OpenAI's Codex: This Model Is So Fast It Changes How You Code

OpenAI’s hottest app isn’t ChatGPT—it’s Codex. In the last few weeks alone, the Codex team shipped a desktop app, GPT-5.3 Codex (a new flagship model), and Spark, the fastest coding model I’ve ever used. Usage has grown fivefold since January, and over a million people now use Codex weekly. Codex was also the app that OpenAI chose to run an ad for in the Super Bowl. Dan Shipper talked to Thibault Sottiaux, head of Codex, and Andrew Ambrosino, a member of technical staff who built the Codex app, for Every’s AI & I about what OpenAI is building and how they’re using it internally. If you found this episode interesting, please like, subscribe, comment, and share! Want even more? Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: https://every.ck.page/ultimate-guide-to-prompting-chatgpt. It’s usually only for paying subscribers, but you can get it here for free. To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Head to granola.ai/every and get 3 months free with the code EVERY. Timestamps: 00:00:00 - Start 00:01:27 - Introduction 00:05:27 - OpenAI's evolving bet on its coding agent 00:09:42 - The choice to invest in a GUI (over a terminal) 00:20:38 - The AI workflows that the Codex team relies on to ship 00:26:45 - Teaching Codex how to read between the lines 00:28:45 - Building affordances for a lightening fast model 00:33:15 - Why speed is a dimension of intelligence 00:36:30 - Code review is the next bottleneck for coding agents 00:41:24 - How the Codex team positions against the competition Links to resources mentioned in the episode: Thibault Sottiaux: Tibo (@thsottiaux) Andrew Ambrosino: Andrew Ambrosino (@ajambrosino) Every’s vibe check on everything the Codex team launched: OpenAI's Codex App Gains Ground on Claude Code, GPT-5.3 Codex—The 10x Engineer, Now More Fun at Parties, AI as Fast as Your Train of Thought

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Speaker 00

  The first time I showed it to someone, they were like, no way. This is like a fake demo. Like this cannot be this fast. This will change everything, especially because it's not yet the fastest that we can actually get it to be.

• 0:11Dan Shipper?

  My experience was trying the app. I didn't really want to go back to a terminal. What I realized is actually GUIs are great, IDEs are just the problem. There's something that's a GUI for programming that's not an IDE. And it seems like you're figuring that out, but I don't even know what that's called.

• 0:25Speaker 00

  It's called a code exam.

• 0:44Dan Shipper?

  Dan here, and I want to take a second away from the episode to tell you about Granola. Granola is an AI note taker for your meetings, and I use it pretty much every day. That may sound a little bit weird or a little bit creepy, like transcribe all your meanings. Well, for me, it's actually kind of indispensable as a leader. Every is about 20 people now, and it's really important to me that I understand how decisions get made, how I'm showing up in meetings and how I can help my team the best way I can. Granola acts a little bit like a leadership log for me, so I can see how I've done in meetings, what situations came up in a particular week, and how I can do better next time. If you're trying to improve as a leader and scale your company, try Granola as your AI-powered notepad for meetings. Head to granola.ai/evry, code every, to get three months free. And now, back to the episode. Tebow, Andrew, welcome to the show.

• 1:28Speaker 00

  Hey, thanks for having us.

• 1:30Dan Shipper?

  Thanks for having us. Great, great to get to chat with you. So for people who don't know, Tebow, you are the head of Codex OpenAI, and Andrew, you are a member of the technical staff on the Codex app at OpenAI. And you are the people of the moment. They just ran a Super Bowl commercial about Codex, OpenAI did. How are you feeling?

• 1:50Speaker 00

  Yeah, that Super Bowl I was quite surprising, wasn't it?

• 1:53Dan Shipper?

  It really was. I think the core thing, and I think the reason, the place I want to start this conversation is It feels like that that is a strategic shift. You would expect OpenAI to have run a ChatGPT commercial during the Super Bowl. And maybe not, especially if you looked at Codex's positioning like three or four months ago for professional engineers, maybe not have run

• 2:19Dan Shipper?

  an ad targeted at a much more, at a much broader audience. It felt like for a long time, there was this divide where Codex was for professional engineers. And if you want to do vibe coding, you do that in the ChatGPT app. And it seems like that that has shifted a lot over the last like month or two. Can you tell me about that?

• 2:36Speaker 00

  Yeah, I think especially like in, you know, we can talk about last week, right? So like last week on Monday, we released the Codex app. Immediately, we saw like a ton of downloads, like more than a million downloads in the first week. And then we knew that we were releasing like an extremely strong model, like, you know, five, three Codex on Thursday. That just made, I think, this it very visible that, you know, we're here to, you know, put incredible experiences out there. We're very committed to Codex. And like also agents are really starting to work and be able to create these things, you know, even if you're like a little bit less technical. I think like the app really showed that, you know, it's like it's much more inviting for people to just try it and like, you know, run multiple agents.

• 3:16Speaker 00

  You know, with our models being like very, um, very good at sort of like allowing for multitasking and being reliable for long running, uh, long running sessions. So like allows you to create a lot more. So it just felt that, you know, maybe we can inspire more people to build and then show that agents are here, right? It's like, it's not, it's coming, it's going to be mainstream. You know, why don't you try and like create something new and, you know, inspire people? I felt like the right thing that we wanted to reinforce.

• 3:44Speaker 02

  Yeah, wh- while we were designing and developing the app, one of, one of our like internal mandates to ourselves the whole time was that we had to make something that we love to use and that we used for like all of our work. And if we couldn't do that, then we weren't going to put this out. And this was back when we started. And I think that we surprised ourselves a lot with how fun it was. And especially as we started to build this app. Before we started to build agent skills. And then, once we kind of paired them together. It became this really rich, interactive experience where you could open the browser. Or you could connect to these various services. And so all of a sudden, we started to feel this like really connected, interactive experience.

• 4:29Speaker 02

  And wanted to share. Like, I, I kind of see the, the ad as like a, a love letter to builders, right? I have never seen a Linux CD in a Super Bowl ad. And so, you know, like, that was really cool to watch.

• 4:44Dan Shipper?

  What, what was the impact of the ad?

• 4:46Speaker 00

  We're still to measure that. We'll see like, you know, how, how it plays out over the long term. But we saw a giant surge of traffic, actually, like remarkably, like, you know, very, very quickly after 4pm, like PSC, when it aired. Like the surge and like our systems were like under heavy load. So it was, it felt kind of weird to me, like, you know, people are watching the Super Bowl and then going and like, you know, installing the app. And they're just like trying it out right there and then. But that, it happened. And a lot of, a lot of people reached out and like saying they were really inspired by, by, by it. And just wanted to build afterwards, which is, you know, what we're like aiming for as well.

• 5:25Dan Shipper?

  Timmy, back, I, I still want to talk a little bit about the, the strategic shift. So Codex app moving from, or Codex in general, moving from something that is really for professional developers, moving to something that has a more, a broader audience. And, and, and maybe moving some of the vibe coding from ChatGPT into the Codex app. Tell me about that.

• 5:46Speaker 00

  I, I don't think we're trying to move vibe coding, you know, from, from ChatGPT into the, the Codex app. Like, we're very much, you know, two things are happening. Like, one, we're pushing the frontier on like professional software development, like five, three Codex, like beats every single other model, like on the top benchmarks for coding. So it is a very, very capable model. And, you know, it's also like. At the, at the speed and cost, it's like, you know, it's, it is a top performer out there. I think the app, the second thing is like, the app does make things more accessible. And so like, it does appeal to like a wider audience. But internally, we're also seeing the app, you know, just, it is very much used within research, within our own team, like the entire Codex team uses the app. It makes people more productive.

• 6:29Speaker 00

  So it's like very much leaning in into, you know, how we think agents are best used. The patterns that we were seeing, you know, that we're making people like very uh productive here at the company and outside. And then it's just sort of like going all in on that. It does happen at the same time also, it's like, hey, it's just delegation is finally here. It works, you know, and it's like much more accessible. And we're gonna try and see like how we can package that and actually ship this to like, you know, much, much wider audience. But that's, that might not be the Codex app.

• 6:59Speaker 00

  You use that all the, it's like you just build in there.

• 7:01Speaker 02

  Ninety-nine percent of the code that I write is using the Codex app.

• 7:05Speaker 00

  Same, I mean, I live in there now.

• 7:07Speaker 02

  Yeah.

• 7:07Dan Shipper?

  Um, okay, well, that's, that's actually really interesting. I, I definitely want to talk about the app in particular, but I want to go back to the thing you just said, which is, um, maybe if I, if I'm reading you right, you're, you're kind of like, we're pushing the frontier. We're seeing lots of people who are um maybe broader than just like senior engineers using this. However, the overall idea of like, who is doing what in which app? Like, maybe you haven't totally figured out yet and it's, it's not as clean of a line as like, no longer vibe coding and chat GPT are really vibe coding in Codex. It's like, you can do it in both, but we haven't figured out exactly like which thing you're gonna do where.

• 7:45Speaker 00

  Yeah, I, I think. Codex is like the most powerful experience, right, out there? So you, you should be fairly technical so that you understand like, hey, you know, code is actually getting written, you know, it's gonna get executed on your machine, by default, it's executed in the sandbox. Um, but you should probably be able to read code uh in order to use, you know, Codex to like its, its fullest. We will bring a similar experience to chat G P T at some point, which will have like different uh properties in terms of like the sandbox and like how concepts are represented. Maybe we won't be showing like, you know, hey, it's like this scary terminal command like thing is like running and you know, you should probably approve it. It's like, you know, of course you shouldn't do that to someone who is not technical.

• 8:27Speaker 00

  And Codex is really there to like appeal to, you know, it's just all coders, builders, you know, technical, like people who are close, like either technical themselves or like technical adjacent, you know, like data science, these kinds of things.

• 8:41Speaker 02

  Yeah. And you know, if if you use the Codex app for any amount of time, you can see the inspirations from chat. You know, the layout's very similar. We auto name your your conversations. We've got contextual actions, but it's pretty clean, right? The composer looks very similar. Um, and you'll see some of that inspiration back in chat for for other types of things. Um, but we we still believe that uh some, you know, when we set out to make something that was for the professional software developer and for us, that it deserved a dedicated experience that could could really showcase the power of the models and the way that the models could change the development lifecycle. And so we, you know, we made something very tailored to that.

• 9:25Speaker 02

  Um, and we've we've had a lot of success internally with research teams, with product teams. Um, and so, you know, we're we'll look beyond, but I I think we're really happy with where we've ended up on that kind of tailored, the tailored approach to this.

• 9:42Dan Shipper?

  Can you tell me about the decision to invest in a GUI over a two E? I feel like two E's are are so hot right now and obviously you have one for Codex already. And you you could have said, okay, we're gonna double down and and just make the make the terminal terminal experience even better than it is now and really invest in that versus, okay, we're gonna go. You know, I think uh yeah, making GUI is a little bit of like a counterintuitive or uh uh like counter narrative thing to do. So tell me about that decision process.

• 10:12Speaker 00

  I think it wasn't counterintuitive, it's more maybe it's not mainstream. And so we we experiment with a lot of different approaches, like I very much consider that we're still in the experimentation phase. Uh, and you know, we're responsible primarily for two things, it's like, you know, building the most powerful entity out there, you know, that's capable of coding. And then, you know, increasingly, this will become like a multi-agent system and it will become like more and more capable and, you know, you will have to figure out like how to steer and supervise, like its outcome and its behavior, you know, that's like one thing that we're building. And then we're also building like how you even, you know, interact with this, it's like, you know, what is the optimal way to have visibility into what this like very capable entity or like system of entities is doing?

• 10:56Speaker 00

  How do you steer them? How do you supervise them? And so we we're very much still experimenting with what that is, it's like, you know, sure, you can do it in the two E, it's like, at some point, it starts to feel like very limiting, you know, especially on like multimodal, like, you know, actually, like the models can like draw little diagrams and generate images and, you know, or, you know, you can talk over it, you know, using voice, um, maybe you have like many of them going in parallel and so you start to lose track. So we felt like we needed to start experimenting with something else. And it is only when, you know, we started to become like super, super popular internally, we were like, we have to ship this externally, like this is kind of like, this has come to a point where it's like too good to sort of like just keep it to ourselves. Um, I mean, that was like the journey that you went, you know, you were now building in the app.

• 11:41Speaker 00

  Uh, although like, when did you start building in the app? That was actually like fairly quickly, like when the app was building itself?

• 11:46Speaker 02

  That that was, yeah, that was pretty quickly. And yeah, because I was starting with the two E and with the the IDE extension. And I think that my goal personally was how can I get to fully building the app on the app as fast as possible? Right? It's like, it's really easy when building this stuff to slip into the mode of like, oh, this will be good for somebody, like somebody would love this, a certain type of like, they will love this, right? So we really wanted to get quickly to like, I want to be able to build the app on the app. I wanted to be able to run itself with skills. I wanted to click around on the app. It spawned and I I want this to be like part of my workflow as soon as possible.

• 12:27Speaker 02

  And there like I I still use the two sometimes when I want to fire something quick, but I think that like there is something about the flexibility of controlling UI and being able to have some pains be persistent and others be ephemeral. And be, you know, we're we we shipped voice with the app, so you can prompt with with voice. We have mermaid diagrams in the app. We have full image rendering. So all of those things I think are like the tip of the iceberg and what we want to do with a dedicated UI. And it's it's pretty simple and it's simply intentionally, but I think we're going to do a lot with dynamic stuff there.

• 13:08Speaker 00

  I mean, yeah, the the ceiling is just much higher.

• 13:11Dan Shipper?

  Yeah, it's interesting. My experience was trying the app, trying the app. I didn't really want to go back to a terminal. And I had been coding most mostly in Claude code and and some and some codecs in the terminal for the last like for several months before that. And I think what I realized is actually GUIs are great, IDEs are just the problem.

• 13:36Dan Shipper?

  And like there's some there's something that's a GUI for programming that's not an IDE. And it it seems like you're kind of in that figuring that out, but I don't even know what that's called.

• 13:46Speaker 00

  It's called a codec sound.

• 13:51Speaker 02

  You know, there there there was a moment during the development of this where everybody and their mother was forking the same IDE. And we we kind of looked at each other and we were like, hey, should we have done a fork of VS code as well? Like it like very seriously, I I remember exactly which day it was. And I think. I don't know if I I don't know if I would say that IDEs are the problem. But I go back to like the truck analogy sometimes with them, which is that like I will open an IDE here and there. Like I opened one today.

• 14:31Speaker 02

  Um, it was something very specific that I wanted to do that, um, I don't even remember what it was. But then I closed it and I went back to using the Codex app. And I think that there there is something there with like the Codex app being a great um, daily driver. And like occasionally you need an IDE or occasionally you need like a really complex terminal setup. But that this should be your home base, it should be your command center for the agents that are running and a place that you can come back to and track all this stuff. And you know, there are a lot of uh, design decisions around like, do we allow free form panels like an IDE? And we kind of came to the conclusion that a lot of what these models are great at. Is knowing what is needed in the moment for what type of task.

• 15:17Speaker 02

  And and so we wanted to have kind of more full control over what was able to show at what point, right? And you can see that in plan mode where you're not necessarily getting a composer, you're getting a really quick way to answer questions. Um, you can, you know, and you've got your plan and you can edit your plan and um, I think we only want to do more with that as we go.

• 15:40Speaker 00

  It seems like you were surprised that you didn't want to go back to the the two year after.

• 15:46Dan Shipper?

  I was.

• 15:48Speaker 00

  Yeah, is that?

• 15:51Speaker 02

  Were you like a a like, like Greg, Greg did an interview and Greg was like, I'm a two E power user. I thought I would never leave the terminal.

• 15:59Speaker 00

  Yeah. Greg lives in Emacs.

• 16:01Speaker 02

  Are you like a?

• 16:02Dan Shipper?

  I was a two E power user for like six months, starting with, starting with like when Claude Code first got really good. And I was like, holy shit, this is so much better than being cursor or WinSurf or whatever. And now I feel like we I speed, I speed ran my two E era and now back in back in Gois. Like I'm I'm kind of flipping back and forth right now, but I can, I sort of see the light where um. It just, if you're, especially if you have a bunch of them going at once, the affordances of GUI are just like, make it much nicer.

• 16:30Speaker 00

  Yeah, and there's a lot more to come there. And it was a very intentional thing for us. Like, we sort of see, you know, agents will act and are already acting on like much more than code, right? And so they need to be a companion, you know, to like every single app and every single thing that you can do on your computer. Um, it's like we integrate with like linear Slack and you know, of course, you know, also need to be able to like, you know, read the code and like produce code, but maybe, you know, it can do like a deploy through your cell as well. Like, are you going to do all these things from the IDE? That would sort of like feel very odd. Um, and so it's like, it's like this command center for your agent.

• 17:10Speaker 00

  We optimize the entire experience around that, you know, around the idea that you have a very capable, intelligent entity that you're like controlling, steering and supervising. And you know, you, you never need to like, sort of like go in there and like, you know, do the things yourself. It's like, you know, the thing is very capable of like, you know, being delegated to. Like, I think, you know, when, when you accept that that is like, you know, what we're headed towards and like, you know, with five to codex is like, you know, it just feels like, you know, we're getting like almost there, right? Then you're like, well, you know, it's the same with, with you, right? You know, like when I talk to you about like a feature idea or something, it's just like, you know, there's, you know, you go and you get inspired and you go and do it. It's just like, you know, I don't suddenly jump into your IDE and like, you know, just go and like implement it.

• 17:55Dan Shipper?

  You could.

• 17:55Speaker 00

  Yeah, I mean, I think you would find it disturbing, right? It's like, I mean, so that's the way that you will, you know, everyone will work with agents. It's like, you just talk to them.

• 18:06Dan Shipper?

  How has your, your workflow changed with five three codex versus five two?

• 18:10Speaker 00

  I was surprised at how much faster it was. Um, and sort of like I had to adjust on, I had been optimizing a lot more for like long running, sort of like multitasking. Um, and you know, I sort of like had an explanation of like, okay, this type of task will take like, you know, 10, 15 minutes. I'm going to kick like, you know, four, like, you know, different things and then come back. So. I'm able to like, you know, maybe do a little bit less multitasking and like, you know, be more in the flow. So that, you know, felt really good. And then it just feels now very satisfying as well, like, you know, to kick off like automations with it, using skills. It's like it's it's a more generally capable model. It's like less sort of like

• 18:51Speaker 00

  super focused on code, right? And so I find it like much more reliable, like, you know, sort of like going through like Twitter replies and like, you know, summarizing like the important themes or like filing bugs in like linear and then, you know, coming back to that and using automation so that, you know, things are like implemented like daily. Um, feels it's like much more robust for these things. Um, I mean, but you're really like the superpower user here. And there's like, you know, it's just like the kind of stuff like, you know, he does is just like, you know, it's like, I have very vanilla usage of Codex compared to Andrew.

• 19:24Speaker 02

  Uh, no, I mean, well said. Um, I had a a series that I I had intentions to run this for a while and I only ran it for three days on on on X Twitter. Uh, which was that I was I was setting up a prompt to basically add a feature to the Codex app, like some random like non-shippable feature to the Codex app. I had this long prompts like about the the quality bar that we had to do. And um once I switched it to five three Codex, the results got actually much more interesting. Like we did a Subway Surfers panel on the right was one of them. Um, like a little Minecraft UI for the subagents was another one that we did that, I don't know, maybe, maybe we'll ship it.

• 20:07Speaker 00

  I was like, get back to work.

• 20:09Speaker 02

  Yeah, yeah.

• 20:11Speaker 00

  Why do we have Minecraft in the Codex app now?

• 20:13Speaker 02

  Yeah, but uh, can explore. No, I mean, five three Codex, like it's it's it's neat. It's fast. It's capable. It's multimodal. Um.

• 20:26Dan Shipper?

  What are, Tebow says you have a lot of cool use cases, like what are, what are the like more interesting ways that you're using like the Codex app that? Maybe people should try but haven't thought of yet.

• 20:38Speaker 00

  Andrew came up with automations and I think that's sort of like shifts the way that you know you're thinking about these things when they can just like sort of like hop it in the background, you know, on a specific trigger at a specific time. And then, you know, just you can sort of like program it yourself.

• 20:53Speaker 02

  Yeah.

• 20:53Speaker 00

  You're using that a lot.

• 20:54Speaker 02

  There are a lot of things that I use um the app for that are a little bit outside of just like coding features. Um, I keep it to uh, I, I use it to keep my PRs mergeable with automations. And so it'll resolve merge conflicts, it'll keep them updated, it will fix like build issues so that basically like as soon as they're ready to go, like they're ready to go. There's no like, oh, hey, somebody merged a big thing and there's a conflict now. Um, so I do that.

• 21:22Dan Shipper?

  So you said like, so at what point is the, is the automation trigger? Cause I thought the automation triggers like at a certain time schedule, but it sounds like there's other triggers I didn't know about.

• 21:32Speaker 02

  Um, I, yeah, I, we're looking at a lot of things. I have it right now just on a time schedule. And I use our GitHub skill and um some internal skills for our CI. And that, that runs hourly or every two hours and kind of just cleans everything up.

• 21:49Dan Shipper?

  I see. So it's like through all, you know, if there are any changes on main and it just looks through any PRs and just like make sure that they're all up to date so that whenever you're ready to go, it's never like, that's actually, that's good. I like that.

• 22:00Speaker 02

  Yeah, it's, it's actually really helpful. It's surprisingly helpful. Um, I have one that every day at like nine AM, uh, I get sent all of the contributions that have merged to the Codex app over the last day. And so it'll do like a nice report of who merged what and it will um, I have a group it by theme. So I can be like, all right, like three people worked on this part of the composer, two people worked on automations, like here's what happened so that I can at least be like knowledgeable what's happening, because things, things get chaotic uh uh, right before launch and yeah.

• 22:38Speaker 00

  One automation I have is uh, it's I, I run it like multiple times a day and it's like pick a random file and uh, find and fix like a subtle bug.

• 22:49Speaker 00

  And then it's kind of funny because it actually does pick a random file. Uh, so it will run like, you know, Python like random and then it will like, you know, find a random file and it will start from there. And so it's like every time it sort of like explores like a new one.

• 23:03Dan Shipper?

  Has it caught anything?

• 23:05Speaker 00

  Oh, yeah, yeah. It was like we, we catch like, it's often latent bugs that, you know, are not triggering actually like on the critical path, but you know, they're actually bugs. Uh, and then, you know, just it's like trivial to fix it, like merge it, um, takes very little time. And it's a thing that, you know, I would have never found myself, uh, find like an issue and I constrain sampling like the other day. Yeah.

• 23:26Dan Shipper?

  That's really cool. Do you have other, other automations that are worth sharing?

• 23:31Speaker 02

  Let's see. I feel like I have sixty that are running at all times.

• 23:36Speaker 02

  Some for testing and some for real. Um, some of the members on the team really like this one. That looks at the PRs that you've done in past day or so and quietly cleans up any bugs you shipped.

• 23:50Speaker 02

  And kind of like looks at a few of the observability platforms to see and, and like tries to basically ship a fix before anyone's noticed that you shipped a bug.

• 24:00Dan Shipper?

  That's cool.

• 24:00Speaker 00

  Everyone is not coding related, which is like marketing research. It runs daily and it's just sort of like it's, uh, prompted with like a specific skill to do like a deep marketing research, um, which I've like sort of like tuned over time. And then that, uh, just goes and like searches the web on, you know, any sort of like new things that sort of like came up. Terms of like how, you know, just like how users are like receiving, talking about, uh, Codex. And then I just received that little report, um, and it always makes for like an interesting read. Um, yeah. We can just go on. It's like, these are just examples that, you know, we do rely on, you know, they run. Yeah.

• 24:36Dan Shipper?

  Yeah. Do you have any particular skills that you guys? Like that are beyond the normal kind of, you know, I have a GitHub skill and that, that kind of stuff.

• 24:47Speaker 00

  I love Andrew's, uh, yeet, yeet skill, which, um, it just like takes like the change and then, you know, does the commit, does the PR writes like the draft. Um, that puts it in draft and like, you know, publishes a PR with like a, a PR title and, and body.

• 25:03Speaker 02

  Yeah, it's very satisfying.

• 25:04Speaker 00

  Uh, yeah, it just does everything. Um, that one is like makes, definitely makes people like productive. What are the top use ones for you?

• 25:13Speaker 02

  Um.

• 25:15Speaker 02

  Image gen is a cool one.

• 25:16Speaker 00

  Yeah.

• 25:17Speaker 02

  Um, for both like silly automation purposes, like, hey, make me an image that characterizes my last day of work. Um, not my last day of work, my previous day.

• 25:28Speaker 00

  Yes, yes, yes, Andrew.

• 25:31Speaker 02

  I, you know, the, um, the image gen skill was actually really cool. Uh, for I, I used the Codex app to make a book for my daughters. Um, and so I had, I like, you know, put together this prompt for teaching it about like a script that I wanted written. So like twenty four pages, here are my daughter's ages, here's like where we've lived in the past, like we were in Boston and moved to New York and then moved over here. Um, and then I said, like, after that, we went through that, I agreed on the script and then we went through and I, I said, like, all right, now it's time to use the image gen skill. And it made, um, like it prompted for every page in the book based on the script.

• 26:12Speaker 02

  It prompted for the image and then it kind of put them all together and use the PDF skill to put together the book's PDF. And then I printed it. Um, and so we've got like a super custom book that, you know, I read to my kids and it's, it's really cool.

• 26:26Speaker 00

  It's just this awesome thing when you can combine like the intelligence of like the agent and then it's like, like works in a programmatic way, like known by using skills and then you can just combine them in like novel ways. So like, yeah, I think the, the PDF and image gen one is like, uh, it's a common combo that we see.

• 26:45Dan Shipper?

  It feels like the Codex model, it obviously it's got faster, which makes it much more usable and, and it also feels a little more obacy, like it's a little more, has a little more emotional intelligence, but it still has a little bit of that, like, it does exactly what you say thing in a way that is a little, it can be annoying. How, how are you guys thinking about how you shape the way the model feels and which way you're pushing it?

• 27:09Speaker 00

  It's something that we obsess over, so we we definitely want the model to excel at coding and be really good at instruction following. At the same time, when we optimize a little bit too much in that direction, it can like over index on like, you know, specific words or, you know, sort of like misunderstand the intent, you know, in ways that, you know, humans wouldn't.

• 27:32Speaker 00

  Like, sometimes I will just like have a typo and then, you know, the typo like, you know, actually find its way into like the file and I'm like, you know, obviously, you know, I didn't mean like, you know, the typo is like, you know, I meant like this name of this class. So that's something that we're, you know, definitely continuing to push on. But like the thing that we're pushing on the most right now is like really efficiency, you know, speed, and then also like what we now refer to as like personalities, like, you know, how supportive is it? And then we understand that not everybody has the same preferences there. Like the previous default, you know, was definitely like super blunt, like pragmatic personality. Now we've also introduced like a more supportive, like friendly personality and you can just pick between those. And I think for things that don't have like sort of like a

• 28:16Speaker 00

  universal, like, um, accepted, you know, thing that, you know, everybody that, you know, should just use is that, you know, we're probably going to introduce like some way for you to just make it your own, right? You know, you should feel like you have your own little personal codex, um, that, you know, works in exactly the way that you want it to work.

• 28:35Speaker 00

  Do you use the friendly or the pragmatic one?

• 28:37Dan Shipper?

  Pragmatic.

• 28:37Speaker 00

  Pragmatic. Yeah, okay. I'll say it's pragmatic.

• 28:43Dan Shipper?

  Interesting. I think, um, you guys recently put out a model that is so fucking fast. I was testing it before it came out and I was just like,

• 28:54Dan Shipper?

  I can't, I can't really keep up with this thing. So I'm curious how that changes, how you think about,

• 29:01Dan Shipper?

  what is now possible with coding with a model like this and also the affordances that you need in order to manage models that are so quick effectively.

• 29:09Speaker 02

  Yeah, the first, yeah, the first time we used this model in the app. We had kind of that same thing happen where all of a sudden there was just like this wall of text and we were at the bottom of the scroll. And we were immediately like, all right, we need to smooth this thing out, uh, coming in. And so we actually do slow it down. Ever so slightly, just so that you can see the words come in like a little bit smoother.

• 29:33Speaker 00

  That's so funny.

• 29:34Speaker 02

  It's, it's like a really funny problem, um, but this thing has been super fun. And I think. I think what I'm most excited about is what sort of capabilities we can start to add to the app that are really, really dynamic. That we couldn't with a model that wasn't this fast. So yes, this model is going to allow you to iterate really, really quickly. But it also opens up a lot of new opportunities to how, like how you code and how you interact with the Codex app.

• 30:06Speaker 00

  Yeah, the, the first time I, I showed like the, the, the very first prototype, uh, when we hooked everything up and like, you know, obviously like the model is like powered by, uh, Cerebras. And it's like, you know, we've talked about the, the partnership there and like, we're very excited to put like, you know. The first model that we're serving through that, uh, you know, there like it's, it's, you know, obviously like, uh, still like very early is it's like literally the first time we hook it all up. And, uh, we're just like so excited that we want to share it. But the first time I, I showed it to someone, um. They were like, no way. This is like a fake, a fake demo. It's like, you know, this is not real, like this cannot be this fast. And then they tried like a few prompts that were just like.

• 30:52Speaker 00

  It's just like, oh, I could just, I literally cannot keep up. It's like, this is insane. Uh. And yeah, I think this will change, this will change everything, especially because it's not, it's not yet the fastest that we can actually get it to be, um. Like with the preview, we're putting it out like, you know, quite early, we're actually going to layer a number of optimizations on top of it, uh, which should be able to like make it, you know, maybe two to three X faster than the experience that you have experienced. So that's going to change things and we're thinking about this also from a point of view of like delegation, you know, like we think this model has a huge role to play um as part of like a system of like, you know, multi-agent systems.

• 31:32Speaker 00

  And as a way to like speed up, you know, maybe the the slower, more intelligent agent as well. Uh, so we're going to be experimenting that uh in that way.

• 31:42Dan Shipper?

  Hmm. And do you do you expect the same hardware speedups on like the more intelligent agents to come out soon?

• 31:50Speaker 00

  Um, so we, a lot of the things that we worked on were interesting, so like distributed systems and like infra problems that we uncovered because the model, we were able to sample from the model at like unprecedented, like unprecedented speeds, right? And then if you're, if you're getting tokens back this fast, you need to go and like optimize, you know, the entire set of bottlenecks that you sort of like uncover on the critical path of serving. All of those benefit, you know, like the current, uh, they benefit like GPT five three codex and like, you know, all future models. And there's one thing that we've been doing as well, which we're, I'm sure we're going to put in like a more detailed blog post at some point, which is

• 32:33Speaker 00

  we wrote the entire server stack to be based on like web sockets and like a persistent connection and to do things like a lot more incrementally and like statefully. And that decreases like the overall latency, like, you know, across all models, like we haven't chipped it by default yet, but it's, you know, it it is something that, you know, we are making the default for uh this new like super fast model. And then we're also going to enable like on the other models and like it makes things uh decreases like overall turn latency by like something like thirty, forty percent. Um, I can. Uh, we can look into the exact numbers like.

• 33:05Dan Shipper?

  Yeah. What are the most surprising things that you've seen using the model internally in terms of like what a, what a speed, speed up like this enables?

• 33:14Speaker 00

  It, it just allows you to be super, super in the flow. Um, and you know, it's just, you're almost like just in real time, you know, sculpting the experience or like the code. Uh, it's just a very different feel to it. Um, it's, it's very unsettling at first and then, you know, and then once you get into it, it's very hard to go back to any other model. Uh, that's like the feedback that we've seen. That's like what I have felt myself. Uh, and so it's, it's like this very. It, it, it takes like five minutes to adapt and then, and then you're sort of like, no, okay. It's like, this is how I'm going to use this thing.

• 33:48Speaker 02

  Yeah. I also don't think that we've poked at the full extent of what we could do with it.

• 33:55Speaker 00

  Yeah.

• 33:55Speaker 02

  But it's very early. We haven't had it for very long.

• 33:58Speaker 00

  Yeah. Someone on the team like Channing was just showing like, oh yeah, it's so fast and it can actually like play pong, you know, not very well, but.

• 34:06Speaker 00

  The model is able to react to things like, you know, almost like real time, right?

• 34:10Speaker 02

  It, it like, you start to see how it might replace some deterministic steps. So we have, we have in the Codex app, a, a set of Git actions, right? And as everybody knows with Git, like certain configuration of things or certain states that you can be in. Can make it really hard to run those without a ton of error handling and like all sorts of like error messages and guidance. And it's really hard to create a good Git experience, which is why like nobody ever has.

• 34:43Speaker 02

  But if you have a model that's as, almost as fast as running these scripts, then you can imagine a world where these things turn into skills or something like that. And you can have your operations run a little bit differently with some, like some intelligence. And, and not have the same latency that you have today when you're asking it to go track something down the code mix. Right? You can kind of like vaguely gesture and be like, hey, like send this up and, and have that be fast enough for, for a button.

• 35:15Speaker 00

  What I'm very excited about is like when it's gonna come together with, you know, one, one thing that we shipped with five, three codex as well as like this thing. That we call like midterm steering, you know, where you're, you're just, you start with your prompt, it's like it, it got to work and then you send another prompt like. While it's still working and it adapts like in real time as well, like it will just sort of like receive that message. Acknowledge it and then, you know, continue its work. Like if you start to think about, okay, what would this look like with voice? And then with a model that is as fast as the one that we just shipped, uh, then. That's like a whole other experience that, you know, we would be very excited to bring, um, you know, hopefully very quickly.

• 35:55Dan Shipper?

  Hmm, because you can easily interrupt as you're.

• 35:59Speaker 00

  Yeah, if you're, if you're just talking and engaging with like, you know, lateral language and then doing the midterm steers. And then the, you know, implementation happens like almost, you know, instantly. Cause of this speed is like, it becomes like a very pleasant thing to use. Like right now, you can sort of emulate it, you know, with like voice, uh, voice dictation and then send it and midterm steering and then, you know, watch the model implement and it's like a very cool thing. I think we're gonna have a step change in that experience when we just like really just polish it.

• 36:30Dan Shipper?

  If speed as a bottleneck is like. Close to being solved, what do you think is the next bottleneck? What is the next limit on making the thing you want?

• 36:40Speaker 00

  Uh, the, the bottleneck that is very apparent is like, you know, how fast can you verify that, uh, things are correct?

• 36:49Speaker 00

  So like we, we, I mean, we can generate like code faster than ever before, uh, we can implement entire features. And, you know, we like, I saw like someone just. Based on a description of, you know, the codex app, if you sort of like synthesize that into a plan. Uh, just based on screenshots, like the models are very much capable of like reproducing ninety-five percent of the features and just rebuilding the app from scratch. Um, now is it going to be bug free? Is it going to, you know, is everything like implemented to like, you know, perfection in the same way that, you know, the actual app is? It's like that takes like a lot of time still, you know, for like a human to go and click and verify and, you know, make sure that. Um, you know, it's like, it's the designs are like consistent and to that, you know, there's like no bugs here or there.

• 37:33Speaker 00

  Um, that the settings panel, like, you know, when you click that button, it actually does the thing that you expect. I think verification, you know, definitely becomes a bottleneck. Like we have people on the team like complain, you know, like. Just too much code to review, it's like, you know, that's what we're trying to solve for.

• 37:49Speaker 00

  I mean, you you complain about that.

• 37:50Speaker 02

  I complain about that. There's so much code to review now.

• 37:55Speaker 02

  Both that like co- like on your own machine and like from another peer, it's it's like. We're gonna have to figure that out.

• 38:02Speaker 00

  Yeah, you're already reviewing, you're reviewing the code the first time because the agent is just presenting it to you and then you have to review, you know, the code. Produced by your peers, you know, who are like. There's like these two rounds of reviews and.

• 38:16Speaker 02

  Yeah, I mean, this is something that we're working on. Uh, a lot of us still do have to review code. And we want, you know, we're taking a look at what that experience should look like with the model involved, right? Um, we've got a review mode in the Codex app that works really nicely and kind of annotates your diffs on the side. With findings and stylistic things and. Lots to do.

• 38:41Speaker 00

  Yeah, it's one thing I'm I'm sort of like also excited like about, you know, like making the models faster and then this like, you know, this one that we just put out, it's like, you know, which is. Mind blowing and fast, it's like you can also use it, you know, you can imagine using it like. In a way to understand code, understand features, um, you know, helping you with code review, like helping you understand like, you know, the code that. A peer wrote and it's it's like. Much more pleasant because this is something that you wanna do, like, you know, you wanna be. There in the flow, it's like something that has to be like synchronous, uh, it's not something that you delegate, you cannot delegate understanding, right? It's like, you know. You're trying to like, you know, get to. Uh, understand something and so like speed there like is a real advantage, so it's sort of like. Helps offset as well, like, you know, the fact that.

• 39:24Speaker 00

  Models are like producing more and more code is like, you know, speed helps you understand, you know, this code faster as well.

• 39:30Dan Shipper?

  Yeah, I mean, I definitely think, I I I've found this already with this with this new model is. Speed, especially for end to end to end testing is faster, because if you're having it do end to end testing, like manual integration testing. Often there's like a toast that pops up and it pops up for like a second and if the model's not fast, it's not gonna. Get it. Um, and it seems like it's better for that, because it it it the cycle times are much much shorter, so I'm and and I definitely find this too, it's like. I can produce so much code, but when I see a PR come in or when I make a PR, the my first question is like. Is there evidence that you've actually tested this and this actually works like not just unit, it's like you've gone through it by end to end?

• 40:13Speaker 00

  How do you, how do you handle this?

• 40:16Speaker 02

  I mean, I've seen a lot of PRs that I have the same question about. It's like, it's so easy to, to code things now, right?

• 40:25Speaker 02

  Yeah, I mean, I, we have gotten the Codex app to be pretty good at, through some skills that we have of running itself, clicking around, screenshotting itself for evidence and uploading it to the PR. There's, there's like a lot that's pretty interesting there, especially when we make this like more async, or when, you know, the models get really fast at this stuff, like, I don't know exactly what it looks like yet, but there is a lot there around like, hey, here's a bug fix, this is exactly like what it looked like when it was happening. And here's exactly what it looks like now with the same exact click path. And so, like, maybe that's the turning point that code review becomes

• 41:10Speaker 02

  less important, when it's like you can verify that part instead, so you have to kind of like, do less through the code as a proxy. But there's, there's definitely more to explore there.

• 41:21Dan Shipper?

  Last, last couple of questions. I'm curious, what have you guys learned from API and Claude Code? Claude Code and how do you think about your positioning in the market versus them? Like, how do you think about the differences?

• 41:34Speaker 00

  I, I think they were first to put something out there and that was interesting to us because we had been working on similar ideas for a bit. But I think our models were a little bit at the time not ready, like, you know, they were not like reliable, like, on long horizon tasks, like, you know, they were not able to like do like reliable tool calls and, you know, stay on topic. And so, as soon as like, we started to really invest on that and, you know, especially with GPT-5 is like, you know, we were like, okay, the models are there. We know how to make them even better. Five two like brought, you know, even like better like long context, long horizon, like reliability and on context understanding.

• 42:18Speaker 00

  And what we were seeing is that Anthropic was sort of like, you know, to us, like, losing a little bit of steam when it came to the model. And we were in this fortunate position where, like, the way that we run Codex is like, you know, we've got like product, we've got engineering, but we've also got research. And we're just like all work together and sit together and solve problems together. And it's like a highly creative space where, you know, at times we decide to like solve problems in the product, in the harness, but at times we also, we're like, hey, how can we actually improve the model? And like, let's just, you know, talk about it and like, you know, idea together. And then like, research will come and be like, hey, you know, we've got this like picture that we're sitting on. It's like, would this be like, sort of like something that we can ship? And then it was just sort of like, I get excited about that.

• 43:03Speaker 00

  One of the examples was, we had a lot of complaints on compaction. Um, you know, compaction was like, something that people felt like, whenever you would hit compaction, you know, people would complain, it's like, it's losing too much, uh, context. And so we sort of like solved that, uh, end to end. And like, you know, we decided to do like, end to end RL training and, um, you know, introduce compaction like within research and then, you know, make the model like, you know, itself like, you know, very familiar with the concept of compaction and like producing like optimal, like sort of like delegating to itself like across time. And, you know, once we had that and we had solved it at the model level, like sort of like the harness problem became like so much easier because it was just like, oh, just let the model do it and it's going to be like very reliable. So through that and like through that collaboration, it just felt like,

• 43:49Speaker 00

  like the momentum has been like very strong and that we're so like able to improve like models and like, you know, ship a model like roughly on like on a weekly, a, a, a monthly cadence. And then we took like a bit of a different bet and like a different approach with the Codex app, which turned out to be like, you know, an awesome thing, you know, to just try and do is like, and not just like sort of like force ourselves, you know, and like trying to cram everything into the tool. I mean, it was like, it was like a great challenge, right? You know, you were like, I'm really, it's like, let's build an app, like, just like, where do I get started? And then, you know, just like, you just got obsessed by it.

• 44:23Speaker 02

  It's hard not to.

• 44:24Speaker 00

  Yeah. I mean, it's like, how was it to just like, you know, build something that was quite contrarian, I, I suppose?

• 44:33Speaker 02

  Yeah, I mean, I remember you and I talking about whether or not, like, early on, we were like, we don't know if we'll ship this.

• 44:40Speaker 00

  Yeah.

• 44:41Speaker 02

  Like, we'll try it out. We'll see if we can get there with something that we love and see if we can get. I remember saying like, let's get some PMF internally. Let's, let's get everybody at OpenAI to want to use this thing without being forced to use it. Let's see, let's see if we can do it, right? We did, and it was like, adopted very quick. I mean, the, the minute it was barely usable, the research folks like put dev boxes on it, right? Like, which was like this crazy hack at the time.

• 45:11Speaker 00

  Yes, yes.

• 45:11Speaker 02

  Um, but now they use it like for everything.

• 45:14Speaker 00

  Yeah. Yeah, it was like including in training like the five three codecs and so like I think, I feel really good about having hit the point where like, you know, like, everyone technical at the company, like almost everyone at a technical at the company like uses codecs, but like, the people who use it the most are, you know, actually building codecs and building the models. And so, you know, we're just able to like, you know, improve things at like, crazy, crazy speeds and, you know, just like no signs of it slowing down.

• 45:41Dan Shipper?

  Amazing. Well, I'm excited for what you ship next. Um, thank you guys for your time. I really appreciate it.

• 45:47Speaker 00

  Thank you. Thank you for having us.

• 45:48Speaker 02

  Thanks.

• 45:57Speaker 03

  Oh, my gosh, folks, you absolutely positively have to smash that like button and subscribe to AI and I. Why? Because this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard, but instead of gold, it's filled with pure unadulterated knowledge bombs about ChatGPT. Every episode is a roller coaster of emotions, insights and laughter that will leave you on the edge of your seat, craving for more. It's not just a show, it's a journey into the future with Dan Shipper as the captain of the spaceship. So do yourself a favor, hit like, smash subscribe and strap in for the ride of your life. And now, without any further ado, let me just say, Dan, I'm absolutely hopelessly in love with you.