Mark Stuart (@markstuartdev) header
Mark Stuart (@markstuartdev) profile picture

eng @openai; APIs, SDKs, and Dev Experience. prev Rocket, @ebay, @paypal ٩(̾●̮̮̃̾•̃̾)۶

United States
Joined November 2008
Photo by Mark Stuart (@markstuartdev)Photo by Mark Stuart (@markstuartdev)Photo by Mark Stuart (@markstuartdev)Photo by Mark Stuart (@markstuartdev)Photo by Mark Stuart (@markstuartdev)Photo by Mark Stuart (@markstuartdev)Photo by Mark Stuart (@markstuartdev)Photo by Mark Stuart (@markstuartdev)Photo by Mark Stuart (@markstuartdev)Photo by Mark Stuart (@markstuartdev)
Mark Stuart retweeted
software factories feel like a temporary problem. the models will learn to build them for you the more interesting question to me is how to build a workspace where agents can collaborate with you
577
334
182
7,471
538,844
Mark Stuart retweeted
Labs innovating together ftw
Replying to @claudeai
Also new: with interactive connectors, you can now open the full version of a tool inside Claude. Work in Adobe, Atlassian, and Box beside your conversation. Make changes yourself, or ask Claude to make them with you. Rolling out on web and desktop.
509
162
104
6,012
1,320,524
Mark Stuart retweeted
Today is the day! Start building your own homebrew games inspired by the classics of the Game Boy Color for ModRetro Chromatic devices. Watch the video and read the article to learn how it works - very grateful too for @covacut 's brief (but painful) cameo 🙏
17
15
2
131
13,513
Mark Stuart retweeted
Friends don't let friends use slop WebSocket client code in their apps. Check out the new official WebSocket helpers in the @OpenAIDevs SDKs - Responses, GPT-Live, and Realtime APIs all supported, efficient, and properly typed. Also major latency wins on tool calls 🧵
2
4
15
906
Mark Stuart retweeted
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.
392
546
414
6,797
1,882,092
Mark Stuart retweeted
Power your browser agents with Stagehand v4 in OpenAI's official SDKs: docs.stagehand.dev/v4/integr…
Browser and computer use got waaaay easier in the latest @OpenAIDevs Python and Node.js SDKs 🧵
6
4
19
977
Mark Stuart retweeted
Use @OpenAI's computer-use and browser-use helpers with E2B to give your agent a private desktop in the cloud that you can watch live while the model clicks and types. Use it to help you complete tedious tasks in an application or test user flows: docs.e2b.dev/agents/openai-c…
Browser and computer use got waaaay easier in the latest @OpenAIDevs Python and Node.js SDKs 🧵
8
5
35
2,339
Browser and computer use got waaaay easier in the latest @OpenAIDevs Python and Node.js SDKs 🧵
10
17
7
89
24,352
Mark Stuart retweeted
Let your app choose the right model, tool, or action in near real-time with Decisions API, now available to all developers in public beta. The Decisions API makes decisions up to 10x faster than GPT-6 Luna through the Responses API.
318
465
417
5,109
2,096,926
Mark Stuart retweeted
super excited to announce plugin extensions today 🎉 you can now use the exact same platform we use to build ChatGPT features like meetings, health, finance, and many others 🤯 all based on the same MCP & MCP Apps you’re already used to: github.com/openai/mcp-extens…
68
123
35
1,796
233,554
Mark Stuart retweeted
Please welcome GPT-6 Sol and GPT-6 Luna to the GPT-6 universe. GPT-6 Sol and Luna build on the advances behind GPT-6 Astra, bringing much of its strengths into faster and more affordable models to support work at scale. We’ve also made caching and inference more efficient, and we’re passing the savings directly to you: 50% lower API prices for Sol and Luna compared with GPT‑5.6 promotional pricing.
2,211
5,230
3,052
53,074
10,232,770
GPT-6 Sol and Luna just landed in Astra’s orbit. Both launch today with API prices 50% lower than GPT-5.6. Build with Sol. Scale with Luna. To production and beyond.
278
739
368
9,595
987,704
Mark Stuart retweeted
GPT-6 Astra is the best-performing model on FrontierSWE Astra achieves a score of 65.5%, outperforming Fable 5.1 (56.3%) and its predecessor GPT-5.6 Sol (32.2%)
16
25
8
388
87,756
Mark Stuart retweeted
Singularity
Replying to @OpenAI
GPT-6 Astra is state-of-the-art on FrontierMath Tier 4, ARC-AGI 3, and TerminalBench-4.0. GPT‑6 Astra is also a major advance for scientific discovery, with state-of-the-art performance on Terminal-Bench Science 0.1 and HealthBench Pro.
95
137
24
3,763
321,239
Mark Stuart retweeted
GPT-6 Astra is here. We hope it will begin to enable a new generation of entrepreneurship, scientific discovery, and building. We believe it is the best model in the world for computer use, professional work, science, coding, cybersecurity, and more. It took us some extra time to ensure that we could meet the safety and alignment standards required for this capability level, but we think you’ll find it worth the wait. It scores 98% on FrontierMath Tier 4, 99.9% on ARC-AGI 3, and 100% on ExploitBench.
2,247
4,345
1,198
55,093
4,833,916
Mark Stuart retweeted
Everyone is waking up to the fact that code-review is the bottleneck of 2026 I'm bullish on ramping review agents - but the vibes coming from - 0github.com - asi.review - pierre.co start to hit closer to home on where we need to go
1
4
23
5,823
Mark Stuart retweeted
Trying to visualize that Server-Side Rendering (SSR) isn't just about SEO, it actually makes the site faster. And why PPR is the goat. Main cost = 🟥 JS load & Hydration 🟡⇆🔵 Region Latency
11
27
6
313
42,112
I love node.js so much, overnight it multiplied my earning power, made me full stack where it counts, introduced to me to life long friends and collaborators, literally took me across the world many many times, and now I’m building a company on top of it. Unbelievable software.
4
15
3
285
26,919
Mark Stuart retweeted
Introducing the fastest way to build a Marko app! @marko/run offers zero configuration, live-reloading, directory-based routing, and great TypeScript support 🚀 Built with❤️and @vite_js. Beta release today! 👇 github.com/marko-js/run
3
31
6
147
26,475
Mark Stuart retweeted
New post: Building Reliable Distributed Systems in Node This introduces the concept of durable execution, which is used by @Stripe, @Netflix, @Coinbase, @Snapchat, and many others to solve a wide range of problems in distributed systems. temporal.io/blog/building-re…
1
23
3
170
23,187