Filter
Exclude
Time range
-
Near
K4V 0n6 retweeted
codex blender is insane
26
94
1,336
86,890
Let's see how good of a JVM Codex can implement in Zig purely via /goal. I've got a ChatGPT Pro sub and a dream.
うまる retweeted
Replying to @SourabhGurwani
if name == "sourabh.gurwani": return False And every time a user registers, you start a Codex automation job to add a new if clause (very quickly). If you want to optimize you can use GPT-5.3-Spark, which is faster. If you want to optimize further, ask Codex how to implement an index.
18
6
301
9,493
Replying to @thsottiaux
When will codex automations run in the cloud when laptop is off? I have been using old o3 agent to run daily for medical literature search summaries.. but that's 1 year old tech. I guess I should either run tasks via thinking model on chatgpt or via codex on laptop, which can also use browser for better access?
1
Replying to @mark_k
My experience with GPT 5.5 codex is actually quite the opposite of this, its quite good at visual understanding
ᛗᚨᚷᛁ ᛞᚨᚾᚷᚱ 「ᚦᚨᚢ᛫ᚺᚨᚾ᛫they᛫he᛫ᛚ᛫⁂」 retweeted
Codex Blenderのクリエイティブ例で、数少ない素晴らしいコンテンツです。#b3d 机の上に散らばった数百個のビーズをカメラで認識し、AIがBlenderのPythonスクリプトを自動生成。現実空間の配置をそのまま3Dシーンへ再構築している。
el.cine

1
45
3,614
Replying to @VincentLogic
有很多方法可以換 Codex 的模型,Ollama 甚至可以一鍵 launch Codex 換成不同的模型和复原,而且挺稳定
Replying to @thsottiaux
Why you are not releasing codex app for Linux users? Do openAI treats Linux users as a sub customer?
Codex GitHub repo has only a few open issues labeled macOS, but hundreds for Windows. Windows has the extra challenge of supporting both native Windows and WSL workflows, and that complexity shows up in the issue tracker. I think it’s time for me to pause on WSL mode in Codex Desktop and go back to running Codex CLI directly inside WSL until things stabilize.
1
Replying to @thsottiaux
Latest codex desktop version is really slow ( first time I see a Mac OS Spinner while using codex multiple time ). Not clue why, but I'm using the terminal model in the meantime ☹️
2
Replying to @thsottiaux
Hi Tibo i'm ghostpen, and i just discovered a sever bottleneck in the codex workflow: it can't write my exams for me and that rather seems a little odd, especially in relation to the capabilities of these models. /goal update university system to 2026, make no mistakes.
3
AM9:21🥦 retweeted
Replying to @YuYoshimuta
2 in the Codex app, a couple hundred on a devbox (experimenting on something)
1
1
10
734
AM9:21🥦 retweeted
Hi, I'm Tibo and I just discovered Codex. AMA
189
7
265
9,981
Developers, you have $20. Which one are you buying n why? – Claude – Codex
2
I am just finishing things up and cleaning up a build and plan mode for when window launches and digging into it until it is perfect. I am going to dig into this for a while as I test it. I have so many codex-spark tokens, as they are diff limits than gpt that I use, so I am trying to get them ripping constantly. I am moving to this coding tool probably today if all goes well and the kanban loop systems will rip on my gpt-codex-spark tokens until limits constantly as I am not using them with my expensive plan. Most R&D has been on how everyone handles build and plan states. The kanban system also throw up a system where you can trigger a TDD state so it tests again written tests. You can subtask kanban cards also for this yet TUI is just one at a time for now. The GUI plugs in with more exotic abilities and so will the mobile app. I needed this for my company to keep moving while doing other things as I have so many extra codex-spark tokens. This will evolve and enable permutations. I will link the baby ref zoo idea below. It is getting way more complex and I am throwing up a backend website for it rn. It will help my humanoid also in many ways so a win win as it is built for hyper-accelerating delegations so I can use my time on budling actuators and humanoids as I do have to work my assembly line and all is custom with wiring/topologies/etc. CAN lines both star and daisy. Actuators all custom with custom drivers. I use gpt 5.5 xhigh for this tool atm and it is in rust. I shared at it can do below as it has new features i have not seen others do. The context zoo def hits having a few diff reference styles.
8
Replying to @thsottiaux
Codex team size?
2
Montgomery retweeted
I wanted to use Codex App without worrying about API bills. So I built Navo. It lets Codex run through OpenCode Go’s free models No config.toml edits. No browser-exposed keys. No provider setup headache. Pick a model. Use Codex normally.
3
10
381
Replying to @thsottiaux
Codex asked me to re-authenticate today and sent a verification code to my old phone number, which is no longer active. I can still access my account via email and use ChatGPT, but I’m locked out of Codex. Is there a way to update my phone number or recover access?
5
anarcher retweeted
18h
Interviewer: What tech stack are you using? Me: Backend is Codex Frontend is Claude Code Interviewer:
35
32
1,549
32,519