NeoGrAIph

@DevAdventur3s @thsottiaux Nice 1 0

@thsottiaux Thanks 😉

Hi. Over the last 24 hours we had three separate small incidents that affected Codex reliability. Those are three too many and we are taking active steps for them to not reproduce. I have reset usage limits for Codex across all paid plans. May the tokens flow again.

@michael_waples @thsottiaux @thsottiaux I suggest creating separate exception lists for such whiners, so they can enjoy it )

@thsottiaux This is not fair. I hadn't been on for a couple of days very much and I still had 85% left. I budget about 14% a day. So again many people are worse off with a reset.

@stark4833 @OpenAIDevs Make sure to see a psychologist. You shouldn't be attached to a model like that, they're not alive, even though it seems like it. Not yet 🙄

@OpenAIDevs No one cares, that’s why your company is going downhill, pretty much every model has been slop, you may as well just give us back 4o it’s the only decent model you have. #keep4o

Look closely. There’s more in the Showcase.

@minchoi I have a Pro and I'm sad 😥

This is wild. OpenAI just dropped Codex Sites. Now anyone can give it a plan, dashboard, launch doc or idea, and turn it into an interactive app with a URL. 5 wild examples:

@interstellargw As can be seen from the structure of the new engines, these are detonation engines — hence the pulsations and efficiency. However, Bezos went further and made a detonation rocket 😅 @elonmusk I wonder, does Elon make use of the synergy from the shock waves of multiple detonation?

Starship in True 120FPS Slow-Motion. Hello shockwaves. Watch the full below.

@thsottiaux @thsottiaux How? Does `Sites` work on a pro account?

Tons of goodies for use of codex for day to day work. If you are on a business plan you can now host and share websites, we launched vastly improved plugins and skills for broad roles and you can give feedback to your agent through visual annotations in docs, slides, sheets and more.

@sama Is there a chance that you will respond to this post? Is there any chance that OpenAI will give a small amount of its company shares to those who liked this post?

@OpenAI I have a PRO plan, and I want this tool too. Why are we being left out? (((

Building apps has never been easier. With Sites, Codex can turn your work, ideas, and plans into an interactive website or app your team can explore, use, and share with a URL. Rolling out to Business and Enterprise plans, before expanding more broadly.

@thsottiaux No. People will get confused because of the similar spelling.

Should we rename Codex to ChadGPT?

@thsottiaux My congratulations! Great work by the entire OpenAI team and a well-deserved result. Bravo!

Five million users would agree. Resetting the limits tomorrow morning to celebrate. Time to go /fast

@blader My congratulations! Great work by the entire OpenAI team and a well-deserved result. Bravo!

nothing like switching to claude for a few days to try out a new model and going back to codex xhigh to remind you how much better 5.5 is right now it's really not close

@wyqtor @blader This is a task of understanding the physical world, not software algorithms, and secondly, ChatGPT seems to understand the real world better than you do, which means that you can overload two trucks a little bit because 25 extra pounds won't make a difference (26+27+27).

@blader I beg to differ

@thsottiaux I can only guess what number on the Codex panel you're referring to, but I looked at how 5.5 worked today and it reminded me of the movie "Mission Impossible." It's a great job, and it's a pleasure to witness the model's high-quality performance and the results it delivers.

I looked at a number today on a codex dashboard and it made me happy. More news about the number soon. 👀 Thanks to everyone who keeps adopting codex. We are still early. So early.

@daniel_mac8 Tell it to Microsoft and Uber 🤣

Big Token doesn’t want you to know this... Codex Computer Use can control Claude. Here Codex opens Claude, points it at my writer repo, and recreates a complex project. You will own the future if you get the best agents to work together. Codex + Claude > either one alone.

@Cizzl2 @Hp2ai I didn't even get a notification about the successful submission of the request (I'm not sure if it went through or not. Can anyone tell me what a successful submission of a form looks like? I would be very grateful.

@Hp2ai 😂提交了，虽然感觉通过的可能性不大

试试去申请6个月免费的 chatgpt pro 得高星的开源仓库， 申请挺快的，有项目的直接扔项目链接就过了 openai.com/ja-JP/form/cod… (直达链接)

@Hp2ai I didn't even get a notification about the successful submission of the request (I'm not sure if it went through or not. Can anyone tell me what a successful submission of a form looks like? I would be very grateful.

@lxstf1sh @Hp2ai I didn't even get a notification about the successful submission of the request (I'm not sure if it went through or not. Can anyone tell me what a successful submission of a form looks like? I would be very grateful.

@Hp2ai Despite actively maintaining a 4500-star repository, I haven't received any response from them. I'm not sure if I should send another request

@thsottiaux I draw conclusions based on my own experience and the opinions of people I trust. --- Please fix it: ``` Error running remote compact task: stream disconnected before completion: error sending request for url (chatgpt.com/backend-api/co…) ```

Do you still trust benchmarks or do you just listen to your friends? What makes you try a new model?

@thsottiaux I test the model myself

@jxnlco That's a great question, but do you even need to ask about such things? ) I did it in my Codex fork half a year ago ))) It's very helpful ;)

did you wish codex ask__user_question tool was available outside of plan mode