@mweinbach Do you guys know if the problem is on the Model or on Codex? I've been using with pi.
English
Marcelo
12 posts
Marcelo
@itsmemarcelorm
Software Engineer(15yoe)
Florida Katılım Eylül 2015
81 Takip Edilen7 Takipçiler
We are not crazy! GPT 5.5 fix incoming
Tibo@thsottiaux
We found and fixed two issues that could explain this degradation of the capability of GPT-5.5 in Codex over the last ~ 48 hours. We are monitoring over the coming hours to fully confirm and I will reset usage limits this evening. Apologies and now is the time for /fast maxxing.
English
Wild that Linux and Windows are so close in usage for T3 Code 👀
English
@itsmemarcelorm @narek_gevorgyan Yeah just discovered this, it was a bad update to marketing page 🙃
I hate intel support so much holy shit, @jullerino why did you curse us with this
English
@theo @narek_gevorgyan He is running under Rosetta, @narek_gevorgyan you should download the arm64.dmg on github releases !
English
@theo @narek_gevorgyan It's not a bug, I sent you a dm @theo , this is because the default dmg download is x64 not arm64
English
@Archetapp @martinlasek There is no comparisson, those chinese models were all benchmaxed, if you use daily as an engineer you will notice that is all crap compared to Claude Opus or Codex.
English
@martinlasek Do you have a model that you recommend that competes with Codex or Claude?
English
You can pay $200/m for Claude for eternity
Or buy a Mac Studio for $166/m and run your own model for free
Best part? You own it after 12 months at 0% interest:
> M4 Max
> 36GB Memory
> 512 GB SSD
Hmmm…
English
2. Notifications. Claude Code Desktop now pings you whenever Claude needs approval, you can keep working while Claude runs in the background
English
Just shipped two cool updates for Claude Code in the Desktop app.
1. Plan mode is now available on Desktop. Have Claude map out its approach before making any changes
English
In the video above, I used GPT-5.2 thinking on high reasoning effort.
English
I've been testing GPT-5.2 for a while now.
It's a serious leap forward in complex reasoning, math, coding, and simulations.
It built a full 3D graphics engine in a single file. Interactive controls. 4K export.
One shot.
The pace of progress is unreal.
English
You can decide how much autonomy you give to the agent in @antigravity
Drop asynchronous feedback within artifacts and the agent folds it in when the time is right.
English
@apples_jimmy Meanwhile google gave us unlimited access to 2.5 pro on release.
English
Plus users need higher o3 limits.
Tool use + search with o3 feels like magic for my use cases, coding is still 2.5 pro for me but everything else it’s o3.
English
📣 @OpenAI o3 and o4-mini are now available in GitHub Copilot!
o3 is designed for deep coding workflows and complex technical problem solving while o4-mini focuses on efficiency.
Try them out ⬇️
github.blog/changelog/2025…
English