YouSaid · the spoken record

OpenAI Guest

lines on the record: 137
first: 2025-09-16
most recent: 2025-09-16
sittings or episodes: 1
sources: podcast

Every line below is reproduced as it was said and linked to the record it came from. Nothing here is summarised or generated. Directory · Search · Corrections

“Really care about this. Let's just do everything we can to have the best product. So, like, we actually did a similar thing with GPD 4.1, where we basically were getting a bunch of feedback from developers. We said, okay, let's go talk to a bunch of developers, like make custom evals for them, right? Deeply understand what our model is great at, what they want us to get better at, and then we release the custom model. Right. And then the goal should always be okay, whenever we do this, like we have 4.1, okay, the next version of our like sort of general model.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“And, like, there's some transfer, so it kind of knows a bit of software engineering. And then, like, that's fine, but you could make it way more useful for the human trying to use the agent if it has those first few years of job experience. So, I think that there's no reason that that knowledge couldn't be Exactly upstream and upgraded. But I think that having the freedom to go and explore these ideas relatively cheaply. And see what sticks and what doesn't, it is really powerful. So frankly, I don't really know to what extent it makes sense to have a bunch of custom post trains for absolutely everything that matters. But I think for something as important as like coding to us, I think that I think we're willing to say like, hey, for coding,”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“And they're not like those ideas I just mentioned are not like higher model intelligence nor even really a higher ability to call the right tools. It's just like this understanding that I likened to the first few years of job experience of a software engineer, right? Like you start, you have O3s like this incredibly precocious college grad, like very smart, but doesn't actually know how to be a software engineer, just knows how to code.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, that's a really interesting question. I definitely don't know if I have the answers to this. But what I can say is that one of the best parts of doing an optimized version of O3 was that we got to make a bunch of hybrid research product decisions very quickly. And I think that is incredibly exciting for thinking about how to make something useful. So if I imagine we would have had this idea of like, you know, it's like really important that the agent knows how to write really good PR descriptions and tests code in a certain way that's used to working in varied environments. And when it runs some tests, it doesn't just tell you that it did, but it sites deterministically, like in the logs, the output so you can verify that yourself. Those are a bunch of product ideas, really.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Reduce the cognitive burden of the onboarding, fewer decisions to get to the magic. Exactly. Okay, got it. What has it changed most about Research and the frontier of where frontier models are going, right? In your mind, does this mean that is the efficacy of how goodex is as a bow-strained version of O3 Pro at using tools, at logging to this workflow? Does it make you go, well, it just makes sense for an unlimited amount now of compute on post training models to get better and better at being autonomous coding agents? Or do you think there's some marginal plateau point at which you go, you know, after this point, there's not really much the user is getting from better and better tool usage? How should how does this change the trajectory of progress when it comes to the frontier research?”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Then the other thing, though, that is a bit of an update is like just thinking about how people learn to use these tools. I think right now there's some things that are pretty clunky. Obviously, we've talked a lot about environment setup. I think also some of the things that you have to do, like updating agents.md is very manual and you have to like commit to your repo to get that context of the agent. And so for me, I'm just thinking a lot now about like, okay, how do we make this way easier to try?”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah. And this is kind of like when we're getting to interactive agents. I think that's just like a big open area. But it's like, how do we have agents who understand what your team is trying to do and respond to like stuff and your team workspaces? And then, how do we have an agent that understands what you are trying to do? And it's almost like this agent is like both in all your tools, but like sitting next to you while you're working on your computer and like kind of just being like, oh yeah, like I can help you here So that's like actually the conviction that it's deepened, right? We're like, yes, all of this works when you give it its own computer and we need to figure out how to create this infrastructure for ecosystem integration and like make that safe and so forth.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“It should just like, I kind of think of it as it should be sort of a ubiquitous teammate. Is just in your tools, in the tools you want it to be in at least. And we'll start very gentle, just like, hey, you decide when codecs does work. And then over time, we'll figure out for it to kind of more proactively chime in. And we had a jam about this recently. It's kind of an interesting point. I don't think we want it to proactively DM you all the time every five minutes when something happens. So I think there'll be some evolution of tools where We come up with, like, if anyone here has played video games, there's always press X to like, and if you're next to a door, it opens a door. If you are next to some object, it picks up the object. It's a conceptual action.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, exactly. So there's like that. And I think I mentioned Best Event. I think thinking about how to make the most, like basically how do we spend more compute for you on your behalf? Is like very exciting. And then, how do we bring this closer to the tools you work in? For me, the interface in ChatGPT. Actually, like very functional, but it's not where developers go when they want to write code, right? Like where do you go when you want to write code? You're either your terminal or your IDE, right? Similarly, like, where do you go when you want to triage issues? Well, like, you go to your issue manager, right? And so forth. And it's like seeing what's going on in your team and like picking stuff up for you.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Right now we clone your repo every time you do a task, even if it's a follow up. Then we run your setup scripts from scratch every time. And so if you have a large repo and a lot of dependencies to install, like that thing is slow.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah. So I think there's one sort of conviction that has deepened and then one prior that's been slightly updated. So the conviction that deepened is that this form factor of an agent working on its own computer in the cloud is the future and is incredibly powerful and worth figuring out how to get right. So we're continuing to invest in making that environment set up faster, making like performance just first time user onboard.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Let's talk about that. It's been 35 days now. As a product lead, you've had a chance to actually see the best laid plans rarely survive contact with reality. So now what priors have you updated the most and what comes next? Where does Codex go in the V2? Because this was just a research preview, but what are the biggest improvements and what's the shape of the arc of the product in the future?”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah. So it's just like, anyways, long story short, it's much easier, I think, to build software, to deploy that software and to maintain it. I think that's just going to, we're just at the beginning of this change.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Similarly, you know, even we're seeing it was like this is not codecs, but we're seeing products out there that will write the app for you and then deploy it for you as well. And so it's just like all in one.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“So I think that there are so many places where we could use software and that software could be more personalized to small groups or even individuals. That we just are missing out on. And so, yeah, now I believe that with just the acceleration we're seeing in software development, I think we'll have many more of those tools existing. And they'll be much cheaper to maintain as well. Like that's the thing we're on the tip of now as well, where you're starting to see AI agents getting plugged into GitHub or like Slack or Linear has the agents feature. And I think that will make it Much more efficient to actually have some app out there and running”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Some of my favorite examples like internally are like when people build new internal tools that accelerate the rest of their team. And it's the kind of thing like someone's complaining in Slack. Like, I wish we had this tool to like, I don't know, look at these logs in a better way. And, you know, it just can't be bothered. Everyone's too busy. And then now you have this great parser.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“But yeah, my take is we can do, like you were talking about this, right? Like we can do so many more things now. And we hear this from customers too, like and from users. They're just like, hey, I would never have bothered doing this before. But I threw the idea into codecs just for the sake of it. And I do this all the time. And, you know, a lot of the time I do that and then I see the output. And I'm like, I just still don't really care to do this. But then sometimes this thing that they would not have even bothered doing codex either straight shots it or gets it to like 90 and they're like, you know what? I'm excited enough to do the last 10% here. Let's get this merged. And then this thing that would never have happened now happens.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Because then I would just feel like I'm falling behind, it'd be like. You went to college, but you were only allowed to write assembly and you could not write C back in the day. That would just be deeply worrying, I think.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“So, my take is that it's two things first of all, I think it's still a great time to major in CS. I think there's going to be so much more software created and therefore so much more software engineers needed. But I also think figure out how to be using AI constantly while you do it. And hopefully you're at a university that's like very forward leaning. And so they're kind of embracing it. I hear about policies like, hey, use AI as much as you want, but you just have to say how you use AI as part of your assignment. That's great. If you're at a place where the main place where I would be worried if I was a student right now is if I was studying CS and my college didn't allow the use of NEI.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“If there's a whole team called the product and engineering team whose job it is to ship great features, why did it take this special thing called a hack week to produce such great features? And there is something about when you reduce the cost of prototyping new ideas, that you end up getting things that don't make it through the usual PRD flow. And it sounds like that's what a lot of users are using Codec for now, is like that first to reduce the time to magic, essentially, the time to first prototype. Let's change stack for a bit because there's this elephant in the room, right? which is that if Mark famously wrote an op-ed in 2011 or 2012, which is like, you know, software is eating the world. And after I saw that chart, you mentioned of the GitHub merge success rates of AI agents starting 35 days ago hitting 80%. And as of this morning, the volume being 350,000, it sounds like AI is eating software engineering. Does it even make sense to study software engineering anymore to get a CS degree? If you're a freshman at Stanford today.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Compiling. This is why hackathons have proven to be this magical sort of type of event where you get people together and commit to getting over the hump of the first prototype. But in many ways, I think something like Codex or broadly speaking, really good coding agents have turned every day into a hackathon because they've collapsed the energy you need to get over the hump of all the plumbing, all the environment set up to test an idea. When I was at Discord, we used to have this ritual across the company that was an annual tradition called Hack Week. And some of the, where the entire company would just stop for like a week. And it wasn't just engineering. It was product marketing, sales, ops, the entire company could hack on anything they wanted. And some of the most enduring and popular features that made it into production, the company over the years came from hackathon projects. And it begs the question of, well,”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“The speed to prototyping has basically collapsed completely with something like Codex. Broadly speaking, this is the explosion of vibe coding, right? I think it's That makes sense to me because when you're prototyping a new idea, I find the most rewarding is when you actually, if you can get to the first draft really fast and then kind of iterate from there, that's fun. Sometimes the worst is when you have an idea, you kind of want to see it and then you lose steam between like firing up your IDE and seeing the first version of it.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“But actually, by far the thing that people use Codecs for is building new features. And I don't know. That was just slightly surprising to me because that is some of the most fun stuff to do. If you read like, you know, Blog posts by folks who are using codecs in that way. It does look like they're having quite a lot of fun because of just the sheer speed they're experiencing. Right.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“I mean, so my intuition was that people would use codecs for fixing bugs. Lot Know bugs are somewhat well defined, ish. You can kind of tell if it's fixed. You might even have some logging data, telemetry data that you could just paste into the model and it's excellent at fixing it. Some of our earliest delight moments were like dumping in the stack trace and then just and it just figures it.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“I think they would like to use it for debugging. They probably aren't using it yet for that because there's often my knee-jerk when I'm using an agent is that it just doesn't have enough context to fix for routine tasks like some piece of boilerplate React is broken, like debugging is totally fine. But I find I use it more and more for well-defined, well-scoped, well-contained tasks like create this new UI element that does blah or a refactor that's like where the atomic unit is very well constrained. But I'm curious, what are you actually seeing?”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“And then also that you're making these decisions not based on like reading raw code in the case of front end at least, but maybe you're making decisions based on the outcomes, you know, like in the case of front end, like you're just choosing screenshots or like clicking around a preview or like if it's back end, maybe there's like some tests you agreed on and you're just like looking at test outputs to sort of decide. The other thing that's interesting is that, well, if you were to guess, let's say I'll give you a few things that people use Codec for and are curious what your guess would be the most like the biggest ones are, like let's say it's like building new features, asking questions, planning, debugging, and fixing bugs. What do you think people would use Codex for more?”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, these are the teenagers. I think, to be real, that's true. Maybe you don't get to write as much of the code yourself right now. I think we will get to that more exciting place pretty quickly because it turns out environment setup is probably something that an agent can also massively help with. We can close that loop where you're not comparing four diffs or something like that. But we've figured out the interaction model with the agent. So you're kind of like making decisions in a way that feels like more like talking to another human. Was just like really smart and fast”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Where it's like the model does some work, and then we run the stuff, we take the model in its environment, runs the app, and then takes four screenshots, and you actually just like have this similar curatorial UI. Like, just pick the one you like most.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“So if I ask you to fix a bug, there might actually be four reasonable ways to fix that bug with sort of different architecture implications. And I haven't explored the solution space myself. That's why I'm delegating this. I kind of want to know what the ways are. And then I want to, you know, maybe I would pick the one that the model thinks is best too. But it's like helpful for me to see, like maybe that sucks in some way. But it's helpful for me to see the other ways that have larger trade offs to then be confident in the right one. So that's for fixing a bug, which is a very verifiable type thing. If I ask you a model to the classic example, implement tic-tac-toe or something. I might not know what I want either. Like maybe there's different styles and different approaches you could take at various steps along the way.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, I mean, basically, I think an unsolved problem, and it's both a research and a product problem, is like how do we steer agents? That are working independently. And you're talking, you mentioned, like, hey, is best event there to, you know, so the model has more shots on goal?”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“But what's surprising is you're actually describing that same for a pretty verifiable domain, like coding. Because at the end of the day, it sounds like there's still enough stochasticity in the sampling of a model, even as it gets better at reasoning, that makes sense to try, use it like a best-of-end machine. And this has led to the, I guess, a popular set of critiques against reasoning models that they're not, you know, RL from verifiable rewards doesn't actually introduce new capabilities. It's just really good at pulling out capabilities that are already in the model. It's really good at sampling. Do you think that this is just an interim awkward phase where like, yes, the best of is better at getting sort of the right answer from the existing model? It's not adding new capabilities yet. But where we are going, a year from now, there will be actually new capabilities that come from running verifiable RL on all the codecs usage that is about to happen from users.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Like Dolly and Midjourney One, they start to get more coherent, but there was this trick that a lot of product people started using. And David from Midjourney was one of the first to do this where he added four generations in the”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, I think so it's interesting hearing you talk about how there was this evolution from like the moment where you were using the tool as this very precious first iteration tool where you put a ton of sort of weight and context into it hoping to get back a really useful answer the first time around and then there was an aha moment where you're like actually this is more like a slot machine because other modalities in AI have played out very similarly So this is the case with image models, for example, right? Two years ago, people were trying really hard to get the first version of image models, which were like GANs, you know, general adversarial networks, even pre-like stable diffusion to produce useful sort of coherent images. And they just weren't there, right? They would produce these artistic renders, which were great for artistic exploration, but they weren't sort of useful because they didn't have the concrete coherence of a graphic design, a piece of graphic design, for example. And then if you remember the first era of diffusion model,”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, and so where I think we want this to go is there's just like one idea of codecs and it's just like where do you want it working? And there's going to be times where it's just simply easier. Like you don't have to set up an environment when it runs locally, right? So maybe if you're trying something for the first time. Yeah, just yeah, or like you don't even know if you like codecs yet. You know, you're just a new user. Like maybe you just want to use the CLI or something. And then maybe then you're using it and you realize, hey, I want all this cool parallelization and all this stuff. Let me have this run in the cloud. And you set up the cloud environment. And from then on, like you should still be able to interface with that in the CLI if you want. Except now it's running cloud environment. So it's more powerful.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah. So the place where I want this to get to is just like there's GitHub, right? And GitHub has a website and a CLI and a mobile app and it's not confusing. Right now it's a little bit confusing in that they are just completely distinct experiences. We have codecs in ChatGPT, which is an interface that you can write a prompt and then we run codecs in the cloud and then you get back a different answer or an answer to your question. We have the Codex CLI, and that's a completely distinct experience with a lot of the same ideas in it, which is basically you can run this tool in your terminal and we'll hit our model via API and basically this agent will work locally with you and your computer. So right now I kind of think of it as you delegate to codecs in ChatGPT remotely. And then you pair with Codex CLI on your computer”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, exactly. I see. And so, like the Codex CLI, which we haven't talked much about, but in my mind, like the Codex CLI might evolve into that where it's like, hey, if you want to run the agent loop in your own environment, then we can help you do that and you can use something that's an evolution of the CLI.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“If you're going to use your compute, then we can work with you and provide you as much of a harness as possible to automate things. But you're going to have to want to manage that compute. And for the agent, basically, that environment for the agent, here are the tools it should have. Here's how you should sandbox it.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“And so I think what we're going to get towards is like there's this default way of working with things. And then we'll basically have like some flavor of like on-prem or bring your own compute that we support where it's like, hey, here are all the things we manage for you when you use our compute.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“So, yeah. So there's that. However, also, you know, the majority maybe of valuable code is actually written by enterprises who rightly so are like really locked down all their IP and their code. And so something we've been thinking about as well is like how do we meet these enterprises in a way that we can like provide value to them as well, in a way that they like.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“So I think we'll get towards that, and I think we'll be able to build a really nice managed system for that that lets you use more capabilities safely and with some product pushes from us on how to make the most of it. So, for example, recently we shipped Best of N. It's a very simple feature, but in our minds, it's like kind of just the beginning of taking advantage of the fact that we're not running on your laptop, so we can explore four versions of the”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“API access, and it's like gets piped the right credentials at the right time. And so, like, you kind of think of yourself when you're hiring your new agent for your new startup, which you might do before you bring on a co-founder even, you know. You think of yourself as just like setting up that environment. And it's, and you're just getting like this fairly generalist employee that can code. Like if you think of Codecs right now, it's like, Basically, it takes prompts and turns them into messages and diffs. And that's like not general. I can't be like, oh, yeah, hey, can you move engineering sync? 30 minutes later because I have a conflict, but like a real software engineer can do that, right? A real software engineer can go peruse any source of data, can like find out they don't have potential. I mean, they can just use the internet.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Where would Yeah, no, totally. So I think it's actually more like for whom or who will use what. Like, I think that the average user or maybe like the new startup that is building with agents from scratch will just do things in a very different way. And they'll basically have a bunch of agents with this compute environment that scales really well, that has like all the credentials they need, but is also protected with the right forms of sandboxing applied at the right times. With the right monitors on all network egress and all this stuff. Maybe this kind of computer, I think of it as a laptop, although obviously it's not, is actually the thing that many agents use, right? And it contains many tools, not just the terminal, but it has a browser and it has whatever.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Do you think that is the arc of product development of agents such that do you think the shape of the industry will be more and more applesque where you'd go, well, gold starts are a problem for the containers because that's a really terrible user experience. So instead of outsourcing containers to some third-party vendor who then we're reliant on for providing us cold start, we're just going to bring this all in-house. Is the most magical experience going to be a full stack end-to-end integrated experience where all the dependencies, all the middleware is all done in-house? Or do you think that this is going to be more Android desk where you guys, a company like OpenAI has an opinionated experience, owns the agent sort of interface, but everything else is mostly like a collection of different tools orchestrated by different vendors?”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“This is how I want to use it. This thing is like basically obviously it's not HDI, but it's like, oh, is it like, it's this like super smart model? Why can't it just like, all I want you to, you wrote this amazing PR. I just want you to change one thing. Why can't you do it? And so, you know, obviously the bug that I mentioned we fixed, but that's something now we're thinking more about. Like, okay, how do we enable that kind of multi-teraction? How do we make it faster as well? Like container startup, just for example, takes time. And there's a lot of optimization we can do. But for now, if you need to incur a full container startup to like change one variable name.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“And do you think that's basically because internally OpenAI employees are sophisticated enough to know that you do all this upfront context building work for the agent to try to get as much as you can in the first turn? But a user, once you've made it fully cloud connected, so the cost of the marginal cost of doing kicking off an agent was so low that they just quickly got to the third, fourth turn without too much thinking.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“And so for me, that was really interesting to see that people had this intuition for how they wanted to use the product, and that wasn't the reprompt intuition. It was the, hey, like, I'm going to get this main thing. And then I kind of want to babysit that across the way to like actually landing it without it ever touching my computer. And that like, we kind of knew that might be a thing, but it was much more of a thing than we expected.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Exactly. And this is just like a plain old deterministic bug. It's not like a weird model behavior thing. It's just like we implemented the code wrong because no one ever just got to turn four basically.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“So basically, like I was saying, we, and we told our alpha users, I guess, to do this. We basically said, hey, just like reprompt to fire many prompts. And maybe you can go back and forth. It turns out that if you go back and forth more than once, so you do like three turns total, right? Product was completely broken and that we were not correctly carrying over the diffs from the prior steps.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Which they are. Right, and like we didn't like obviously, we have many ideas, we had ideas for how to enable network access. We just wanted to do that carefully. And then we, on the environment setup stuff, like we have ideas that we haven't shaped yet on how to make that better. Yeah, simple model loop to help write it and so forth. But we just cut scope and ship the really early research preview. So there's a bunch of that expected feedback. Now, one of the things that really surprised me. That there was one feature that we didn't expect people to use, and in fact, we used it so little internally that it just had a bunch of bugs we hadn't caught before releasing. And that was multi-turn.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, okay. Throw stuff at it. And also, you don't need to have the code on your computer to get and like decide to merge that code to get value. You could just be asking questions. You can be like, hey, explore this four different ways so I can pick the right way that I then want to do it. You can almost treat it as like your to do list of things that you will get to later in the day. So that was some of the learnings we had when we ran the alpha were, hey, we need to kind of change the product so that it feels more like parallelization is like a key part of how to use it. And so to more like make it so you like let go of what it's doing. Okay, so then we shipped broadly externally. And we got a bunch of feedback that we expected, like, hey, the containers don't have network access. This is really annoying.”
2025-09-16 · a16z Podcast · How OpenAI Built Its Coding Agent · IDENTIFIED FROM THE TRANSCRIPT · source