Vurijano Pinas

@OmedVibeCodes I use both so like to see that really

I ll try hermes and pi next

This completely changes how I look at AI benchmarks. Qwen 3.8 Max Preview felt nearly unusable in OpenCode and Qwen Code. With the Claude Code harness, it suddenly came surprisingly close to Kimi K3 and Fable 5. Same model. Same task. Different harness. Wildly different result. How is this even possible?

@Da7_Tech Yeah I feel like the resets masked that problem and now we are seeing it real life. @thsottiaux the 10 mil will not hold. You need to fix the token rate. If need to wait 6 days. Yeah om going to kimi3

Ignoring the constant resets, is Codex actually a generous subscription right now? With Sol heavy token usage, does the plan still feel like good value on its own?

@LeQuickest @Danelerc Your whole name says you need a life. Asap

@Danelerc And the Cult think Hamilton is nailed on this weekend, I can't wait to see the tears when Leclerc obliterates him again.

Pole in the 4th fastest car beating Mclaren rocketships by 0.02s & 0.04s when his teammate couldn’t even make it into Q3 Enjoy this generational lap

@gdb Done

Was very cool to hear about the reasons people love Sol. We're doing the promotion again, except this time for ChatGPT Work: Tweet what you love about ChatGPT Work, claim $100 in free credits, get more work done. First 10k get the free tokens: share-chatgpt-work.openai.chatgpt.site

@justine_chang39 @thsottiaux How if I don't have tokens and another more people with me!

i feel like something special might happen for 10 mil Codex users yes? @thsottiaux

@rezoundous if been using spark run out within days.

Just used my 2nd banked codex reset. I'm running low on resets, guys.

@Danelerc You only get overtake when your close that close. Lewis was first fighting piastri and after that went after Charles so don't lie of get it twisted.

Hamilton seemed faster only bc he had the overtake while Leclerc didn’t btw

@GazzettaFerrari @fiagirly We need to start calling out these racist. #BcImBlack

❤️ Charles Leclerc: “I believed in the win until the end. We had a little bit of luck, obviously, with the VSC at the right time for us, but the pace was relatively strong.” “There were some five or six laps on the hard tyres where I was struggling with the front axle, and then it came back a little bit. I felt better with the car. So there’s some work to do, but surely it’s a step forward.”

@GazzettaFerrari @karunchandhok Your a fck sellout!! Wereld was Lewis neede to go. You don't know that we see!!. We see you!! @fiagirly

@xikhar @thsottiaux You'r just waisting tokens. That why give it to the people who really need it. Its like seeing homeboys with 30k mac and spark setup but then turn around and asked me if i have any good idea! Where empty within a week. I need to wait 6x days damnn. @thsottiaux

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

@thsottiaux I'm building a Saas with already beta users. I need those banked resets to be able to complete more. You guys have helped me gain so much time. I could finish weeks of work thanks to you @thsottiaux

What are you building this weekend?

@FerrariF1FRA Fred you have 2 drivers i see you but is okay. do your thing.

🔴 Ferrari : les déclarations de Frédéric Vasseur après les qualifications du Grand Prix de Spa-Francorchamps. - « Il est difficile de dire si Charles a perdu une ou deux places. Les écarts étaient vraiment minimes : Norris est devant de justesse et Russell le devance de quelques millièmes. Je ne sais pas exactement ce qui s'est passé, mais il est certain que Charles a dû lever le pied, ce qui lui a coûté au moins une place par rapport à Russell ». - « Nous devons nous concentrer sur la performance pure et je pense que nous avons réussi à regagner du terrain au cours du week-end. Nous avons fait un bon pas en avant après la FP3, en retrouvant la compétitivité nécessaire en qualifications, et c'était un aspect très important. La course sera longue et nous savons que nous avons souvent été plus compétitifs le dimanche qu’en qualifications ». - « Hier encore, la simulation de course s’est avérée assez représentative, notamment parce qu’il existait plusieurs possibilités en matière de gestion de l’énergie. D’un point de vue stratégique, nous assisterons à un beau duel entre toutes les écuries pour déterminer où utiliser au mieux l’énergie, tant en phase défensive qu’en phase offensive ». - « C’est aussi une question liée à la manière dont la puissance est utilisée. La distribution de l’énergie est également fondamentale pour préparer l’entrée en virage, et on voit clairement que Mercedes travaille de manière très différente de McLaren, Alpine ou Williams ». - "Drapeau jaune ? Honnêtement, nous n’en avons pas discuté avec la FIA, mais cela dépend beaucoup de la position du commissaire. Aujourd’hui, le commissaire était posté avant le dernier virage. Comme il s’agit d’un virage très lent, il se trouve pratiquement dans le champ de vision du pilote. Sur d’autres circuits, en revanche, le commissaire est beaucoup plus éloigné de la piste. Pour Charles, la situation a été assez pénible, car la présence du commissaire a également limité son champ de vision au moment même où il abordait le dernier virage ». (autoracer.it/vasseur-recupe…)

@FerrariF1FRA @SkySportF1 Yeah fred being fres always charles this charles that.

🔴 Fred Vasseur (Ferrari) à @SkySportF1 : « Leclerc a levé le pied, je ne sais pas ce qui s’est passé dans le dernier virage, il a perdu au moins une place par rapport à Russell. Mais Norris va être pénalisé et nous allons donc tout de même regagner une place. Les écarts sont minimes, la course sera longue, et ce week-end encore, nous progressons séance après séance ». (formulapassion.it/f1/f1-news/ban…)

@OpenAI @thsottiaux Models seems to become more dumb down. I lost a lot of tokens doing the same shit over and over again. before all those millions of uses a had no problem. Don't lose it. I'm getting pissed of the models seems stupid now.

@thsottiaux We need ghe banken reset. I'm on beast mode right now

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!

@thsottiaux Yo, tibo. You've mad us addictive to the reset. Now we have a major problem, i'm working in beast mode with OAI is handing out the reset and now i'm back on to normal cause resets are running out. You have made us a junk and now we need some crack-tokens..😂😂😂

@thsottiaux So I like you guys but I need some answers so all my resets are you giving me my weeks in advance? When I use a reset, I see the next reset shift very far.

Just call Sol

@thsottiaux Men I'm not a bot even if Elon think so. But what your doing also with the reset available in codex. Men I glad is support you guys. I was gone to opus one time but yeah, everyone cheats sometimes. Be faithful to us and let is build with the best tools.

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

@robinebers Saying I never build that app and he has not got any app in his memory.. they where ready to steal and I was ready to defend my fucking idea.

i know this sounds crazy because GPT 5.6 Sol is a great model but if i had to choose between 5.6 Sol and Opus 4.8 i’d still pick Opus hear me out on this i promise this is not bait claude models remain the best at writing, design, and “jack-of-all-trades” intelligence. they’re still the best at everyday tasks and obviously OpenAI knows this GPT 6 is now rumored to be rushed to the finish line to better compete with Anthropic for probably that exact reason if all models would disappear overnight and all i had was Sol, i’d be extremely happy. but the model isn’t quite the jump that Fable was, and it still lacks behind across the board explicit examples include model behaviors too GPT 5.x series models have this weird habit of digging themselves into a hole that is very hard to convince them to get out of the only model doing this even more is Grok Opus and Fable feel more natural, more agreeable, more eager to understand YOU and think about different angles and despite having a $200 Codex sub, i still spend my time running down Fable in Claude, and switching to Opus for less important tasks instead of using GPT 5.6 it’s been a few days now and i’ve tested them A LOT i’ll obviously continue to test and use them, and i’m impressed what OpenAI was able to squeeze out of the old model base but it’s time to move on