swapp 🥭

@TrollFootball Ok you can take that parking spot, god!

Argentina reaching the semi final

@elonmusk Please reset grok 4.5 weekly, I have been using it a lot with fable 5 as the PM

Grok 4.5 even ranks slightly above Fable, which is an incredibly good model, on some software benchmarks!

@banteg Yes but now we exhaust weekly in one day and then wait for a week 😅

5 hour limit is really gone in codex. amazing, hope it stays that way. never made any sense to me.

@thsottiaux Wow thanks for listening to the community and being so pro active 😀

Morning. The last 48 hours of Codex and ChatGPT Work have been intense! Three important updates: - Temporarily removing the 5 hour usage limit restriction for all Plus, Business and Pro plans - Rolling out changes that will make GPT 5.6 Sol more efficient across the board and that will be reflected in less usage being used so that it can take you further. Exact impact to be quantified and shared - We hit 6M active users, and are landing a usage reset in the next hour Go do things

Much better design, actually I would like the models to be smart enough that we don’t need so many models and sliders in the first place!

This is annoying, I can get any work done with these limits even after 2 resets from OpenAI.

@Austen The guy was clearly acting and fake falling for no reason. Fake fouls like this deserve a straight red, not even a yellow

As soon as there's a red card the rest of the game is packing the box and trying to hold on. Miserable for everyone involved. Clearly designed for egregious fouls. Not what's happening now.

Red cards completely nuke the game. They either need to hand out far fewer of them or reduce the penalty.

@JaunJaun19 @DxBruyneSZN Yup and they will say referees are in the pockets of Messi 😅

@DxBruyneSZN people will say its rigged and then their opponents will do sum bs like this 🤣🤣🤣🤣

EMBOLO WITH THE WORST DIVE I HAVE EVER SEEN AND HAS BEEN SENT OFF 😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂 x.com/MildredDri6667…

@DxBruyneSZN All this actors need to be banned from the sport forever. What a disgrace!

@DschlopesIsBack Why is this the most popular sports again? All they do is flop and dive and give Oscar tier acting performances

Soccer is a sport that rewards you for being the smaller, weaker and softer man.

Exactly

I watch football every four years and this is all they do lol! 😂 see you in another four years!

@FOXSports Football is just players diving and acting like it’s their last fall, what a terrible unmanly sport

After a VAR review, Embolo is sent off with his second yellow for simulation 🟥

@BrickCenter_ Give this man an Oscar for his brilliant performance

Breel Embolo was CRYING after getting sent off with a red card

This looks like something Grok would write for sure

@kimmonismus The 5 hour gets consumed within an hour unfortunately even if I use Terra and Luna for most of my work

Another reset, which is unfortunately necessary as well. Unfortunately, it is becoming increasingly clear that the token burn rate is simply insane. I have never come close to hitting the 5-hour and weekly limits this quickly on the Pro tier as I have with 5.6 Sol. I mostly use High, not Fast Mode. 5.6 is undoubtedly better. The improvement is most noticeable in frontend work. That was where I immediately noticed that they had genuinely caught up. 5.6 also works better and remains agentic for longer. I am very satisfied overall. It is a significant step forward, if it were not for the rapid consumption. I also still do not understand the “super app” concept. Why should I use the “Work” environment when Codex does exactly the same thing while also displaying more information? And why do I still have the classic ChatGPT app? Perhaps I missed something, but at the moment this is once again creating more confusion. I am still hoping for resets, because otherwise this will become difficult. As for the claim that 5.6 is 54% more token-efficient, I consider that made up. It does not align with my usage at all. In fact, the opposite seems true. It feels more like 54% less token-efficient. So, 5.6 is a good update with one major caveat.

This was the right workflow until I completely exhausted the weekly grok limit

@evi77ain @theo Yeah Codex seems lacking in this front!

I wonder if this is intentional or not. It seems like Codex just wasn't quite prepared for the 5.6 release. Sol is a different beast and requires some adjustments to its harness. I'm pretty sure OpenAI will be able to squeeze much more out of the 5.6 series with further Codex updates.

If you set gpt-5.6-sol to "ultra", all the subagents it spawns will also be set to ultra. IMO this is a fumble. Causes massive token burn for no good reason. At the very least, I should be able to hard-set the subagent effort level to "medium". Claude Code is far ahead here

@theo What’s the point of sub agents if it can only spawn the same model?

Let me act for you is a foundation for a new kind of entertainment, agents creating actors, soon this actors will have their own personalities acting in their own movies!