Don't forget about the UI for AI
The Stack Overflow Podcast
October 20, 2026
Recorded at OpenAI Dev Day 2026, Ryan sits down with Andrew Ambrosino, member of the technical staff at OpenAI, for a conversation on OpenAI's strategy for merging ChatGPT and Codex into a unified experience, the advantages of localized computer access in their successful desktop application, and...
Speakers Ryan Donovan, Andrew Ambrosino
TopicsTechnologySociety & Culture
Ryan Donovan (0:09)
If solving difficult problems is what drives you, Raytheon is hiring software, systems and hardware engineers to take on some of today's most complex technical challenges. Explore opportunities at careers.rtx.com/raytheon.
Hello and welcome to the Stack Overflow Podcast, a place to talk all things software and technology. I'm your host, Ryan Donovan, and I'm here at the OpenAI Dev Day, 2026 We're going to be talking about the new unified ChatGPT work app, and also something new the announced today. So my guest for that is Andrew Ambrosino. He's a member of the technical staff here at OpenAI. So welcome to the show.
Andrew Ambrosino (0:49)
Thanks for having me.
Ryan Donovan (0:50)
Of course. So before we get into it, can we do a little flyover of how you got into software and technology?
Andrew Ambrosino (0:56)
I mean, I grew up with all sorts of the stuff as a kid. Yeah. Did a lot of early website developments when I was in high school.
Got a degree for computer science, did a lot of design, and now I'm here and I work on the desktop app, I work on Space, work on Codex, all great things.
Ryan Donovan (1:13)
Yeah. I think there was a, I don't know if I'd cry is the right word when the ChatGPT app and the Codework app merge together. I think Codex merged with that too, is that right?
Andrew Ambrosino (1:22)
Yeah.
Ryan Donovan (1:22)
What was the sort of reasoning behind that?
Andrew Ambrosino (1:25)
Where we want to go is to build one place that you can come and type in what you need, or speak what you need and have our most powerful models and HARDIS put that together for you and that's across software development, that's knowledge work, that's quick questions and answers.
And you shouldn't have to worry about how much reasoning or which mode you're in in all of this. And so that's kind of what has been in our heads as we've tried to take ChatGPT as it has existed for years with over a billion consumers. And then this Codex app that was really taking off at the start half of this year.
Ryan Donovan (2:01)
Right. And then the Codex for Work app, which was sort of Codex.
Andrew Ambrosino (2:06)
Yeah.
Ryan Donovan (2:06)
Was there something different with it?
Andrew Ambrosino (2:08)
ChatGPT Work was us bringing all of the power of the Codex Harness to a broader audience, both through the brand ChatGPT that people were very familiar with, but also through taming some of the raw nature of the coding agents. And things would just get in the way of it feeling nice to use day to day for a lot of people. So that's been ChatGPT Work. It's been wildly loved. There was a bit of a lot of thoughts about how we might merge the apps, and we're certainly not done there.
Ryan Donovan (2:37)
Yeah, because it's still two tabs right now.
Andrew Ambrosino (2:40)
Yes.
Ryan Donovan (2:40)
Something interesting I noticed, I was using it the other day, and it was like ChatGPT do this huge complex thing, is just like, you want the other tab. I was like, that's interesting to have that logic built in. I don't know if it's the logic or the model.
Andrew Ambrosino (2:52)
The invariants for us are that type in chatgpt.com, and you type in something that needs a quick answer, you need to get it right away.
Ryan Donovan (3:01)
Yeah.
Andrew Ambrosino (3:01)
On the other side of the house, if you want to build this giant thing and you need the best of Astra and the best of Codex, you need to be able to do that.
The minute we feel like it's the right time to make this continuous spectrum that can do both of those without a toggle, we are going to do that. In the meantime, we're not going to shove these things together before we can deliver on that promise. We're not going to say, everybody's got this long thinking, reasoning trail of Codex when they're trying to get a search results.
Ryan Donovan (3:31)
Yeah. The press conference, there was a hint at future model routing being built in. Did you do any of that now?
Andrew Ambrosino (3:38)
We have a history with the routers in ChatGPT. We've tried certain things multiple times, but we've got a lot of really cool things coming here. I think that's what I find myself wanting, is not to touch these things, wanting to see code when it makes sense and not when it doesn't.
Ryan Donovan (3:52)
Everything operates in the browser.
Why a desktop app? Yeah.
22 more minutes of transcript below
Thousands of transcripts fetched by people building searchable podcast archives
Fetch the whole transcript
The demo key returns a sample episode in full, no card needed:
curl -H "x-api-key: pt_demo" \
https://spoken.md/transcripts/1000651996090Markdown with the speakers named, for your notes, your knowledge base, or anything that makes HTTP calls.
From $0.10 per transcript. No subscription. Credits never expire. Prices exclude VAT, added at checkout for EU customers. Not what you expected? Email us within 14 days with 20 or fewer credits used and we refund the pack in full.
Using your own key:
curl -H "x-api-key: YOUR_KEY" \
https://spoken.md/transcripts/1000797194738