Sirui Zhang

@ChrissGPT If you upgrade to the $200 plan, you still can't let it work for two hours.

This model can’t work for two hours without needing me to upgrade to the $200 plan.

@DavidOndrej1 I consumed all of my 5 hour usage quota in 1 hour, reset and then consumed all the usage quota in 1 hour again. For the second time I was not even enabling fast mode or using ultra.

surely i'm not the only one...

@ImSh4yy I consumed all of my 5 hour usage quota in 1 hour, reset and then consumed all the usage quota in 1 hour again. For the second time I was not even enabling fast mode or using ultra.

It seems like GPT 5.6 Sol is using my 5 hour codex limit much faster than GPT 5.5 despite it being more token efficient?

5.6 sol is unusable, I consumed all of my 5 hour usage quota in 1 hour, reset and then consumed all the usage quota in 1 hour again. For the second time I was not even enabling fast mode or using ultra.

@jun_song They are cooking something big

Bro disappeared like never existed

@thsottiaux not at math, though 🫪

GPT 5.6 Sol is our best model so far at ~everything. It's remarkable how stark the difference is with GPT-5.5 across coding, hard context and strategy tasks, building sites, ... and literally anything I need to get done. Totally requires raising the ambition of what you try.

@jxnlco maybe the resume is in markdown

What!?? Codex can read PDFs?

@SeeLos Not working for me😭

Tanstack has no marketing budget. They say if you say it 3 times in a row, you summon a reply from Tanner himself. Tanstack Tanstack Tanstack

Tanstack Tanstack Tanstack

I can finally talk about gpt 5.6 now. Please give access, please, I really want it.

@mattpocockuk it’s more developer-centric than those a lot vibe-centric skills

Folks who have adopted my skills at your org, I have a question for you: What was the thing that made people go "yes, let's do this"? What were its advantages over similar tools?

@DavidOndrej1 I can wait

can't wait for Grok 4.5

@patience_cave okay, you are right again

@patience_cave 🙄

it’s a terrable day to be the strawberry man. who will solace him in his lunacy? no GPT-5.6 today, tomorrow, or ever

5.6 5.6 5.6

@synthwavedd Please don’t

No, GPT-5.6 is not coming today Take a seat 💺

@VictorTaelin calm down Taelin

so fucking good, so fucking good

it is so hard not to be over enthusiastic about this model, the way it competently navigates the complexity and spots small but important issues that other models and I oversaw. I'll try to shut up and do my job now, I'm very hopeful for a next week completion. lfg

@treidius @jumperz How to disable routing to opus?

@jumperz I disabled routing to opus. Seems pretty great so far. Achieved a goal in hours Opus has been working on for days. To be fair, their usage reset gave me like 12 hours to spend a week's worth of usage so I'm going all out on everything (also in case they take it away again)

so i tested fable for straight 4 hours.. > its clearly nerfed > it keeps automatically switching me back to 4.8 > burns through quota way faster than it should > flags normal coding as if it's something dangerous > the one-shot magic is gone > the output feels like slop now > half my prompts never even reach fable, they hit Opus instead its like you're paying the fable premium for a fallback answer.. until they tune the safeguards down and fix the metering, fable in this state isn't worth building with honestly.

@patience_cave I will help you.

fable is too strong help me elder pliny, you’re my only hope

@iruletheworldmo Give me 1 grand I will set up a meeting for you two.

i’ve tried ringing dario regarding fable all day, does anyone know where he is?