Stephen (@siegerts) header
Stephen (@siegerts) profile picture

codex @openai. working with devs. creating. prev dx @awscloud.

Miami
Joined May 2011
Photo by Stephen (@siegerts)Photo by Stephen (@siegerts)Photo by Stephen (@siegerts)Photo by Stephen (@siegerts)Photo by Stephen (@siegerts)Photo by Stephen (@siegerts)Photo by Stephen (@siegerts)Photo by Stephen (@siegerts)Photo by Stephen (@siegerts)Photo by Stephen (@siegerts)
Stephen retweeted
🇦🇷 New Argentinian voices in ChatGPT! Meet Faro and Tonada — two great new voices that speak Argentinian Spanish in ChatGPT Voice. Available globally today.
6
1
1
30
1,507
I've been waiting for this since Sites launched. So excited about Remix!
Your teammate built a great site. Naturally, you have notes. With Remix, make your own version of a site by telling ChatGPT what you'd like to change. Then keep editing your copy in chat. Now rolling out to ChatGPT Business and Enterprise accounts.
1
2
35
2,230
Kickstart your weekend build with the new Showcase tab in the OpenAI Developers plugin. Eligible ChatGPT Pro and Business subscribers can claim API credits in billing settings to cover their app’s API usage.
119
58
41
1,017
156,005
Stephen retweeted
Your teammate built a great site. Naturally, you have notes. With Remix, make your own version of a site by telling ChatGPT what you'd like to change. Then keep editing your copy in chat. Now rolling out to ChatGPT Business and Enterprise accounts.
156
91
53
1,497
159,926
There will be signs… C O D E X
8
378
Stephen retweeted
The team is cooking and we are continuously making dots better every week! Lots of cloud browser improvements coming soon to make the auth experience smoother, computer use more reliable, and takeover more robust.
the team has been laser-focused on making dots significantly faster and more reliable. some updates in the latest app release… - you can now reply to your dot inline from a notification on iOS - share anything directly to your dot in iOS - open your dot from the iPhone Action button - faster loading when you tap in from a notification - gmail links deeplink to the exact email inside the gmail app
13
3
1
62
4,249
Today we’re announcing that OpenAI will acquire @pierrecomputer to accelerate our vision for making Codex a place where teams can build software together with AI, from first idea to the version they ship. Pierre’s open-source developer tools already power parts of Codex today. Together, we’ll build on that foundation for the agentic era. openai.com/index/openai-to-a…
276
292
190
4,631
544,697
Stephen retweeted
welcome @_catwu to the team!!
Some news: I’m joining OpenAI to lead product management for Core Products! I have a lot of respect for OpenAI for showing the world that scaling works, for bringing AI to over a billion people, and for believing great products are core to the mission. I’m excited to work with @thsottiaux, an incredible PM team, and everyone across OpenAI. Together, we’ll build agents that have your back and your team’s, and keep you in control, so you get more time for the people and work you love. Lots to learn, and lots to build. Please keep your feedback coming!
80
43
19
2,215
177,042
If you’re not user obsessed, then you’ve lost the plot.
I love this. It’s the reason I’m on Twitter. What it means to build product has changed but being user obsessed still pays dividends.
1
2
287
Stephen retweeted
Side chats in ChatGPT no longer expire or disappear when you restart the app! When I joined OpenAI, I found this to be one of the biggest pain points for side chat users, and as of today, it's fixed. Never lose data just because you updated, restarted, etc.
83
30
22
715
166,261
Learn about Pando, our new backend for our OpenAI monorepo
We built Pando, a new Git backend for our monorepo, to handle more pushes and fetches without changing how our engineers and agents use Git. Pando cut push latency by ~80% and now serves nearly a petabyte of Git data a day. We can grow Git capacity alongside agent usage.
7
13
109
25,560
Stephen retweeted
Pando is a Git backend which can scale to very large monorepos. We took the hard road of continuing to use Git, which means we could enable Pando with no change to devex. Considering providing this to others, let me know ([email protected]) if you'd be interested.
We built Pando, a new Git backend for our monorepo, to handle more pushes and fetches without changing how our engineers and agents use Git. Pando cut push latency by ~80% and now serves nearly a petabyte of Git data a day. We can grow Git capacity alongside agent usage.
210
90
24
1,717
175,039
Stephen retweeted
Fellow resetters, heads up that we're working on expanding the family of frontier models that power dots, including GPT-6 Astra and GPT-6.1 Terra and some others in the future. Terra brings speed and a nice personality upgrade, and will help us bring dots to more people.
1,875
325
428
11,378
2,222,665
Stephen retweeted
Don't sleep on the @OpenAIDevs Codex plugin. Develop AI apps and agents with OpenAI best practices. This is great for all things integration including the Agents API and Decision API. And if you're not familiar, the Agents API lets you build durable cloud agents with a managed Codex harness. This gives your app access to the Codex harness through an OpenAI-managed API.
5
1
19
1,640
Don't sleep on the @OpenAIDevs Codex plugin. Develop AI apps and agents with OpenAI best practices. This is great for all things integration including the Agents API and Decision API. And if you're not familiar, the Agents API lets you build durable cloud agents with a managed Codex harness. This gives your app access to the Codex harness through an OpenAI-managed API.
5
1
19
1,640
Stephen retweeted
Banked 1/2
1,599
234
268
10,110
1,779,457
Building with the Agents API? Here's what we shipped this week for you:
🗣️ The Agents API team has a shipping problem – we literally cannot stop. Here’s what we cooked up for you beautiful people this week: 💂 Auto Review: Just like in codex, auto-review will evaluate commands for potential bad behavior before executing. 🗜️ Async Compaction: Speed up your sessions by allowing compaction to happen in the background. 🕐 Time awareness: An experimental feature that allows the model to have a sense of time passing. This means the model will better act on queries like, ”timebox CI fixes to 10 minutes.” 🔨 Tool Updates: You can now update a session’s tools at any time. 💰 Better prompt-cache awareness: System prompts are now automatically cached across all sessions, saving you money and time
113
35
43
660
124,485
Stephen retweeted
Day 26/ You can now easily switch between multiple accounts on mobile, and coming soon to desktop too. Next two days will be resets… banked… do with this what you may 👀. help.openai.com/en/articles/…
2,622
650
958
14,481
3,432,150