Some of you have been asking very politely. Some of you have just been asking.
GPT-6.2 Astra and Sol are now available.
Super efficient and built to perform where it counts—the real world.
https://t.co/qr2iP0GpfX
Theo deleted the reply where he called me a "stupid bitch". He also deleted the one where he tagged three ppl who follow me so they unfollow. Then he blocked me. 425k followers, YC founder, and thats how he handles one post about his employee. I saved both
To put this into perspective, I've been a subscriber since February 1, 2023. End of an era for me but until there is a drastic change I will not be coming back.
Not going to miss chasing resets while paying $200 a month.
#itsJoever ✌️
Things will change again and again and again. We’re still very early and agents today are incredible, and yet so frustrating still. Can’t wait to crack things to get that flow state back. Long journey ahead.
We’re on day 26 of the Codex improvement push. Yesterday, our $200 plan got to keep the usage it already had. So far today, there’s been no announcement.
Quite the home stretch.
Day 25/
We are doubling all usage limits for all Pro 100/200/500 tiers and Business Premium, effective today.
We heard your kind feedback and won’t be reducing usage limits for Pro 200, so your Work and Codex usage will stay the same. We’re also going to continue offering extended limits for dots for now, and usage of your dot will still continue to be separate from your default usage.
And we'll of course also keep shipping better models and other efficiency improvements that increase your effective usage over time.
How are you all handling Codex memories across projects?
I can see the benefit of not repeating the same context, but I’m curious how Codex handles memories that might only apply to one project.
Do you leave them on, or rely on AGENTS.md in each project?
@rockyshi_93 That makes sense. Keeping project context in the repo means it gets reviewed alongside the code and stays useful to the whole team. Assumptions from one project carrying into another are exactly what I’m trying to avoid.
OpenAI promised an improvement or a reset every day for 28 days.
Day 25 for $200 Pro subscribers: no improvement, no reset. Just OpenAI deciding we can keep what we already paid for.
Over the next 28 days, each day we’ll either ship one thing that is a clear improvement and relevant for most codex/work users or ship a full reset. Let the improvements begin.