from your phone, even when your Mac is locked and the screen is off. #locked-use" target="_blank" rel="nofollow noopener">developers.openai.com/codex/app/comp…

@ziwenxu_ @thsottiaux @sama Maybe version 5.6 is coming out soon?

One tweet saying "we're on it" would save thousands of users from thinking they broke something. @thsottiaux @sama

@nicdunz Tomorrow?

5.6

@thsottiaux x.com/laurensnys/sta…

At some point I counted one like, so I went and did the thing. Enjoy your Codex usage. We had a few things to celebrate this week 👀

@OpenAIDevs Need to update? What's the latest version? Version 26.513.31313 (2867)

We’re having way too much fun working through your feedback. (Please, keep it coming.) Keyboard shortcuts are now customizable. Set Codex up around how you actually work, then tweak shortcuts from settings instead of adapting to our defaults.

@TheRealAdamG Codex hasn't been updated since last Thursday—how awful!

I’ve been looking forward to today (Thursday) for a few weeks now.

@thsottiaux When I click on this menu item, nothing happens (Version 1.2026.119.1 (d408daf5cad))

In /side mode, after a period of inactivity, the error “Loading model” appears, Version 26.506.31421 (2620) @thsottiaux @embirico

@mark_k @OpenAI That would be very expensive, and the Pro X20 subscription just won't cut it😃

Codex by @OpenAI is reportedly getting an "Ultra-Fast" mode. Up to 5x faster agentic code generation. ⚡⚡ This could be huge. The biggest bottleneck with coding agents is not intelligence anymore, it’s waiting for the agent loop to finish. If Codex gets meaningfully faster while keeping quality high, the whole workflow starts feeling much closer to real-time pair programming.

@robinebers Is it with the x10 from the party?

Codex 200x subscription now at 46% can I burn it to the ground? I don't think so estimated to have 12% left by reset

@OpenAIDevs when in the EU, and the memory is the same?

Codex can now take on more of your browser dev work. With the new Chrome plugin in the Codex app, it can test web apps, gather context across tabs, use web DevTools efficiently in parallel, and keep results organized without taking over your browser.

@nicdunz openai?

big day tomorrow

@thsottiaux @ajambrosino Please add the terminal output to the side, not at the bottom. In Codex, thanks!

@Suraj_RH @cursor_ai Yeah, me too!

Question for the Cursor community: Is anyone else on a pre-Sept 2025 legacy plan seeing their "AUTO" model usage suddenly counting towards the $20 limit? 🤔 Bought mine in July 2025 and it was fine until last month. Did something change or is this a bug? @cursor_ai #CursorAI

@nicdunz And now it's not superapp?

superapp on thursday?

@dedene @cursor_ai Zentty I've already found it

@dedene @cursor_ai Can you tell me what this application is?

Asking @cursor_ai real questions