Rezon
319 posts

Rezon
@misterallhands
Building MyQuitPal .. more coming soon
Russia Katılım Nisan 2023
21 Takip Edilen159 Takipçiler

🚨 GPT-6 Leak
-GPT-5.6 will be the final model in the GPT-5 series
-GPT-6 is reportedly targeting an August launch
-Built on a completely new, much larger pretraining foundation
-Expected to be a major leap over the entire GPT-5.x family
-GPT 6 Designed specifically to compete with Anthropic's upcoming Mythos models
Do you think GPT-6 will beat Anthropic's Mythos?

English

I love Codex but I am thinking to move away to Kimi K3 or Grok 4.5 due to limit issues.
Codex is incredible to work with but they drain out so quickly and baby sitting model between Luna, Terra and Sol is painful.
Looks like the reset era is over, and Codex team will do it at their own convenience.
My Codex barely lasts for 2 days on Sol 5.6 medium.
How has been your experience?
English

@thsottiaux Let’s be honest : is that because of Opus 5? Everytime a new model comes out, resets happen more often.
English

We have reset usage limits for all Codex and ChatGPT Work users.
Last night around 2am to 4am we suffered an almost global outage. All well and recovered, but you know what comes next.
We learn. We reset. Enjoy.
bluedev@blueemi99
Hey does this mean a reset?? A banked one too maybe?
English

@thsottiaux @Ananth7e Perhaps before you do Tibo u gotta put an automation for codex to keep pushing that button every 3-4 days while u be vacationing
English

Do ya’ll now believe in team codex ? I bet people would shit their pants (people: aka Claude users) if OpenAI and Tibo @thsottiaux made 200$ cheaper for one month for people to genuinely get the absolutely most out of gpt 5,6 sol. It’s truly , truly insane how capable this model actually is. Very underrated.
I turned off autistic mode and it started behaving better than before.
English

Anthropic better drop something fire soon, because these Codex and ChatGPT resets are getting on my nerves tf
Tibo@thsottiaux
Another reset for our Codex and ChatGPT Work users. Actually hit 9M active users way earlier today, but then got distracted by the approximately millions of things the team is doing to keep the systems up and reliable. Should have that sweet 100% weekly usage limit back in a few minutes. Go be your productive self and close twitter. Shoo!
English

@thsottiaux @iamsaranhere Tibo, can you reset Anthropic limits too please ?🙏🏻
English

@rezoundous 200$ plan is infinitely infinite. No worries about reaching your limit or when the next reset will come. Running goals for days, weeks, I’m not gonna say month cuz that will be bulshit but… it worth it if you someone insanely into coding like me.
English

@rispectrum @thsottiaux Try codex pro 20x
Its infinite. Especially while 5 hour usage is removed
English

@thsottiaux I'd like to upgrade to Codex. I'm currently on the Claude 20x plan, but it just isn't meeting my needs and it not enough. I've tried using the Codex API instead, but it consumes my usage limits too quickly
English

@thsottiaux It’s better if you just give us resets so we can use it ourselves when needed. And on top of that remove the expiration time for resets :)
English

Or… what if we gave you $100 in Codex credits if you tell us what you love about GPT-5.6 Sol or why you switched?
Tweet it, claim your gift, enjoy more usage. First 10k get the free tokens!
switch-to-codex.openai.chatgpt.site
aman@amankumarhq
codex should give one month free when you send them your claude cancelation screenshot
English

@BenjaminBadejo I asked Fable 5 to fix my codex Agent.md and it found tons of flaws. Surprisingly after some edits , Sol became extremely good. It even started to have some taste in designing.
English

I believe there is an active, organized effort by certain X users to make false claims about GPT-5.6 autonomously going rogue and making destructive mistakes (deleting files, canceling services, etc.). Why do I believe that these claims are false?
Well, the X users making these allegations claim that some harmful outcome happened autonomously while using GPT-5.6. But they refuse to share any evidence. They refuse to share their complete prompt, conversation history / transcript, config.toml, personalization settings, or, if they have one, their AGENTS.md file.
Without this information, it is reasonable to infer that the allegation being made at a minimum is not the whole story, and may even be an outright lie.
They have to tell the whole story.
They have to tell the truth.

English










