dominik kundel retweetledi
dominik kundel
14.3K posts
dominik kundel
@dkundel
@OpenAI DevX, Codex, gpt-oss, TS Agents SDK - he/him - Opinions my own
San Francisco, CA Katılım Temmuz 2009
1.6K Takip Edilen12K Takipçiler
@GitMurf @embirico @ajambrosino Flagged it internally. How is the Codex falling back to using powershell blocking you from using the app? There are hacky workarounds in the meantime but trying to understand how it's blocking you
English
@dkundel @dkundel I have confirmed with other users that similar to me, I can roll back to 0.113 to resolve for Codex CLI but the Codex App evidently does not leverage the same rolled back version so I cannot use Codex App until this is resolved. cc @embirico @ajambrosino
English
@jxnlco Most of the TS ecosystem is increasingly written in Rust. Other than the TS compiler that's written in Go. Also Codex itself is Rust + TS 🙃
English
I think we should rank them and add an upvote/downvote button and comments. Will be my first PR.
English
@jphme @charliermarsh "As part of our developer-first philosophy, after closing OpenAI plans to support Astral’s open source products" 🫡
English
@dkundel great acquisition. but please let @charliermarsh continue to do his stuff making python awesome ✌️
English
uv is the tooling I wish Python would have always had. So excited for the team to join! Let's go 🙌
OpenAI Newsroom@OpenAINewsroom
We've reached an agreement to acquire Astral. After we close, OpenAI plans for @astral_sh to join our Codex team, with a continued focus on building great tools and advancing the shared mission of making developers more productive. openai.com/index/openai-t…
English
@jxnlco It's like the reverse mullet of technology. Party in the front(end), business in the back(end) 😂
English
English
You can provide nicknames to your subagent in Codex so I spawn @Dimillian to audit my PRs
OpenAI Developers@OpenAIDevs
Subagents are now available in Codex. You can accelerate your workflow by spinning up specialized agents to: • Keep your main context window clean • Tackle different parts of a task in parallel • Steer individual agents as work unfolds
English
dominik kundel retweetledi
You can now summon Codex from anywhere on your desktop. It's easier than ever to reach for Codex.
English
The team is absolutely incredible and has cooker with the Codex app-server!
Jessie Frazelle@jessfraz
I don’t give a lot of compliments but the way Codex cli & app is designed so it reuses code (that anyone else can reuse as well) is really quite elegant. Elegant in a way that it could only be the result of an experienced & thoughtful team. Which is rare at their speed & scale.
English
@nickbaumann_ Should I make one @ Nick that just slacks you whatever I asked Codex to do 😂
English
dominik kundel retweetledi
We just brought our community work into one place, making it easier to find events and programs like Codex Ambassadors and Codex for OSS.
There are 15+ community-led events coming up around the world, with more to come!
Where would you like to see a Codex meetup next? 🌏
English
@dkundel Can i ask the base 5.4 agent to use three or four 5.4-mini subagents
English
GPT-5.4-mini is a wildly capable model and gives you ~3.3x more usage on Codex tasks compared to GPT-5.4. It's excellent for spinning up new subagents!
OpenAI@OpenAI
GPT-5.4 mini is available today in ChatGPT, Codex, and the API. Optimized for coding, computer use, multimodal understanding, and subagents. And it’s 2x faster than GPT-5 mini. openai.com/index/introduc…
English
@danshipper This should have been fixed now and was a hiccup. Let me know if you still run into issues.
English
lol i got rate limited by codex for using too many subagents
English
here's an early look at the codex app sidebar I wanted to ship. i was silenced
English
@dkundel I am pretty much forced to use full access always, because otherwise codex can't use dotnet cli on macos.
English
💡 Codex tip: Rules
You can have Codex analyze past conversations. This comes in especially handy if you want to create rules files to have your Codex automations run inside the sandbox without using "full access".
Have Codex do the task inside the sandbox and approve requests, then have Codex analyze the past conversation to create a rules file.
English
@Parmartejas @OpenAIDevs Spark is faster but only available to Pro users and the Mini model is slightly more capable but slower
English
