Why Dwarkesh is Wrong about Computer Use + How OpenAI shipped its Jev competitor in 1 Week

Three months ago Dwarkesh, who has been posting incredible blogs and episodes https://x.com/search?q=from%3Adwarkesh_sp%20RL&src=typed_queryabout RL, posted https://x.com/dwarkesh_sp/status/2070672008946589922 a framing question for his video essay on RLVR which upset a lot of Computer Use folks: We are no strangers to learning in public https://learninpublic.org/ and are no strangers to the stress of getting things wrong when you have a big platform. However, we were at Anthropic for the Computer Use launch https://x.com/swyx/status/1852786783710539972, there for Claude Cowork https://x.com/swyx/status/2016899888718442842 with the first big podcast https://www.latent.space/p/felix-anthropic on it, organized the first Computer Use track at AIE https://www.youtube.com/watch?v=1UmZHb_E_SM&list=PLEz0frWjePik&pp=sAgC presenting the state of the art, and were close to the OpenAI-Sky Software acquisition https://openai.com/index/openai-acquires-software-applications-incorporated/ that now powers the complete domination of computer use that Codex enjoys today. This is why we’re excited to bring you today’s first guest, Ari Weinstein https://x.com/AriX/status/2088364788984217753, cofounder of Sky and now leading all the amazing CUA progress that casuals might miss: Ari explains why Computer Use is now “180 degrees different” from where it was months ago, how agents are learning to debug and recover from failures, why combining screenshots with accessibility data, the DOM, Playwright, and generated code changes the speed equation, and why the next frontier is making agents literally superhuman at using software. OpenAI clones Jev In the second half, Nikunj Handa from OpenAI’s API team breaks down the new developer stack: async tool calling, mid-turn steering, WebSockets, UltraFast inference, the Decisions API, prompt caching, pre-warming, compaction, and the Agents API. Given that we were the first Jev podcast https://www.latent.space/p/jev, we particularly focus on the unusually fast sprint on the Decisions API: And why it is just a Luna wrapper for now but the team is motivated and egoless enough to clone what they consider to be good patterns. We discuss: * Why OpenAI thinks Computer Use has changed dramatically in just the last few months * Dots and what changes when every agent gets its own Linux computer * Why Computer Use can now complete some tasks faster than the average human * The path from human-level to “literally superhuman” computer use * Why modern agents are much better at debugging and recovering from failure * How screenshots, accessibility trees, the DOM, Playwright, and generated JavaScript work together * App Shots and why they give models much richer context than ordinary screenshots * Why Computer Use can close the loop between writing software and testing it * Trust, permissions, and safety when agents can make payments and operate websites * Async function calling and why models no longer need to stop reasoning while tools run * Mid-turn steering, WebSockets, and the architecture behind more responsive agents * UltraFast inference and how OpenAI is pushing frontier models toward much lower latency * The rapid internal story behind the Decisions API * Why Decisions API is more than structured outputs at low latency * GPT Live, fast tool calling, and real-time computer control * How OpenAI is already using Decisions API for support classification and internal workflows * Longer prompt caching, cache pre-warming, and cache-aware applications * Server-side compaction vs manual compaction for long-running agent threads * What should live inside an Agents API versus a developer’s own harness * OpenAI as an “AI cloud” and the search for higher-level primitives beyond raw model APIs Ari Weinstein * Product & Engineering, Computer Use at OpenAI * X: https://x.com/AriX https://x.com/AriX?lang=en * LinkedIn: https://www.linkedin.com/in/weinsteinari/ Nikunj Handa * Product, API at OpenAI * X: https://x.com/nikunjhanda * LinkedIn: https://www.linkedin.com/in/nikunjhanda/ Timestamps 00:00:00 OpenAI DevDay: Dots, GPT-6.1, Agents API, and Decisions API 00:02:52 Dots and Personal Cloud Computers 00:04:59 Why Computer Use Is “180 Degrees Different” 00:06:04 From Sky to Self-Debugging Computer Use Agents 00:09:24 How Computer Use Sees and Operates Software 00:12:09 From Faster Than Humans to Superhuman Computer Use 00:16:03 Agents API: Trust, Permissions, and Safety 00:17:31 Computer Use for Coding, Testing, and QA 00:19:14 GPT-6 APIs, Async Tool Calling, and UltraFast Inference 00:23:21 The Rapid Story Behind Decisions API 00:25:32 What Decisions API Is and How It Works 00:30:24 What OpenAI Is Building With the New APIs 00:32:23 Prompt Caching, Pre-Warming, and API Performance 00:35:20 Context Compaction for Long-Running Agents 00:37:13 Memory, Higher-Level APIs, and the AI Cloud Transcript Introduction: OpenAI DevDay and the New Agent Stack Vibhu [00:00:00]: Okay. We’re very excited to be here. Today is OpenAI DevDay. Special podcast Swyx [00:00:08]: We’re the first podcast after your livestream. Vibhu [00:00:10]: First podcast. We have Ari here, who leads the product and engineering team for Computer Use agents. Before we kick in and dive deep on Computer Use, you wanna give a quick recap? What was announced? What’s the quick slew of announcements you guys had today? Ari Weinstein [00:00:24]: Yeah. yeah, it was a super exciting day. we just got out of the keynote. It was really sick. there were a bunch of Computer Use announcements that I think are worth thinking about. We have, Dots, which is the new, sort of personal assistant product, and, that has some really exciting Computer Use features. There’s GPT-6.1 Sol, which is this amazing new model, that I think is particularly great for Computer Use ‘cause of, sort of the cost and speed, advantages. I think, I think we shared that it’s, a fifth of the cost of Astra and a seventh of the cost if you’re looking at Computer Use specifically, which is really amazing. sorry, there were so many things. I’m trying to sort through it. Swyx [00:01:02]: And the API. Ari Weinstein [00:01:03]: Agents API, which now has Computer Use in it, which is really cool, ‘cause now developers can build on the same Computer Use, that is part of Codex, and ChatGPT. and then there were some demos of our existing Computer Use features, like app shots, where you can take the context of something you’re doing on your computer and bring it into Codex and ChatGPT really fast. And then, like, native Computer Use on your Mac, where Roman had it taking screenshots of his app, automatically, and he could do other things on his computer while Computer Use was using his applications. so yeah, really exciting keynote. Swyx [00:01:35]: And not to mention the Decisions API. Ari Weinstein [00:01:37]: Decisions API. Swyx [00:01:38]: Off the bat, are they all the same model? Like, this is. Or the same dataset distilled to different models? Swyx [00:01:44]: Like, basically, like, is Computer Use using Decisions API, or are they, like, kinda separate? Ari Weinstein [00:01:49]: So what’s really cool about the Decisions API is it, you know, it has all these new capabilities. It does inference in parallel. it doesn’t have reasoning. It’s a smaller model, than the ones we use for Computer Use. and so those capabilities make it really fast. Dots and Delegating Work to a Cloud Computer Swyx [00:02:07]: Yeah. Ari Weinstein [00:02:07]: They also make it a little bit less good at doing, like, long horizon, sort of sophisticated tasks. And so I think I would say it’s still an open area of research for how we, like, bring those approaches together. But, yeah, I’m really excited to see what people build with the Decisions API. Vibhu [00:02:24]: One of the interesting things is Dots now have attached personal computers. Ari Weinstein [00:02:28]: Yeah. Vibhu [00:02:28]: So it seems like they’re very much more persistent. You’ve been using them for a while. How should people push the bounds? Like, what should people aim for? What should they try? Personally, right now I use it for a lot of customer service. Like Ari Weinstein [00:02:41]: Cool Vibhu [00:02:41]: “Oh, this was wrong. I don’t wanna sign in. I don’t wanna authenticate.” Find whatever and just get it fixed. Ari Weinstein [00:02:45]: Yeah. Vibhu [00:02:46]: How should we push further? What should people try? Ari Weinstein [00:02:50]: Dots Are a really cool product because each Dot has access to its own Linux virtual computer in the cloud, which is different from our other products. you know, traditionally, we’ve have access to a browser in the cloud, or it has access to your own computer, but now you get your own entire Linux computer in the cloud. And so it can run full desktop applications, and it can also use a web browser. And so, yeah, you know, I think the powerful thing about Computer Use and the reason why I think it’s so, exciting is because it makes it so that the agent can do anything you as a, as a person can do, because all the software in the world was designed for humans, and now agents can use that same software, and you can delegate to the agent. So, yeah, like, anything that you would do on a computer, you can ask a Dot to do. Yeah, I think what particularly is useful is gonna really depend on who the end user is and what- what’s valuable in their life. but yeah, I would just start by thinking about, like, one of the things that you spend time on and how could you delegate those to an agent. Swyx [00:03:47]: Yeah, a lot of flight booking and shopping and honestly even, like, playing a game or whatever, right? Ari Weinstein [00:03:52]: Totally. Swyx [00:03:52]: Yeah. Ari Weinstein [00:03:53]: Yeah, I don’t know. For me, something I did recently, I’ve been working on. I’ve, subscribed to a meal prep service ‘cause I was trying to, like, eat healthy, you know? And I really like this meal prep service I found because it lets me customize the meals I order to, like, a high degree of granularity. So I can say, like, “I want this many grams of chicken and this many grams of rice.” but it was so complicated. It took me two hours to do an order, and I found that I could ask Computer Use to do it for me, and it did it in 15 minutes. so I actually saved two hours. it both did it eight times faster than I could, and it saved me two hours on GPT-6.1 Sol. Swyx [00:04:32]: Yeah. Ari Weinstein [00:04:32]: So those are the kinds of tasks that I feel like, are really powerful. Swyx [00:04:36]: As a creator, I can tell you automatically, immediately, my number one use case is automating YouTube. Ari Weinstein [00:04:40]: Nice. Swyx [00:04:40]: Because, YouTube doesn’t expose a lot of things via API. Ari Weinstein [00:04:43]: Yeah. Swyx [00:04:43]: And you have to just put it in a VM and just, like, run it, for, like, let’s say, let’s say their AB testing feature or making community posts. None of this is available by API ‘cause they hate developers. Swyx [00:04:53]: Anyway, so, Ari Weinstein [00:04:55]: I’ve heard that from our developer experience team too. They use it with YouTube a lot. Yeah. It’s really awesome. Swyx [00:04:59]: So I wanna draw for, you know. let’s say, I wanna get a little bit spicy. One of our, the leading AI podcasts, our friends, is famous for saying that Computer Use hasn’t advanced in the last two years. How Computer Use Has Changed in the Last Year Ari Weinstein [00:05:12]: Yeah. Swyx [00:05:13]: Which is a very interesting statement, and I think you’re one of the best people in the world to talk about this, like, how have things have progressed, right? Ari Weinstein [00:05:20]: Yeah. You know, they said that a few months ago, I think, and I hope they have a different perspective now because Computer Use is, like, 180 degrees different than it was. Swyx [00:05:26]: He’s a, he’s a tough guy to impress. Ari Weinstein [00:05:27]: Yeah, okay. well, we’re working on it. Swyx [00:05:30]: But, you know, you worked on. You’ve, like, basically spent your whole career working on, like, some kind of computer automation, right? Ari Weinstein [00:05:34]: Yeah. Swyx [00:05:34]: Like shortcuts Ari Weinstein [00:05:35]: Yeah Swyx [00:05:35]: At Apple, and then Sky, and then, and then joining OpenAI. Can you draw, like, what your through line is for, like, what is driving you and what- you, what wasn’t possible back then maybe Ari Weinstein [00:05:47]: Yeah. Swyx [00:05:48]: And, like, what your sort of milestones were. Vibhu [00:05:49]: I guess to add on to that as a follow-up question, what’s the major change from using Codex Computer Use from, like, last week Ari Weinstein [00:05:57]: Yeah Vibhu [00:05:57]: Through to today? Is it model? Is it dots? Is it harness? So all the history plus what really just changed in today’s announcements? Ari Weinstein [00:06:04]: Yeah. On the through line, I guess I’ve always been excited about automation and helping people automate tasks because then you can, like, save time in your life and focus on things that are more important to you than, like, operating a computer very intricately. And so, yeah, that was why we worked on some of those products. I was at Apple before. we made a company called Sky. we ended up joining OpenAI, which is really exciting. and I think something that was Swyx [00:06:27]: And almost like you have to hack around Apple until Apple was like, “Fine, like, we’ll just hire you and you can just work on the inside,” right? Like. Ari Weinstein [00:06:35]: It was, it was a cool place to get to work. what was really interesting looking back at Sky is we were, we were working on Computer Use there as well, and the models were so much less capable. And now the models, just in the last one year, have become extraordinarily capable at Computer Use. I think the biggest delta that I see is before they could, like, reliably start tasks, but then they would run into problems, and now they’re really good at debugging. They’re really good at trying again, introspecting what is and isn’t working. and I think we’ve also brought the Computer Use the Computer Use field itself has moved forward. I think we’re using more techniques. now Computer Use, often writes code. So if you actually look at it in Codex and you expand the tool calls manually, you can see that it’s not just doing one action at a time. It’s actually writing JavaScript code that it executes, that the computer executes to perform sometimes many actions at once, which is a great, you know, speed up and great capability. We use more accessibility, sort of multimodal interfaces. So, the model may use screenshots, it may use accessibility, it may use Playwright. it can use a lot of different mechanisms, based on the task at hand. and then, yeah, the model acceleration has been, has been just amazing. So, yeah, what’s different today? I think we’re making computers better all the time, so I think just, like, one day’s difference, is probably a little bit less consequential than, like, even the past month or the past two months. but, yeah, I think the Computer Use in Dot is really exciting as well as, the new model that we came out with. Measuring Computer Use and Improving the Harness Vibhu [00:08:03]: On the keynote, Tejal was mentioning 7x improvements in Computer Use speed, a lot better on a few benchmarks. How do you guys think about measuring it? Computer Use is one of those things where, as you say, you know, it’s improvements over time. Ari Weinstein [00:08:20]: Yeah. Vibhu [00:08:20]: Is it harness? Is it model? Is it post-training? Ari Weinstein [00:08:22]: Right. Vibhu [00:08:22]: How do you guys look at it internally about measuring how good it is, and what were the changes with the new model? Ari Weinstein [00:08:29]: We actually have a bunch of different ways of measuring it, some of which are on different permutations and configurations of the harness. It’s a bit of a complicated story because, you know, our production products have, you know, some more safety checks, and, you know, those are configured differently based on the needs of the, of the task at hand. So there’s a lot of ways to measure it, but I think regardless of how we measure it, we find pretty consistent gains. and those gains are, sometimes in the harness and sometimes in the model. and yeah, I was really excited by this result that GPT-6.1 is even more cost-effective for Computer Use than its baseline cost improvement as compared to Astra. It’s, like, really cool to see. Swyx [00:09:10]: Yeah. I mean, one of the visuals I really liked from the livestream was that, you’re sort of improving the Pareto frontier of, your, curve, and there was a lot of talking about how you’re improving it together with the harness. Ari Weinstein [00:09:24]: Yeah. Swyx [00:09:24]: Can you give some examples of aha moments that you had, whether it’s on, like, model driving the harness driving the model, whatever? Ari Weinstein [00:09:32]: I don’t mean to repeat myself, but I think, like, introducing more modalities has been really powerful. Swyx [00:09:36]: Okay. Ari Weinstein [00:09:36]: One more specific example of that is, in the past, I think we saw a lot of Computer Use, products had to spend a lot of time, like, scrolling, you know? So it would, like, take a screenshot. It would try to do something. It would be like, “Oh, I gotta, like, scroll down to the next page of results,” and then it would take a screenshot, and then it would try to do something. It would scroll down again. And so I think, with accessibility and other. and, direct access to the DOM and other things like that, now the language model can actually see, like, an entire page or an entire application. It can write code that can do multiple steps at once. And so I think those have been probably the biggest single aha moments. There’s, like, a lot of tiny ones that are less exciting in comparison, but actually we do find also that a lot of speed improvements are driven by, like, a lot of little paper cuts that we gotta go in and introspect. App Shots, Accessibility, and Better Computer Context Swyx [00:10:21]: Yeah. A lot of really hard engineering. Ari Weinstein [00:10:23]: Yeah. Swyx [00:10:23]: I mean, app shots in general, right? Like, I think people don’t quite get the difference if. because there’s, like, a nice visual in Codex when it Ari Weinstein [00:10:30]: Yeah Swyx [00:10:30]: When you take an app shot, but they don’t maybe they get the difference that, you are able to actually drive each button and you have the, you have each text, in a very optimal representation. Ari Weinstein [00:10:40]: Yeah. Exactly. Yeah. It’s kind of fun actually. If you wanna be, like, really nerdy about it, you can go into Codex, take an app shot by hitting the two command keys. So you grab the content from whatever app you’re working with, bring it into the, Codex or ChatGPT chat. And then the. if you click on the attachment and you click on this, like, little tiny button in the top right, you can see the raw text and you see the raw accessibility representation. And yeah, we’ve put a lot of work into, putting Swyx [00:11:04]: Just dumping everything out. Yeah. Ari Weinstein [00:11:05]: Dumping it out, but also making it token-efficient, doing it efficiently. There’s, like, a bit of an art to it. And, you know, it turns out that the same technology that was invented for humans, you know, who maybe have accessibility needs, who wanna use a screen reader technology, that technology is really helpful for them to be able to use computers. It’s also really helpful for LLMs to be able to use computers. So that’s been, like, really fun to get to work on. Vibhu [00:11:27]: For context, I feel like a lot of people don’t understand app shots. They don’t even know it’s a feature. Ari Weinstein [00:11:30]: Yeah. Vibhu [00:11:31]: It’s when you double hit command, it pulls in what looks like a screenshot Ari Weinstein [00:11:34]: Right Vibhu [00:11:34]: And you’re like, “Oh, why have I opened up just a screenshot and thrown it in?” No, it’s actually pulling all the metadata, all the code, everything. Ari Weinstein [00:11:40]: Yeah, exactly. Yeah. So it’s like, you know, if you take a screenshot of a webpage that has a link- The screenshot doesn’t include where the link goes. It doesn’t include, you know, maybe you take a screenshot of your calendar, the ca- event ti- titles are truncated, you know? But when you take an app shot, it gives, like, the language model, like, full context about everything and, that lets it, just sort of, like, do much more. Swyx [00:12:02]: Yeah. For those who wanna see more, Jason Liu, I invited him to do a full workshop on this, at AI Engineer. Ari Weinstein [00:12:07]: Amazing. Swyx [00:12:08]: Did a great job. Vibhu [00:12:09]: I have a broader vision question Toward Superhuman Computer Use Ari Weinstein [00:12:11]: Yeah Vibhu [00:12:11]: On Computer Use agents. So your example of take a screenshot, scroll page, take a screenshot is where we were. Ari Weinstein [00:12:17]: Right. Vibhu [00:12:17]: Today, they can automate a lot. what are the bottlenecks? Is it models? Is it harnesses? What. Where do you see it going in, like, two years? Do you see it just running for hours? How do we get there? Any predictions on where Computer Use goes? Ari Weinstein [00:12:32]: Yeah. I mean, I think what’s really crazy that I think, You know, the team’s accomplished over the past couple of months is that now Computer Use is, like, faster at accomplishing tasks than, like, the average human probably in most cases. and I think that the next frontier is to have Computer Use be, like, literally superhuman in its performance where it actually is as fast or faster at using software than, like, expert Computer Users like us. and I think that’ll be really consequential and exciting when that happens because I think we’ll be able to all of a sudden build products, that, provide just much more real-time experiences. And I think it’ll also. lowering the barrier to entry of, or the activation energy, I suppose, of using Computer Use I think will make us start to default to doing certain things in agents that we’ve become accustomed to doing manually. And I think that’s exciting also ‘cause it’ll save us a ton of time. and I think there’s a, you know, there are a lot of different little paper cuts and bottlenecks that are sort of standing in the way of that. I think that there’s, yeah, there’s things on the model side, there’s things on the inference side, there’s things on the harness side, there’s things in the, in the representation. You know, we find that as Computer Use gets faster, we’re increasingly bottlenecked by just, like, the speed of doing an operation. Like, for example, you know, a non-trivial amount of time in our benchmarks of Computer Use tasks is actually, like, let’s say you’re automating a task on doordash.com. Like, a lot of the time is actually waiting for doordash.com itself to load, you know? Swyx [00:14:04]: Yeah, then you just write a wait and then you execute the wait. Ari Weinstein [00:14:07]: Yeah, totally. And you wanna get. Yeah, actually, it’s actually really important that you get that de- like, you want as little delay as possible between when it finally finishes loading and when you go and Swyx [00:14:16]: Yeah Ari Weinstein [00:14:16]: Trigger the LLM to do the next action, which is actually- itself a statistical science. Swyx [00:14:20]: Like an event-driven way maybe to do that. Ari Weinstein [00:14:22]: When possible, you want it to be event-driven. Swyx [00:14:24]: JavaScript has some load events. Ari Weinstein [00:14:25]: And JavaScript has load events for. or the web browser has load events for web navigation, but there’s other types of events that actually really can’t be event-driven. So there’s a lot of complexity Vibhu [00:14:34]: The one that comes to mind is, like, chatting with customer service. Ari Weinstein [00:14:37]: Yeah. Vibhu [00:14:37]: Replies could take 30 seconds, could take three minutes. Ari Weinstein [00:14:39]: Oh, right. Swyx [00:14:41]: I have dealt with so many bots with Codex. it’s great, but I also wonder if the other side knows that they’re talking to a bot ‘cause I’m, like, answering in complete sentences. Like, I’m capitalized correctly. Ari Weinstein [00:14:50]: That’s hilarious. Swyx [00:14:51]: Like, I’m giving full num- full reference numbers and everything. Like, it’s too. it’s clearly too good. I don’t care. Like Like, I’m just, like, trying to get my support case. Vibhu [00:14:58]: I’ve prompted it to, like, you know, “Don’t pretend you’re a bot. Be very annoyed human.” Vibhu [00:15:02]: Short one-liners, like Swyx [00:15:04]: Yeah Vibhu [00:15:04]: Push it, do all this. I also tell it, “While you’re waiting for responses, like, use subagents to research better ways to figure out what we need.” Ari Weinstein [00:15:12]: Nice. Vibhu [00:15:12]: It’s just, like, human little intervention. Ari Weinstein [00:15:14]: That’s awesome. I also feel like half the time it’s a bot on the other end, so now you Vibhu [00:15:17]: Yeah Ari Weinstein [00:15:17]: Got the bots talking to each other. Swyx [00:15:18]: Yeah. I will also say, you know, like, you know, one milestone of Computer Use that we are, we’re at now is, you know, three, four years ago, we were scared of hooking up LLMs to the, to the web and to Ari Weinstein [00:15:31]: Yeah Swyx [00:15:31]: To our, to our devices. And now I’m having it configure DNS for me. Ari Weinstein [00:15:35]: Wow. Swyx [00:15:36]: I’m having it pay my bills, and, like, really, like, tens of thousands of dollars of, like, stuff I’m just sending it over and yoloing with Computer Use and, like, you know, what’s the, what’s the worst thing that can happen? Swyx [00:15:48]: So that- that’s all, that’s all really good. Building Safely With Computer Use in the Agents API Ari Weinstein [00:15:50]: Yeah. Swyx [00:15:50]: I think now that you’ve. you know, obviously, you also have to dogfood your own products and all these things. Now that you’ve sort of released this in API, what are some pitfalls or tips that you wanna tell developers, because they’re about to, I guess, encounter all this, firsthand? Ari Weinstein [00:16:03]: First of all, I’m just really excited that we brought Computer Use into the Agents API. I think this is, really great because obviously a lot of developers are building applications that wanna be able to work with third-party websites and services. And so Computer Use has this universality to it. It can work with anything. So now all of a sudden, developers can build using the same Computer Use implementation that we’re building on. I think there’s great work to be done if you wanna build your own Computer Use harness, but it’s hard. And also, we train our models on our Computer Use harness, so there is, an advantage to using the one that’s in distribution for the model. There actually might be a speed and cost and accuracy advantage. So I think it’s really great for people to get to build on top of that. And, yeah, you know, I think kind of to the point that you were making, like, I think we’re all sort of still in the process and maybe, like, some of us are ahead of many people in the world of, like, getting comfortable with this technology and trusting it. And so I think it’s incumbent on us to, sort of build that trust over time by making sure we’re building things that are reliable, by building, the right kinds of safety checks, by asking for the user’s consent before doing something consequential like making a payment, by, asking, you know, maybe depending on the application, making sure you’re only letting it access the websites or applications that it actually needs for the task. So that’s, I think, something important to think about. but yeah, I’d really encourage people to try the new Agents API, build all kinds of cool stuff on it. We’d love to hear your feed- feedback if, you know, depending on how it goes. Vibhu [00:17:31]: Have you seen any changes in the way it affects dev workflows? So one of the things with dots is, you know, you’re seeing it in Slack. Ari Weinstein [00:17:38]: Yeah. Vibhu [00:17:38]: You’re seeing people use voice and build. the example Roman showed of change this app and send me screenshots along the way and all this. Computer Use for Testing and Closing the Software Loop Ari Weinstein [00:17:46]: Yeah. Vibhu [00:17:46]: Is anything that you’re seeing there in adoption about how people are using Computer Use for coding workflows? Any tips people should take from that? Ari Weinstein [00:17:55]: One of my favorite use cases for Computer Use actually, and one that we see a lot in the wild, is Computer Use letting the agent- actually test the software that the agent has built, which is far more consequential than it sounds. Because traditionally, you know, you’d build something in Codex and then the-- and the Codex builds it for you, and then you have to test it, and you are now like QA for the agent, right? So with Computer Use, you can complete the develop-- the software development life cycle, where, the agent can build software, it can test it. So I have a lot of fun, you know, building stuff, having the agent test it. By the time it comes to me, it’s already working. I have, extra fun because sometimes I’m, like, developing Computer Use itself, and so now I have a Computer Use agent that’s using my Computer Use agent that’s using something else. so yeah, I really, I really think this is a super powerful class of use case. Swyx [00:18:44]: I have a visual play test skill that I’ve developed that, really catches a lot of design issues, Ari Weinstein [00:18:49]: Nice Swyx [00:18:50]: That, you know, normally when you just look at code, you wouldn’t really pick it up. it’s also really good for cloning apps, though. If you’re using a shitty SaaS and you wanna kill the SaaS You just clone it screen by screen by screen. and Obviously, Computer Use can completely drive everything, take screenshots, note it down, and then clone everything with Codex. Ari Weinstein [00:19:06]: That’s really cool. Swyx [00:19:06]: But yeah, thanks for all your progress. I think, that is Ari Weinstein [00:19:08]: Absolutely Swyx [00:19:09]: Our time. Nikunj Handa: What’s New in the OpenAI API Ari Weinstein [00:19:10]: Yeah. Swyx [00:19:10]: This is not the last that we’re gonna talk. Ari Weinstein [00:19:12]: Yeah, cool. This has been really fun. Thank you guys for having me. Swyx [00:19:14]: All right. Vibhu [00:19:14]: All right. Okay, we’re a strict cutoff. We’re just gonna dive right in. Nikunj Handa [00:19:17]: Let’s do it, yeah. Vibhu [00:19:19]: Okay, so, Nikunj, we’re very excited to have you. You shipped a lot on the API side, like we just Nikunj Handa [00:19:25]: Yeah Vibhu [00:19:25]: Talked about with Ari. You can now build with Computer Use agents. Anything you wanna highlight, the API side of changes, and introduce yourself a little and what you do? Nikunj Handa [00:19:34]: Yeah, for sure. My name is Nikunj. I lead product for the API team. Been here for roughly three years. been working on launching models. I feel like that’s just been, like, a thing, constant thing throughout my time, here at OpenAI. And, with every new model, we try to, like, basically work super closely with the post-training team, the research team, to figure out what’s new in it. and then we, like, expose those capabilities in the API. so that’s, like, the basic way of putting it. and if you just look at, everything that’s new with GPT-6, the cool new capabilities that we launched were, firstly, async function calling. so what you see with, like a lot of the things that you’re seeing in, like, Codex and Dots and everything is that tool calls take so long that you don’t have to, like, pause the model’s execution while, the tool is running. So you could just, like, kick off a tool call, keep running, keep reasoning, and then check back in. so we launched async tool calling. We launched, like, mid-turn steering, so now you can, like, inject messages while the model is reasoning, in the middle. so as your tool call finishes, you can put in that instructions. Async Tool Calls, Mid-Turn Steering, and WebSockets Swyx [00:20:43]: And that’s also partially a model alignment capability, right? Nikunj Handa [00:20:46]: Yeah. Swyx [00:20:46]: Like, they have to train in the ability to train. Nikunj Handa [00:20:48]: Exactly, yeah. And Vibhu [00:20:49]: I feel like we’ve had it in the app. You could always, as it’s reasoning, you could steer. Nikunj Handa [00:20:54]: Yes. Vibhu [00:20:54]: It wasn’t the best. It’s gotten much better. Nikunj Handa [00:20:57]: Yeah. Vibhu [00:20:57]: Excited to see how it does this in version Nikunj Handa [00:20:58]: Yeah, and I like our main Vibhu [00:20:59]: And now Nikunj Handa [00:21:00]: Goal in, our main goal in the API is to, like, put things in the API once it’s trained into the harness. And so we kinda wait for that moment until it’s good enough. And a lot of that is, like, actually being powered by WebSockets, which we launched, a few, I wanna say months ago. And so WebSockets just opens this, like, whole bidirectional, like, communication thing with the model. This is not, the GPT Life thing. I’m just talking about GPT-6. and you can do all these, like, async tool calling, async reasoning, injecting messages. It’s a really fun API to work on. I think, like, really enjoying. Swyx [00:21:33]: Yeah. This is why we are the engineering podcast, because we get to talk about WebSockets. UltraFast and the Inference Stack Nikunj Handa [00:21:36]: Yeah. Swyx [00:21:37]: This also pairs very well with UltraFast, right? Nikunj Handa [00:21:39]: Oh, yeah. Swyx [00:21:39]: Like, that is now, like, I think for the first time ever available in the API. Nikunj Handa [00:21:43]: Yes. Swyx [00:21:43]: Which is, which is basically the theoretical fastest speed you can ever get, Frontier of Intelligence. Nikunj Handa [00:21:49]: Yeah. It’s been so exciting to work on that project. I think, before I go into the API, the most fun part of, UltraFast has been just watching the inference team cook with Astra. Like, they’re just, like, constantly having these, like, Codex agents running, trying to, like, squeeze out more performance. And, I would say, like, at least for a couple of months, a lot of it was focused on efficiency and driving the cost down, which is how we, like, were able to cut the Luna price by, like, 80%. It was, like, a lot of that was driven by, like, all the inference improvements they landed. And then now they’ve, like, shifted gears towards, like, how can we make this run as fast as possible? And so UltraFast has just been, like, amazing to see on a mo- on a model like Astra. Like, to go that fast has been really cool. And yeah, WebSockets is like. actually it was like the first time we launched WebSockets, it was for GPT, 5.3 Codex Spark, which was. Can’t believe we named a model that, but, you know, that’s what we launched it for. And obviously, it helps so much because, like, you gotta have the tool calls. you had, like, really reduced the overhead, of going back and forth with tools. And so, WebSockets is awesome for that. Swyx [00:22:57]: Yeah. it’s always cute to see, like, I have my reset usage limit, and then I have my Spark usage limit that I never use. Nikunj Handa [00:23:03]: Yeah. Swyx [00:23:04]: Like, it’s there if I want it. Nikunj Handa [00:23:05]: I think it’s gone finally. Swyx [00:23:06]: It’s gone. It’s gone, yeah. Nikunj Handa [00:23:07]: I know it’s gone, so. Swyx [00:23:08]: Yeah. you’re slowly killing off all the, you know, the Nikunj Handa [00:23:11]: The old ones, yeah. Swyx [00:23:11]: Oldies. Vibhu [00:23:11]: This is a great week. I mean, it was the first time we had Frontier Intelligence at extreme speeds. Nikunj Handa [00:23:17]: Yeah. Vibhu [00:23:18]: People really liked it. Nikunj Handa [00:23:19]: Yeah. Vibhu [00:23:19]: So Swyx [00:23:20]: Yeah Vibhu [00:23:20]: First time it comes back. Swyx [00:23:21]: Yeah. for, 5.3 Spark is explicitly attributed to Cerebras. You guys are not confirming or denying that, UltraFast is related to Ce- Cerebras, but people are. I’ll just say that people do care and, are wondering about it. And you have your own silicon as well. elephant in the room, decision models. Decisions API: OpenAI’s Fast Decision Model Nikunj Handa [00:23:38]: Oh, yeah. Swyx [00:23:38]: Decisions API. We were the first podcast to do a big Jev, deep dive with, Diogo, and I also, you know, featured him at AI Engineer. How quickly did you see Jev and go like Nikunj Handa [00:23:49]: Oh my gosh. Yeah. Nikunj Handa [00:23:50]: Yeah. Firstly, like, huge props to Diogo and, like, the Jev team for, like, really inspiring the Swyx [00:23:55]: Yes Nikunj Handa [00:23:55]: Like, whole segment in the market. Like, obviously Jev comes out, everyone’s, like, losing their minds over it. Our users are, like, hitting us up. But also, like, our internal teams are like, “We need, like, a much faster classification system.” We can. I don’t wanna, like, get ahead of some of the dots features that are gonna come Swyx [00:24:16]: Whoo Nikunj Handa [00:24:16]: But you’re gonna see, like, some cool, like, really snappy, fast things built on top of the decisions API. but, you know, like, yeah. Props to Jev for, like, inspiring this whole thing. obviously a bunch of people at OpenAI get nerd sniped by that, and they’re like, “How can we, like, make this work? We’re not gonna, like-” Swyx [00:24:33]: Okay. Nikunj Handa [00:24:33]: “. train a new model.” But Swyx [00:24:34]: Like, four weeks ago, this was not on the dev radar, right? Nikunj Handa [00:24:37]: No, not at all. No. Swyx [00:24:37]: Okay. Nikunj Handa [00:24:37]: This is like Swyx [00:24:38]: Wow Nikunj Handa [00:24:38]: Jev-inspired and, like Swyx [00:24:40]: I think you are officially the first one to your lab to, like, clone and, adopt this. Nikunj Handa [00:24:44]: Yeah. Yeah. I feel like, OpenAI has such a strong, like, hacker culture and, like, people are just, like, they get excited about things. And so, guy from inference, this one awesome guy from, the infra team are like, “ this is amazing. We’re gonna, like, hack on it.” They build a prototype, it, like, works, and now we- we are just, like, hill climbing on latency and trying to make this as fast as possible, and we wanna, like, launch it in the coming days. so as soon as we hit our, like, latency target, we’ll try to get this out. Vibhu [00:25:13]: It’s interesting. At the same time of hacker culture, you also, as Sam said, like 99%, one of the most reliable APIs with Nikunj Handa [00:25:20]: Mm-hmm Vibhu [00:25:20]: I think probably the most usage, which is your team directly. how should people see decisions API? I feel like a lot of people saw Jev, heard the buzz, haven’t built with it. You’re making it very mainstream. What Decision Models Are Good For Nikunj Handa [00:25:32]: Mm-hmm. Vibhu [00:25:33]: What should people see it as? How should they use it? Nikunj Handa [00:25:36]: Yeah. I think the main use cases we’ve seen is, like, really fast classification. all the Computer Use demos have been amazing and really cool. I think there will be limitations, of course, in terms of, you know, having Astra, like, write, like, a JavaScript-like script to control your computer, versus having Luna pick, like, one action at a time. I think, it’s not gonna be at the same intelligence level, but, like, maybe there’s some Computer Use tasks that this is good enough for. So excited to see that come through. the other cool prototype I’ve seen internally is people hooking it up with GPT Live. So GPT Live is like, you know, our bidirectional, like, real-time, Swyx [00:26:14]: Voicing Nikunj Handa [00:26:14]: A- API. And, it’s built on this, like, model of front-end models and back-end models. So GPT Live is this, like Swyx [00:26:20]: Think or talker Nikunj Handa [00:26:21]: Super fast. Yeah, think or, talker thing. So GPT Live is the talker, super fast, really good at delegation, and you have something like Astra sitting at the ba- at the back. But tool calling has always felt, like, really slow in GPT Live. and so people have been, like, putting together these, like, tool calling demos of GPT Live controlling a computer, and it just feels like so much more snappy and natural. So I’m, like, kinda excited to see, like, what people do with Live and with Luna on decisions API. so that’ll be pretty exciting. Yeah. Swyx [00:26:55]: So I wanna iron this out for people, especially from the product side, because a lot of people have been putting out Jev clones. There’s been about 100 in the last two weeks. What Makes a Decision Model Different Nikunj Handa [00:27:01]: Oh, really? That’s amazing. Vibhu [00:27:03]: The first couple days. Swyx [00:27:04]: But like, it. Like, they can clone a Jev API, which is honestly structured outputs Nikunj Handa [00:27:09]: Yeah Swyx [00:27:09]: Which OpenAI was first to. Nikunj Handa [00:27:10]: Yeah. Swyx [00:27:11]: Right? So, like, I think let’s iron out for people what is a decision model, as far as Nikunj Handa [00:27:16]: Yeah Swyx [00:27:17]: As far as, like, what is important? It is not just latency. It’s not just structured output, right? Because I could just have Luna as it’- The decision model is priced the same as Luna, right? Nikunj Handa [00:27:26]: Mm-hmm. Swyx [00:27:27]: Have turned off reasoning and then have structured output. Do I have a Jev? you know, no, right? And that’s the Nikunj Handa [00:27:33]: Yeah Swyx [00:27:33]: That’s the real Vibhu [00:27:34]: There’s a confidence there. Swyx [00:27:35]: Yeah. Nikunj Handa [00:27:36]: Yeah, totally. I think, the way that. So we haven’t trained, like, a new model for this. Swyx [00:27:40]: Yeah. Nikunj Handa [00:27:40]: We’re, like, building this purely on top of the same Luna weights that we have. Swyx [00:27:44]: Oh. Nikunj Handa [00:27:44]: So yeah. This is, like, really just Luna. And, on top of that, what you’re doing is you’re constraining. So, like, structured output’s a big part of it. you’re really optimizing the inference stack to, like, get very fast on TTFD. And because you can have multiple questions, what you do is, like, you basically run those in parallel, Swyx [00:28:05]: As a batch. Nikunj Handa [00:28:06]: Yeah. You run those in the-- as a batch. you-- All sorts of, like, inference techniques people are working on to try to make it as fast as possible. But I’d say, like, at least our implementation of it at the start and this first version is, like, zero-shotting this on top of Luna, to see how it goes. And obviously, you wanna, like, put it out there. Like, this is OpenAI’s, like, classic iterative deployment thing. Put it out there, see what people think, and then, like, we’ll make more model improvements, as needed. so yeah. That’s, the decisions API. Swyx [00:28:38]: Yeah. And, obviously as a benefit, you have vision. They don’t have vision, right? Nikunj Handa [00:28:42]: That’s true. Swyx [00:28:42]: Obviously, Jev’s comes with Nikunj Handa [00:28:43]: Yeah. Like, we get it for free with Luna. Yeah. Swyx [00:28:45]: Yeah. I do think that, like, you know, some of the innovations, it sounds like, it’s still to come if it’s still the same Luna weights, which is, like, the confidence stuff, like, the in calibration is something that we’ve talked about on the podcast with, benchmarking calibration. ‘Cause basically, the whole point is that RLHF kind of collapses you towards what you want to hear. Calibration, Architecture, and the Open Research Questions Nikunj Handa [00:29:03]: Yeah. Swyx [00:29:03]: But, like, not actually, like, what the amount of confidence is. Nikunj Handa [00:29:06]: Yeah. Yeah, totally. I’m eager to see how it pans out. Maybe there’s, like, gonna be. These are gonna be, like, the key areas where we may have to, like, hill climb Swyx [00:29:15]: Yeah Nikunj Handa [00:29:15]: With the, with the future model release. But, yeah. Swyx [00:29:18]: And then architecture-wise, the other thing that’s in the debate, obviously, you-- Nobody knows because Jev doesn’t talk about it, but the two speculations are, one, maybe diffusion model instead of autoregressive. Nikunj Handa [00:29:28]: Mm-hmm. Swyx [00:29:29]: But you are able to achieve the parallel, generation in your way. And then the other one is some mech interp type thing Nikunj Handa [00:29:37]: Mm-hmm Swyx [00:29:37]: That you’re, like, analyzing the activations and then just outputting Nikunj Handa [00:29:40]: That would be cool Swyx [00:29:41]: The weights. Nikunj Handa [00:29:42]: Yeah. Swyx [00:29:42]: Which, like, you guys have all done the research on this. People have speculated. Vibhu [00:29:45]: There have been demos on Swyx [00:29:46]: Yeah Vibhu [00:29:46]: Both of these as well. I think Gemini shared a Gemini diffusion, Gemma diffusion on a Jev-style output. Nikunj Handa [00:29:53]: Oh, sick. Vibhu [00:29:53]: And, interp people have also, you know, pulled out interp from a middle layer, but this is all speculation. Swyx [00:29:59]: It’s just like, what are you trying to aim for, right? Because you can achieve the API. Everyone can achieve the API. It’s actually pretty trivial. But, like, then there’s the speed, then there’s the accuracy, then there’s the other calibration features. Nikunj Handa [00:30:11]: Mm-hmm. Swyx [00:30:11]: I don’t know what else. Nikunj Handa [00:30:13]: Yeah. Yeah. No, totally. It’s so cool that this, like, whole space has been kicked off now and people are gonna do so much cool stuff and everyone’s gonna learn from each other. And, yeah, I’m excited about it. What Developers Should Build Next Vibhu [00:30:24]: I feel like being on the platform team, a lot of your job is to empower builders. Nikunj Handa [00:30:27]: Mm-hmm. Vibhu [00:30:28]: What do you think people should build with decisions API and also Computer Use agents? Any stuff that you’ve- been building with internally that you think really opens up after the new change? Nikunj Handa [00:30:39]: Yeah. okay, let’s think. decisions API, use cases internally have been pretty obvious. Like, the user ops team was, like, jumping on it. We were like, “We gotta classify all of our support tickets.” what else came up? obviously, there were, like, the really cool GPT Live demos. I’m sure, like, the Codex app team might, like, pick this up and try to do something cool with it. So, you know, like, this whole thing started, like, a week ago, so it’s, like, very early and Swyx [00:31:06]: Oh, one week. Nikunj Handa [00:31:07]: We’re excited. Yeah. Yeah, pretty much. Vibhu [00:31:08]: There was a big push in, evals, LLM as a judge having really low latency there. Nikunj Handa [00:31:13]: Right. Yeah. That’ll be interesting to see. and then, with the Agents API, we have-- we’re basically, like, having a bunch of first-party products, like, at OpenAI built fully on top of it. we’ve had the Codex security stuff that just went out that’s fully built on top of, the Agents API. We have, sort of the-- we- we are having, like, a meetings type of thing launching today. Agents API and OpenAI’s First-Party Products Swyx [00:31:40]: Mm-hmm. Nikunj Handa [00:31:40]: I think there was, like, a demo. do you remember, like, the plugin extensions when Sam was showing it? There was, like, a demo for, like, you’re in a calendar, you can sort of, like, have your meeting notes Swyx [00:31:51]: Like, drop into a single Nikunj Handa [00:31:52]: Flow into like your space Swyx [00:31:52]: Like, Google Docs type thing. Nikunj Handa [00:31:53]: Yeah. Swyx [00:31:54]: Right? Nikunj Handa [00:31:54]: And so the-- all of that stuff is, like, fully built on top of, the Agents API. and yeah, I’m, like, just excited to see. Like, we’re just getting this out, and let’s see what people build on top of it. Vibhu [00:32:04]: I think you showed it off very well. The whole edit spaces, pages, collaborate, add in your dot. Like, that’s a lot, so Nikunj Handa [00:32:12]: Yeah Vibhu [00:32:12]: There’s a lot of inspiration people can go to. Nikunj Handa [00:32:14]: Yeah. All possible with Astra, you know. Like, thing- things just move so fast now. Like Swyx [00:32:19]: Yeah Nikunj Handa [00:32:19]: People go from idea to execution so quickly, it’s amazing. Swyx [00:32:23]: Is there something that you want, people to focus on to give you feedback? Like, what-- like, you know, maybe you’re just putting this out there and you want-- and there’s, like, a fork in the road and you want developers to help you decide. Responses API Performance and Long-Lived Caching Nikunj Handa [00:32:35]: So I think Agents API and decisions API, they are like, these are our newest products. Would love, like, any and all feedback on that to figure out where to take them. I think, over here, we’re, like, very open on Responses API, which is sort of like our workhorse over here. like, really focused on performance right now, and the performance comes in, like, two main ways. first is just, like, latency. We’ve been, like, rewriting the whole Responses API stack to, like, make it as fast as possible from a TTFT perspective, DVD perspective. So there’s like-- that, like, continues to be, like, a main area of focus for us. The second thing we’ve been trying to do is, like, really go deep on caching, particularly with these, like, personal agents that are, you know, like, basically, like, a single thread that just goes on and on forever. We’ve been, trying to, like, really up our game on caching. We provide now guarantees of, like, cache hits within, like, 30 minutes. We’re actually, like, we-- for one of our users, we just launched, like, a much longer cache window. So we have, like, a 12-hour caching guarantee, that we offer so that you have, like, guaranteed cache hits for Swyx [00:33:40]: Is that a public API? Nikunj Handa [00:33:42]: Not yet. That’s in preview. Nikunj Handa [00:33:43]: We’re gonna, like, try to get that out to everyone as soon as possible. But, like, just pay a little bit more for the cache write, and we, like, guarantee, like, cache reads for, like, a much longer period. So even if, like, your instinct thread, for example, like, you just, like, do something on it and then come back to it, like, three to four hours later, you- you’re still getting the caching performance out of it. And launched Vibhu [00:34:04]: And you cut the cost there quite a bit too, right, with the new model? Nikunj Handa [00:34:07]: Oh, yeah. That’s right. Vibhu [00:34:08]: Like, 25% cheaper, so Nikunj Handa [00:34:08]: Yeah, with, like, driving down cache reads, yeah. Cache Pre-Warming and Cost-Efficient Agent Threads Vibhu [00:34:10]: For builders, they should implement Nikunj Handa [00:34:13]: Yeah Vibhu [00:34:13]: Because it’s significantly cheaper. Nikunj Handa [00:34:14]: Yeah. Yeah. Just, like, building your apps with, like, to be very cache aware and sort of, like, use our prompt diagnostics or cache diagnostics tool to figure out, like, where things are dropping off. And, so the caching part is, like, really important. yeah, I also wanted to talk about pre-warming. We have that in the API now. So, like, if you know that, “Hey, I’m gonna get a cache,” like-- sorry, “I’m gonna get this prompt. I just wanna, like, pre-warm the cache, pay, like, the cache write fee right now, and then, like, have it sort of ready to go for the next 30 minutes for whenever.” Swyx [00:34:49]: And it can spawn many instances of that thread. Nikunj Handa [00:34:51]: Exactly, yeah. Swyx [00:34:52]: Yeah. Nikunj Handa [00:34:52]: You can just keep going and have Swyx [00:34:54]: Yeah, just keep messing with the prompt there Nikunj Handa [00:34:55]: Tons and tons of that. and so, yeah, like, I’m very excited about getting feedback on, like, the low-level performance things that we can keep making Responses API the most performant and reliable way to, like, build on top of an LLM. And then you basically have our, like, new products where I’m just looking for, like, any and all feedback. Swyx [00:35:15]: Yeah, just use it, right? Nikunj Handa [00:35:16]: So yeah, just use Swyx [00:35:16]: Tell us what to Nikunj Handa [00:35:17]: Yeah. Define our roadmap for us, please. So yeah. Swyx [00:35:20]: I think for me, the caching thing, great, right? Like, obviously very needed. But at the end of the day, you’re still bumping up against a million-token context Compaction and Managing Million-Token Contexts Nikunj Handa [00:35:28]: Mm-hmm Swyx [00:35:28]: And that’s probably not gonna change for the foreseeable future. Nikunj Handa [00:35:31]: Mm-hmm. Swyx [00:35:31]: Like, you still need good compression. Nikunj Handa [00:35:33]: Yeah. Swyx [00:35:33]: What is the best practice there? Nikunj Handa [00:35:34]: Yeah. Yeah, totally. so firstly, OpenAI has its own, like, proprietary compression, comp Swyx [00:35:40]: Which is in Nikunj Handa [00:35:41]: Compaction. Vibhu [00:35:42]: Compaction. Swyx [00:35:42]: It’s in the agents. Vibhu [00:35:43]: It’s in the API. Nikunj Handa [00:35:43]: Yes. Vibhu [00:35:43]: Agents API. Nikunj Handa [00:35:44]: Yeah. Swyx [00:35:44]: You decide for us, right? Nikunj Handa [00:35:45]: Yeah, exactly. So in the Agents API, it comes built into the harness. and if you’re in Responses API, there’s, like, two ways of doing it. One is what we call server-side compaction, which is you basically tell Responses API that if you ever hit this threshold of tokens, just auto-compact it and, like, go back, or sorry, like, reduce the context, being used. And the second way is, like, /compact, which is, like, if you want full control. So you can, like, /compact at any time Swyx [00:36:15]: I hear you Nikunj Handa [00:36:15]: Have your own logic on when to, like Swyx [00:36:17]: It’s not AGI. Nikunj Handa [00:36:18]: It. Swyx [00:36:18]: It’s not AGI. Nikunj Handa [00:36:19]: Yeah. Yeah. Swyx [00:36:20]: Yeah. But it, I mean Nikunj Handa [00:36:20]: Yeah Swyx [00:36:20]: It is the manual override. Nikunj Handa [00:36:21]: Yeah, it is the manual way. And like, I don’t know, but a lot of the big coding agents like to do it manually. I mean, like, if you look at the Codex implementation of it in the Code- open source Codex harness, you can see that they use /compact and do it. and, there’s also, like, new, by the way, new compaction techniques that we are working on. Some of them you will be able to see in the Codex harness. Like, it’s already implemented in the Codex harness. And so, they’re like some file-based, systems that we are, like, experimenting with. So yeah, lots of cool stuff going on around in compaction as well. Swyx [00:36:57]: Cool. we are running out of time. Nikunj Handa [00:36:59]: Okay. Swyx [00:36:59]: I think you’ve talked about, a lot about performance and talked a lot about, the new APIs that you’re launching. Can you give us any other hints as to things that you’re interested in as far as the future of the platform is concerned? Higher-Level Platform Primitives and the AI Cloud Nikunj Handa [00:37:13]: We’re obviously like very low level. Like, I used to work at Stripe before this, and, at Stripe a lot of the game was like building these higher level primitives and products on top of like the core payments primitives. and, I’m always like curious about what the best way of doing that is in AI. And I think we’ve had a couple of attempts at that. We like had launched assistance API like way back in the day, and like wasn’t really the right fit. We were sort of like going off with this like Agents API, and, it gives you the codex harness, but like where’s like the, what’s the right amount of flexibility to give in that? That’s like an open question. Like how should we like have memory walls and like all of these like higher level like API objects to take away, also like to abstract away more, like storage concepts. Like this is like a whole, like, there’s a whole space that I’m like very curious about figuring out how we design. I think a lot of things in AI are just have a low-level API primitive and see an example harness and go and have your coding agent implement that. But how much of that do we build into the API is like a constant question that I’m thinking about. Swyx [00:38:24]: Yeah. Nikunj Handa [00:38:24]: So I don’t know if folks have thoughts on that. If anyone has ideas, it would be super interesting to hear. Swyx [00:38:30]: Yeah. The analogy I always bring back to, and we’ll end there, is, you’re building an AI cloud, right? Nikunj Handa [00:38:35]: Mm-hmm. Swyx [00:38:35]: Like, which is, something that, Sam said a year ago Nikunj Handa [00:38:38]: Mm-hmm Swyx [00:38:38]: Where, and you’re, it’s almost like you’re kind of doing the AWS invention and you have to do, okay, this is EC2 Nikunj Handa [00:38:45]: Yeah Swyx [00:38:45]: And this is S3, and this is like. But you’re doing the AI-native versions of each of these. Vibhu [00:38:48]: There are a lot of analogies, so you’re pre-warming caches for stuff that you know will be Nikunj Handa [00:38:53]: Yeah. Vibhu [00:38:53]: And it’s nice that it’s all exposed to builders Closing Nikunj Handa [00:38:56]: Mm-hmm Vibhu [00:38:56]: ‘cause it just opens up ways that you can build new things. Nikunj Handa [00:38:59]: Yeah, absolutely. Swyx [00:39:00]: Okay. Vibhu [00:39:00]: Awesome. Well Swyx [00:39:01]: That’s everything. Nikunj Handa [00:39:01]: Thank you, guys. Vibhu [00:39:02]: Thank you. Nikunj Handa [00:39:02]: Yeah. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.latent.space/subscribe https://www.latent.space/subscribe?utm_medium=podcast&utm_campaign=CTA_2

• 0:04Speaker 00

  Okay, we're very excited to be here. Today is OpenAI Dev Day.

• 0:08Speaker 01

  We're the first podcast after the last stream.

• 0:11Speaker 00

  We have Ari here, who leads the product and engineering team for computer use agents. Before we kick in and dive deep on computer use, you want to give a quick recap? What was announced? What's the quick slew of announcements you guys had today?

• 0:24Speaker 02

  Yeah, it was a super exciting day. We just got out of the keynote. It was really sick. There were a bunch of computer use announcements that I think are worth thinking about. We have Dots, which is the new sort of personal assistant product, and that has some really exciting computer use features. There's GPT-6.1 Sol, which is this amazing new model that I think is particularly great for computer use because of sort of the cost and speed advantages. I think we shared that it's a fifth of the cost as Astra and a seventh of the cost if you're looking at computer use specifically, which is really amazing. Sorry, there were so many things. I'm trying to sort through it.

• 1:02Speaker 01

  And the API?

• 1:03Speaker 02

  Agents API, which now has computer use in it, which is really cool because now developers can build on the same computer use that is part of Codex and ChatGPT. And then there were some demos of our existing computer use features like App Shots, where you can take the context of something you're doing on your computer and bring it into Codex and ChatGPT really fast. And then like native computer use on your Mac, where Roman had it taking screenshots of his app automatically and he could do other things on his computer while computer use was using his applications. So yeah, really exciting keynote.

• 1:34Speaker 01

  And not to mention this Decisions API.

• 1:36Speaker 02

  Decisions API.

• 1:38Speaker 01

  Off the bat, are they all the same model? Like this is the same dataset? They're still to different models? Like basically, is computer use using Decisions API or are they like kind of separate?

• 1:49Speaker 02

  So what's really cool about the Decisions API is it, you know, it has all these new capabilities. It does inference in parallel. It doesn't have reasoning. It's a smaller model than the ones we use for computer use. And so those capabilities make it really fast. They also make it a little bit less good at doing like long horizon sort of sophisticated tasks. And so I think I would say it's still an open area of research for how we like bring those approaches together. But yeah, I'm really excited to see what people build with the Decisions API.

• 2:24Speaker 00

  One of the interesting things is Dots now have attached personal computers. So it seems like they're very much more persistent. You've been using them for a while. How should people push the bounds? Like what should people aim for? What should they try? Personally, right now I use it for a lot of customer service, like, oh, this was wrong. I don't want to sign in. I don't want to authenticate, find whatever and just get it fixed. How should we push further? What should people try?

• 2:50Speaker 02

  Dots are a really cool product because each dot has access to its own Linux virtual computer in the cloud, which is different from our other products. You know, traditionally we have access to a browser in the cloud or it has access to your own computer. But now you get your own entire Linux computer in the cloud and so it can run full desktop applications. And it can also use a web browser. And so, yeah, you know, I think the powerful thing about computer use and the reason why I think it's so exciting is because it makes it so that the agent can do anything you as a person can do, because all the software in the world was designed for humans and now agents can use that same software and you can delegate to the agent. So yeah, like anything that you would do on a computer, you can ask a dot to do.

• 3:34Speaker 02

  Yeah, I think what particularly useful is going to really depend on who the end user is and what's valuable in their life. But yeah, I would just start by thinking about like one of the things that you spend time on and how could you delegate those to an agent?

• 3:47Speaker 01

  Yeah, a lot of flight booking and shopping and honestly even like playing a game or whatever.

• 3:52Speaker 02

  Totally. Yeah, I don't know. For me, something I did recently, I've been working on, I subscribed to a meal prep service because I was trying to like eat healthy, you know? And I really liked this meal prep service I found because it lets me customize the meals I order to like a high degree of granularity. So I can say like, I want this many grams of chicken and this many grams of rice. But it was so complicated. It took me two hours to do an order. And I found that I could ask computer use to do it for me and it did it in 15 minutes. So I actually saved two hours. It both did it eight times faster than I could and it saved me two hours on GPT-6.1 Sol. So those are the kinds of tasks that I feel like are really powerful.

• 4:36Speaker 01

  As a creator, I can tell you automatically, immediately, my number one use case is automating YouTube. Because YouTube doesn't expose a lot of things via API. And you have to just put it in a VM and just like run it for like, let's say their A/B testing feature or making community posts. None of this is available by API because they hate developers. Anyway, so.

• 4:55Speaker 02

  I've heard that from our developer experience team too. They use it with YouTube a lot. Yeah, it's really awesome.

• 5:00Speaker 01

  So I want to draw for, you know, let's say, I want to get a little bit spicy. One of our, the leading AI podcasts, our friends is famous for saying that computer use hasn't advanced in the last two years.

• 5:12Speaker 02

  Yeah.

• 5:13Speaker 01

  Which is a very interesting statement and I think you're one of the best people in the world to talk about this, like how things have progressed.

• 5:20Speaker 02

  Yeah, you know, they said that a few months ago, I think, and I hope they have a different perspective now because computer use is like 180 degrees different than it was.

• 5:27Speaker 01

  He's a tough guy to impress.

• 5:29Speaker 02

  Well, you know.

• 5:30Speaker 01

  You worked, you've like basically spent your whole career working on like some kind of computer automation, right? Shortcuts at Apple and then Sky and then joining OpenAI. Can you draw like what your through line is for like what is driving you and what you, what wasn't possible back then maybe, like what your sort of milestones were?

• 5:49Speaker 00

  I guess to add on to that as a follow-up question, what's the major change from using Codex computer use from like last week to today? Is it model? Is it Dots? Is it harness? So all the history plus what really just changed in today's announcements?

• 6:04Speaker 02

  Yeah, on the through line, I guess I've always been excited about automation and helping people automate tasks because then you can like save time in your life and focus on things that are more important to you than like operating a computer very intricately. And so, yeah, that was why we worked on some of those products. I was at Apple before. We made a company called Sky. We ended up joining OpenAI, which is really exciting. And I think something that was special.

• 6:28Speaker 01

  You have to hack around Apple until Apple was like, fine, like we'll just hire you and you can just work on the inside, right?

• 6:34Speaker 02

  Like. It was a cool place to get to work. What was really interesting, looking back at Sky is we were, we were working on computer use there as well. And the models were so much less capable. And now the models, just in the last one year, have become extraordinarily capable of computer use. I think the biggest delta that I see is before they could like reliably start tasks, but then they would run into problems and now they're really good at debugging. They're really good at trying again, introspecting what is and isn't working. And I think we've also brought the computer use, the computer use field itself has moved forward. I think we're using more techniques. Now, computer use often writes code. So if you actually look at it in Codex and you expand the tool calls manually, you can see that it's not just doing one action at a time.

• 7:18Speaker 02

  It's actually writing JavaScript code that it executes, that the computer executes to perform sometimes many actions at once, which is a great, you know, speed up and great capability. We use more accessibility sort of multimodal interfaces. So the model may use screenshots. It may use accessibility. It may use playwright. It can use a lot of different mechanisms based on the task at hand. And then, yeah, the model acceleration has been, has been just amazing. So, yeah, what's different today? I think we're making computers better all the time. So I think just like one day's difference is probably a little bit less consequential than like even the past month or the past two months. But yeah, I think the computer use in DOT is really exciting as well as the new model that we came out with.

• 8:03Speaker 00

  On the keynote, Tijal was mentioning 7X improvements in computer use speed. A lot better on a few benchmarks. How do you guys think about measuring it? Computer use is one of those things where, as you say, you know, it's improvements over time. Is it harness? Is it model? Is it post-training? How do you guys look at it internally about measuring how good it is and what were the changes with the new model?

• 8:29Speaker 02

  We actually have a bunch of different ways of measuring it, some of which are on different permutations and configurations of the harness. It's a bit of a complicated story because, you know, our production products have, you know, some more safety checks. And, you know, those are configured differently based on the needs of the task at hand. So there's a lot of ways to measure it, but I think regardless of how we measure it, we find pretty consistent gains. And those gains are sometimes in the harness and sometimes in the model. And yeah, I was really excited by this result that GPT-6.1 is even more cost effective for computer use than its baseline cost improvement as compared to Astra. It's like really cool to see.

• 9:10Speaker 01

  Yeah, I mean, one of the visuals I really liked from the live stream was that you're sort of improving the Pareto frontier of your curve. And there was a lot of talking about how you're improving it together with the harness. Can you give some examples of aha moments that you had, whether it's on like model driving the harness, harness driving the model, whatever?

• 9:31Speaker 02

  I don't mean to repeat myself, but I think introducing more modalities has been really powerful. One more specific example of that is in the past, I think we saw a lot of computer use products had to spend a lot of time scrolling, you know, so it would like take a screenshot. It would try to do something, it would be like, oh, I gotta like scroll down to the next page of results. And then it would take a screenshot and then would try to do something, it would scroll down again. And so I think with accessibility and other and direct access to the DOM and other things like that. Now, the language model can actually see like an entire page or an entire application. It can write code that can do multiple steps at once. And so I think those have been probably the biggest single aha moments. There's like a lot of tiny ones that are less exciting in comparison.

• 10:13Speaker 02

  But actually, we do find also that a lot of speed improvements are driven by like a lot of little paper cuts that we gotta go in and intercept.

• 10:21Speaker 01

  A lot of really hard engineering. I mean, app shots in general, like I think people don't quite get the difference. Because there's like a nice visual in Codex when you take an app shot. But they don't, maybe they had the difference that you are able to actually drive each button. And you have each text in a very optimal representation.

• 10:40Speaker 02

  Yeah, yeah, exactly. Yeah, it's kind of fun, actually. If you want to be like really nerdy about it, you can go into Codex, take an app shot by hitting the two command keys. So you grab the content from whatever app you're working with, bring it into the Codex or ChatGPT Chat. And then if you click on the attachment and you click on this like little tiny button in the top right, you can see the raw text and you see the raw accessibility representation. And yeah, we've put a lot of work into.

• 11:03Speaker 01

  Just dumping everything out, yeah.

• 11:05Speaker 02

  Dumping it out, but also making it token efficient, doing it efficiently. There's like a bit of an art to it. And you know, it turns out that the same technology that was invented for humans, you know, who maybe have accessibility needs, who want to use a screen reader technology, that technology is really helpful for them to be able to use computers. It's also really helpful for LLMs to be able to use computers. So that's been like really fun to get to work on.

• 11:26Speaker 00

  For context, I feel like a lot of people don't understand app shots. They don't even know it's a feature. It's when you double hit command, it pulls in what looks like a screenshot.

• 11:34Speaker 02

  Right.

• 11:34Speaker 00

  And you're like, oh, have I opened up just a screenshot and thrown in? No, it's actually pulling all the metadata, all the code, everything.

• 11:40Speaker 02

  Yeah, exactly. Yeah. So it's like, you know, if you take a screenshot of a webpage that has a link, the screenshot doesn't include where the link goes. It doesn't include, you know, maybe you take a screenshot of your calendar, the event titles are truncated, you know? But when you take an app shot, it gives like the language model like full context about everything. And that lets it just sort of like do much more.

• 12:01Speaker 01

  Yeah. For those who want to see more, Jason Liu, I invited him to do a full workshop on this, AI engineer.

• 12:07Speaker 02

  Amazing.

• 12:08Speaker 01

  Did a great job.

• 12:09Speaker 00

  I have a broader vision question on computer use agents. So your example of take a screenshot, scroll page, take a screenshot where we were.

• 12:17Speaker 02

  Right.

• 12:17Speaker 00

  Today, they can automate a lot. What are the bottlenecks? Is it models? Is it harnesses? What, where do you see it going in like two years? Do you see it just running for hours? How do we get there? Any predictions on where computer use goes?

• 12:32Speaker 02

  Yeah, I mean, I think what's really crazy that I think, you know, the teams accomplished over the past couple of months is that now computer use is like faster at accomplishing tasks than like the average human, probably in most cases. And I think that the next frontier is to have computer use be like literally superhuman in its performance, where it actually is as fast or faster at using software than like expert computer users like us. And I think that'll be really consequential and exciting when that happens. Because I think we'll be able to all of a sudden build products that provide just much more real time experiences. And I think it'll also lowering the barrier to entry of, or the activation energy, I suppose,

• 13:17Speaker 02

  of using computer use, I think will make us start to default to doing certain things in agents that we've become accustomed to doing manually. And I think that's exciting also because it'll save us a ton of time. And I think there's a, you know, there are a lot of different little paper cuts and bottlenecks that are sort of standing in the way of that. I think that there is, yeah, there's things on the model side, there's things on the inference side, there's things on the harness side, there's things in the, in the representation. You know, we find that as computer use gets faster, we're increasingly bottlenecked by just like the speed of doing an operation. Like, for example, you know, a non-trivial amount of time in our benchmarks of computer use tasks is actually like, like, let's say you're automating a task on doordash.com.

• 14:01Speaker 02

  Like, a lot of the time is actually waiting for doordash.com itself to load, you know?

• 14:04Speaker 01

  Yeah, then you just write a wait and then you execute the wait.

• 14:07Speaker 02

  Yeah, totally. And you want to get, actually, it's actually really important that you get that, like, you want as little delay as possible between when it finally finishes loading and when you go and trigger the LM, do the next action, which is actually itself a statistical science.

• 14:20Speaker 01

  Like an event-driven way maybe to do that.

• 14:22Speaker 02

  When possible, you want it to be event-driven. And JavaScript has load events for, the web browser has load events for web navigation. But there's other types of events that actually really can't be event-driven. So there's a lot of complexity.

• 14:34Speaker 00

  The one that comes to mind is like chatting with customer service. Replies could take 30 seconds, could take three minutes.

• 14:39Speaker 02

  Oh, right.

• 14:40Speaker 01

  I have dealt with so many bots with Codex. It's great, but I also wonder if the other side knows that they're talking to a bot. Because I'm like answering in complete sentences, like I'm capitalizing correctly. Like, I'm giving full reference numbers and everything, like it's clearly too good. I don't care. Like, I'm just like trying to get my.

• 14:58Speaker 00

  I've prompted it to like, you know, don't pretend you're a bot, be very annoyed human, short one-liners, like, bullshit, do all this. I also tell it while you're waiting for responses, like use subagents to research better ways to figure out what we need.

• 15:12Speaker 02

  Nice.

• 15:12Speaker 00

  It's just like human little intervention.

• 15:14Speaker 02

  That's awesome. I also feel like half the time it's a bot on the other end. So now you've got the bots talking to each other.

• 15:19Speaker 01

  I will also say, you know, like, you know, one milestone of computer use that we're at now is, you know, three, four years ago, we were scared of hooking up LLMs to the web and to our devices. And now I'm having it configure DNS for me.

• 15:35Speaker 02

  Wow.

• 15:36Speaker 01

  I'm having it pay my bills and like really like tens of thousands of dollars of like stuff. I'm just sending it over and yoloing with computer use and like, you know, what's the worst thing that happened? So that's all really good. I think now that you've, obviously, you also have to dog food your own products and all these things. Now that you've sort of released this in API, what are some pitfalls or tips that you want to tell developers? Because they're about to, I guess, encounter all this firsthand.

• 16:03Speaker 02

  First of all, I'm just really excited that we brought computer use into the Agents API. I think this is really great because obviously a lot of developers are building applications that want to be able to work with third-party websites and services. And so computer use has this universality to it, it can work with anything. So now all of a sudden, developers can build using the same computer use implementation that we're building on. I think there's great work to be done if you want to build your own computer use harness, but it's hard. And also, we train our models on our computer use harness. So there is an advantage to using the one that's in distribution for the model. There actually might be a speed and cost and accuracy advantage. So I think it's really great for people to get to build on top of that. And yeah, you know, I think kind of to the point that you were making, like,

• 16:48Speaker 02

  I think we're all sort of still in the process and maybe like some of us are ahead of many people in the world of like getting comfortable with this technology and trusting it. And so I think it's incumbent on us to sort of build that trust over time by making sure we're building things that are reliable, by building the right kinds of safety checks, by asking for the user's consent before doing something consequential, like making a payment, by asking, you know, maybe depending on the application, making sure you're only letting it access the websites or applications that it actually needs for the task. So that's, I think, something important to think about. But yeah, I'd really encourage people to try the new Agents API, build all kinds of cool stuff on it. We'd love to hear your feedback if, you know, depending on how it goes.

• 17:31Speaker 00

  Have you seen any changes in the way it affects dev workflows? So one of the things with dots is, you know, you're seeing it in Slack, you're seeing people use voice and build. The example Roman showed of change this app and send me screenshots along the way and all this.

• 17:45Speaker 02

  Yeah.

• 17:46Speaker 00

  Is there anything that you're seeing there in adoption about how people are using computer use for coding workflows? Any tips people should take from that?

• 17:54Speaker 02

  One of my favorite use cases for computers, actually, and one that we see a lot in the wild, is computer use letting the agent actually test the software that the agent has built, which is far more consequential than it sounds. Because traditionally, you know, you'd build something in Codex and then, and the Codex builds it for you. And then you have to test it and you are now like QA for the agent, right? So with computer use, you can complete the developer, the software development lifecycle, where the agent can build software, it can test it. So I have a lot of fun, you know, building stuff, having the agent test it. By the time it comes to me, it's already working. I have extra fun because sometimes I'm like developing computer use itself.

• 18:36Speaker 02

  And so now I have a computer use agent that's using my computer use agent that's using something else. So yeah, I really, I really think this is a super powerful class of use case.

• 18:43Speaker 01

  I have a visual play test skill that I've developed that really catches a lot of design issues. Nice. That, you know, normally when you just look at code, you wouldn't really pick it up. It's also really good for cloning apps, though if you're using a shitty SaaS, you want to kill the SaaS, you just clone it screen by screen by screen. And obviously, computer use can completely drive everything, take screenshots, note it down, and then clone everything with Codex. That's really cool. But yeah, thanks for all your progress. I think that is our time. Yeah. This is not the last that we're gonna talk. Yeah, cool. This has been really fun. Thank you guys for having me. All right.

• 19:14Speaker 03

  All right.

• 19:15Speaker 00

  Okay, we're strict cutoff. We're just gonna dive right in.

• 19:17Speaker 03

  Let's do it. Yeah.

• 19:18Speaker 00

  Okay, so Nikunj, we're very excited to have you. You've shipped a lot on the API side, like we just talked about with Ari. You can now build with computer use agents. Anything you want to highlight the API side of changes and introduce yourself a little on what you do?

• 19:34Speaker 03

  Yeah, for sure. My name is Nikunj. I lead product for the API team. Been here for roughly three years. Been working on launching models. I feel like that's just been like a thing, constant thing throughout my time here at OpenAI. And with every new model, we try to like basically work super closely with the post-training team, the research team, to figure out what's new in it. And then we like expose those capabilities in the API. So that's like the basic way of putting it. And if you just look at everything that's new with GPT-6, the cool new capabilities that we launched were firstly async function calling. So what you see with like, like a lot of the things that you're seeing in like Codex and Dots and everything

• 20:18Speaker 03

  is that tool calls take so long that you don't have to like pause the model's execution while the tool is running. So you could just like kick off a tool call, keep running, keep reasoning, and then check back in. So we launched async tool calling. We launched like midterm steering. So now you can like inject messages while the model is reasoning in the middle. So as your tool call finishes, you can put in that instructions.

• 20:43Speaker 01

  And that's also partially a model alignment capability, right? Like they have to train in the ability to train.

• 20:48Speaker 03

  Exactly, yeah.

• 20:49Speaker 00

  I feel like we've had it in the app. You could always, as it's reasoning, you could steer.

• 20:54Speaker 03

  Yes.

• 20:54Speaker 00

  It wasn't the best. It's gotten much better. Excited to see how it does this.

• 20:58Speaker 03

  Yeah, and like our main goal in the API is to like put things in the API once it's trained into the harness. And so we kind of wait for that moment until it's good enough. And a lot of that is like actually being powered by WebSockets, which we launched a few, I want to say, months ago. And so WebSockets just opens this like whole bidirectional like communication thing with the model. This is not the GPT Live thing. I'm just talking about GPT-6. And you can do all these like async tool calling, async reasoning, injecting messages. It's a really fun API to work on, I think, like really enjoying.

• 21:33Speaker 01

  This is why we are the engineering podcast, because we get to talk about WebSockets.

• 21:36Speaker 03

  Yeah.

• 21:36Speaker 01

  This also pairs very well with UltraFast, right? Like that is now, like, I think for the first time ever available in the API.

• 21:42Speaker 03

  Yes.

• 21:43Speaker 01

  Which is basically the theoretical fastest speed you can ever get from tiered intelligence.

• 21:49Speaker 03

  Yeah, yeah. It's been so exciting to work on that project. I think before I go into the API, the most fun part of UltraFast has been just watching the inference team cook with Astra. Like, they're just like constantly having these like Codex agents running, trying to like squeeze out more performance. And I would say like, at least for a couple of months, a lot of it was focused on efficiency and driving the cost down, which is how we like, we're able to cut the Luna price by like 80%. It was like, a lot of that was driven by like all the inference improvements they landed. And then now they've like shifted gears towards like, how can we make this run as fast as possible? And so UltraFast has just been like amazing to see on a model like Astra, like to go that fast has been really cool.

• 22:33Speaker 03

  And yeah, WebSockets is like, actually it was like, the first time we launched WebSockets, it was for GPT-5.3 Codex Spark, which was, can't believe we named a model that, but you know, that's what we launched it for. And obviously, it helps so much because like, you gotta have the tool calls. You gotta like really reduce the overhead of going back and forth with tools. And so WebSockets is awesome for that.

• 22:57Speaker 01

  Yeah. It's always cute to see, like, I have my reset usage limit, and then I have my Spark usage limit that I never use. But like, it's there if I want it.

• 23:05Speaker 03

  I think it's gone. Finally, it's gone. I know it's gone, so.

• 23:08Speaker 01

  Yeah. You're slowly killing off all the, you know, the.

• 23:11Speaker 00

  It was a great week. I mean, it was the first time we had frontier intelligence at extreme speeds.

• 23:17Speaker 03

  Yeah.

• 23:18Speaker 00

  People really liked it.

• 23:19Speaker 03

  Yeah, yeah.

• 23:20Speaker 00

  For something comes back.

• 23:21Speaker 01

  Yeah, and for 5.3 Spark is explicitly attributed to Cerebras. You guys are not confirming or denying that UltraFast is related to Cerebras, but people are, I'll just say that people do care and are wondering about it. And you have your own silicon as well. Elephant in the room, decision models.

• 23:37Speaker 03

  Oh, yeah.

• 23:38Speaker 01

  Decision API. We were the first podcast to do a big Jev deep dive with Diogo. And I also, you know, featured him at AI Engineer. How quickly did you see Jev and go like?

• 23:49Speaker 03

  Yeah, firstly, like huge props to Diogo and like the Jev team for like really inspiring the

• 23:55Speaker 01

  Yes.

• 23:56Speaker 03

  whole segment in the market. Like, obviously, Jev comes out, everyone's like losing their minds over it. Our users are like hitting us up, but also like our internal teams are like, we need like a much faster classification system. We can, I don't want to like get ahead of some of the Dots features that are gonna come, but you're gonna see like some cool, like really snappy, fast things built on top of the decisions API. But you know, like, yeah, props to Jev for like inspiring this whole thing. Obviously, a bunch of people at OpenAI get nerd-sniped by that, and they're like, how can we like make this work? We're not gonna like train a new model.

• 24:34Speaker 01

  Like, four weeks ago, this was not.

• 24:36Speaker 03

  No, no, no, no, no. This is like Jev-inspired and like.

• 24:40Speaker 01

  I think you're officially the first frontier lab to like clone and adopt this.

• 24:44Speaker 03

  I feel like OpenAI has such a strong like hacker culture and like people are just like, they get excited about things. And so guy from inference, this one awesome guy from the infra team are like, this is amazing. We're gonna like hack on it. They build a prototype, it like works, and now we're just like hill climbing on latency and trying to make this as fast as possible. And we want to like launch it in the coming days. So as soon as we hit our like latency target, we'll try to get this out.

• 25:13Speaker 00

  It's interesting. At the same time of hacker culture, you also, as Sam said, like 99%, one of the most reliable APIs with, I think, probably the most usage, which is your team directly. How should people see decisions API? I feel like a lot of people saw Jev, heard the buzz, haven't built with it. You're making it very mainstream. What should people see it as? How should they use it?

• 25:35Speaker 03

  Yeah, I think the main use cases we've seen is like really fast classification. All the computer use demos have been amazing and really cool. I think there will be limitations, of course, in terms of, you know, having Astra like write like a JavaScript like script to control your computer versus having Luna pick like one action at a time. I think it's not gonna be at the same intelligence level, but like maybe there's some computer use task that this is good enough for. So excited to see that come through. The other cool prototype I've seen internally is people hooking it up with GPT Live. So GPT Live is like, you know, our bidirectional like real-time API. And it's built on this like model of front-end models and back-end models. So GPT Live is this like

• 26:20Speaker 01

  Thinker talker.

• 26:21Speaker 03

  Super fast, yeah, thinker talker thing. So GPT Live is the talker, super fast, really good at delegation. And you have something like Astra sitting at the back. But tool calling has always felt like really slow in GPT Live. And so people have been like putting together these like tool calling demos of GPT Live controlling a computer. It just feels like so much more snappy and natural. So I'm like kind of excited to see like what people do with Live and with Luna on decisions API. So that'll be pretty exciting. Yeah.

• 26:55Speaker 01

  So I want to iron this out for people, especially from the product side, because a lot of people have been putting out Jev clones. There's been about 100 in the last two weeks.

• 27:01Speaker 03

  Oh, really? That's amazing. Okay.

• 27:04Speaker 01

  But like, they can clone a Jev API, which is honestly structured outputs, which OpenAI was first to.

• 27:10Speaker 03

  Yeah.

• 27:10Speaker 01

  Right? So like, I think, let's iron out for people, what is a decision model? As far as like, what is importance? It is not just latency, it's not just structured output, right? Because I could just have Luna, it's the decision model is priced the same as Luna, right? Have turned off reasoning and then have structured output. Do I have a Jev? You know, no, right? And that's the real.

• 27:34Speaker 00

  There's a confidence there.

• 27:35Speaker 01

  Yeah.

• 27:36Speaker 03

  Yeah, totally. I think the way that, so we haven't trained like a new model for this. We're like building this purely on top of the same Luna weights that we have.

• 27:43Speaker 01

  Oh.

• 27:44Speaker 03

  So yeah, this is like really just Luna. And on top of that, what you're doing is you're constraining, so like structured output is a big part of it. You're really optimizing the inference stack to like get very fast on TTFT. And because you can have multiple questions, what you do is like you basically run those in parallel.

• 28:05Speaker 01

  As a batch.

• 28:06Speaker 03

  Yeah, you run those as a batch. You, all sorts of like inference techniques people are working on to try to make it as fast as possible. But I'd say like at least our implementation of it at the start, and this first version, is like zero-shotting this on top of Luna to see how it goes. And obviously, you want to like put it out there, like this is OpenAI's like classic iterative deployment thing. Put it out there, see what people think, and then like we'll make more model improvements as needed. So yeah, that's this decision API.

• 28:38Speaker 01

  Yeah, and obviously, as a benefit, you have vision, they don't have vision, right?

• 28:42Speaker 03

  That's true. Yeah, yeah, yeah. Like, we get it for free with Luna.

• 28:45Speaker 01

  Yeah, I do think like, you know, some of the innovations, it sounds like it's still to come if it's still the same Luna weights, which is like the confidence stuff, then calibration is something that we've talked about on the podcast with benchmarking calibration. Because basically, the whole point is that RLHF kind of collapses you towards what you want to hear.

• 29:02Speaker 03

  Yeah.

• 29:03Speaker 01

  But like not actually like what the amount of confidence is.

• 29:06Speaker 03

  Yeah, yeah, totally. I mean, you're to see how it pans out. Maybe this like gonna be, these are gonna be like the key areas where we may have to like hill climb

• 29:15Speaker 01

  Yeah.

• 29:15Speaker 03

  with a future model release, but yeah.

• 29:18Speaker 01

  And then architecture-wise, the other thing that's in the debate, obviously, you, nobody knows because Jev doesn't talk about it. But the two speculations are, one, maybe diffusion model instead of auto-regressive. But you are able to achieve a parallel generation in your way. And then the other one is some mech and TARP type thing, that you're like analyzing the activations and then just outputting

• 29:40Speaker 03

  That'll be cool.

• 29:41Speaker 01

  the weights, which like, you guys have all done the research on this. People have speculated.

• 29:45Speaker 00

  There've been demos on both of these as well. I think Gemini shared a Gemini diffusion, Gemma diffusion on a Jev-style output. And Inter people have also, you know, pulled out Inter from a middle layer, but this is all speculation.

• 29:59Speaker 01

  It's just like, what are you trying to aim for, right? Because you can achieve the API. Everyone can achieve the API. It's actually pretty trivial. But like, then there's the speed, then there's the accuracy, then there's the other calibration features. I don't know what else.

• 30:13Speaker 03

  Yeah, yeah, no, totally. It's so cool that this whole space has been kicked off now and people are going to do so much cool stuff and everyone's going to learn from each other. And yeah, I'm excited about it.

• 30:24Speaker 01

  I feel like being on the platform team, a lot of your job is to empower builders. What do you think people should build with Decisions API and also computer use agents? Any stuff that you've been building with internally that you think really opens up after the new change?

• 30:39Speaker 03

  Yeah, okay, let's think. Decisions API, use cases internally have been pretty obvious, like the user ops team was like jumping on it. We were like, we're going to classify all of our support tickets. What else came up? Obviously, there were like the really cool GPT live demos. I'm sure like the Codex app team might like pick this up and try to do something cool with it. So, you know, like this whole thing started like a week ago, so it's like very, very early.

• 31:06Speaker 01

  Oh, one week.

• 31:07Speaker 03

  Yeah.

• 31:08Speaker 01

  There was a big push in evals, LLM as a judge, having really low latency there.

• 31:13Speaker 03

  Right, yeah, yeah, that'll be interesting to see. And then with the Agents API, we have, we're basically like having a bunch of first party products like at OpenAI built fully on top of it. We've had the Codex Security stuff that just went out, that's fully built on top of the Agents API. We have sort of the, we're having like a meetings type of thing launching today. I think there was like a demo. Do you remember like the plugin extensions when Sam was showing it? There was like a demo for like you're in a calendar, you can sort of like have your meeting.

• 31:51Speaker 01

  Like drop into a Zoom call, like granola type thing.

• 31:53Speaker 03

  Yeah, and so that all of that stuff is like fully built on top of the Agents API. And yeah, I'm like just excited to see like we're just getting this out and let's see what people build on top of it.

• 32:04Speaker 01

  I think you showed it off very well, the whole edit spaces, pages, collaborate, adding your dot, like that's, that's a lot, so.

• 32:12Speaker 03

  Yeah.

• 32:12Speaker 01

  There's a lot of inspiration people can build from.

• 32:14Speaker 03

  Yeah, yeah, all possible with Astro, you know, like things just move so fast now. Like people go from idea to execution so quickly, it's amazing.

• 32:23Speaker 01

  Is there something that you want people to focus on to give you feedback? Like what, like, you know, maybe you're, you're just putting this out there and you want, and there's like a fork in the road and you want developers to help you decide?

• 32:35Speaker 03

  So I think Agents API and Decisions API, they're like, these are our newest products, would love like any and all feedback on that to figure out where to take them. I think over here, we're like very open. On Responses API, which is sort of like our workhorse over here, like really focused on performance right now, and the performance comes in like two main ways. First is just like latency, we've been like rewriting the whole responses APIs track to like make it as fast as possible from a TTFT perspective, TBT perspective. So there's like, that's like continues to be like a main area of focus for us. The second thing we've been trying to do is like really go deep on caching, particularly with these like personal agents that are, you know, like basically like a single thread

• 33:20Speaker 03

  that just goes on and on forever. We've been trying to like really up our game on caching. We provide now guarantees of like cache hits within like 30 minutes. We're actually like, for one of our users, we just launched like a much longer cache window, so we have like a 12 hour caching guarantee that we offer so that you have like guaranteed cache hits for.

• 33:40Speaker 01

  Is that a public API?

• 33:42Speaker 03

  Not yet, that's in preview. We're going to like try to get that out to everyone as soon as possible, but like just pay a little bit more for the cache write and we like guarantee like cache reads for like a much longer period. So even if like your instinct thread, for example, like you just like do something on it and then come back to it like three to four hours later, you're still getting the caching performance out of it.

• 34:04Speaker 01

  And you've cut the posture quite a bit too, right? With the new model?

• 34:07Speaker 03

  Oh, yeah, that's right, yeah, we're like driving down cache reads, yeah.

• 34:10Speaker 01

  For builders, they should implement because it's significantly cheaper.

• 34:14Speaker 03

  Yeah, yeah, just like building your apps with like, to be very cache aware and sort of like use our prompt diagnostics, our cache diagnostics tool to figure out like where things are dropping off and, and so the caching part is like really important. Yeah, I also want to talk about pre-warming, we have that in the API now, so like if you know that, hey, I'm gonna get a cache, like, sorry, I'm gonna get this prompt, I just want to like pre-warm the cache, pay like the cache write fee right now and then like have it sort of ready to go for the next 30 minutes for whenever.

• 34:49Speaker 01

  And it can spawn many instances of that thread.

• 34:51Speaker 03

  Exactly, yeah, you can just keep going and have.

• 34:54Speaker 01

  Yeah, just keep a system prompt there.

• 34:56Speaker 03

  And so, yeah, like I'm very excited about getting feedback on like the low level performance things so that we can keep making Responses API the most performant and reliable way to like build on top of an LLM. And then you, you basically have our like new products where I'm just looking for like any and all feedback.

• 35:15Speaker 01

  Yeah, just use it, right?

• 35:16Speaker 03

  So, yeah, just tell us what, yeah, define our roadmap for us, please. So, yeah.

• 35:21Speaker 01

  I think for me, the caching thing, great, right? Like obviously very needed, but at the end of the day, you're still bumping out against a million token context and that's probably not going to change for the foreseeable future. Like you still need good compression, right? What is the best practice there?

• 35:34Speaker 03

  Yeah, yeah, totally. So firstly, OpenAI has its own like proprietary compression.

• 35:40Speaker 01

  Which, which is in, it's in the API. Agents API. You decide for us, right?

• 35:45Speaker 03

  Yeah, exactly. So in the Agents API, it comes built into the harness and if you're in Responses API, there's like two ways of doing it. One is what we call server side compaction, which is you basically tell Responses API that if you ever hit this, this threshold of tokens, just auto compact it and like go back or sorry, like reduce the context being used. And the second way is like slash compact, which is like if you want full control, so you can like slash compact it anytime, have your own logic on when to like.

• 36:17Speaker 01

  It's not EGA.

• 36:18Speaker 03

  Yeah.

• 36:20Speaker 01

  But I mean, it is the manual over.

• 36:21Speaker 03

  Yeah, it is the manual way and like, I don't know, but a lot of the, the big coding agents like to do it manually. I mean, like if you look at the Codex implementation of it in the open source Codex harness, you can see that they use slash compact and do it. And there's also like new, by the way, new compaction techniques that we are working on. Some of them you will be able to see in the Codex harness, like it's already implemented in the Codex harness and so they're like some file based systems that we are like experimenting with. So, yeah, lots of cool stuff going on around in compaction as well.

• 36:57Speaker 01

  Cool, we are running out of time. I think you've talked about, a lot about performance and talked a lot about the new APIs that you're launching. Can you give us any other hints as to things that you're interested in as far as the future of the platform is concerned?

• 37:12Speaker 03

  We're obviously like very low level, like I used to work at Stripe before this and at Stripe, a lot of the game was like building these higher level primitives and products on top of like the core payments primitives. And I'm always like curious about what the best way of doing that is in AI. And I think we've had a couple of attempts at that. We like had launched Assistance API like way back in the day and like wasn't really the right fit. We're sort of like going off with this like Agents API and it gives you the Codex harness, but like where's like the, what's the right amount of flexibility to give in that? That's like an open question, like how should we like have memory vaults and like all of

• 37:53Speaker 03

  these like higher level like API objects to, to take away, also like to abstract away more like storage concepts? Like this is like a whole, like, there's a whole space that I'm like very curious about figuring out how we design. I think a lot of things in AI are just have a low level API primitive and see an example harness and go and have your coding agent implement that. But how much of that do we build into the API is like a constant question that I'm thinking about. So, I don't know, if folks have thoughts on that, if anyone has ideas, it'd be super interesting to hear.

• 38:30Speaker 01

  Yeah, the analogy I always bring back to and there is you're building an AI cloud, right? Like, which is something that Sam said a year ago and it's almost like you're kind of doing the AWS invention and you have to do, okay, this is EC2 and this is S3 and this is like, but you're doing the AI native versions of each of these. There are a lot of analogies, so you're pre-warming caches for stuff that you know will.

• 38:52Speaker 03

  Yeah, yeah, yeah.

• 38:53Speaker 01

  And it's nice that it's all exposed to builders because it just opens up ways that you can build new things.

• 38:59Speaker 03

  Yeah, absolutely.

• 39:00Speaker 01

  Okay. Awesome.

• 39:01Speaker 03

  Awesome, thank you guys.

• 39:02Speaker 01

  Thank you.