Inside OpenAI’s Agentic Browser, Atlas

The AI labs fighting for attention during the Super Bowl call to mind another iconic Super Bowl moment: Apple’s 1984 ad for the Macintosh, which promised that the personal computer would be a source of unbound wonder, freedom, and delight. They were right, but over time, the personal computer has also become cluttered with errands. These “computer errands”—downloading a W-2 when tax season rolls around, hunting for the right coupon code before checkout, or navigating the unholy labyrinth of the Amazon Web Services dashboard just to change one permission setting—have taken over our digital lives. Atlas, OpenAI’s agentic browser, sprang from the idea that AI should handle this tedium for you. In this week’s episode of AI & I, Dan Shipper sat down with two members of the Atlas team, Ben Goodger and Darin Fisher. Goodger is Atlas’s head of engineering, and Fisher is a member of the technical staff. Both are legends of the browser world. They’ve spent decades building the modern web, working together on Netscape, Firefox, and Chrome before arriving at Atlas. From that vantage point, they told Dan how they think browsing is about to change, why building a browser is harder than it looks, and what it’s like to create a new one with AI coding tools like Codex. If you found this episode interesting, please like, subscribe, comment, and share! Want even more? Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: https://every.ck.page/ultimate-guide-to-prompting-chatgpt. It’s usually only for paying subscribers, but you can get it here for free. To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Move fast, don’t break things Most AI coding tools don’t know which line of code will actually break your system. Try Augment Code, which understands your entire codebase, including the repos, languages, and dependencies that actually runs your business, and use their playbook to learn more about their framework, checklists, and assessments. Ship 30% faster with 40% shorter merge times. [Playbook at ⁠augmentcode.com⁠] Timestamps: 00:01:57 - Introduction 00:11:51 - Designing an AI browser that’s intuitive to use 00:15:24 - How the web changes if agents do most of the browsing 00:25:06 - Why traditional websites will not become obsolete 00:29:00 - A browser that stays out of the way versus one that shows you around 00:39:51 - How the team uses Codex to build Atlas 00:44:47 - The craft of coding with AI tools 00:52:33 - Why Goodger and Fisher care so much about browsers Links to resources mentioned in the episode: Ben Goodger: Ben Goodger (@bengoodger) Darin Fisher: Darin Fisher (@darinwf) OpenAI’s browser, Atlas: Introducing ChatGPT Atlas

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

• 0:00Speaker 00

  I think one of the things that has excited me about this world is it's not just the pace of development, because I think to get a feature to work right, it's always going to take a few iterations. It's how quickly you can decide that something is worth pursuing.

• 0:13Dan Shipper?

  The big unlock that I had with Atlas is I realized I never need to look at a settings panel ever again.

• 0:20Speaker 02

  You're not alone.

• 0:35Dan Shipper?

  If you work in large codebases, you know what it means to hold too much in your head. Which file imports what, what service depends on what database schema, and what will break if you change this one line? The bottleneck isn't writing code. It's holding the entire system in working memory long enough to make a decision. Augment Code is an AI coding assistant that offloads context. Its context engine understands your whole codebase, including what's in your current file and the architectural shape of your entire system. It works with multi-language interactions, legacy code, and the dependencies that aren't documented anywhere. The system is what makes it work, and Augment documented it in their AI-powered engineering at scale playbook. Inside, it includes how to assess your current state, the four-phase framework for moving from individual experiments to team-wide deployment,

• 1:18Dan Shipper?

  ready-to-use checklists, and the specific workflows that produce 30% faster PR velocity and 40% shorter merge times at companies working on code where mistakes are expensive. This is designed for enterprise teams working on high-stakes production systems. It's both for compliance, correctness, and maintainability. It's both for the moments you're not just prototyping but shipping code that millions of people depend on, and teams are seeing measurable results. 30% faster PR velocity and 40% shorter merge times. Download the AI-powered engineering at scale playbook at augmentcode.com/resources/AI-poweredengineeringatscale. That's augmentcode.com/resources/AI-poweredengineeringatscale. And now, back to the episode. Ben and Darren, welcome to the show.

• 2:00Speaker 02

  Hey, thank you. Great to be here. Yeah, likewise. It's awesome.

• 2:04Dan Shipper?

  So for people who don't know you, you are both building ChatGPT Atlas, which is an agentic browser. Ben, you are the head of engineering. Darren, you're a member of the technical staff. I believe you both worked on Chrome originally. Is that true?

• 2:22Dan Shipper?

  That's right.

• 2:23Speaker 02

  That's right. We worked on a number of browsers and together and for a long while.

• 2:29Dan Shipper?

  Oh, that's really cool. So I didn't realize that you're you're this is like a it's an evolving partnership through many different products and companies. That's really interesting.

• 2:38Speaker 00

  We worked together first at Netscape, then on Firefox together for a few years and then with with Chrome and now Atlas, which is super exciting.

• 2:47Dan Shipper?

  Absolute OGs. Okay, this is really cool. So I'm using I'm a daily Atlas user and I switched from Dia, which I know Darren, you used to work at the browser company. I'm good friends with Josh and Hirsch. So if you're if they're listening, you know, maybe there's a way to get me back, but Alice is Alice is is pretty good. What's really interesting to me about using Atlas and using just just really agentic browsers is I for the first couple of days, I was like, I have no idea what to do with this.

• 3:17Dan Shipper?

  Like, I know it has this power, but I don't I can't think of a time when I want I might want to use it. And now I'm just like every single day, there's like 50 different things that if I had to like click through another fucking form or settings page, I would like blow my head off.

• 3:33Speaker 02

  But isn't that kind of the journey that people have with AI tools in general, like ChatGPT or these coding tools, you kind of don't really understand the power until you get into it?

• 3:43Dan Shipper?

  I think that is true. I didn't quite have that experience. Like, the first time I just saw it, like writing GPT three writing stuff, I was like, whoa, this is crazy. But yeah, I guess that is true. Well, I guess I'm curious from your from from both of your perspectives, like. If someone is listening and they're like, I know that agentic browsers are a thing and maybe I've tried it, but I actually don't even know why I would use this or like what it's useful for. What is what is the sort of vision for agentic agentic browsers? And let's be let's try to be more specific than like, yeah, it just does everything for you. You know, like, what is the like, what are the real day to day things that agentic browsers change about how you might use the web?

• 4:22Speaker 00

  Yeah, so I think that, you know, maybe the future will get to a place where like more and more of your workload can be can be automated. And I think we're making progress in that direction. But but today, we wanted to design Atlas with this idea that you could bring ChatGPT with you wherever you go on the web.

• 4:42Speaker 00

  And so, yeah, I mean, I think the thing that you know, like, what do I do with this? This is something that we we hear a lot from people, but then also we hear some aha moments as they go on the same journey that that you have and begin to figure out some use cases for it. This is something that we actually want to take some of that that learning that we have from how people are using it and help offer more proactive advice to people like in products to help them figure out how to optimize use of the tool. But I think today, like, one of the things that I noticed when I use Atlas versus when I go back and use a sort of pre-AI browsing environment, I find myself just able to ask just a lot more questions and just be more knowledgeable about a topic.

• 5:23Speaker 00

  If I'm doing online shopping, I can feel confident that I'm getting the best deal, or I have the right coupon code, or I have all that sort of stuff. If I'm like researching a topic that's of interest to me, I can sort of brainstorm, you know, different viewpoints on it. I can just sort of have this this sort of friend or advisor that this sort of comes with me and I can just like have this conversation with it. And that that's just made the web a lot richer and more dynamic.

• 5:47Dan Shipper?

  Can you make that more concrete for me? Because I think some of those things, someone might be listening and being like, well, yeah, I could do that with ChatGPT now. That's what ChatGPT does for me. So what is it? What does it mean to have that in the context of your browser?

• 6:00Speaker 00

  It just means that you don't need to go, you know, I think if, you know, for anyone that's had ChatGPT in a tab, you probably have the experience of going and taking some content from another tab and pasting it in and asking a question about it perhaps. Whereas when you have a browser that's built with this at the core of it, you know, that context is provided directly to the model. So you kind of don't need to keep repeating yourself. It will just ChatGPT will just see what you're looking at and be able to offer, you know, its thoughts on that.

• 6:29Speaker 02

  I think that's really the big the big unlock and the power of this whole thing. It's like, I think as people use ChatGPT for more things in their life, they realize that maybe they should start more of their queries with ChatGPT, right? You start to learn that for yourself at a certain point, you're like, why am I? Doing things the old way, that was very manual, but instead I should ask this AI model, it will help me save some steps. And this browser puts that at the center of it. That's what the URL bar will guide you towards for your queries, right? It helps you get into chat GPT with a lot lower friction. And as Ben was saying, you know, if you're on a webpage and you're scratching your head about something, ask chat GPT is right there. You can ask it. It has the context. You don't have to

• 7:13Speaker 02

  copy paste and say, can you now ask this answer this question? So it's just a lot more streamlined. That's, that's kind of the core value proposition of this whole thing. And on top of that, we build, you know, features that people can opt into around web memories. So the agent or the model is there and on your journey, you can also query it later about things that it's, it knows. And that can be very powerful to you as you're trying to get back to things or trying to make sense of just all the things in your world and you know, whatever kind of journey you're on, whatever research project you're on, whatever work you're trying to do. Having it there sort of passively, it can be very powerful too.

• 7:54Dan Shipper?

  I gotta tell you like, and hopefully maybe this can be like a little bit of a user research session too, because like, I feel like I'm, I'm doing something with this that I'm very excited about. And I'm curious if you guys are doing it, if you're seeing other people doing it, how you're building for this. So the, the big unlock that I had with Atlas is I realized I never need to look at a settings panel ever again.

• 8:19Speaker 02

  You're not alone.

• 8:21Dan Shipper?

  Yeah. And that is such a refreshing feeling. It's, I think it's both refreshing for users and for software developers. I think it's refreshing for software developers because you don't have to worry about adding another knob because someone like the agent's going to do that. So you can, you can make software more custom customizable more easily. But for users, like, I think the canonical example for me is looking at the AWS dashboard. I don't know if you like, I assume you guys are both logged into that and it's like 50 different services and then like your, the settings, the like, the permissioning system is like, it's like launching a nuclear like missile in order to like do anything. And I run a company and we have like 20 people and so I'm, I'm sort of constantly being asked,

• 9:07Dan Shipper?

  hey, can we like add a seat to this or like, can you change the permission on this thing or, and it's like some account that we set up five years ago that I don't even remember.

• 9:14Speaker 02

  You don't do these things so frequently. And so, yeah, it's like not top of mind how to do it again.

• 9:20Speaker 00

  Yeah, my, my example of this that I've been using was, um, uh, I used it to help me create Google Forms to do user research. And, you know, the Google Form Builder, I think is maybe less complicated than the AWS Control Panel, but, still it's not something I use every day. And so I think for, for me to be able to ask the agent to go off and do that and have it do that in a few minutes and come back and I can just submit. You know, certainly allowed me to get to the, the meat of the problem much quicker.

• 9:49Dan Shipper?

  Yeah, it's, it's one of those tasks where like, there's a certain amount of activation energy and you don't have to spend the activation energy anymore. Darren, what were you gonna say?

• 9:59Speaker 02

  I was just saying, it's that time of year to go into workday and figure out how to get my year end to date pasted up so I can share that with my tax advisor. And I'm like, where do I go again? They moved it again, you know, and I'm, I'm good there often enough. So I think it's super powerful for navigating like web apps, especially complex ones, like you said with AWS.

• 10:25Speaker 02

  And it's just, that's, that's, that's one of the definite superpowers of these things.

• 10:29Dan Shipper?

  So how are you seeing that evolve with your user base? Like what percentage, if you can share, what percentage of people have actually figured that out? Because I, it's super powerful, but I also imagine it's not necessarily a daily use case. It's like, a couple of times a week, it is a lifesaver, but other than that, I may not use it. For this, like, I'm, I'm only going into settings like a couple of times a week. So I'm curious, is that one of the, one of the use cases you can hang your hat on and are, are people really discovering it? Or is it still sort of nascent?

• 11:01Speaker 00

  I don't know if we have the exact stats on the sort of agent like browser drives kind of

• 11:08Speaker 00

  a thing, but we do know that just in general, people interacting with that side chat is a main like use case for the browser. And I think, you know, like probably most people are using that on a on a regular basis, just because it is kind of the main value add. So the main surface in terms of what tools or capabilities people use from that, I don't think they've got that broken down quite the same way.

• 11:33Speaker 02

  Yeah, what we what you see is sort of what you'd imagine is that people are, you know,

• 11:40Speaker 02

  you, when you first come to these tools, you don't know all the things that it can do. And that's definitely a topic for us. How do we introduce people to things, but not also overwhelm them at the same time? You know, you want to have, you want to balance something that's familiar, simple, seems approachable, but also it's powerful under the hood. So you get rewarded as you discover further. You know, I think that's, that's kind of the nature of UX development, right? You can have a very powerful, complex tool, a browser really is. But you want it to also be approachable and easy. And you got to think about like, what are the patterns people do? And how can we meet them in those moments? Right?

• 12:18Speaker 00

  What are the some of the decisions that you've made to like to do that, like to to to enable the sort of progressive disclosure of complexities that Alice is really intuitive, but yeah.

• 12:28Speaker 02

  One of the features that is pretty powerful, but or relatively, or I should say, we struggled with how to expose it is this feature called cursor chat. If you're interacting with a form field in the browser, you'll see a little icon, a little chat to BT icon. And you can hover over and then interact with the model and interact with the model in the context of that specific form field.

• 12:52Speaker 02

  We were, we struggled with how to how in your face to make this, right? We want people to be aware of this power. It's actually really powerful. The people who use it are the people who rave about this, helping them compose and that sort of thing. But actually, a lot of people don't discover it, even though we have this little hint. And so it's always a question, how big do you make that hint? How do you introduce this to people? Certainly during onboarding, we already have a lot of things we try to tell people about because this is an AI browser. There's new things to learn, fundamental things like web memories and, and, and, you know, capabilities like side chat and so on. But we can only tell you about so many things at once. So that's been a challenge for us from a design perspective, for sure.

• 13:33Dan Shipper?

  That makes sense. I've seen that that that little icon, I have not clicked it. So now I need now I feel like I need to click it.

• 13:40Speaker 00

  It's one of those things where it's like, it's a another advantage of having this sort of fully integrated with with your browsing environment as opposed to just having chat GPT in a tab is that you can kind of summon it into the specific text field. So this is a feature that my wife uses quite often. She has to write emails. She's involved in a number of different things and it just helps like speed up her workflow quite a lot, having it there. And the thing is, is it's not just, it is like your chat GPT there. So it has your personalization, your, you know, custom instructions, all that kind of stuff, you know, behind it. So it, you know, writes the way you want it to write and all of that. So it's pretty cool.

• 14:18Speaker 02

  Probably speaking, we're really interested in the whole idea of like, how the model can interact with the web and the ways that we interact and how can it dovetail with what you're already doing. So, you know, the agent is that you invoke with slash agent inside chat is like a very

• 14:36Speaker 02

  all in sort of manifestation of that where you're asking it to take a task and go interact directly with the page and all the and push the buttons and do everything for you.

• 14:45Speaker 02

  And that's, that's sort of like, maybe the grandest representation of this kind of idea. But there's all these sort of smaller in the moment kind of versions of that, you know, like we said with cursor chat or just the fact that side chat has the context and when you ask a question, it can understand what you're doing.

• 15:01Dan Shipper?

  Yeah, that's, I think that's one of the the most valuable parts of it is because it's in my browser, it's logged into all my websites and it can act as me

• 15:12Dan Shipper?

  on any number of websites. And so even though it's not me, it's like, it has all the same affordances and and and all that kind of stuff. And I'm curious about your opinion on how the web will evolve for that because right now, there's like, there's a, it's really designed for this like bifurcation between bots and humans and there's a human experience and there's a bot experience that. You're presumed to be crawling and there's bots on text and robots on text and all that kind of stuff. And this is sort of this sort of in-between thing where it's personal and it's driven by you, but it is not you. And like, yeah, how do you think the the web should evolve for that kind of thing?

• 15:55Speaker 00

  Yeah. So I mean, this is a super interesting one. And I do think over time, like, there'll have to be some like notion of, you know, maybe a non-human operator that is acting nonetheless on behalf of a human, like for a specific request, because I see these things as quite different. To example, to, for example, web crawlers, you know, web crawlers are out there traversing websites and, you know, sort of synthesizing across that for the benefit of many. Whereas like, you know, this is, you could do the same thing, you know, admittedly much more painfully, if you were to write a, you know, local shell script that would go off and obtain the content of a website, maybe issue like the direct HTTP requests to the the resources that you wanted and so on. And this is much closer to that, where

• 16:38Speaker 00

  there is like your own personalized intent behind it. So I think just from how we think about these things conceptually, that that's how I look at it. In terms of how things evolve, I think one of the most interesting things about it is, at some level, like, stuff doesn't need to evolve, because we have, you know, computer use models that can just go off and like, read the screen and click and do all that, that sort of thing. I think a lot of the evolution here will come from, are there ways to make that more seamless? Are there ways to make that, you know, higher performance so that we can do many things at once, you know, do, you know, just basically support sort of scaling this up? Because I think what we really want to do is have something that can do many things on your

• 17:21Speaker 00

  behalf simultaneously over the course of time. And that will just require like a lot more sort of interesting sort of evolution of the platform. And I think there are probably a variety of different ways to do that. One of the wonderful things about the web is that it's a very declarative medium. And so this is something that we've begun to tap into, but I don't think we've fully like realized the potential of that, that interesting property of the web yet.

• 17:44Dan Shipper?

  Can you explain for you who are listening, what declarative means? And then why that is an interesting and important property?

• 17:51Speaker 00

  Yeah, so the web, powering the web is this technology called HTML, Hypertext Markup Language. And it's a way that all of the webpages are built, all of this UI that you interact with on the web today is a combination of just text formatted in this specific manner. There are these things called tags. So a button might be a button tag that encloses the text that is rendered on the button. And so what the browser does is it reads all of this and it knows that if it sees a tag that says button or input or something like that, that there is a specific meaning to it. And then what's interesting, for example, with forms is that a form is the way that you do effectively like a call to a remote function with some data that the user provides.

• 18:35Speaker 00

  So when I fill out a form, for example, to run a search, I take values that I, there's a text that I type into this field and then I call some remote function with that text and then I get another page. And so there's all of this sort of, this is sort of inherent to the way the web is designed. And it allows, you know, the browser itself is referred to as a user agent specifically for this reason. In that the browser is designed to go and read all of these tags and figure out how to present it to the user in a way that is satisfactory to them.

• 19:07Dan Shipper?

  And so Atlas is sort of a user agent agent?

• 19:11Speaker 00

  That's right.

• 19:13Dan Shipper?

  Do you think we need different user agent strings for, is that like, is that one potential solution or extension of the HTML standard?

• 19:23Speaker 00

  I'm not sure. I think just like looking at the way the web works, you know, there's a lot of, and just thinking back to various browsers that we've worked on, there's a lot of subtlety to user agent strings. And also like, the situation I don't want to get into is where websites don't work because we've changed something about it. And sometimes there are sites that will check for very specific parts of that string and it will be. They'll say something, you know, they'll so trigger behavior based off of that. And I know early in the Chrome days, for example, we would see, you know, sort of behavior like that where it would cause sites not to render properly. And so from that sense, you know, with Atlas being predominantly Chromium, we feel like it's just, you know, from a developer perspective, they should perceive it.

• 20:08Speaker 00

  They should, you know, build for it the same way that they build for any Chromium-based browser. But there's probably other signals or stuff like that that that we will need to come up with over the course of time. It's just it's very early for us to figure out what that looks like.

• 20:20Speaker 02

  But your original question about like how the web might change is a really interesting one. I think as more and more of the user agents are perhaps driven by agents or models,

• 20:35Speaker 02

  you know, why not end up having some bearing or impact on how developers create their content?

• 20:44Speaker 02

  I think at some point, maybe there is an inflection point there. If, you know, it'd be interesting to see how the ecosystem evolves, right? You know, people create content for human consumption. In the past, we've always, we've had moments when we're pushing heavily semantic web. Make a web that's more understandable. Look at all the benefits that come from that. Screen readers will work better. Websites will be more machine understandable. What's happened in this now with these AI models is they're able to make sense of the websites that aren't very ordinarily machine understandable. But because these models are interacting with it in the way humans do, they're able to glean the information just as humans do.

• 21:27Speaker 02

  And that's kind of a big unlock for the computer to help you because it can understand these websites, right? But as as that unlocks more and more computer models, base models driving these systems, these websites, maybe, who knows? Maybe, maybe the websites start changing as well. I mean, it reminds me of discussions about what happens when all the code is being created by coding agents. And and the coding agents are directing the coding agents and, you know, where where does where does everything go? And and what what programming language ought ought they use and all these kinds of things? You start to wonder, maybe there's some sci fi stuff there to kind of dream and imagine how things might have evolved.

• 22:11Speaker 02

  I would be lying if I told you I know. But I can imagine things changing.

• 22:17Dan Shipper?

  Totally. That's the kind of the interesting thing is like, right now, browser uses, it's a really good way to bootstrap this because you don't have to change anything for it. But once, like, once you've bootstrapped and everyone's using agents, I'm sort of curious if

• 22:31Dan Shipper?

  that is actually the most efficient way. For example, Ben, you were, you were talking about, you know, having it do multiple things for you at once, you know, having a, watching Atlas scroll through websites is kind of slow. And there, there may be a more agent native way to allow agents to interact websites like MCP, for example. Are you guys thinking along those lines? Or is, are you still really just focused on the core stuff?

• 22:58Speaker 00

  We're thinking through like a whole host of different, different technologies to help us drive, drive, you know, web browsing.

• 23:07Speaker 00

  I think as well, like beyond the Atlas team, just to think broadly about what ChatGPT is doing, like we've also, you know, launched these, these, this app ecosystem around, around the product. And I think that that's sort of a very direct way in which we're encouraging developers to build for a more dynamically composed world. But that's, that's, you know, that's of course in the browser, but it's, you know, maybe not like part of Atlas in particular. So I think some of these things are, we're going to try a few things and, and, and see how it works out.

• 23:40Speaker 02

  Plus, you know, a lot of the technology that's powering the ChatGPT Atlas agent now, you know, has its roots in the original operator tech preview that, that OpenAI put out. If you rewind the clock back to then and compare the performance then to now, start to see, you know, it's sort of the rate of improvement. There's been like leaps and bounds improvement, sort of the quality and, and this performance. And we're kind of on that curve of, of figuring out how to optimize and make these things work a lot better. And I think there's a lot of exciting work ahead and opportunity ahead. And this is, this was a meaningful step to share with people. And I think it's, it opens the door to like

• 24:21Speaker 02

  imagination and possibilities and for people to have some real things that it can help you with, like what you were talking about earlier. But there's so much more to come, you know?

• 24:32Dan Shipper?

  Do you think agentic browsers will make the web unnecessary? And by that, I mean, do you think there's a chance there's a there's a future state where it actually becomes just better to stay inside of chat GPT? And your agent is going off and doing all the browsing and then, you know, maybe it's maybe it's building like a custom website for you in real time, based on what the brand or the writer has wants wants you to see. But you're not actually like seeing rendered HTML in the same way that you would have been, you know, five years ago.

• 25:05Speaker 00

  I don't think so myself, and maybe maybe this is just me not not a mad not being imaginative enough yet about like where chat GPT will go. But I I do think that there's an aspect of, I think we will see people delegate a lot more to these tools, especially as they grow more powerful and they're going to get like amazingly powerful over the next 12 months.

• 25:27Speaker 00

  But

• 25:29Speaker 00

  I still think that there's a lot of stuff that people want to do themselves.

• 25:33Speaker 00

  And whether it's, you know, even just things like entertainment or like, you know, there's aspects of of, you know, shopping or trip planning that I'd like I do want to be deeply involved with, and it's probably going to start at least with some like curiosity that I have. And I'm going to go out there on the web and find it. And I think one of the most exciting things about the web is it has so much stuff on it. And so I'm always like excited to explore it. And I don't think that will ever go away. Maybe it will be different. Maybe there will be folks that, you know, maybe they're like the the kids today that haven't sort of lived in a world without some of the stuff like they may have a different view on it. But that's just mine. I don't know about you, Darren.

• 26:10Speaker 02

  I know I I think people like window shopping. I think people like browsing. I think people like that sort of thing. Or, you know, I love taking Waymo, but I also love driving my stick shift car. And, you know, there's going to be moments when both are, you know, important. There there's moments when I want the Waymo and moments when I want to be just driving myself, you know? And I think that's kind of the future is going to always be that way. And

• 26:38Speaker 02

  Also, it depends on what you're trying to do. You know, I think that these models can be just incredible at synthesizing things for you that might lead you on to the manual mode part of it. Right? And, and, and you're probably gonna just incorporate these things in a very natural way in your life. You're gonna go between them where, where it makes sense to you and people are gonna figure out, figure out that. But there's going to be, there's always gonna be a need to interact with, with them, you know, web apps, if you will, or applications. And the web is a tremendous medium to distribute those things. E-commerce, the web is an amazing medium for that. Yes, you could ask your model to please prepare you a, you know, a shopping cart of

• 27:22Speaker 02

  items, but you're gonna wanna go look at it and you're gonna wanna go see things yourself. You're not just gonna be like, yeah, buy that for me without seeing it in most cases. And so, you know, I think there's, there's kind of this blended world that we're probably.

• 27:37Speaker 00

  There's aspect as a, of, of the AI as a, you know, like actually like a workmate or a coworker or something that you can delegate to. And then there's an aspect of the, the AI as a, as a thought partner or collaborator in that sense. And I think that these worlds sort of are actually elegantly, you know, it's neither one or the other, it's kind of both. Yeah.

• 28:01Speaker 02

  Yeah, definitely as a thought partner. This is already the case for these models, you know, when you're researching something for, at home, you're asking the, you know, the chatbot about it. Saves you some time, figure, you know, just as an exploration, bouncing ideas off. When I'm coding, I'm doing it that way. So many things I'm bringing chat GPT in my life to help me sort through my thoughts and what kind of problem I'm working on. And I think that's, that's sort of what, what I imagine, you know, I can imagine lots of parallels to that in the future.

• 28:36Dan Shipper?

  So here's something I'm curious about. When Josh and Hirsch were first starting the browser company, I'd been friends with them for a long time. And so we actually talked to them for a little while about being the CEO. And so I spent a long time thinking about browsers for this specific thing. And one of the

• 28:56Dan Shipper?

  one of the things that I was kind of interested in is the role is the role of browser in someone's life. And it seemed to me at that point that mostly a browser was sort of like a taxi. It's like it takes you from one place to another and it's supposed to get out of your way. It's very utilitarian.

• 29:14Dan Shipper?

  And that we might be moving to a place where maybe it's more of like a tour guide. Like it helps you figure out where you want to go and what you want to do and then does some of it for you.

• 29:24Dan Shipper?

  But there's this interesting tension there where

• 29:29Dan Shipper?

  inserting yourself between the user and what they want to do sometimes is like super frustrating. And your tour guide is super annoying. And people think of browsers as being, I think in a lot of ways, like I think of it as like a, it's an invisible window pane. Like you don't even realize the browser is there most of the time. That's the point. How do you guys think about those?

• 29:48Dan Shipper?

  Do you think that that like dichotomy is is useful or interesting? How do you think about it? And how do you think about the trade off of

• 29:57Dan Shipper?

  fulfilling the sort of expectations that browsers are more or less invisible versus helping the user get more of what they want, even if they didn't necessarily know that they wanted that thing?

• 30:08Speaker 00

  Well, there's a sort of duality here present in Atlas. And I say this not as a punt maybe, but just to observe that we have tried to make our browser UI like fairly streamlined and minimal. So that you can focus on the thing that you're looking at. But then chat GPT is sort of at the heart of the experience. So it is there. And then you can choose how much you want to engage with it. I think the value of it comes from like, I think the big thing that most people struggle with in their day to day life is like ambiguity sometimes is like, what, what do I do next in this situation to achieve whatever the objective I have is? And that's where chat GPT is just incredibly amazing at helping with that.

• 30:50Speaker 00

  It was sort of the first that back, that was sort of the original idea that I had for this was when I would. Just ask ChatGPT in my existing browser tab, like, what should I do to solve this problem? And then like a friend that would step through, you should do like these three things. And then my question was, well, could you just do some of those for me?

• 31:09Speaker 00

  You know, sometimes, you know, it's still a lot of things that can't do today, but but we can make it do more of those things.

• 31:14Speaker 02

  Yeah, we get reports from users asking, hey, I asked Chat, I asked Atlas, asked ChatGPT through Atlas to do this thing for me and it and it didn't work. We're like, great, let us know. We will keep note of that and work on those things, you know?

• 31:28Speaker 02

  And so it is, it is, it is, it is that kind of thing where you start to feel like I should be able to ask it anything. I should ask it to help me with anything. And so, you know, that's, that's a nice start.

• 31:41Speaker 00

  I think one of the things about this form factor, though, is that it's very, you know, it's very familiar to people. I think most people, you know, can kind of relate to a browser. They kind of know how to use it, that kind of thing. And so there, I think it's not a huge leap. I think if you go to a world where everything is intermediated to you by some other thing, you know, it's kind of hard to know what you can do with that. Whereas with the browser, you kind of know how to just start browsing the web and doing stuff with it. And then it's the opportunity presents itself in various points along the way, like that you can at your own choice. Even with agent mode, or especially with agent mode, you choose when and how you want to use it. And then it's really on your terms. And of course, I think probably over the course of time, we'll find people will want to use it more and more.

• 32:25Speaker 00

  And so you want to help show them where that's going to work well. But yeah, our goal definitely is not to be annoying. I remember the sort of original mantra with with Chrome was, you know, sort of trying to like really minimize the the Chrome as as it were and focus on the content. And I think we want to continue to have that be the case. But this, in this case, the content is whatever the user is trying to get done.

• 32:51Speaker 02

  Yeah, it's got to be a good browser first and foremost, right? It's got to actually work the way people expect it to work. And that's, that alone is, keeps us busy. And, you know, there's a lot of aspects to just that alone.

• 33:05Dan Shipper?

  I can imagine.

• 33:06Speaker 02

  Yeah. And then, and then, you know, how do you, how do you sort of add on to that, right?

• 33:12Dan Shipper?

  What are the things that I might not realize about why that's hard? Because like, I'm sitting here using your product all the time, being like, yeah, browsers are basically solved, except for this AI stuff.

• 33:24Speaker 02

  I guess that's true at some level.

• 33:28Speaker 00

  But like what makes it hard that if you're if it's keeping you busy like what are what are the sorts of things that are keeping you busy?

• 33:33Speaker 02

  Oh, well, I mean, if you think about it, you know, browsers have definitely evolved over the years, right? You know, rewind back to Netscape and then think about Firefox, then think about Chrome and think about when Chrome first launched. And then think about all the features that have been added since. And, you know, not everybody uses all of those features, but some people use them. And we hear from those people. And Atlas is has a significant subset of those features from the get go. Because we knew they were important. And building on top of Chromium meant that some of them we were able to expose, but many things. We had to reimagine, rebuild, figure out how to build in a new way.

• 34:18Speaker 02

  And, you know, some things we have not yet done. So we're in them. For example, one of the things we heard about early on when we launched Atlas was where's my tab groups? Right? And that's a feature that Chrome added a few years back, but it certainly wasn't there in the initial version of Chrome. And I know that when we first launched in Chrome, not that many people were excited about it or used it. It was a sort of a small feature until eventually it's become something that maybe a good number of people actually do care about. And we hear about those those we hear from those people. Because they didn't want to carry their workflows over, you know?

• 34:56Speaker 00

  So one way to think about a browser is that it's kind of like a it's like an embedded operating system. And so in that sense, you might think of a browser as an app, but I think that's maybe not the right way to look at it. A browser is more is closer in complexity to an operating system. It has an app runtime. It has a window manager. It has, you know, various notification surfaces and and launchers and other stuff. And so there's just a lot of complexity in building all of that that stuff out. Now, you can short circuit a bunch of that. I think, you know, Darren says maybe it's a solved problem. I think for a lot of browsers, it is with including Atlas, part of it is solved because Chromium, like the fact that Chromium is open source. It presents this just amazing, incredible baseline upon which to build.

• 35:41Speaker 00

  And you could you could stand up a browser very quickly that looks more or less like Chrome. I think our product ambition ran a bit deeper than that. I think we wanted to differentiate a bit more in our product UX. And so that caused us to take a different path, which we've written about. But that does mean that there's a bit more of this legwork for us to go and like, make sure all of this functionality that people expect works in the way that they expect. But we think that at the end of the day, that will give us a lot more

• 36:11Speaker 00

  ability to sort of shake the product in new and interesting ways.

• 36:14Speaker 02

  Yeah. There's some various for instances, but like we, we, if you're familiar with the blog post that Ben was referring to, we, we run Chrome completely out of process. And so our app, the Atlas app is a pure Swift app that presents all of the browser, familiar browser UI through UI elements that we had to, we had to craft. Again, they were not just using the implementation from Chromium for any of the UI components. What we leverage from Chromium is the fact that it's great at rendering webpages and all of the accessory support associated with that, you know, when it comes to

• 36:56Speaker 02

  various kinds of permission dialogues and whatnot, we, we hook into that and we present those dialogues, but in our own UI. And so there's just a lot of very table stakes kinds of components there that because of our choice to build the app wholesale in, in Swift environment, all the UI components, I should say. We had to rebuild a lot of different things. And of course, we had a prioritization there.

• 37:22Speaker 00

  Although the thing that

• 37:25Speaker 00

  the advantageous about this approach for that is, you know, actually a sort of fun fact about Chromium is that much of the UI is built using C++ as a programming language, which is the thing that you did when you were building a Windows app back in 2006 era. But it turns out to be hard to find engineers in this day and age that want to do UI development in C++.

• 37:48Dan Shipper?

  Why, why is that?

• 37:49Speaker 00

  I have no idea. Speaking as a long time C++ developer, I'm very confused.

• 37:53Speaker 02

  I love it. What's the problem?

• 37:56Speaker 00

  But, but yeah, there's a lot of iOS developers out there, it turns out, and iOS developers often know Swift and Swift UI. And if you know Swift and Swift UI, you are also, you can be a Mac developer. And so we take advantage of that and it's worked really well. Like we've been very successful at building a team.

• 38:12Speaker 02

  And Swift's actually a remarkable language, very like, very much like a modern alternative to C++. You know, has, you know, there's a garbage collector, so it's got a very streamlined sort of memory management sort of setup. Kind of like if you were just being really straightforward about using smart pointers in C++ and that sort of thing. So at any rate, we, I feel like this has worked out very well for us and we were leveraging this, this and this to also bring the product to Windows.

• 38:43Dan Shipper?

  What, what percentage of your code is written by AI?

• 38:48Speaker 02

  Oh, man, I don't even have stats on that, but I know everybody's leveraging Codex and ChatGPT heavily as part of this project.

• 38:56Dan Shipper?

  I would say just like finger in the wind, if you had to guess.

• 38:59Speaker 00

  Majority of it, I would say. I, I, I can't pick the precise amount. It wouldn't surprise me if it was north of 75%, just that like most people's PRs start with Codex.

• 39:13Speaker 00

  You know, maybe there's some like dialing in that you do through the process, but that, that just means in terms of raw volume, Codex is like probably authored, you know, well over more, more than half, safely more than half of the like net new code that we have at this point.

• 39:27Dan Shipper?

  You guys have been building browsers for many, many years. You started at Netscape, you worked together at Chrome or on Chrome.

• 39:35Dan Shipper?

  How does, how does it compare being able to build a browser with, you know, Codex at your side? In terms of team size, velocity, all that kind of stuff, like what is, give me a sense for what's different or maybe it's, maybe it's very similar. But yeah, how does, how does it compare?

• 39:50Speaker 00

  Yeah, I was gonna say, we have a very small team, although we continue to grow to take on a bunch more possibilities. I think one of the things that. Has excited me about this world is it's not just the pace of development because I think to get a feature to work. Right. It's always going to take a few iterations. It's how quickly you can decide that something is worth pursuing. And so there will be an idea that I'll have in my head even as like a team manager. Where I want to see if the juice is worth the squeeze, as it were. And I will just run off and do that in Codex and I'll have a build and I'll see if I like the thing or not. And if I do like it, then it's it makes sense to go and invest in that area. And sometimes we spend, you know, a long time, like in the pre-Codex world.

• 40:36Speaker 00

  Sort of wondering about if you should do this or that because it takes so long, even to prototype. Whereas Codex just makes prototyping a matter of minutes or hours for a lot of things.

• 40:48Speaker 02

  And you know, for as long as we've spent in the Chromium codebase across our careers. Man, that thing's complicated and it's grown. And so being able to ask Codex questions about Chromium is just invaluable. And you know, any kind of very large legacy codebase is going to have so much complexity and layers to it. And so, you know, the ability to ask these agents questions about it is just unbelievably useful. But same thing goes for, you know, figuring out how to build. Certain kinds of UI effects, you know, constantly probing ChatGPT for like, what's the right way to.

• 41:28Speaker 02

  To set this thing up. So I'll get a good animation or something like that. Just trying to like, learn some new strategies with core animation or something like this. So we have like. Like Ben said, a lot of our code is is able to be created by Codex. Because, you know, there's a lot of straightforward aspects to what we're doing. But there's also very delicate aspects that we're doing. We have to get in there and really study it. But these tools can be tremendous companions as we're trying to figure out, well, exactly what that. What's the right strategy here to kind of explore the solution space? I I just I just can't believe how useful it is, but it's been such an accelerant for this project for sure.

• 42:09Dan Shipper?

  On the topic of being able to prototype things more quickly,

• 42:13Dan Shipper?

  is there anything like weird or crazy that you have in your head that you've been wanting to try? That isn't quite that, that you know, you want to share with us?

• 42:20Speaker 00

  Oh yeah, let me tell you about something I've been working on.

• 42:25Speaker 00

  Yeah, just in the process of, I'm like a heavy tab user and I nerd out on, on like the little details of how tabs work. So like the Chrome tab strip, like a lot of the way it behaves around like where tabs get inserted, what gets selected after you close them, how like the tab strip like reflows, animates when you move your mouse out of the, like, I worked on that like years and years ago. Like, you know, it's almost 20 years ago at this point. And although like I have not have had less of a direct engineering role in Atlas myself, I do like to poquet different things. And so one of the things I've been playing with, with, you know, as Darren and the team work on, on tab groups,

• 43:07Speaker 00

  I have been exploring ways to just help make sure that the tab layout and scroll position remains stable as you switch back and forth between tasks. And you might be deeply buried down on a task. You might have like lots of tabs, lots of tab groups open. You might have scrolled your sidebar of tabs down to a certain position. And then I have this moment where I want to go back and check my Gmail. And I like get a like a tracking link or something and I open it up. And all of a sudden my tab strip is flung back to the top, like it gets scrolled back to the top. And so this is, this is what happens today in Atlas. And so I was able to go off and prototype a solution to that in Codex in about an hour. Or I'm actually able to go and check on something without messing with the scroll position.

• 43:53Speaker 00

  And it's just like a transient, a transient world where I can go and like look on something quickly. So that's the kind of thing where like, if you're interested in just making the app better, you can go off and just do like a really quick exploration and determine that something, you know, makes sense.

• 44:08Dan Shipper?

  Isn't that the best?

• 44:09Speaker 02

  Yeah, a lot of times we get feedback from people too about like, hey, I wish this thing or that thing, or would if this was possible. And then invariably somebody on the team will have gone off and tried it. And it's because it's not that expensive to try it to Ben's point.

• 44:23Dan Shipper?

  It's really great. Do you all have mixed feelings at all? Like, I know a lot of professional programmers, even people that work every, even people who are super psyched about AI, who are also like, it also is kind of a bummer that, you know, a lot of code isn't being written by hand anymore, and there's a certain craft to it that is maybe, you know, you just sort of like writing code. How do you guys feel about it?

• 44:46Speaker 02

  I like writing code, but I think I would, I like the sort of crafting aspect. There's some, something there, almost like therapeutic about it, you know, just sort of, it's like art or something, you know, but um, I still feel like there's a lot of elements of that. What, what I, the way I really view this is, it's like, it's a tool that will accelerate, like the mundane parts of the work. For example, I tediously did a refactoring across the codebase that was a little bit tedious because each time, each part was different, and I didn't really quite know how to prompt it through all of that. But then, once I had

• 45:29Speaker 02

  done it, I need to do another one. I was like, Codex, just do that for me. Do the other one. And it was of similar scale, and it knocked it out within an hour, right? And it was because it could follow my pattern for all the, all the times when I worked through all the quirks, it could just follow those quirks, those patterns. I thought that was amazing. And then, you know, like I said, if I'm crafting some animation or something like this, I'm, you know, Codex is going to be really useful to give me ideas, but I gotta get in there, try it and see. And sometimes that, that's just how, how I work. But I find, I find that it still is accelerating me quite a bit. And I still get that satisfaction of getting in there and crafting.

• 46:10Dan Shipper?

  I think maybe there's some, like some version of this that will know that, like, we've achieved some level of

• 46:15Speaker 00

  Maybe even super intelligence with this stuff, if it can just go off and build something like Chromium or WebKit or like that, that sort of thing of that scale with like very minimal prompting. But I think we're a bit from that point. So I do think that there's an element of individual engineers have judgment that comes from experience that can sometimes see things that aren't evident in the code, because what a coding agent is doing is it's reading the code and it's oftentimes making really good choices about things. I'm surprised sometimes at how elegant some of the solutions that

• 46:55Speaker 00

  that Codex can come up with are, but it doesn't always hit because it doesn't always know some of the context that isn't stated there. And so that's why I think, you know, to a lot of extent, you know, Darren talked about asking Codex questions about Chromium.

• 47:12Speaker 00

  I think, you know, people would, you know, I remember being on the Chrome team when everyone had asked Darren questions about how Chromium worked and Darren's asking Codex questions. There's still

• 47:25Speaker 00

  a need in many, especially more sophisticated, more subtle places for that judgment to be applied. And to like, but then once you have that judgment, you just go so fast because you just tell it like, I think you should create a cache in this format. And you should, you know, you should put it in this place in this package. And then it just goes off and does it at like much faster than you could have. And at least myself, I don't feel precious about typing that code. You know, it's more like the idea, right?

• 47:52Speaker 02

  One thing that's been an interesting phenomenon is that thanks to Codex, actually, we have a lot more unit tests. Because it doesn't, the overhead of creating a unit test is greatly reduced when you can just prompt for what you want to have tested. And even the model is able to go and like consider cases I didn't prompt for it because really I'm saying, can you unit test this API for me? Or I've been really impressed with this because

• 48:18Speaker 02

  That's a mundane task, creating unit tests for any crafting the API. It's an interesting task. I'll work on that. And then, once I have it, hey, Codex, can you create a whole bunch of tests for me? It's been a fabulous, it's been a fabulous friend in that regard. And I think we've seen a lot of benefit from that. And tests are, of course, super valuable. Those tests help us not make further mistakes. So, you know, it's just been really, that's, that's been a definitely a sweet spot.

• 48:48Dan Shipper?

  Well, you were talking about getting feedback from users, asking you for things to, to fix things. I have a, I have a quirk that I would love to know if there's a, if there's a way to make it better now, like just for me prompting better, or if just, just to put it out in the ether, if it was fixed, it would change my life. So I run a media company, so we publish articles all the time. And there's a lot of copy editing going on. And so I have an article that I wrote that's coming out tomorrow. And like, it's, it's full of edits. And the editor who does it, like, some of it is, it really requires a lot of editorial judgment. But some of it is the equivalent of writing unit tests. It's just like, you know, you're, the capitalization is wrong here. And there's a comma missing here.

• 49:33Dan Shipper?

  And there's a bunch of copy edits, basically, that are constantly being made. And we do it in Google Docs. And I've tried, we have a whole style guide. And I've tried to have Atlas go through and suggest changes on the Google Doc according to the style guide. And it, it kinda happens a little bit, but then it just gives up. And says, I did it, and it definitely did not, it did like one thing, you know? And I think partly it's, it's, it's sort of the, the structure of Google Docs is so complicated. It requires a lot of dexterity. But I'm curious, what, what do you guys think? And is that something that you could mix? Yeah.

• 50:13Speaker 00

  Yeah, quick question for you. Are you using the agent mode to do that? Is that what you have?

• 50:18Speaker 02

  Yeah.

• 50:18Speaker 00

  There's been a known issue with our agent. We call it laziness. Where sometimes you'll see it say things like, oh, this task is too time consuming. I, you know, basically I give up and it's not just Google Docs. But it would, you know, for a variety of sites where the task might take like very many steps or an extremely long time to run. And especially if it's like having to like scroll multiple times to get through like, you know, if you're, imagine you could be tens, hundreds of pages even. It may give up under those conditions. That's something that the team has been working on.

• 50:52Speaker 00

  As improvements to that, but you're also right that Google Docs is a fairly complex web app. It's not something that, it's a bit different to a lot of web content. I talked before about declarative web where there's just a, you know, a tag that you can read through and see everything, whereas Google Docs is much more like a traditional app. It uses a canvas. It just sort of renders text directly when you scroll. It is the one drawing, not, not the web runtime. And that makes it a bit more challenging to get all of the context out. And so, yeah, I think the agent is maybe the right way to do complex things there, but the sort of laziness fixes will, will, should eventually help with that kind of thing.

• 51:32Speaker 02

  There's issues when the agent has to know if it should scroll. You know, and things of this sort, which can be critical for a web app. That's, that's not just straight up HTML. But I have seen it excel in some cases like this elsewhere. I've been impressed watching it tediously close like ads in order to reveal a content below in order to then complete my task. So I can sort of see on the horizon where it's gonna, you know, these, but those are definitely cases of complexity that, you know, where it has to interact.

• 52:06Dan Shipper?

  Ad based businesses are quaking in their boots hearing, hearing about chat GPT Alice agent clicking like X on ads to get to the actual content that you want.

• 52:18Speaker 02

  Well, again, it's doing what I would have done.

• 52:22Dan Shipper?

  I agree. I agree. I'm, I'm here for it. We only have a couple of minutes left.

• 52:28Dan Shipper?

  I, I think the one big thing that's left on my mind is

• 52:34Dan Shipper?

  you, you guys have been, been doing this together for many years and have been working on browsers for many, many years. Like, why do you care so much about this problem?

• 52:43Dan Shipper?

  Oh, God.

• 52:46Speaker 00

  It's the most interesting app in the world. Like I said, it's like a mini operating system and is all of this amazing content. Like when I was so I got into the web when I was a teenager, I lived in New Zealand, which is like the other side of the world. And I felt very disconnected from the world of tech, like at least at that point, I think New Zealand has grown a lot in terms of its technological prowess over the years. And the web was amazing because it felt egalitarian and that anyone anywhere could get involved in it and they could like publish a website. And then eventually, you know, when I got involved with Mozilla, that you know, you could actually go and help shape the thing. And like open source and all of that, it's all kind of tied together. And I just love it. I wouldn't, I wouldn't work on anything else.

• 53:31Speaker 02

  Yeah, I think for me, I have somewhat of a different but similar origin story of getting involved in all this stuff. Found myself in college using Linux and feeling like, man, this system would work a lot better if the browser worked better. So I took a job at Netscape to try to make that browser better, you know. And but it was so liberating. I remember that when I did things through web, it meant that it didn't matter what computer I had, I could still do those things. I think it's sort of a fantastic idea. And it's sort of a fantastic that we've had this thing. And it can be better. It's kind of like this, this thing where web and browsers, they've been good and powerful and we depend

• 54:14Speaker 02

  on them, but they, you can all point to crafty aspects to them and things that could be better. And so it sort of feels like it's not done yet. It's felt that way for a long time. And so, you know, that kind of keeps me going because there's more stuff to do. There's more, more to make better.

• 54:30Dan Shipper?

  Ben, Darren, this is awesome. Thank you so much for joining. Really appreciate all the work that you've done through the years and thanks for making Alice. It's great.

• 54:39Speaker 02

  Awesome. Thank you.

• 54:40Speaker 00

  Thanks for having us.

• 54:49Speaker 03

  Oh my gosh, folks. You absolutely, positively have to smash that like button and subscribe to AI and I. Why? Because this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard. But instead of gold, it's filled with pure, unadulterated knowledge bombs about ChatGPT. Every episode is a roller coaster of emotions, insights, and laughter that will leave you on the edge of your seat, craving for more. It's not just a show. It's a journey into the future with Dan Shipper as the captain of the spaceship.

• 55:21Speaker 03

  So do yourself a favor. Hit like, smash subscribe, and strap in for the ride of your life. And now, without any further ado, let me just say, Dan, I'm absolutely, hopelessly in love with you.