@xikhar @thsottiaux well if it auto applies the second it expires we wouldn't even need to check, also I think they all have the same expiry time which is OpenAI server time no?
English
Nour Eddine Hamaidi
2.4K posts
It would be great if Codex limit resets also shows the time of reset in the desktop app.
And they auto-apply when they expire (if they don't already)
@thsottiaux
English
As a veteran League of Legends player, I really miss the original Summoner's Rift.
Maybe K3 can make it happen.@riotgames 🙏
x.com/young_agi/stat…
Young@Young_AGI
🆕LoL Classic mode isn't just nostalgia. Coding agents proving that many "we had to change it" , What used to be too expensive to keep alive is suddenly becoming feasible again. Which game's old version do you want coding agents to resurrect next? 🤔
English
@b_nnett Edit this post, yours happend due to Tipo not auto apply.
English
@charliermarsh is there a way to choose between sorting the sessions by creation date / last updated? now we only have the latter.
English
In the next Codex release, Command+R search gets ~100x faster, especially for large threads
English
@thsottiaux This reset was meant to render the bank one expiring today useless.
English
Oops... I did it again.
Enjoy reset usage limits for all paid users for Codex and ChatGPT Work. Super grateful for an incredible team who is iterating at lightspeed and keeping the infra up as we scale faster than ever.
Enjoy the weekend!
Tibo@thsottiaux
GPT-5.6 Sol confirmed to be an extremely good model
English
@ZourrexSlim @thsottiaux @iamsaranhere I know, blasting it fast would keep you waiting till end of 7 days, unless we get another bliss.
English
English
English
English
@PaulSolt I meant the ability to switch the icon is only available to mac
English
@EliotGevers @thsottiaux @iamsaranhere Yes, we don't know if that date is utc openai server time or our local time. At gmt+1 it's already July 18th, couldn't take the risk.
English
English
@PaulSolt been looking for that evern since ChatGPT took over, I can search for it, but now where to tweak it on windows.
English
@github Very desperate move. At least make it competitive
English
@cherry_mx_reds I have no idea what these agents are up to, and at this point I'm too afraid to ask.
English
Added to prinzbench: GPT-5.6 Sol Pro.
As previewed a few days ago, this model has saturated my benchmark, with a total score of 91/99.
For context, prinzbench contains two questions that no model tested to date has ever been able to solve (one requires extremely thorough 50-state research that probably requires /goal mode to solve, and another has a really tricky regulatory approval that no model has ever been able to find). Putting these two questions (which are worth 6 points) aside, GPT-5.6 Sol Pro provided correct responses to 91 out of 93 prinzbench questions.
prinzbench performance for OpenAI's Pro models:
GPT-5.4 Pro (Extended): 79/99
GPT-5.5 Pro (Extended): 82/99
GPT-5.6 Sol Pro: 91/99
My benchmark was released in January 2026 and was saturated in June 2026. The acceleration is real!
As a result of this model's performance, future OpenAI Pro models will no longer be tested on prinzbench (there is no point in testing them).
Benchmarking for other GPT-5.6 models to follow soon(TM).
English