Cognition’s CEO on What Comes After Code

The future has a way of showing up early to some places. In software engineering, one of those places is Cognition—the startup that made headlines in early 2024 with Devin, the world’s first autonomous coding agent, and more recently with its acquisition of the AI code editor Windsurf. Scott Wu, Cognition’s cofounder and CEO, has a front-row seat to what comes next. In this episode of AI & I, we talk with Wu about why the fundamentals of computer science still matter in an AI-first world, the direction he sees for the short- and long-term future of programming, and why he believes we may already be living with AGI. Timestamps: 00:00:00 – Start 00:02:02 – Introduction 00:02:32 – Why Scott thinks AGI is here 00:09:27 – Scott’s personal journey as a founder 00:16:55 – Why the fundamentals of computer science still matter 00:22:30 – How the future of programming will evolve 00:26:50 – A new workflow for the AI-first software engineer 00:29:33 – How Devin stacks up against Claude Code 00:40:05 – Reinforcement learning to build better coding agents 00:50:05 – What excites Scott about AI beyond Cognition 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 Links to resources mentioned in the episode: Scott Wu: Scott Wu (@ScottWu46) Learn more about Cognition: https://cognition.ai/ Try the world’s first autonomous coding agent: https://devin.ai/

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

• 0:00Dan Shipper?

  Software engineering is being radically changed by AI. Being able to program in English by launching agents to build features and fix bugs is changing all of the techniques and the primitives and the best practices that if you're a software engineer, you've grown up with. And for a lot of people, there's a big question about whether we're going to need software engineers at all anymore. That's why I brought Scott Wu, the co-founder and CEO of Cognition Labs on the podcast. Scott is one of the most important experts on this topic because cognition builds Devon, an AI software engineer. Devon came out just a couple of years ago, and it's already at 73 million in ARR. You can think of it like another teammate that you can talk to on Slack that has access to its own computer and can build small features or fix bugs basically autonomously.

• 0:45Dan Shipper?

  Cognition also just acquired Windsurf, a cursor competitor. So in addition to having a fully autonomous AI software engineer, now they have a programming editor with AI built in. So they're one of the foremost players shaping the entire landscape of what programming is going to be like over the next 10 or 20 years. And that's what I talk about with Scott. We talk about what AGI is and whether it's here or not. And we talk about what programming is going to look like now and into the future. We talk about the different bets that players like cognition and Anthropic and OpenAI are making to win the programming and AI race. We talk about the recent wave of CLI tools that have taken off like Claude Code and Codex CLI. We talk about how Scott sees Devon fitting into the landscape and why he acquired Windsurf.

• 1:28Dan Shipper?

  This is a great episode because Scott is that rare combination of guests that both has really practical, hands-on frontier experience because he's building and he's also incredibly smart and incredibly articulate. If you're looking for a conversation that gets down to the actual brass tacks of what the future of software engineering is like, this is the episode for you. Enjoy.

• 2:02Dan Shipper?

  Scott, welcome to the show.

• 2:03Speaker 01

  Yeah, yeah. Thanks for having me.

• 2:06Dan Shipper?

  Of course. So for people who don't know, you are the co-founder and CEO of Cognition. You are the makers of Devon, the AI software engineering agent, and recently the acquirers, the lucky winners of Windsurf.

• 2:20Dan Shipper?

  It seems like you've had a really crazy couple of months over there.

• 2:23Speaker 01

  Yeah, it's been a fun few months for us. I was gonna say, I mean, it's been an interesting time for everyone, I think, in the AI coding space, but a crazy few months especially for us.

• 2:32Dan Shipper?

  So the thing I want to start with first is you said something on John Colson's podcast recently that you think AGI is here. Explain.

• 2:40Speaker 01

  Sure. No, I mean, so it's at least a little bit facetious, obviously, but I think it's worth thinking about that, you know, 10 years ago, what would we have called AGI? Right? And we would have said, okay, it's got to be able to pass the Turing test. Obviously, it's got to be able to converse with you and just like, you know, come off as a human and just be able to relate to you and think and, you know, in much the same way that a human does. It's got to be able to solve like, you know, tough technical problems. It's got to be able to do a lot of the same tasks. It's got to be able to interact with the real world the same way that a human would. Right? And I think to first order, we've basically done all of those things. I mean, passing the Turing test, we've obviously done, you know, we have, you know, OpenAI and others, you know, have

• 3:24Speaker 01

  released work on, you know, getting a gold medal at the IMO and the IOI, you know, solving incredibly hard technical problems, building agents that can go and actually interact and reason in the world. And obviously, you know, I think there's an interesting question of, well, there's still so much more that humans do, and then there's so much more to it. And I think that's true. Maybe one way to put it is, you know, my view is that's going to be true for quite some time to come. And sometimes people ask about AGI from the perspective of like, well, AGI is when humans have nothing left to do at all, you know, or something like that. Or, you know, one of the definitions that people use is like, AGI does 80% of knowledge work or things like that. You know, I think these things are really hard to define and really hard to kind of.

• 4:10Speaker 01

  Exactly clarified because humans specifically do the parts that are not automated, right? I mean, it's it's kind of like, like it whether eighty percent of human work has been automated. You know, I claim that it already has been a long time ago, actually, because as soon as we had the tractor and as soon as we have, you know, it's it's like, if you think about what people did a thousand years ago, we are doing way less than twenty percent of that work. Right? And so a bit facetious for sure, but I guess my point is like, you know, I think we have a lot of levels of AI development that occur. I'm not sure there's one hard cutoff on what counts as AGI, but I think it's also very clear that, you know, we've hit a lot of the things that people would have considered insane, you know, just a few years ago. So.

• 4:52Dan Shipper?

  I think that's such a good point. Like, that's why I hate the eighty percent of knowledge work definitions because knowledge work changes. It's not like it's not a static thing. And I think people underestimate the, once you, once you automate one level of work, there's always another level of work above that. And I mean, we've all seen this over the last three years. A lot of the stuff that I do today is, a lot of the stuff I was doing three years ago is automated now. And I'm just doing more, like more per unit work, which is really interesting. Yeah.

• 5:24Speaker 01

  Yeah. And as humans, we're always so, you know, we're we're human centric in our view, I guess, was the way to say it. We're very proud of ourselves and our work, which we should be. But but, you know, you can imagine at some point, it's like, you'll just be able to just like think a couple of thoughts and then have all of this come out and happen in reality. And we'll still be saying, oh, you know, well, AI can't do that, you know, humans are still doing all the important work, right? And of course, it's like AI, you know, at that point, or or technology in general, at that point, will have made us like ten thousand times, you know, faster by virtue of doing ninety nine point ninety nine percent of the work. But but but it's kind of, it's very hard to define what what counts as percentage of labor, right?

• 5:58Dan Shipper?

  Yeah. So I have a particular definition of AGI that I'd love, I'd love to bat around with you. Feel free to criticize, poke holes in it, but also I'm interested in what you think. So the the definition of AGI that I like actually comes from.

• 6:13Dan Shipper?

  Child psychology. So when children are born, they are essentially like totally dependent on their caregiver. You can't leave them alone for any length of time. And as they get older, you can leave them for progressively more amounts of time to be on their own. So, you know, an infant or like a toddler, you can leave for like five minutes or 10 minutes or something like that in their room. As they become children, you know, you can leave them alone for like hours or more. As teenagers, they go away for, you know, maybe a night at a time and then they go to college. Fully autonomous.

• 6:48Dan Shipper?

  And so my definition of, and I think if you look at the development of agents and just AI in general, it has followed that same trajectory. So when GPT three was first on the scene, we were just at the tab complete, you know, level of autonomy. And now we're seeing, you know, Devon or GPT five or Claude code run for, you know, 10 or 15 minutes, 10 or 15, 20 minutes at a time. And you can sort of see the smooth lengthening of that leash in the same way that you see a smooth lengthening of the leash for children. And so I think a good definition of AGI is when it is economically profitable to never turn your AI off. It's always working. It's always doing something.

• 7:31Dan Shipper?

  And when enough people are doing that, I think that counts as AGI.

• 7:35Speaker 01

  Yeah, yeah, I think it's super, it's super fair, I would say. One thing is obviously it's very dependent on dynamics in the sense that, well, if everybody has an AGI, you know, then the AGIs are competing with one another for their, you know, usefulness or something, right? And so there's like some of that, but, but, but I, I, I, I think that's right. Yeah, like I think there is a point when you can truly just have an always on agent that's going and doing meaningful work and, and producing value off of it.

• 8:05Speaker 01

  Economic value is, I, I, I think the, the, the one thing I would push back against is the idea of economic value, just because as we're saying, so much of economic value is depending on, you know, how substitutable it is that you're providing, you know, or, or, or things like that. But, but no, that's cool. Yeah, I, I, I feel like the, to, to your point about like the, the, the doubling time of, of how long these agents can operate. I mean, it's like, it's, it, it has continued. It's, it's, it is insane how long that trajectory has continued. You know, it's like, there's always this saying of like, you know, you can never trust an exponential curve or you can never keep predicting points in an exponential curve. And yet like they, they, they've kept coming. So.

• 8:43Dan Shipper?

  They certainly have. I'm curious, actually, one of the things that this makes me think about is, because I'm thinking about growing up and I'm thinking about the process of growing up for you. I think that Devon is your first, Cognition is the first company you started. And is it?

• 9:00Speaker 01

  So I actually, I started a company before this. It was called Lunch Club. So I ran it for about five years.

• 9:06Dan Shipper?

  Okay, so you're, okay, so you're more of a veteran than I thought.

• 9:10Speaker 01

  Well, it's, you know, still very much a new, so.

• 9:15Dan Shipper?

  I am curious, though, like, what has that been like? You've been running Devon, or you've been running Cognition for at least a few years. What were you like when it started? And what did you believe about yourself and the world? And what are you like now?

• 9:27Speaker 01

  Yeah, you know, it's honestly crazy.

• 9:31Speaker 01

  I think especially because I had run a company before and in the sense of like, you know, I think over the last decade or so, you know, there are a lot of different, you know, great companies that got built. But, but, you know, the pace of what's happened in AI and the trajectory of AI has already, I think, been very vastly different from a lot of that. And it's already gone much faster. I think for me,

• 9:55Speaker 01

  there were a few, there are a few elements for sure. There's a little bit of the chip on the shoulder of, you know, I feel like I could do better. I feel like I could do more. But honestly, I think there was also just a feeling of like, I just, I have to try, is kind of how I thought about it at the time. Like, I thought about it, the way I thought about it was, if you try and, you know, you built something really meaningful and it works out great, obviously that's great. Yeah. But, but, but, you know, what happens if that doesn't happen? Right? And the question for me was kind of like, would you really, would you rather try and give it everything you had and just find out that, you know, it didn't work out and you weren't the one and whatever else?

• 10:35Speaker 01

  Or would you rather not try and wonder about whether you could have done it? And I think for me, the answer was pretty clear that I just wanted to give it a go. And so that's a lot of what it was like for me. In practice, obviously, it was like, It was almost kind of like walking our way into building a company. You know, it's, it's, it's not even necessarily the case that we were saying like, oh, we're gonna build a company. You know, I, I think at the time it was really just like exploring ideas and AI and looking into the things that we found really interesting, which naturally we're just nerds. And so AI coding is like the coolest thing, right? And so we were messing around with a bunch of these, you know, it was me and a bunch of my friends who I've known for like years and years.

• 11:16Speaker 01

  But as it became more clear that AI coding is gonna take off and stuff like RL is gonna really work, you know, over the next while. And it's gonna unlock a lot of these product experiences. Like, I think there's a real question of like, is this the thing that we want to commit and spend our, you know, all of our focus and all of our effort on? And, and that was the trade off for me.

• 11:38Dan Shipper?

  Yeah. And how are you different now?

• 11:41Speaker 01

  Yeah. And now I think, um, I've been having a great time, to be honest. It's, it's, and I, I, I consider myself very lucky, you know, in that. And I, I think there's like, there, there are a few things I think about it that are really nice. I think obviously the problem that we work on is great. I think people, I, I, I think of the people that you work with as the most important thing. You know, someone gave me this advice a long time ago that you're gonna spend most of your time working. And so you might as well work with people that you really like. And, and I still, I, I still always thinking about that. And, and so like the, um, no, I, I, I, a lot of the different, you know, I, I think I've learned more things.

• 12:23Speaker 01

  I, I, hopefully I've gotten a little bit better over the course of the last couple of years. But, but, but, but in a lot of ways, I think it has been much the same way. You know, I, I, I, I think that, do you know the line of like, um, you know, leave it all on the field?

• 12:41Speaker 01

  Yeah. And, and I really like that mindset of like, you want to go and try your best, but you also want to be able to live with Yoko. And, and I think that's how we very much think about it today of like, we, we give it everything that we have. We, we, we do the best that we can. You know, you can control the inputs, you can't control what happens at the end. And, and we, we just want to be able to say that we gave it everything we have.

• 13:02Dan Shipper?

  I feel that. I mean, I definitely feel like inside of every, I just love the people that I work with. And that makes it so much better to run a company when you're just, everyone's having a great time together, you know? And I think another way to frame leaving on the field that I've, I've felt myself is. I would do this even if it failed. And even if it didn't make a lot of money. And I think that's actually somewhat rare today. And, and, and it sounds like that is a big part of your journey too, because these are things that you're just interested in and playing around with yourself anyway, regardless of whether it was be a gigantic company.

• 13:42Speaker 01

  Yeah, it's, it's like, you know, everything could blow up today. You know, who, who knows what happens, you know, all the, we have a huge AI winter or, you know, something happens with the hardware or whatever. And then, you know, AI collapses and I would still, you know, and our company collapses and whatever, you know, God forbid. And I would still be like, that was an amazing two years. Like I had a great time. I'm really happy that I got to do this for sure.

• 14:04Dan Shipper?

  But how does it, how has it changed your relationship to something that you used to love and just play around with, having the amount of responsibility that you currently do to do that thing?

• 14:16Speaker 01

  Yeah. Yeah, that's a good question. I mean, it's, I grew up doing a lot of coding, obviously. I mean, funnily enough, you know, despite all of these, arguably, you know, because of, because of my day to day work, I get to do less coding now than I did before. And so, so I don't know exactly what that implies, you know, and I obviously like, like to do more coding whenever I can. But, but I certainly have not gotten to the point of saturating my desire to write code, if that makes sense. I do think there's something really satisfying about

• 14:45Speaker 01

  just building the like, you know, it's, it's funnily, I think one of the things that comes to mind here for me is like, is the, the otter logo of Devon. I don't know if you've seen the otter like on Twitter or on things like that. It, it is, it has always been an informal logo of ours. There's a question of whether to make it the official logo. But, but like the, I know, random company stuff, right? But, but, but like, the reason I say it is because it actually is really how we think about it internally, which is Devon is just like our little buddy, you know, like a little, you know, cute little otter with his own computer and just like typing away and, and, and doing tasks for you. And, and that's how, kind of how we have always thought about it. Like, I, I think if we were, I mean, we, we are all programmers ourselves, obviously.

• 15:28Speaker 01

  You know, if we really felt like, like this was going to be the end of programming, I think we would be way, way, way less excited about this problem. And I think instead it's, it's, it's, it is kind of just like teaching your own buddy how to code and then starting on that journey in a way that's been really fun for us.

• 15:46Dan Shipper?

  I think this is, that's a really good segue into the thing, one of the things I wanted to talk about is just how you see the discipline of programming changing. I think I've seen on my end, and I'm curious if this is similar to what you're seeing, I've seen on my end, there's this, obviously, there's people who don't use AI at all. But then there's this sort of bifurcation between, I think, more traditional engineers who are, who are adding AI into their existing processes. And then there's like kind of AI-first engineers who are, who maybe only learned to code with AI, or maybe they are senior engineers from the past, but are just like going full on into, into AI. And there's, they're AI-first, and they're only touching the code if they absolutely have to, which is a very different mindset.

• 16:32Dan Shipper?

  And I think that group of engineers has, there, it's, there's a whole different set of ways of thinking and different primitives for how to do good engineering if you're only orchestrating agents. I'm curious if that's what you're seeing or how you see the landscape evolving.

• 16:47Speaker 01

  No, I think that's definitely the case. And it reminds me of like, like, you know, one of, one of my favorite fun facts, actually, that I like to share is, do you know that teachers actually used to, to picket and protest against the idea of calculators?

• 17:00Dan Shipper?

  I did not know that.

• 17:01Speaker 01

  So when calculators first came out, there were a lot of protests of like, you know, we can't have this, this threatens math education and all that good stuff. And, you know, obviously, I mean, we did okay as a society despite having calculators in our lives. And, and, and I guess by the, the point that I want to make with it is like, sure, I, I think there are some things that go away and, and, and, you know, maybe people are, for example, maybe people have their multiplication tables memorized a little bit less, you know, in the post-cal calculator era. But obviously, you know, if you just look at the combination of humans with the tools and what they can do, you know, the answer is much, much more today.

• 17:35Speaker 01

  And so I, I, I think what is going to happen, or, you know, what's kind of actually happening already is, I think there's going to be a somewhat different education path for, you know, how, how to be a really great engineer in the post-AI age. The thing that's interesting, it's like, there's so many levels of AI improvement that are like actively happening right now that kind of changed that answer. But, but, but, but, you know, from, from what we can see, I think we can kind of imagine that a, a lot of what that looks like is more about. Really deeply understanding, you know, logical fundamentals, being able to break down problems and articulate the answers to them, you know, being able to think about different strategic trade offs, thinking about architectures and so on, right? And less about, you know, just going and debugging your Kubernetes or, you know, knowing

• 18:18Speaker 01

  all of these kind of obscure libraries or understanding, you know, some very particular like esoteric syntax or something like that, right? And I think, and I think that trend is already happening, you know? And so, so I think the like, some, some people say that that means that like, computer science has no value, some people say that computer science has way more value. I, I, I tend to think it's more of the latter. And the reason for that is because obviously you are still the one at helm making the decisions, right? And a lot of how you make decisions and how you decide what to build and how you think about, you know, the trade offs that you're making is, you know, it all goes back to computer science fundamentals.

• 18:56Dan Shipper?

  Yeah, I agree with that. I think if you want to make the analogy, and I think that it is a good analogy to make to say, well, you're becoming a manager instead of an IC when you, when you use these agents. The best managers are typically have, if you're, if you're an engineering manager, typically have technical backgrounds, or the best CEOs too, for software products, for example, tend to be able to like go deep into how everything works to help resolve issues. And, and also to have good expectations set for what, what can be done.

• 19:26Speaker 01

  Yeah, it's like turning bricklayers into architects is one of the things that we've said as well. And yeah, it's like to your point, it's, you know, if anything, the technical architect at the company is actually like the sickest software engineer, you know? It's not somebody who's just like walked in and right? And like, it's like, you know, if you say like, oh, this person like insane software engineer, like, what do you mean? Usually you don't, you don't mean that they like type really fast, you know? What you mean is like they, they can break down problems, they just like have a really great feel for things, they just like think really logically, they cover all the cases, right? And I think those are the same skills that you're going to want to have. I think the thing that's kind of interesting is, and this is by the way, not true, true, not just in code, but, but, but, you know, I would kind of describe it as a lot of professions

• 20:09Speaker 01

  today, you know, there's for, for people who just get started, there's almost like a hazing experience where you like spend your first few years doing the most boring stuff, right? And then you get to graduate and do the interesting stuff, right? And I think what we are going to have now is a little bit more of like an officer's school of like, you know, going straight into learning the interesting things. And if anything, that's probably more true in like, you know what I mean? Like, it's like, it's probably more true in like, investment banking or something like that, that like, you know, you spend like the first three years, you know, just going and going, going through spreadsheets, right? And then you get to do some of the cool stuff. But, but I think in code, obviously, yeah.

• 20:44Dan Shipper?

  I think it's like, it's like, uh, it's, it's not even in, in coding, like, it's maybe less intentional hazing, but you have to go through six months of, uh, you know, learning what a while loop is and what an if statement is before you can build anything interesting. And with Devon or Claude Code or ChatGPT, you can build something like on your first prompt, and that's a huge, huge difference.

• 21:09Speaker 01

  Yeah, yeah, yeah, I think it's like, it's, it's like, and I think it's, it's not intentional hazing, you know, anywhere, or at least in most places, we like to think.

• 21:18Dan Shipper?

  Well, I mean, investment banking, I don't know.

• 21:21Speaker 01

  For, I guess I was gonna say, it's kind of like, like, it's, it's like, there's a lot of this work that has to be done, and like, somebody has to do it. And so it's kind of like, you know, naturally, it ends up being like the most junior team members that go and have to take it on, but, but, but now that's Devon, right? And then you kind of get to, you know, it's, it's, it's to your point, it's a kind of like skipping one of the runs to the ladder and being able to be a manager directly and being able to be like an architect directly. Yeah, yeah.

• 21:47Dan Shipper?

  Totally. Well, but I want to, I want to get deeper into this. So, you know, we're talking about what, what does the future of software engineering look like? What does the future of the, of the landscape look like? And in particular, what I'm really interested in is the day to day of what software engineers are doing in this new world. And I, I'm curious for specific, because I think the best way to, to think about this stuff is just look at what people are doing right now, because there are people who are living that way right now. I assume some of them are inside of cognition. I assume some of them are your customers. So what I want to understand is, is what does that actually look like? And what are the new interesting things you're learning about the way that engineering works from this perspective?

• 22:27Speaker 01

  Yeah, yeah, for sure. Yeah, so I'll give the the long term answer and the short term answer. It's my favorite topic to talk about, by the way. It's like, what is the future of software engineering? Because, you know, it's it is, I think, still a pretty open question. I think in the long term, I think it's very clear that, obviously, these systems will continue to get more powerful. And a lot of what that looks like is just you as an engineer being able to operate at higher and higher levels of abstraction. Right? And, you know, it's it's kind of in the same way that we made the jump from like assembly to like Python or JavaScript or something. It's, you know, we're going to make that leap from like looking at a bunch of boilerplate Python code to just being able to express your ideas in English of what you want to build, right? And so at some point, you're not looking at your code. You're just like looking at your own product and you're, you know.

• 23:11Speaker 01

  I I actually think the Jarvis kind of Iron Man style future is, in a lot of ways, correct in terms of what we'll have. Like, like, a lot of the interfaces are going to change pretty significantly when you have like an intelligent agent that can go and execute tons of things for you and can just go and work with all these things. Like, it's not obvious that keyboard and mouse is necessarily the right input format, right, in that world. And so that's like the long term future. What does that mean for us today? Obviously, you know, we're not all, you know, working with our own personal Jarvis quite yet today, right? But but but I think in code, you kind of see these different form factors emerging, right? And I think, you know, the the older one that has existed is, you know, what I'd call kind of like the the IDE category, right, of basically making you faster when your hands are on the keyboard, right?

• 23:56Speaker 01

  And and that's all the tab complete and the chat with codebase and and all the tools there. And then, you know, the newer school is kind of this fuller agentic thing, right? Running agents asynchronously in the background, having them take on full tasks. And, you know, and and the simple way to describe it is up until the point where the agents are capable enough to to handle everything and let you just operate 100% in that higher layer of abstraction, you want to have both, right? Because you want to have agents for the things that they can go and take on and just do it entirely independently. And then you want to have the synchronous IDE experience for the things that really need you at the wheel. And I would guess that that phase lasts for about like, let's call it like three years or so.

• 24:40Speaker 01

  You know, like for the next three years, we will have both IDEs and agents. And then, you know, at some point beyond that, it's kind of like, everything will just be dictating what you want to some kind of agent form factor. Obviously, it's not, again, there, there's a cutoff of like, well, what counts as an IDE? You know, and what counts as an agent and, you know, the interfaces.

• 25:00Dan Shipper?

  Yeah, when you talk about, for example, Claude code, or sorry, when you talk about, for example, like the IDE or background agents. Are you counting Claude code as a background agent? Like, where does, where does the new CLI, all the new CLI stuff fit into this worldview?

• 25:12Speaker 01

  Yeah, so it's all a spectrum for sure. And I think about these CLI agents as, it's definitely somewhere in the middle. I would describe it as a bit more, it's a bit closer to like a synchronous agent. Right? And so, you know, if you compare it to like a cascade or something in WinSurf, like it operates a little bit more like that where, yes, it is an agent that can do multiple steps, but one, you know, you're kind of meant to be checking in with it more deeply. Right? And two, it is not fully, fully autonomous in the sense that it doesn't go all the way and like, you know, create pull requests for you and work with all of your systems. And like, you know, it usually doesn't go and test all your code for you or things like that. Right? And so, so, so it's more spectrum than a binary for sure.

• 25:51Speaker 01

  I think in general, you know, I think we will be kind of operating on the spectrum and things will be gradually shifting more and more agentic and more and more autonomous. But we will have the spectrum at least for the next couple of years. And, and then I think the natural question is like, what that experience should look like of using this suite of tools across the spectrum. Right? And so you have like the full like synchronous things. Like I think Tab Complete itself is probably the most synchronous thing. It's, it's like, you are still really, you know, going and dictating every line of code. You know, Tab is just like helping you go a little bit back. Tab is kind of speculative decoding is my, is my nerd view on it. If you know what I mean by that. And then it goes all the way to these like full autonomous agents. And I think having the suite of tools is great, right?

• 26:33Speaker 01

  And then the question is kind of like, how do you split up your tasks into which ones should go into which buckets? And also for for more complex tasks that are going across buckets, like, how do you use these tools in tandem with one another? Right? And I honestly, I think that's a pretty unanswered question today, frankly. Like, I think there are, you know, and I think there's a lot of progress that different folks are making in the space. And there's a lot of really, you know, really great thinkers in the space. But but I think how you start with a synchronous experience and then hand off to an async and go back. You know, a simple example I might give is like, a lot of what you want to do, let's say, like, in the world today, you know, with humans. You sit down and you're like, all right, I have this project idea, I think we should build it, right?

• 27:18Speaker 01

  Like, what's the first thing that you do? You know, it's it's not necessarily, I mean, hopefully, it's it's not that you just immediately sit down and start typing code, right? Like, a lot of it is like, you're just fleshing out the details, like, thinking about, you know, all the decisions that you're gonna have to make. All right, like, we should build this new feature, and this feature is only going to imply to users in X, Y, and Z buckets. And, you know, if they're in bucket X, then they already have something that looks like this. And so, you know, we need to go replace that in the UI with with the new thing that we're trying to build. If they're in Y, then it's like a totally fresh thing, so we should walk them through the onboarding. You know, you're fleshing out all the details of what you need to do, right? And then, you know, I think the next step is is typically something like building out a clear spec, right? Like, thinking about the technical details and building out all of that, right?

• 28:01Speaker 01

  And then, you know, depending on the cycle, obviously, there's there's more things. And then at some point, it's like kind of handing off the implementation. And I guess my point is, I think AI coding agents should be able to help you through the full cycle. Or like this kind of suite of of things should be able to help you through this this whole thing, right? But but naturally, there are parts of it that you want to be doing synchronously and parts of it that you want to be doing asynchronously, right? So going and making these decisions of how you handle users in different buckets or whatever is something where it's like, you should be able to have the Jarvis experience of talking directly, you know, live with your agent. And your agent is like, oh, by the way, yeah, there's this if case, there's this case, there's this case. How do you want to handle each of these? Let's talk it through together. By the way, like, you know, I looked deeper into the code paths and here are the things that I found. But like, obviously, the decision is yours ultimately, right?

• 28:47Speaker 01

  And then, you know, maybe there's other things of kind of just like building out the PRD itself, right? And then at some point, when you're going and doing the literal implementation of the code and testing and just like making sure that works, like that's something that probably should happen more async, right? Like you don't have to be involved. Once you've kind of fleshed out all the details in the actual implementation itself, right? And then maybe when you get some comes, comes time to do the PR review cycle, then you want to be synchronously there. You want to be able to read the diffs, right? And so there are a lot of these kind of like, these flows in our work today where naturally you want to be able to go from like sync to async to sync to async, right? And I think there's, there's still a pretty open question of how you should be kind of working between those together.

• 29:34Dan Shipper?

  One thing I'm curious for your take on is I think the AI coding space had this really interesting shift like three months ago where prior to three or four months ago, everybody at every, including me, we're all using cursor and WinSurf. And then Claude Code came out and I mean, I used, I used Claude Code with Opus for like before it came out and I was like, holy fucking shit. This is crazy. And literally overnight, everybody at every, and I think a lot of people around the space switched to these new CLI form factors. What do you make of that? Like, why was, why did that happen? Obviously, some people are still using WinSurf. They're still

• 30:16Dan Shipper?

  using cursor, whatever, but the, a lot of the momentum went to CLIs. Why do you think it was so successful? And what do you make of it?

• 30:24Speaker 01

  Yeah, yeah. Well, first of all, I think it's an incredible product experience, to be clear. And I think Anthropic has done very, very well with that. I think, I think there are a few things going on here, you know, but broadly, the way I would describe it is

• 30:39Speaker 01

  The capabilities, you know, well, the capabilities change like every week, honestly, but there's, I would say relatively meaningful step function changes every few months, let's say. And the thing that's really interesting is the correct form factor or like the correct interface is a pretty tight function of the capabilities, if that makes sense, right? Like you, you, if you were trying to do full autonomous things, you know, I'm making fun of myself a little bit here. If you were trying to do full autonomous things in the GPT 3.5 era, you know, it's like, there were things that you could do, but obviously.

• 31:11Speaker 02

  Good luck, younger Scott.

• 31:13Speaker 01

  Yes. And it's obvious, you know, there are a lot of kind of like different versions of this that that happened. But, but I, so I think there were a few, few shifts that happened, right? I think the capabilities like really improves to a point where you could start to handle things, you know, a lot of day to day things in a more autonomous way, for one. And then I think the other thing is, is just like, I think Anthropic very clearly put a lot of love into the experience, you know? I actually think of it as, as, I think, a bit less. Something I'll say, maybe this is a controversial take, I actually don't know that CLI itself is the most important part of the experience. And I would claim, you know, the reason I say, you know, we have this debate actually internally at cognition

• 31:57Speaker 01

  of like, like, what is the form factor, you know, like, should the form factor, should it live in the IDE, should it live in Slack, should it live in, you know, should it be its own web app or whatever? And I think the answer that we kind of come to is like, you know, the form factor just is a software engineer, if you know what I mean by that. And it's kind of a non-answer, but also, you know, hopefully it does say something, which is, which is basically like, it's less a question of, well, where do you go to interact with your tools? It's more like a question of like, what did the tools do for you, right? And how do you expect to work with them? And so I think from that perspective, you know, engineers are spending a lot of time in the terminal, they're also spending a lot of time in the IDE, they're also spending a lot of time in Slack, you know, all of these are reasonable things to think about and to work with.

• 32:41Speaker 01

  And I think as time goes on, I think probably a lot of these tools will be integrated with more and more of these and so that you can kind of call them from anywhere. But I think the bigger question, which I think Claude Code took like a bit of a different spin on is how should you be working with the tool? If that makes sense and I think the, you know, the, the, the way that I would describe it is kind of like their view of the tool is like the tool is you. You know, whereas, whereas like, you know, if you're in WinSyrup and you're doing a tab completion, it's like,

• 33:14Speaker 01

  this is like, you know, it, it, it's, it's, it's obviously very kind of like something, something that augments you, right? If you're calling something with Devon,

• 33:26Speaker 01

  then it's very much kind of like your, you know, the software engineer sitting next to you and they have their own virtual machine where all of that operates. And, and, you know, they've spun up the repo themselves, right? Claude Code is kind of like handing the reins over to, to your AI buddy to take the wheel of your computer, right? Which I think is, is, is an interesting paradigm, frankly.

• 33:43Dan Shipper?

  I agree. I think the, the thing that struck me about it was it was a, it was like a full send to a new version of agentic engineering where previous, except for Devon, but previous iterations were always, well, the AI is like on the side and the CLI form factor was actually, no, no. All you need is to talk to the AI and that was the first time that that happened for something that you're using on your own computer, which I think is the other really crucial component, at least for me. Because having it be able to run bash commands on your computer makes it way more extendable and customizable than

• 34:28Dan Shipper?

  if it's in some environment that you don't fully control. Or sometimes, for example, in Codex, the environment would be spun up and then spun down. And Devon, I think it's, I think it's more consistent. At least last time I checked, it was, it was a consistent environment, but still harder to customize than your own machine.

• 34:43Speaker 01

  Yeah, yeah, yeah. And so I think there's a lot of different, it's, we talk about the entire kind of like, there's like a hyperspace of all of the decisions that you can make, right? There's kind of like, you know, synchronous versus asynchronous, there's like local versus remote in terms of like the environment that it operates in, there's like, you know, in the IDE versus in other things, there's like single player versus multiplayer and whatever. And I think what we're seeing is just, there's, there's obviously, you know, it's, there's some exponential amount of possibilities in the space. I think a lot of different single points of the space are pretty interesting. And I, you know, I think Devon is the one point of the space. I think Winserve, you know, and other IDs are another point of the space. I think, I think Anthropic unlocked a new point in the space with Claude Cood.

• 35:27Speaker 01

  I think that the, frankly, I think that there will be a lot of these points that exist for quite a while. And I think the full suite kind of should have, should have a lot of these different experiences because obviously it depends a lot on your particular use case or your flow, which one is best at each point in time.

• 35:44Dan Shipper?

  What do you think the trade offs are of the point in hyperspace that you're in? So in particular, I think the thing that makes Devon unique, at least in my testing, has been, it's an agent that lives on its own computer in the cloud persistently that you can talk to at any time, which is just, it is a different bet than pretty much any other big company has made.

• 36:04Speaker 01

  I mean, it is almost like onboarding a software engineer, right? But, but once you do, there are a lot of tasks, because Devon has its own environment and because it can go and learn how to test things and run all the tests itself, that it just can do, you know, that, that, that basically nothing else out there can do. And I think it's interesting for us because, you know, even before this Winserve, you know, acquisition, we were already thinking about this question of, well, what should we do to basically, you know, make, make it a lot easier and, you know, make an experience that's a lot more accessible for folks, right? And we were talking about a few different ideas and, you know, with more synchronous experiences. And, and then obviously, you know, everything happened with Winserve. It was, it was a great opportunity for us. And, and so a lot

• 36:47Speaker 01

  of how we see it today is, is, you know, I think there is going to be a lot of work in terms of not just like onboarding the agent, but also in, in human software engineers themselves, learning how to work with more and more async agents. And I think it naturally has to kind of transition from a sync to an ASIC environment. And so that's, that's kind of how it's, what has led to a lot of our thinking today is, you know, using WinSurf or having WinSurf as kind of like a really fast time to value, you know, option that you can immediately just kind of download and use and get a lot of value of. Over time, you learn how to work with that, you know, Cascade Agent, or you learn how to kind of like use the Deep Wiki indexing in WinSurf. And then naturally that takes you kind of to more of the ASIC flow. But, but yeah.

• 37:30Dan Shipper?

  That makes a lot of sense. I'm curious, one of the things you said earlier that stuck out to me and I think is really true is that there is, there is a tight dependency between model capability and what the right affordance or what the right harness is to use that model. So, you know, for example, with Claude Code, it becomes possible to do a lot of the CLI stuff because Opus 4 and other models of that generation are good enough to, to, to make that work. Whereas for GPT 3.5, if you do the CLI, it would have been horrible.

• 38:03Dan Shipper?

  And I, I think my question about that is you guys don't have your own models as far as I know. Maybe you have fine tuned versions of models, but you're not building your own coding models. Is that true?

• 38:15Speaker 01

  So we, we do a lot of post-training of models. So we do like fine, fine tuning in RL and things like that. We don't train, we don't pre-train based models.

• 38:22Dan Shipper?

  Yeah.

• 38:24Dan Shipper?

  I guess, why not? So given that there's, you know, given that there's a lot of overlap between the capability of the model and what the right harness or affordance is to use it.

• 38:36Dan Shipper?

  Does that make you worried about competing with OpenAI or, you know, Anthropic? When, when they have this like very tight coupling between these two things that are evolving together very rapidly?

• 38:49Speaker 01

  On the other hand, I think post-training very much is. And, you know, some of the examples that I'd give you are things like, well, you know, we want Devon to be able to predict its own confidence and to have an opinion on, you know, how likely it is to be able to do this, or how well it understands the task, or things like that. Right? Or, you know, maybe a more like direct, practical one is like, all right, you know. One thing that engineers do a lot day to day is pulling up the data dog, finding the corresponding logs and using that to debug what went wrong and then making the right edits. Right. And that's a very specific flow that you obviously need to have like custom training data in for, you know, the, the, the models don't just learn that on their own. Right. All of these things, um, they fit actually quite naturally into post-training as a category.

• 39:33Speaker 01

  And, and, and so, you know, I think from our perspective, it is, it is really a question of what we think we spike most on, of where we want to focus, you know, I think as a startup, your, your edge, um, it always has to be speed and focus. And, and I think for us, it's, it's, it's kind of like, I, I think we, we know what our core DNA is about, and, and a lot of it is just like, understanding the nuances of real-world software engineering and basically teaching that to the models in a way that, that, that you can build a great product experience. Um, and, and that's what we focus on.

• 40:05Dan Shipper?

  In post-training world right now, RL environments are like really hot. And it strikes me that you all have been probably purposely building the perfect RL environment for, for post-training software engineer. Tell me about that.

• 40:22Speaker 01

  Sure. Yeah, I know. I mean, I, it's one of the beautiful things about code, right? And people, you know, people talk about this obviously, but, but the fact that code is, um, it, it, it has a much cleaner feedback loop because you could read, you, you can run the code or you, you know, you have all the, uh, there's, there's all the version control. You could see every commit that was made in history. You could, you know, you, you have so many of these tools, which you would love to have, um, in, in creating these things. Um, and I guess the only thing I would say here is,

• 40:50Speaker 01

  it, it, it really does come down to just building the exact custom environments for the use cases that you care about. Um, and so, so, so all this, you know, we just talked about like data dog or other things. There's, there's honestly like hundreds of these, you know, within code and, and, and like, you know, random things that come like Cobol, you know? Turns out there's still a bunch of Cobol out there in the world, right? Uh, and it's not something that the language models are, are, are super kind of, you know, adapted to understandably, right? But, but like that is, that, that, that is real work and, and, you know, real stuff that, that, that takes a lot of time for people today. Right. Um, and, and I think a decent bit of the work of RL, you know, I, I, I, I've said this before, but, but you know, my, my high level view on RL is kind of like, the, the platonic ideal of RL

• 41:35Speaker 01

  is that you can go and solve any benchmark, right? And and and once, you know, once we have that, which I think we were getting closer and closer to having that, then the question is kind of just like, okay, well, what's the benchmark, right? And now the question that I think a lot of these applications that our companies are thinking about is basically, what is the benchmark? Like, what is the exact set of tasks and environments? What are the tools that you're going to use? What are the decisions you would make? How are you going to decide whether it's a success or failure? And if you have described all of those things exactly, and you've kind of collected enough data points around that, then you can train a model that just does it. It's kind of a crazy, you know, it's, it's, it's kind of insane to think about that. But, but obviously, it just means that, to your point, like, having the right environments and the right use cases is even more important.

• 42:17Dan Shipper?

  And I'll say, that's very hard, like, getting that, getting the answer, like, how do we decide whether this is good or whatever? That is actually quite hard. I guess, it strikes me, though, that there's, there's maybe two, two ways to solve the kinds of problems we're talking about. So, for example, making a great software engineer. One is having, having RL environments set up that mirror the kinds of problems that a normal software engineer would, would encounter, and then using that to generate data to train the model to be able to solve those problems, like the Datadog example, right? And, and basically, having a company enumerate what are the likely things that people are going

• 43:02Dan Shipper?

  to have to do, and what are our users saying they want to do, collect all that data, and then train the model. On the other end, though, you know, there's a lot of talk about continual learning, which I think, I kind of think continual learning is already happening, it's just very sample inefficient. So, so on the other end of the spectrum, instead of having to do all that work, you just, if you just made the model more sample efficient to be able to try stuff and learn, it would, it would make it so you wouldn't have to do as much of the, you know, RL environment post-training type of stuff. So, why, why make the bet over here in the, in the RL environment post-training side, instead of on the more sample efficient learning side?

• 43:43Speaker 01

  Yeah, yeah. Um, no, it's a good question. Uh, it's a, it's a really good question. I, I think like, um, I'll give you my high level view on, on this is just kind of like a, almost like a philosophical question even of like, basically if we are gonna have the full, you know, talked about all the reasons that ASI or AI is like a bad, but, but the, the full, you know, intelligence that can do everything that we want it to do, then obviously at some point it has to learn all of the practicalities of the real world, right? And I would argue, we're bottlenecked by that right now. We're not bottlenecked by pure logical reasoning. Like, you know, we could do some pretty insane logical reasoning with, with language models, right? Um, and so like, how do you learn, you know, for an accountant who's doing all their work every day, or for like a paralegal who's doing, you know, how do you learn

• 44:24Speaker 01

  the practicalities of what somebody does that way and, and, and build a model that is like intelligent about that, right? And obviously, you know, the, the, the best way to learn something is to do it. And so, so you know, you need this actual data of, of, you know, what does, what, what this particular paralegal does in some form, right? And, and so then to your point, I think there's kind of this fork in the road of where, uh, where that data comes from. And I would say, you know, I would add a third one, uh, or, you know, just, just for completeness sake, I think most people agree with that. But, but, but the, the three that comes to mind are, one is, well, the data exists in the world already, you just have to go get it. That was kind of like the pre-training view of the world, right? You just take more and more of the internet, you train it

• 45:06Speaker 01

  all, and because everybody has stuff on the internet, if you just keep doing that over and over, eventually you get a model that knows everything, right? Um, two is kind of like, well, it has to go be built by, you know, experts themselves. You have to go and like really curate an environment and figure out exactly, you know, like these like 500 environments of, uh, of your one task and then do that for every task that you could possibly imagine. And then that's how you, you do that. And then three, to your point is like, you have an agent that can go out and do it by itself. Right. So I think two and three are kind of the that's the those are the versions that you're describing of like, do we go and handcraft the environments versus versus is there some continual learning that works out, right?

• 45:47Dan Shipper?

  Yeah, like it does it and fails, you know, you you onboard it to your company and it fucks up the how to log into Datadog a few times, but then it figures it out, you know?

• 45:56Speaker 01

  Yeah, yeah. And I think the I think the short answer is basically, I think we will get to three. But I think a lot of the problems that you solve along the way actually naturally apply to both. Right? And so I think it's kind of one, like the pre-training world, you know, personally, I kind of think we've we've roughly, you know, we're kind of converging on a lot of the capabilities on pre-training at this point. Two is this RL world, which is like actively the the world that we're all in, you know, is going and doing custom RL to to find particular capabilities. And then three is this kind of like long term, you know, continual learning, which will obviously unlock some really big things. But I guess I would just point out that for for both two and three, to your point, a lot

• 46:38Speaker 01

  of what you have to do is you just have to create actual agents that can operate in the real world, right? And the way I kind of think about it is, I think the most important thing in two, that's making it more successful, is you can just be much tighter about curating the reward function, right? And so like, simple example of this is, you know, one of our evals or one of our environments is like, you know, there's a there's a Grafana dashboard that you need to set up, and for some reason, it's not working. So please figure out what went wrong. And it's very much meant to be like a messy real world software. This is like the kind of stuff that you'll run into day to day. And the way the task works is obviously, you go and install the packages, you run the code and stuff, and then you find some error. It turns out the errors because, you know,

• 47:20Speaker 01

  the the version lock of the packages, you know, was like slightly off in a way that makes it, you know, this kind of stuff that you run into all the time, isn't it, Shere? So then you have to find this, and you realize you got to downgrade the version this, and then, you know, that leads to the next thing, and you figure out what went wrong with that error, and then you get the thing running, right? And at the end, there is dashboard. And the really beautiful thing about an eval like this is you can just make the eval just, so what does the dashboard say? And the thing is, if you did not get the Grafana dashboard running, you will never be able to answer that question. And if you did get it running, you will always get the right answer, right? And this curation just means you have a much, much tighter feedback signal, right? For three, you would want to be able to do this kind of like live in the real world and have that feedback cycle. The problem is it's like a lot tougher of like, well,

• 48:05Speaker 01

  you can get the dashboard running and then have the wrong number. And then like, how are we going to know that that was wrong? You know, or we could do this other thing, right? And so it's, it's not an unsolvable problem. I mean, I think, I think we will make more and more progress on it over time. But I guess my point is just like, either way, building the full environments and the tooling for the agents that can do this is kind of the primitive that you need to be able to, to do, to do both of these routes, so.

• 48:29Dan Shipper?

  That does, that does make sense.

• 48:34Dan Shipper?

  The thing that comes to mind there is, or a worry, which I'm, I'm curious for your opinion on, is the, the Grafana eval. In that case, how generalizable have you found the, being good at that eval is? So the fact that it can set up a Grafana dashboard, if Grafana, you know, changes the way that their whole system works, and that, that breaks the eval. Yeah, like, are you, are you training? Is it, does it end up being too brittle if it's trained for these specific kinds of environments that could end up changing like pretty fast?

• 49:06Speaker 01

  Yeah, so the first answer is yes, you do need like a bunch of environments naturally, right? But, but, but it's the second answer, you know, the, the meta level answer I'd give to you is, is kind of like, it really depends on how you set up the task, right? And so, you know, if the task is literally just like, all right, you just have to recall exactly what packages are needed for, to, to, to run this version of Grafana from memory. And yeah, it's like, that's not very generalizable because as soon as the next version comes out, that's not going to be a knowledge, right? But if the task is meant to be such that, okay, you're going to go and Google this, and then you're going to go and read the docs page of Grafana, and you're going to use that and understand what went wrong. And then you're going to look at the error in your logs and find the file that that corresponded to, you're going to read that file, you're going to use that, right? So, so it's, I guess my point is like, you know, we as humans all figure it out somehow.

• 49:49Speaker 01

  And the, the way I would kind of broadly describe that we figure it out is, we actually interact with the real world in, in a way that like gives us the information that we need, rather than just like pulling it all from memory, right? And as, as long as your agent is set up to do that, that skill is something that is very generalizable.

• 50:05Dan Shipper?

  What's something in AI that you're excited about that has nothing to do with cognition or Devon?

• 50:10Speaker 01

  Oh, interesting. I've always, I've always felt like these personal agents should just be a thing. Like, I'm surprised it hasn't happened already. I guess this is the way I would put it. Like, you know, I think, obviously, there was like operator, right? And there's kind of some deep research, I think is another good example. But, but, but like, I think, just like a mass consumer agent that you can just have on your phone that just takes care of things for you. I mean, it's, it feels like the capabilities are there for that. Maybe I'm wrong. And it feels like something like that would be so valuable, you know? Like, everyone always gives the example of like-

• 50:43Dan Shipper?

  Like, schedule my dentist appointment or whatever? Like, what does it do?

• 50:48Speaker 01

  Yeah, exactly. It's like, everyone always gives the example of booking flights for some reason, which is great, obviously, don't get me wrong, but like, this is not the only thing that I would have my personal agent do. Like, they're all the like, like, I would love to have my personal agent go and call and book a reservation and then, you know, deal with various messages and then make sure, like, the package delivery, like, went through and then go and, you know? It feels like there should be something there, or it's just like buying my Amazon packages for me, just like, hey, like, I need another order of X or Y, whatever, it just goes and gets. And I've always thought, yeah, that that should be something. It's funny, because we actually, I mean, we obviously build Devon, like, entirely for coding, but we've kind of messed around with it. I'm just seeing like, hey, like, can Devon do this?

• 51:30Speaker 01

  And it's like, yeah, like, we actually order all of our Amazon packages with Devon now, you know?

• 51:36Dan Shipper?

  That's amazing.

• 51:37Speaker 01

  Well, the thing is, it's, again, it's, you know, the Slack message or the linear ticket is like, not the right form factor for that, and somebody else should build the right, you know? But, but it's, it's, it's like, the agent capabilities are there, I guess, is my point. And, you know, with Devon, it's like, because you have memory and because you, you know, are storing secret keys, you might as well be able to handle, like, your Amazon account as well, and because you have the browser, like, that is actually the set of things that you need to be able to do that. But, but, but it feels like something like that hasn't really, like, really taken off in a way that I would imagine, you know, like, I would imagine that 12 months from now, we will not be, you know, like, that we will have this, but, but, but I would love to have it sooner, if possible, so.

• 52:19Dan Shipper?

  That's really interesting. Well, I hope to have you back on the show 12 months from now, talking about the future of personal agents and hopefully some really cool updates to Devon.

• 52:28Speaker 01

  Yeah, yeah, awesome. Thank you so much for having me.

• 52:37Speaker 02

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