Romain Huet (@romainhuet) 's Twitter Profile
Romain Huet

@romainhuet

Head of Developer Experience @OpenAI. Empowering builders with o3, o4-mini, GPT-4.1, Codex, ChatGPT, and more. Previously, Product Lead @Stripe.

ID: 3946301

linkhttp://romainhuet.com calendar_today09-04-2007 21:38:32

4,4K Tweet

30,30K Followers

7,7K Following

Romain Huet (@romainhuet) 's Twitter Profile Photo

One thing I love about our latest frontier models is their ability to seamlessly call tools within their reasoning flow. Web search is now supported in the API for o3, o3-pro, and o4-mini! 🌎🔎

Fidji Simo (@fidjissimo) 's Twitter Profile Photo

So many stories like this. The future is bright. One day soon, the idea of entrusting life-altering health decisions exclusively to someone who spends maybe 30 minutes thinking about your case will feel outdated and mildly unhinged.

Romain Huet (@romainhuet) 's Twitter Profile Photo

Quick update on our open model: the team is working super hard on it, but we’ll need a bit more time before it’s ready to share. Really appreciate all the support. We can’t wait to get it in your hands! ✨

Aidan Clark (@_aidan_clark_) 's Twitter Profile Photo

Hi, We’re delaying the open weights model. Capability wise, we think the model is phenomenal — but our bar for an open source model is high and we think we need some more time to make sure we’re releasing a model we’re proud of along every axis. This one can’t be deprecated!

Jakub Pachocki (@merettm) 's Twitter Profile Photo

I am extremely excited about the potential of chain-of-thought faithfulness & interpretability. It has significantly influenced the design of our reasoning models, starting with o1-preview. As AI systems spend more compute working e.g. on long term research problems, it is

Michael Truell (@mntruell) 's Twitter Profile Photo

A conversation with Patrick Collison on old programming languages, software at industrial scale, and AI's effect on economics/biology/Patrick's daily life. 00:15 - Why Patrick wrote his first startup in Smalltalk 03:35 - LISP chatbots 06:09 - Good ideas from esoteric programming

Romain Huet (@romainhuet) 's Twitter Profile Photo

Editing with image generation just got a lot more precise! 🌠 Check out Katia Gil Guzman’s video on setting `input_fidelity` to preserve faces, logos, and fine details in the API. Use "high" to make the model work harder to match your image’s style and features.

Greg Brockman (@gdb) 's Twitter Profile Photo

When we founded OpenAI (10 years ago!!), one of our goals was to create an agent that could use a computer the same way as a human — with keyboard, mouse, and screen pixels. ChatGPT Agent is a big step towards that vision, and bringing its benefits to the world thoughtfully.

Kevin Whinnery (@kevinwhinnery) 's Twitter Profile Photo

I think this is the fastest/easiest way to both deploy and consume a remote MCP server, courtesy of OpenAI Developers and Deno with Deno Deploy. ~ 30 lines of code for a single file server ~ 18 lines of code to have an OAI model use it Tough to beat that. Some details đź§µ

I think this is the fastest/easiest way to both deploy and consume a remote MCP server, courtesy of <a href="/OpenAIDevs/">OpenAI Developers</a> and <a href="/deno_land/">Deno</a> with Deno Deploy.

~ 30 lines of code for a single file server
~ 18 lines of code to have an OAI model use it

Tough to beat that. Some details đź§µ
Romain Huet (@romainhuet) 's Twitter Profile Photo

“If we can make intelligence accessible everywhere, affordable to everyone, and easy to understand, we can drive the biggest opportunity engine the world has ever seen and help more people live better lives.” Thrilled to welcome Fidji Simo to OpenAI next month!