Latest / programmier.bar – der Podcast für App- und Webentwicklung / Deep Dive 220 – Developer Experience at OpenAI: Romain Huet on building for agents
Transcript
- 0:06SPEAKER_00: Hello and welcome to another episode of the Procamirba Podcast.
- 0:10SPEAKER_00: I am your host, Jan Tego Engbetriebel, and with me today in the Saline studio is Dennis Becker.
- 0:17SPEAKER_00: Great to be here.
- 0:18SPEAKER_00: Hi Dennis.
- 0:19SPEAKER_00: Our regular listeners will have noticed that this episode is somewhat unusual for us.
- 0:23SPEAKER_00: It is only our third ever episode in English, and my first ever episode in English for this podcast.
- 0:31SPEAKER_00: Because today we want to talk about how the developer experience is changing with the rise of AI.
- 0:39SPEAKER_00: And maybe I don't know if rise even is the right term anymore.
- 0:42SPEAKER_00: It feels less like a rise because that kind of like has already happened and more like a we're in the dominance area already.
- 0:50SPEAKER_00: Maybe we'll see about that.
- 0:52SPEAKER_00: And while we could have this conversation in English or in German, um, it's much more fun uh to have a guest on as well.
- 0:59SPEAKER_00: And because our guest uh prefers to have this conversation in English, we're totally on board with that because uh the alternative would have been to do this in French.
- 1:06SPEAKER_00: And trust me, you don't want to hear my French.
- 1:08SPEAKER_00: Uh I I can't speak to Dennis's French, uh, but my French is like terrible.
- 1:12SPEAKER_00: It wouldn't be enough for a podcast.
- 1:14SPEAKER_00: Yeah.
- 1:15SPEAKER_00: And uh with that being said, I would like to welcome uh Romain Huyet.
- 1:19SPEAKER_00: Uh welcome to the program.
- 1:21SPEAKER_03: Thank you so much for for having me.
- 1:23SPEAKER_03: Uh guten Tag, ich heiße Romain.
- 1:25SPEAKER_03: Uh, ich freue mich sehr illustr.
- 1:28SPEAKER_03: Uh, you know, I studied German for many years, but I don't think we could carry the whole conversation in in German.
- 1:33SPEAKER_03: So thanks for doing it in English.
- 1:36SPEAKER_00: That's uh totally fine.
- 1:38SPEAKER_00: We didn't invite you here for your German skills, but rather to talk about your actual job.
- 1:42SPEAKER_00: And when we did the uh research on your like checked you out on what we could find on the internet, um you have done or you've been in developer experience for quite some time now.
- 1:53SPEAKER_00: You've been at Stripe and at Twitter.
- 1:55SPEAKER_00: Um, and maybe just as a small anecdote here, when I was doing developer relations at Shopify, Stripe was one of the like go-to companies that we would look at and see like how can you actually do developer experience on a like top-notch level.
- 2:09SPEAKER_00: So uh kind of speaks to your work here.
- 2:12SPEAKER_03: Thank you so much.
- 2:12SPEAKER_03: Yeah.
- 2:13SPEAKER_03: I mean, like I spent uh yeah, five years at Stripe uh building the developer relations, developer experience function, but also obsessing about the product, which was effectively for Stripe, the API design, the documentation, the SDKs, all of the tools that would make developers actually love integrating payments.
- 2:32SPEAKER_03: And when you think about Stripe, um integrating payments had always been a pain for developers.
- 2:38SPEAKER_03: It was always the thing before Stripe that they hated the most doing because it meant, oh gosh, I'm gonna have to leave my favorite Node.js and Ruby and Rails development all of a sudden to integrate with these very legacy APIs.
- 2:50SPEAKER_03: And all of a sudden with Stripe, we made something very delightful and magical to use.
- 2:55SPEAKER_03: And uh yeah, I spent a lot of my time making that uh uh as as great as possible with a fantastic team.
- 3:02SPEAKER_03: And I think what I found the most exciting about Stripe is how everyone, from Patrick and John, the founders, would care so much about the quality of the API and the abstractions that we would put out there.
- 3:14SPEAKER_03: So that was very much in the DNA of the company to have great DX.
- 3:18SPEAKER_03: Interesting.
- 3:19SPEAKER_00: And now you're head of developer experience at OpenAI.
- 3:23SPEAKER_00: Um and what I want to say, uh thank you for the invitation to OpenAI's developer event in Berlin.
- 3:28SPEAKER_00: We sadly couldn't record this on-site in Berlin, but we now get to do this uh remote.
- 3:33SPEAKER_00: And uh you're in from Paris, right?
- 3:36SPEAKER_00: Exactly.
- 3:36SPEAKER_03: Well, we just uh hosted Berlin was the first of our stops in Europe.
- 3:41SPEAKER_03: It was a great event.
- 3:42SPEAKER_03: We did uh Paris uh this week uh after Berlin, and then we're going to London uh on on Tuesday as well to kind of wrap this European leg of DevDay Exchange.
- 3:52SPEAKER_03: And of course, like people have probably followed DevDSF uh about four weeks ago now.
- 3:58SPEAKER_03: It's like kind of like our flagship annual event.
- 4:00SPEAKER_03: And we could stop there, but I think for us it matters also a ton to not just launch things from San Francisco and have a live stream, but also connect with the developer community around the world, right?
- 4:12SPEAKER_03: And I think there are amazing developers in Berlin, um, and uh same in Paris and London.
- 4:17SPEAKER_03: And we want to make sure we also spend time with them, to also listen to their feedback and what they need.
- 4:22SPEAKER_03: Uh, it's important to like have that feedback for us.
- 4:25SPEAKER_03: That's very much the way we make the products better and how we build them.
- 4:29SPEAKER_03: Um, an example of that, for instance, was uh every time I traveled to Europe the past year or so, people kept mentioning that they wanted to do more voice AI, but the accents and the voices in German or in French were not that great yet.
- 4:42SPEAKER_03: And I agreed.
- 4:44SPEAKER_03: And so that feedback was critical into making like GPT Live 1.1, which is now much better with the German accent and French accent, for instance.
- 4:51SPEAKER_03: So yeah, we love spending time on the road and hearing from developers who are building great things in Europe.
- 4:57SPEAKER_00: And what is your response to people who ask you why you still need this face-to-face time?
- 5:02SPEAKER_00: Like lots of development work is becoming more remote, more asynchronous, um, teams are more and more distributed.
- 5:08SPEAKER_00: Why do you care so much about that face-to-face time in person?
- 5:12SPEAKER_03: I mean, the the sense of belonging and community, I think, is more important than ever, uh, especially after like some of the kind of COVID years where people had to uh work um, you know, uh remotely for a while.
- 5:25SPEAKER_03: When you look at the rise of AI and things like coding agents, for instance, it's definitely true that now you can do a lot with those tools, a lot more that you could possibly accomplish before.
- 5:36SPEAKER_03: But at the same time, the sense of like belonging, the learning from each other is becoming more critical, right?
- 5:42SPEAKER_03: Like if you rewind just a few years ago, um, the technology you built upon was not changing that fast.
- 5:50SPEAKER_03: Now, like all of the techniques that you might have practiced for the past like six months are already changing.
- 5:55SPEAKER_03: In fact, I often tell like engineering teams like if you have, I don't know, your skills or your agents MD files that have been untouched for four months or something like that, they're probably far outdated by now.
- 6:07SPEAKER_03: Like the frontier models are becoming so great that um you want to learn from each other.
- 6:13SPEAKER_03: You want to like actually connect in person, share the best practices, see what the others are building.
- 6:20SPEAKER_03: And uh, as I hinted at, also like um the needs from different people from different regions are also different.
- 6:26SPEAKER_03: We mentioned languages, but uh when we go to APAC, that's even more acute, right?
- 6:32SPEAKER_03: So, like in in Japan, in Korea.
- 6:34SPEAKER_03: Um, the price points of of what we can offer these models for is also critical for some other regions.
- 6:40SPEAKER_03: And so, yeah, the the community building is critical.
- 6:43SPEAKER_03: And that's why I think we can do some of that work with our team that we've been growing around the world, but there's some limits to that.
- 6:52SPEAKER_03: And that's why we created programs like Codex Ambassadors, for instance.
- 6:55SPEAKER_03: And Codex Ambassadors are amazing to us because they are passionate builders using tools like Codex that are able to run events in regions uh that we cannot reach yet.
- 7:07SPEAKER_03: You know, like there are cities around the world where we don't have OpenAI employees yet.
- 7:11SPEAKER_03: Uh, it may take us a while to get there even.
- 7:14SPEAKER_03: Um, but luckily we can rely on these codecs ambassadors building events.
- 7:18SPEAKER_03: And yes, this sense of belonging is really beloved by the community.
- 7:22SPEAKER_02: If we're talking about like developer experience, it already includes the word developer.
- 7:26SPEAKER_02: Um, how quickly or at all is it at all changing your target group of people that you want to reach?
- 7:33SPEAKER_02: Because I mean, historically, yes, it was very much a developer role and codex, you first think of uh developers as well.
- 7:40SPEAKER_02: Um, but I guess we for us and also in the market see that like the roles are quickly merging between the different um yeah uh roles that we had before.
- 7:51SPEAKER_02: Uh how quickly do you see that in, for example, your events?
- 7:55SPEAKER_02: Like, did the target group already change, the visitors change?
- 7:58SPEAKER_03: Oh, absolutely.
- 7:59SPEAKER_03: I think like there's there's two dimensions, right?
- 8:01SPEAKER_03: There's like um what is the definition of a developer?
- 8:06SPEAKER_03: And that definition is kind of rapidly changing and evolving.
- 8:09SPEAKER_03: Uh, and then there's also like um, who has now access to these tools and superpowers that would be uh otherwise limited to them in the past.
- 8:19SPEAKER_01: Yeah.
- 8:19SPEAKER_03: And so uh for us, like we um we don't want to draw like a very sharp line between like this binary decision of like, oh, you're either a developer or you're not.
- 8:29SPEAKER_03: Um now what we've noticed is that we always want to serve, of course, the kind of early adopters, the people are kind of pushing the frontier of the tools, the people who are experimenting with the next model every few weeks, you know, and try to collect feedback directly from them because they are the tastemakers.
- 8:47SPEAKER_03: But at the same time, what's amazing to see is that like in the past year alone, now like a product manager is way more technical than they used to be.
- 8:55SPEAKER_03: Now, instead of writing a document to explore an idea with their team, I've seen many PMs at OpenAI included building a prototype and actually reviewing that prototype with the team.
- 9:05SPEAKER_03: Now, a designer can even test an interaction instead of just staying in Figma.
- 9:09SPEAKER_03: Or uh at OpenAI, what we've noticed too, and the whole reason why we relaunched uh ChatGPT as one app combined with Codecs in a few a couple of months ago is because we had noticed the finance team, the legal team, the sales team, they were all on Codecs.
- 9:24SPEAKER_03: Instead of having like uh the need for an engineer to build a dashboard, they could suddenly like build a live dashboard by themselves.
- 9:31SPEAKER_03: Or um, if they wanted to like maintain that dashboard and deploy it every day automatically, they could build that with codecs.
- 9:37SPEAKER_03: Or a salesperson, instead of having a deck for a customer, they could actually build a full-on interactive experience for that customer.
- 9:45SPEAKER_03: Um, so that's been amazing to see how many more people have this like magic and this like superpower at their disposal, and they're all becoming more technical.
- 9:55SPEAKER_03: Um and that gives us like a better feedback loop with the broader community.
- 10:00SPEAKER_03: Um, and you could even argue that at some point we should almost rename our team, like because you know, we go beyond developers to with with tools like dots, if we talk about them at some point, like you know, you have proactive agents kind of like helping you with your goals, both at work and in life.
- 10:15SPEAKER_03: And so we go far beyond developers, but we still think it's fundamental to obsess about the developers because at the end of the day, the engineers are still kind of the early uh adopters of that technology.
- 10:27SPEAKER_03: And we want to make sure that like we're at the frontier with them, listening to their feedback, making the product really great.
- 10:32SPEAKER_03: And if they love it, turns out I think the people right after them will also have a great time.
- 10:38SPEAKER_00: And when you say you don't want to like have a hard differentiation between um like developers and non-developers, is there a differentiation between people who build with open AI and people who build on open AI?
- 10:52SPEAKER_00: So, what I mean by that is there's obviously people who use all these tools that you've just mentioned, right?
- 10:56SPEAKER_00: Dots, codecs, sites, whatever.
- 10:59SPEAKER_00: And then there's people who just want to integrate with your API and your models.
- 11:03SPEAKER_00: And is that two audiences for you, or do you see them merging as well?
- 11:08SPEAKER_03: We see the interplay happening a lot more in real time.
- 11:12SPEAKER_03: You know, in fact, if you rewind, like three and a half years ago when I was joining up on AI, all we had for developers at the time was an API.
- 11:20SPEAKER_03: And we said, hey, we have ChatGPT.
- 11:22SPEAKER_03: And but if you want to take these models and bring them to your application, you can take this API for the model, and you'll be able to do things like structured outputs, you'll be able to like um make your first agents.
- 11:36SPEAKER_03: And um, you know, at the time we talked about RAG and fine-tuning a lot, but that was kind of the API that we offered.
- 11:42SPEAKER_03: But over time, now that you have tools like Codecs, you can actually build software, include like any kind of software, even if it's not an AI-powered feature, but if it's like actually anything that you want to build, but assisted with Codecs and AI.
- 11:56SPEAKER_03: And we've seen this interplay now going hand in hand.
- 11:59SPEAKER_03: The idea of like, I'm starting building an app with codecs, whether it's an iPhone app, an Android app, maybe some web applications or something, I'm iterating quickly.
- 12:08SPEAKER_03: But of course, I want that experience to be awesome for my customers too.
- 12:12SPEAKER_03: And I want them to have the same feeling as I have when I'm using Codecs.
- 12:16SPEAKER_03: So I'm I talk to a lot of developers who are like, I want to bring speech to speech to my app.
- 12:20SPEAKER_03: I want to bring Imogen to my app.
- 12:22SPEAKER_03: I want to bring all of these capabilities that I have in Codecs, but I want those in my app too.
- 12:28SPEAKER_03: And we've noticed that already.
- 12:30SPEAKER_03: And in fact, it's very timely because um just at Dev de Paris this week, uh, what uh what I announced was uh this new launch uh where you can now have, as part of your Chat GPT subscription, you now have API credits as well added on top.
- 12:46SPEAKER_03: And we've also launched an open AI developers plugins for Codec.
- 12:50SPEAKER_03: So, all in all, what that means is that I'm starting building something with Codecs.
- 12:55SPEAKER_03: I want to have the most frictionless experience to bring these capabilities.
- 12:59SPEAKER_03: I don't have to worry about setting up an ABI key because Codecs can do that for me automatically from Codecs.
- 13:05SPEAKER_03: I don't have to worry about putting a card on file again at the beginning because I have credits automatically to start building right away.
- 13:12SPEAKER_03: And guess what?
- 13:13SPEAKER_03: I don't even have to read docs because I can just ask Codec, hey, like I would like you to bring uh speech to speech here with GPT Live.
- 13:20SPEAKER_03: And when my customer is uploading these pictures of their uh home, for instance, I want you to generate an image of what the furniture could look like if you're building like a home decor uh application, for instance.
- 13:33SPEAKER_03: So uh back to your question, we really see this into play more and more, and we actually want to facilitate that.
- 13:39SPEAKER_03: Uh, whether you're an API uh customer on OpenAI or a codex builder, we want that uh to be very like seamless to go uh between the two.
- 13:50SPEAKER_00: And maybe one last question regarding that audience.
- 13:53SPEAKER_00: Um in the past, addressing developers was probably not cheap but straightforward, right?
- 13:59SPEAKER_00: There is like conferences, there is uh content sites where you could advertise, there is events that you could host yourself.
- 14:06SPEAKER_00: Sooner or later you would somehow reach these developers.
- 14:09SPEAKER_00: And now that like product people come in, designers come in every day, people from the street come in and just like start building.
- 14:16SPEAKER_00: How do you actually reach those people and how do you make them aware of the fact that by some definition they are developers as well and they should feel addressed by what you do?
- 14:25SPEAKER_03: Yeah, no, it's fascinating and it's a it's a great question, right?
- 14:29SPEAKER_03: Because these tools are very much blurring lines.
- 14:32SPEAKER_03: Um, that's why on our team, like we've been spending a lot of time trying to educate uh people with video content, uh different kinds of formats, like written guides on what you can accomplish with the platform.
- 14:44SPEAKER_03: The fact that, for instance, you can not just ask Codex to build an app, but then say, hey, actually deploy it on the internet.
- 14:52SPEAKER_03: And all of that, you can have a ChatGPT site up and running.
- 14:56SPEAKER_03: Or of course, if you have like a Vercell or a Cloudflare account, it can use that as well.
- 15:00SPEAKER_03: Like all of these things, like um ChatGPT sites actually having like a full-on uh database, uh, you know, synchronization, WebSocket support, all of these things is quite magical because you don't have to worry about infra as much.
- 15:14SPEAKER_03: Um so yeah, it's a rapidly evolving field.
- 15:18SPEAKER_03: We want to make sure that people know about these capabilities that are being added to the product.
- 15:23SPEAKER_03: Uh, but meanwhile, that's also why we still care a lot about uh DX, because I think uh developer experience is also itself evolving.
- 15:33SPEAKER_03: And what might have been for Stripe, like let's design the best API and the best SDK we can, uh, still very much is relevant, but also expands to other things.
- 15:44SPEAKER_03: Like, well, now I'm fully expecting that my customers are using coding agents and tools to assist them in building software.
- 15:51SPEAKER_03: And so that should be the obsession we now have about developer experiences.
- 15:56SPEAKER_03: Like, is it frictionless to ask the coding agent to build something?
- 16:00SPEAKER_03: Will it find the right primitives, the right model, the right abstractions?
- 16:04SPEAKER_03: Um, and we're effectively designing now both for humans and their agents uh to make sure that they can import very seamlessly.
- 16:11SPEAKER_00: And in that sense, you're in a very privileged position, right?
- 16:14SPEAKER_00: Because you also maintain the coding agent that most of these people will use to actually build the products and then integrate again with OpenAI.
- 16:22SPEAKER_00: What would your message be for every other platform out there that doesn't host its own coding agent, that doesn't bring its own harness, that is like reliant on other coding agents to pick them up and to kind of understand, like Stripe, for example, right?
- 16:36SPEAKER_00: We mentioned Stripe here before.
- 16:38SPEAKER_00: So, what is your message to people like Stripe on how they should be doing developer experience in the age of coding agents?
- 16:45SPEAKER_03: Yeah, um, well, I think one uh thing that's been amazing to observe, in my view, has been that the platforms that had the best DX for humans tend to also be the platform that have the best DX for agents already.
- 16:59SPEAKER_03: Uh, you mentioned Stripe, Stripe is doing fantastic work, but also all the years of crafting great abstractions for humans have actually paid off now, even for agents.
- 17:08SPEAKER_03: Uh, you see um products like Superbase, for instance, like, you know, agents actually have a great time using with Superbase, even though they designed these things before.
- 17:18SPEAKER_03: My message to them would also be like, try to keep on building these great abstractions, but try to see what um tools do agents need to do their best work.
- 17:28SPEAKER_03: So, for instance, if you have an MCP server, that's even better because all of a sudden, like uh the agent can uh access that directly.
- 17:37SPEAKER_03: If your docs are consumed by humans well, that's already a good enough step because the agent will be able to figure out.
- 17:44SPEAKER_03: But if you're able to serve your docs for agents specifically in a more efficient manner, that can make them even more effective.
- 17:52SPEAKER_03: Um and then trying to offer the tools too for like things like WebMCP, for instance.
- 17:57SPEAKER_03: Imagine you're building not just an app for humans, but if you want the app you're building to also uh be well used by agents.
- 18:07SPEAKER_03: Well, it's sure enough, agents like Codex have amazing computer use and act as humans.
- 18:13SPEAKER_03: But if you integrate initiatives like WebMCP, then even the apps that your customers build with your interfaces can have this amazing way to work with agents.
- 18:23SPEAKER_03: So we really think about the whole flow, both for the building side uh side of things, but also for the user interacting with the end product.
- 18:33SPEAKER_03: Um and so for us, for instance, the journey that we've taken is like, you know, we've been the open AI, we've been building the OpenAI developers plugin uh for codecs.
- 18:42SPEAKER_03: I recommend like most platforms to also do such things because then you can just package up skills and functionalities right there.
- 18:50SPEAKER_03: And so now if you're using Codecs or another coding agent, um, it's much easier to integrate with your API or your platform because you have this plugin that's like one click away.
- 19:00SPEAKER_03: And I, as a human, don't have to read every API ref parameter anymore because my coding agent will do that.
- 19:07SPEAKER_00: Do you anticipate a change towards technologies that are maybe less friendly to humans but more optimized for agentic workflows?
- 19:15SPEAKER_00: For example, in the past, APIs basically always meant REST APIs, right?
- 19:20SPEAKER_00: They're easy to read, they're stateless, um, they're easy to document.
- 19:24SPEAKER_00: Um, but there's people out there arguing that technologies like GraphQL, for example, are way more efficient.
- 19:29SPEAKER_00: They're just harder to use, which is why hardly anyone out there actually implements proper GraphQL APIs.
- 19:36SPEAKER_00: But now that I don't need to read these APIs and these instructions anymore, and my agent and my machine take care of that, will we maybe see a shift towards technologies like that?
- 19:46SPEAKER_03: It could, yeah, because like the you know, GraphQL was always fascinating, but a bit hard to reason about because you had to specify the field you needed, the field you did not need, and things like this, but the agent could quickly uh figure this out for you.
- 19:58SPEAKER_03: So that's definitely one way.
- 20:00SPEAKER_03: Um I think the same question goes for SDKs in some ways, right?
- 20:04SPEAKER_03: SDKs were initially meant for humans to abstract away the complexity of interfacing with REST.
- 20:10SPEAKER_03: Like, for instance, at every REST API request I'm doing, I want to also make sure that there is like some uh retries built in.
- 20:18SPEAKER_03: In the case of Stripe, it's important the payment goes only once.
- 20:21SPEAKER_03: And so there is like the idem potency key concept and things like this.
- 20:25SPEAKER_03: You could one on one side, you could argue that like, well, coding agents could just write more code.
- 20:30SPEAKER_03: At the same time, the SDKs can still be interesting there to package that functionality.
- 20:34SPEAKER_03: And if you're actively reviewing the code made by an agent, it's also nice to see that code quite short and easy to digest when the SDK is officially hiding some of that complexity.
- 20:46SPEAKER_03: But sure enough, I think like there are um over time uh we're gonna read less code and we're gonna trust agents more and more.
- 20:54SPEAKER_03: And I could see a world where GraphQL and and some other techniques that maybe the human developers were kind of like Barry Sean, um, could be great for agents.
- 21:08SPEAKER_02: Yeah, at that point I always wonder like what happens or are new technologies still developed?
- 21:15SPEAKER_02: I mean, GraphQL, for example, was developed in a sense that humans uh interact with it and have an easier way uh for it.
- 21:22SPEAKER_02: And I I somehow imagine like, is all of this infrastructure that we have and that we use just come to a complete stop now?
- 21:28SPEAKER_02: And that's just the current state of that agents know, because there's not really a need for new technologies, like that anybody comes up and says, okay, I have a new GraphQL, because the adoption will be very hard in the future as well.
- 21:42SPEAKER_03: I think it depends.
- 21:43SPEAKER_03: I think there's always gonna be like uh, you know, products that um could make agents even more effective.
- 21:49SPEAKER_03: I think like uh you see, like we we try to come up with like something neutral for agents MD to kind of package up the instructions from any coding agent in one place.
- 21:57SPEAKER_03: Same thing for WebMCP.
- 21:59SPEAKER_03: I think WebMC.
- 22:00SPEAKER_03: Try to like you know provide a net new interface for agents.
- 22:05SPEAKER_03: Uh, we've also worked with the the folks who came up with MCP in order to introduce like UI components in MCP.
- 22:12SPEAKER_03: That's how we build like the ChatGPT apps, for instance, and the Codex plugins.
- 22:16SPEAKER_03: You have like um these UI primitives that you can expose, not just for us, but for any kind of client of that technology.
- 22:24SPEAKER_03: So you can see that even if the models are progressing and the coding agents are being more and more effective, there are still ways also to kind of uh bring some standardization across the different agents and always kind of polishing that.
- 22:39SPEAKER_00: I want to touch on um a kind of new set of challenges that you might have experienced in developer experience.
- 22:47SPEAKER_00: Um so in the past, when working in DevX, you most often interacted with developers, right?
- 22:53SPEAKER_00: Or at least with people who were from the same domain.
- 22:56SPEAKER_00: So when you talk to them about like what are the constraints within that you operate, you could explain to them why maybe certain features aren't available or why they might take some more time.
- 23:07SPEAKER_00: And I feel like AI has kind of opened Pandora's box here because people just assume that these machines are like super intelligent and almost to a human scale.
- 23:17SPEAKER_00: And now when they approach you and ask for other features, or why doesn't this work, or why does it behave in this and that way, how do you explain to them the intricacies of like, well, this is an LLM, this is a transformer, it's it's not a human after all.
- 23:31SPEAKER_00: It feels like a human very much and oftentimes, but you still work within certain constraints.
- 23:36SPEAKER_00: And how do you communicate that?
- 23:39SPEAKER_03: Yeah, um it's challenging, right?
- 23:43SPEAKER_03: Because uh even the capabilities are changing so frequently now with with this space of AI.
- 23:49SPEAKER_03: But ultimately, I think that's where the we're kind of reinventing also the the work of the developer, right?
- 23:56SPEAKER_03: What you used to spend time on with all this toil, all of these migrations, now you're spending that time being more creative, be taking an idea and like actually turning it into a real product.
- 24:07SPEAKER_03: And I think like even if you're a fantastic PM and you're able to prototype something and you can drive like excitement among your team to build a feature because you can actually interact with the prototype, it doesn't mean necessarily that the PM should actually go deploy that feature themselves with you know low understanding of the infrastructure components and things like this.
- 24:29SPEAKER_03: But at least you can start speaking like more of the same language, right?
- 24:33SPEAKER_03: Instead of having a PM that speaks documents and the engineers that speak code, at least we're getting closer and closer to like operating on shared surfaces.
- 24:42SPEAKER_03: But you're right in terms of uh the challenge of like, okay, why did why did the coding agent behave like this?
- 24:48SPEAKER_03: I told it to deploy my app.
- 24:50SPEAKER_03: Why is it not working at scale for like 100 million users, for instance?
- 24:53SPEAKER_03: Well, there's there's there's different parts there to the story.
- 24:56SPEAKER_03: You have to have infrastructure to support that, you know, things like that.
- 25:00SPEAKER_03: But um I think that's also part of our um role on you know, developer education and trying to understand like uh how do we teach more users about all of these tools?
- 25:10SPEAKER_03: And when you zoom out on the number of users of ChatGPT today, like we're super fortunate that we have like a billion and 200 million, like 1.2 billion effectively, people using ChatGPT every week.
- 25:21SPEAKER_03: I'm like, how many of those have not had their kind of like AGI moment feeling yet of like, wow, I had no idea I could actually do that by myself.
- 25:31SPEAKER_03: Like, I can actually.
- 25:33SPEAKER_03: And so we have so much more potential to kind of lift up everyone with the power of these tools and be like, wow, I can actually be very creative here and turn my ideas into something tangible.
- 25:44SPEAKER_03: Um, so I think to me that's that that's the exciting part.
- 25:47SPEAKER_03: Uh, and goes back to also like the lines blurring between technical and non-technical people.
- 25:52SPEAKER_02: Talking about lines, like, where do you draw a line within OpenAI when you talk about developer experiences, or is all what is user-facing in some way uh developer experience?
- 26:04SPEAKER_02: I mean, we we mentioned uh dots, for example.
- 26:06SPEAKER_02: Yep.
- 26:06SPEAKER_02: Uh talked about them in the podcast uh um often.
- 26:10SPEAKER_02: Um is that a product you are involved with and where you also talk about developer experience, or is it just somewhere outside your space?
- 26:20SPEAKER_03: Yeah, no, it's a great question because even that for us is blurring a little bit internally, right?
- 26:24SPEAKER_03: By definition, dots is not for just developers, because it's this idea that you can give anyone uh using ChatGPT or Codecs a proactive agent that's always on, that's very capable, that's doing things for them.
- 26:38SPEAKER_03: Uh, even on this trip, my dot has been amazing almost every single day, doing something I would not have perceived.
- 26:44SPEAKER_03: Like the model is really amazing.
- 26:45SPEAKER_03: Like, you know, you land at the airport in a different city, and it tells you in three sentences like something critical that you have to know for like, I don't know, your route to the hotel or the venue for Dev Day or something.
- 26:55SPEAKER_03: That's quite magical.
- 26:56SPEAKER_03: But what's even more interesting, and where my team is involved, is that well, dot is for everyone.
- 27:01SPEAKER_03: It's not just for developers, it's an agentic product.
- 27:04SPEAKER_03: But as an engineer or as a developer, it's actually also giving you superpower because now you can start thinking of a dot as like a very high-agency senior engineer that I can actually delegate tasks to.
- 27:18SPEAKER_03: So I can be on a plane noticing a tweet from you guys about, let's say, like an issue in codex, and I can be texting my dot now, and I can say, hey, can you look into this?
- 27:30SPEAKER_03: I think there's an issue that was flagged by Dennis, like over here.
- 27:35SPEAKER_03: Uh, and it will actually spin up codex task to look at the code base, introspect the issue, prepare the PR, ship the PR, and be like, all right, looked at the logs, found out the issue.
- 27:47SPEAKER_03: This was isolated to this and that kind of customer, prepare the PR, prepared the fix, it's now in review.
- 27:52SPEAKER_03: Uh, do you want me to look at it?
- 27:54SPEAKER_03: Ping someone, do you want me to merge it?
- 27:56SPEAKER_03: And that's kind of like my dot acting as an engineer, right?
- 27:58SPEAKER_03: So it's this interesting thing where, like, even though the dot is for everyone, it will also transform the way we work as engineers.
- 28:06SPEAKER_03: Because now you can think of your team as the humans around you, but also their dots as well in the picture, to be able to take on the work for them, take on the work for yourself.
- 28:18SPEAKER_03: So internally, we have a team working on docs, uh dots, obviously, like product, engineering, research, marketing, and all of these functions.
- 28:26SPEAKER_03: But we're also very well plugged in with them to uh to help them educate the world, especially with the more technical use cases of dots.
- 28:35SPEAKER_03: Where I think, in my view, like dots and codecs are gonna start even blurring a lot more when you start not just prompting codecs to create a feature, but your dot is starting to proactively suggest things.
- 28:49SPEAKER_03: It's like, hey, I've looked overnight at this feedback from customers.
- 28:53SPEAKER_03: There's one theme that keeps coming back, which is this feature is not working the way they anticipated.
- 28:58SPEAKER_03: So I just went ahead and proposed the first version of that feature for you.
- 29:03SPEAKER_03: What do you think?
- 29:03SPEAKER_03: It's like, wow, this is magical.
- 29:05SPEAKER_03: This is already like thinking three, four steps ahead for me.
- 29:09unknown: Yeah.
- 29:10SPEAKER_03: So yeah, can't wait for everyone in Europe to have access to this.
- 29:14SPEAKER_00: Well, we certainly do have uh quite a big number of dots on our uh Slack uh channels already here.
- 29:20SPEAKER_03: Right.
- 29:21SPEAKER_03: And also, of course, because like business, enterprise accounts um can already access it.
- 29:25SPEAKER_03: And then like hopefully in a few weeks, everyone, uh even consumers will have one.
- 29:30SPEAKER_01: Yeah.
- 29:30SPEAKER_02: Yeah, but also looking forward to these.
- 29:32SPEAKER_02: I don't know, uh as far as I know, it's planned to have like enterprise dots as well, right?
- 29:38SPEAKER_02: That can serve us in in specific roles for example monitoring and so on.
- 29:42SPEAKER_02: I think that's that's gonna be really interesting as well.
- 29:44SPEAKER_03: So yeah, I think it's gonna also change the yeah, it's gonna also change the developer experience.
- 29:48SPEAKER_03: You could imagine having on the developer experience side of things, uh, even on-call being reinvented, because the first on-call page is actually a dot that's able to actually decide what's going on and ask a human to wake up when the thing is ready, you know?
- 30:06SPEAKER_00: So the kind of scenario you're outlining here is is very futuristic to some people out there, right?
- 30:15SPEAKER_00: I feel like we see a certain fragmentation in the developer space where some people are very like AI positive, AI first, let's try all the things, let's early adopt everything we can and see where it gets us.
- 30:28SPEAKER_00: And then there are some people who either buy company decisions, regulatory decisions, financial decisions, kind of feel like left out from much of this.
- 30:38SPEAKER_00: And how does that impact your work where you basically want to share like all the goods with everyone, but there is a huge part of your audience that is not directly accessible or perceptible to that?
- 30:51SPEAKER_03: Yeah, I mean, like um the adoption rate goes um slightly differently from like either like company size to company size, industry by industry, or even sometimes country.
- 31:03SPEAKER_03: But what we've noticed is that the positive here is that unlike any previous technology change is being adopted across the board by everyone much faster on average, right?
- 31:13SPEAKER_03: Like, for instance, like in the banking sector, how many years did it take for banks to have a mobile app?
- 31:20SPEAKER_03: For some of them, it took a decade to have an iPhone app after the iPhone came out.
- 31:25SPEAKER_03: Now, what we're seeing across the board is like adoption of AI is much, much faster than any previous tech.
- 31:31SPEAKER_03: Now, you're right that like some startups and digital native companies, they are all reinventing their workflows with AI every week.
- 31:38SPEAKER_03: For some others, they're still kind of like earlier in the adoption phase, kind of like um concerned maybe by like IT safety, security, deployment, or cost.
- 31:48SPEAKER_03: And we're very sensitive to all of these chatter.
- 31:50SPEAKER_03: That's why we're here to help them adopt.
- 31:53SPEAKER_03: And I think sometimes like what I've noticed by all the companies I've spent time with is that success for AI adoption to me comes from two things that have to be true.
- 32:04SPEAKER_03: One is like each company needs to have like one person at the highest level that gives that freedom and that top-down mandate to be like, hey, we're gonna reinvent the way we work on this company with AI.
- 32:17SPEAKER_03: And giving that sense of direction and freedom that it is gonna happen.
- 32:22SPEAKER_03: It also needs, though, like people that are curious, that are passionate, that are trying things, because you're not gonna get everything right on day one.
- 32:30SPEAKER_03: You have to reinvent the way you work with your engineers, the way you submit your PRs, the way you review each other's code, the kind of sensitivity to risk you have before merging to production, depending on the industry you're in, and so on.
- 32:44SPEAKER_03: You need these bottoms-up of like passionate AI engineers that are kind of trying things out.
- 32:50SPEAKER_03: And I think if you have both, you're absolutely gonna succeed.
- 32:53SPEAKER_03: Because the challenge is like if you um if you don't have the top-down mandate, the the few engineers who are passionate might not have enough leeway to make change happen.
- 33:04SPEAKER_03: But if you don't have the passionate, curious people and only a top-down mandate, you're not gonna try enough things and test different tools and actually be ready to reinvent the way you work.
- 33:15SPEAKER_03: And so you're gonna need both.
- 33:16SPEAKER_03: Um, but what I also noticed is that when I share or we share the stories of how we use our own technology at OpenAI, that actually inspires people a lot.
- 33:26SPEAKER_03: Because, like just two weeks ago, for instance, I had a meeting with um a large company from Europe.
- 33:32SPEAKER_03: And they were asking me, like, okay, well, you're clearly writing more code.
- 33:36SPEAKER_03: Sure, we hear you, you're writing more PRs, but let's be honest here, do you feel actually more productive or not at OpenAI?
- 33:44SPEAKER_03: I was like, well, let me give you some examples.
- 33:46SPEAKER_03: Like, I mean, one of the biggest challenges we had recently was that ChatGPT.com was a code base that we started roughly four years ago now, right?
- 33:56SPEAKER_03: Like before the launch of ChatGPT.
- 33:58SPEAKER_03: And you can imagine it's like millions of lines of code.
- 34:01SPEAKER_03: And by the time you start four years ago, you're not exactly sure where you're headed.
- 34:04SPEAKER_03: You have no idea about the exact sequence of model capabilities.
- 34:08SPEAKER_03: But meanwhile, we've seen this outstanding momentum of the ChatGPT codec kind of desktop app this year.
- 34:15SPEAKER_03: That code base is much more modern, was made for like agentic delegation.
- 34:20SPEAKER_03: And we knew we had to do something about these two code bases merging.
- 34:25SPEAKER_03: But if we had tried to do this like three, four months ago, this was effectively impossible to do with AI.
- 34:30SPEAKER_03: And we would probably have like taken like a year or so with our great engineers to do that change.
- 34:36SPEAKER_03: It turns out with the help of Astra and Ultrafast, we were able to get this done in less than a month.
- 34:42SPEAKER_03: And this is done.
- 34:43SPEAKER_03: It's now in it's now in production.
- 34:44SPEAKER_03: And we have also done this right before Dev Day, in the midst of everything else that we had to build.
- 34:49SPEAKER_03: And when I tell people, like, well, if you don't believe this is like productivity, it's millions of lines of code, of very large code bases being merged and now deployed in production.
- 34:58SPEAKER_03: And it worked.
- 34:59SPEAKER_03: We've done that in less than a month.
- 35:01SPEAKER_03: Could not have been done without Astra and Ultrafast.
- 35:04SPEAKER_03: And they start thinking about their migration projects that they've been putting off because it's always something that you want to put off because you always have more important features to build.
- 35:14SPEAKER_03: The best engineers are needed for that migration, but they're also much more needed for the other uh more uh business important features to build.
- 35:24SPEAKER_03: And so when you start telling these stories, I think it really helps for them to reconsider wow, okay, so we need to take these things seriously because if we had considered some tools six months ago, the status has completely changed.
- 35:39SPEAKER_03: Like what you can now accomplish versus six months ago is drastically different.
- 35:45SPEAKER_00: Given that you already touched on model capabilities, I have a question about that because a few months, years ago, maybe, I was at a conference and I heard someone else from another lab, we don't want to mention names here, but I heard someone else speak.
- 36:00SPEAKER_00: And what they said was basically we could stop research into future models right now, and we would still see months and years of new products being introduced that only just start to leverage what we already have.
- 36:12SPEAKER_00: Because the products that we see out there today don't even begin to kind of like fully utilize the models that we have today.
- 36:19SPEAKER_00: Now, at like approaching the end of 2026, would you agree with that?
- 36:24SPEAKER_00: Or do you think we've gotten better at utilizing the models that we have?
- 36:28SPEAKER_00: And is the the gap between utilization products and lab capabilities closing or expanding?
- 36:36unknown: Yeah.
- 36:36SPEAKER_03: It's a great question.
- 36:37SPEAKER_03: It's a feeling I have as well, because um, on one side of the of the picture, you can see there's safety that's paramount for companies like OpenAI.
- 36:50SPEAKER_03: We care like immensely about that.
- 36:52SPEAKER_03: This is our first priority.
- 36:54SPEAKER_03: This is why there's this like conversation in the public about like pacing the frontier of research, doing it the right way, pausing a training run if need be, because of that safety approach.
- 37:05SPEAKER_03: But means in the meantime, you also see on the other side, on the product side, you see the like all of the amounts of ships that we've had at Dev Day in San Francisco, but also what the industry overall is able to accomplish, their velocity, the number of product experiences that they're able to deliver for their customers.
- 37:24SPEAKER_03: And that fee, that that pace is only accelerating, right?
- 37:28SPEAKER_03: Um and I believe that's still true.
- 37:30SPEAKER_03: That like if you take a model like Astra, I mean, the incredible capabilities that are latent in there, I'm sure there are so many more product experiences we could still build today, even if those models were not changing.
- 37:44SPEAKER_03: But meanwhile, what is also very interesting is that when you take the very best early adapters of models, I'm always surprised by how quickly they get used to this novelty and the next frontier of capabilities, right?
- 37:58SPEAKER_03: When when Astra came out, this was this outstanding moment where like the community, for instance, realized, wow, it's so incredible at 3D modeling.
- 38:08SPEAKER_03: And then for a week or two, we saw everyone experiment with Blender and all of these like 3D worlds, which was amazing to watch.
- 38:16SPEAKER_03: And then, like, you know, this has been what, five, six weeks now since Astra, and people are ready for the next one.
- 38:22SPEAKER_03: They're like, okay, let's bring the next one.
- 38:24SPEAKER_03: We want to see what the next Filaquino frontier looks like.
- 38:27SPEAKER_03: And so I'm also surprised by those early adopters and how quickly they're able to kind of poke at the model to find what it's able to do and discover new things that sometimes we were not aware of, like this, this like 3D uh capabilities that were emerging.
- 38:43SPEAKER_03: Um But yes, at the same time, you could pause everything.
- 38:47SPEAKER_03: And there are so many latent capabilities in these models that we have not fully grasped yet.
- 38:52SPEAKER_03: I was seeing a tweet, I think, just this morning, about like multiplayer AI, for instance, and how we interact with each other with our own dots or equivalents.
- 39:02SPEAKER_03: I mean, like, this is not quite just AI capabilities for that to happen.
- 39:07SPEAKER_03: They're there.
- 39:08SPEAKER_03: They're already there.
- 39:08SPEAKER_03: But it's all about like reinventing the product, the UI, the UX.
- 39:13SPEAKER_03: How do we work together?
- 39:14SPEAKER_03: When does it make sense for my dot to write to you, or where is it going to be like poorly perceived?
- 39:20SPEAKER_03: Because my dot should be telling something to your dot instead.
- 39:24SPEAKER_03: And like all of these little UI, UX workflows to figure out that's all product questions that have to be, you know, reimagined with trial and error a bunch of times with the current capabilities we have.
- 39:36SPEAKER_03: So I think there's like really both uh happening at the same time.
- 39:40SPEAKER_03: And even if we pause, or rather, we pace the frontier because we're never going to pause, the progress is very rapid and will continue to be rapid.
- 39:48SPEAKER_03: But even if you pace the research, you will continue to see an acceleration of what the products can deliver.
- 39:55SPEAKER_00: Yeah.
- 39:56SPEAKER_00: So we're approaching the end of our time here.
- 39:58SPEAKER_00: And before I ask my last uh question, I want to ask Dennis if he has any questions remaining.
- 40:05SPEAKER_02: No.
- 40:05SPEAKER_02: Um I mean I mean, yes and no.
- 40:08SPEAKER_02: I I think we could talk endlessly about those topics because everything is interesting.
- 40:12SPEAKER_02: Uh, but yeah, no, I think uh we got some got some great insights.
- 40:16SPEAKER_00: Thank you for having me.
- 40:17SPEAKER_00: Okay, then my last question would be this.
- 40:20SPEAKER_00: Um From what I understand, you've been with OpenAI for like three years now.
- 40:25SPEAKER_00: And you already mentioned in the very beginning like how little of uh developer experience there actually was when you first started and how much has changed since.
- 40:34SPEAKER_00: What are some of the remaining opportunities that you still see for improvement in developer experience?
- 40:43SPEAKER_01: That's a great question.
- 40:44SPEAKER_01: So much.
- 40:44SPEAKER_03: Um ultimately, I think developer experience is like everything that needs to happen for developers to have this like magic feeling when they're using our tools, right?
- 41:00SPEAKER_03: And to me, um maybe in the past, developer experience meant this very precise playbook of like API design, SDK, docs, sample applications, demos, you know, all of that had to be ticked, you know, and we've tried to do as great as possible for all of that playbook in the in the era of Stripe.
- 41:19SPEAKER_03: But now it's like everything that um takes your idea into a product.
- 41:24SPEAKER_03: So that's why, even to me, ultrafast is part of the developer experience, right?
- 41:28SPEAKER_03: If I'm pairing with the model and if it's a frontier model and I'm in the flow, I'm feeling like I want to iterate on something.
- 41:35SPEAKER_03: I'm not sure what the end state should look like, but I have this nebulous idea.
- 41:40SPEAKER_03: I need the model to pair with me.
- 41:42SPEAKER_03: Well, now working with ultrafast is part of having this amazing DX.
- 41:46SPEAKER_03: It's like, wow, I I can in just a few seconds I see something appear on my screen.
- 41:50SPEAKER_03: I want that to be like now the way I interact when I'm in the flow.
- 41:53SPEAKER_03: Uh, but sometimes where I have to do a complete rewrite of a back end, I want to delegate that to codex in the cloud.
- 42:00SPEAKER_03: I no longer want to have my laptop open when I walk around for four hours.
- 42:04SPEAKER_03: This should be completely seamless in the cloud.
- 42:07SPEAKER_03: I can check on that later from my phone.
- 42:10SPEAKER_03: I don't need to worry about any of this.
- 42:12SPEAKER_03: The harness that's the codex harness that's open source.
- 42:15SPEAKER_03: We can let uh developers introspect it, look at it, but it's also the same harness we run locally on your codecs as in the cloud and giving Codex Cloud its own computer.
- 42:27SPEAKER_03: That's I think what we've reimagined recently.
- 42:29SPEAKER_03: We're in the early phases of that.
- 42:31SPEAKER_03: And I think that's kind of also part of the future of DX.
- 42:33SPEAKER_03: It's like maybe my best development machine in the future is just my phone, because I have Codecs in the cloud with the same harness, same tool, same context, same code base, and it has its own computer in the cloud to check its own work.
- 42:48SPEAKER_03: That's also part of the DX, right?
- 42:49SPEAKER_03: And then on top of that, it's the proactivity of the dots.
- 42:53SPEAKER_03: The dots actually being an extension of me, being the teammate that I have always on in the cloud, working with me and for me on these applications that I'm building, coming up with the new ideas, making the market research about what competitors are building.
- 43:08SPEAKER_03: And so to me, it's it's fascinating to see that the DX is like basically the model, the speed at which we're delivering them, also the cost and the token efficiency at which we're delivering them.
- 43:20SPEAKER_03: Because imagine we have these frontier, outstanding models, but they're expensive to run and you're not able to afford them.
- 43:28SPEAKER_03: That's impactful for the development experience because it means the DX cannot be the same for everyone.
- 43:32SPEAKER_03: So we're trying to also push on token efficiency for that reason.
- 43:36SPEAKER_03: And so it's all of the playbook we knew with the coding agent friendliness on top of that, to make sure that like everything that was in your way before, writing code by hand and all of this, that's all gone because it's taken for granted.
- 43:51SPEAKER_03: Then the coding agents will take care of most of that for you.
- 43:54SPEAKER_03: But it's also making sure that you can work effectively, either by yourself when you're in the flow or with your team.
- 44:00SPEAKER_03: Everything going from like how do you do codec codec code review or how do you harden your infrastructure with codec security?
- 44:08SPEAKER_03: Like all of these pieces to me have to all fit together in the sense of like, as a developer, it should be as seamless as possible to not just take my idea into a product that my customers love, but also making sure that I have all of these tools to make it better every day, more secure every day, more cost effective every day, and all of that.
- 44:29SPEAKER_03: So so much more progress to do on each of those, but we can start seeing the convergence of all of these bricks together now.
- 44:37SPEAKER_00: Well, uh, thank you very much.
- 44:39SPEAKER_00: Thank you for taking the time.
- 44:40SPEAKER_00: Uh a bummer that we didn't get to talk about Jolly OS and Jolly Book.
- 44:44SPEAKER_00: I saw that on your LinkedIn and I didn't even realize that was you too.
- 44:47SPEAKER_00: So maybe we need to have a follow-up at some point in the future.
- 44:50SPEAKER_03: We could, we could talk about that one for a long time.
- 44:53SPEAKER_03: But um, you know, it's funny because like you now that you mention it, uh I've actually been reflecting on that recently because I've worked so for context for the audience briefly, this was my first company back 20 years ago.
- 45:05SPEAKER_03: I was building an operating system for the cloud, and at the time, like HTML5 was very nascent.
- 45:10SPEAKER_03: Um, the Chromebooks did not exist yet, but this was this idea that you could buy an inexpensive laptop and just boot it to the cloud.
- 45:18SPEAKER_03: And the cloud would effectively be like where your apps live and where your data lives and everything.
- 45:23SPEAKER_03: Kids ask your parents about netbooks.
- 45:26SPEAKER_03: Yeah, yeah, yeah.
- 45:27SPEAKER_03: Uh netbooks are, yeah, we we used to uh they were like all the rage for maybe two, three years because the iPad did not exist.
- 45:36SPEAKER_03: Multi-touch tablets were not really a thing yet.
- 45:40SPEAKER_03: But we had these small laptops for 300 or so euros, so very inexpensive.
- 45:45SPEAKER_03: They were a very small phone factor, but they were shipping mostly with Windows XP, which was already no longer maintained at the time.
- 45:52SPEAKER_03: And so clearly there was the need for a new OS for this new generation of cloud.
- 45:57SPEAKER_03: But uh the reason I was reflecting on that recently is because when you when you see the progress with AI and the fact that like anyone can create software so quickly, but also this era of like personal software.
- 46:11SPEAKER_03: Like imagine you have an idea for an app for yourself.
- 46:14SPEAKER_03: Well, you would never build such an app back in the day because it would be like too much uh work hiring some developers and such.
- 46:21SPEAKER_03: But now, like a few prompts of pairing with the model like Sol or Astra, and you can just get your app up and running just for yourself.
- 46:29SPEAKER_03: So the idea of uh an OS that's kind of reinvented for each individual is now in sight, right?
- 46:36SPEAKER_03: You you could re-reimagine this like Joliclad, Jolie OS version again, uh, but with AI now.
- 46:44SPEAKER_03: But yeah, we can save that for the for our next discussion.
- 46:47SPEAKER_00: Will do.
- 46:48SPEAKER_00: Okay, uh, thank you so much.
- 46:50SPEAKER_00: Thank you for taking the time today, Omen.
- 46:51SPEAKER_00: It was really nice talking to you.
- 46:53SPEAKER_00: Um, and maybe we can repeat this at next year's uh developer event in whatever cities uh will find you next.
- 47:00SPEAKER_03: Amazing.
- 47:01SPEAKER_03: Well, thank you so much uh for having me.
- 47:03SPEAKER_03: Sorry, we meet each other in per in Berlin, but I'm glad we could uh we could do this today.
- 47:07SPEAKER_03: Thank thanks so much, and thanks everyone for listening.
- 47:10SPEAKER_03: Thank you.
- 47:11SPEAKER_00: Thank you, everyone, and bye bye.