Transcript of ‘How Union Square Ventures Built an AI Brain for Venture Capital’
‘AI & I’ with Matt Cynamon
October 30, 2024
The transcript of AI & I with Matt Cynamon is below.
Timestamps
- Introduction: 00:00:52
- How Matt became in charge of everything AI at USV: 00:01:56
- How AI empowers generalists to be creators: 00:06:22
- The Librarian, a chatbot trained on everything USV has published: 00:10:41
- Portfolio Tracker, an AI tool to track USV’s investments: 00:21:09
- The AI projects that Matt has in the pipeline at USV: 00:27:21
- Meeting Notes, USV’s AI note-taking tool: 00:34:33
- Prompting AI to generate a post for USV’s X handle: 00:44:57
- Why it’s important to diversify ownership over data: 01:00:20
- The Dream Machine, AI that generates images from conversations: 01:03:20
Transcript
Dan Shipper (00:00:52)
Matt, welcome to the show.
Matt Cynamon (00:00:53)
Hey. Really happy to be here.
Dan Shipper (00:00:56)
Psyched to have you. So, for people who don't know, you are what you call a Regular at USV, which is Union Square Ventures, which is one of the top venture capital firms in the world. And you work on all of the AI projects. And I love having you on because USV just keeps putting out these really, really cool projects. You have this one where you tweet out all the meeting notes from meetings that have happened at USV that I read. It's really good.
Matt Cynamon (00:01:22)
If you want, we can actually do a live version of that today, because they usually get done on Fridays. And so we could do it on the podcast and then publish them live.
Dan Shipper (00:01:29)
Let's do it. That would be so great. I think that you have this thing that I try to have and I think it Every tries to have. And then I think it's just really good for working in this sort of AI wave right now, which is the spirit of tinkering. You're just playing around with stuff. You're making stuff. You're constantly shipping new things. And it sounds like you're discovering some cool things along the way. So I want to talk about that. I guess to start, tell us how you got into this. How did you start? How did you become the AI guy at USV?
Matt Cynamon (00:01:59)
So, mostly just by, I would say, following my own curiosity. So I've been at USV for six years now—or just about six years. And for a bulk of that time, I was working on the talent side: So, meeting people who are looking for new opportunities and connecting them to the right people in our portfolio, which was always kind of a weird fit for me because I never came from a talent background in the first place. I'd never been a recruiter, had never hired beyond just hiring people for my own team, but it was still a lot of fun meeting all those people. But I think everyone here knew that my heart was probably semi in it after a while.
Sponsored by: Every
Tools for a new generation of builders
When you write a lot about AI like we do, it’s hard not to see opportunities. We build tools for our team to become faster and better. When they work well, we bring them to our readers, too. We have a hunch: If you like reading Every, you’ll like what we’ve made.
Because I would send these weekly emails around to the team that were just like, here's everyone I met with last week that's looking for a new job. Here's everyone I'm meeting with this week. Who do you want? Who’s a good fit for someone in your portfolio? But then I would sort of cold open all of those emails with, and here's this weird thing I made over the weekend that you might want to play with. And at first it was mostly just what I would call fake movie trailers that I was making in Runway ML.
And I would outline my whole product. This was supposed to be an email about talent. And it was like, so I had this idea about a romcom set in the French Alps. And I gave that to ChatGPT and I asked ChatGPT to write a 30-second script and then timestamp each part of the script. And each timestamp needed to be a digestible prompt that I can free it into Runway ML and would just run that process. And everyone would just be like, okay, looks cool. And then I went on paternity leave. We had our first kid and when I came back, I was having a conversation with Andy and Rebecca, two of the partners here, and they're like, look, the world is changing really fast and there's a lot of really interesting technologies out there both we need to be experts in, but at the same time, we need to be deploying on our own to make us better at our jobs. You are a tinkerer by nature. That's kind of what it is that you do. Would you be interested in just kind of doing this full time? And I think maybe I played it a little cool, but in the back of my head, I was like, you mean I can just make prototypes with AI all day while working here, like, yeah, okay. Let's do it. Let's go. And, so yeah, that's kind of how we got here.
Dan Shipper (00:04:18)
I love that. It's such a good story. Some of the best people like to stumble into things like that—they're doing their job and then they're just sneaking in the thing that they actually want to do. And somehow it becomes their main thing.
Matt Cynamon (00:04:30)
I was inspired by— We had this analyst who worked here, many years ago, who's now the CEO of a company called Jam. Her name's Dani Grant. Maybe you've met her. And when she was an analyst, she would come in over the weekend and just be like, hey, look at this hologram that I made. That sort of made me realize that this was the type of place where that type of experimentation and just having fun on your own time and following your curiosities was really rewarded. And, I think it's proven to be the case.
Dan Shipper (00:04:58)
That's great. So it sounds like you started with Runway clips. What was the first thing that got your eye where you're like, this AI stuff, I kind of want to just start playing around with. And what was it?
Matt Cynamon (00:05:07)
I don't remember whether it was DALL-E or whether it was ChatGPT first, but I do have this distinct memory. I've always been interested in sort of the more creative side of AI and using it as a creative assistant and, I remember I was staying up at a friend's upstate and we were writing a musical about the life of Jeff Koons using ChatGPT and giving it feedback. And it was probably two-plus years ago. And we were like, this is outrageous. It's just coming up with this story live and it's taking our feedback and it's getting better and better. And so I think that was a really pivotal moment. And then the other is: My wife is an illustrator who—I wouldn't call her a Luddite, but she's definitely not terminally online like I am. And my first thought was like, oh, I wonder if she's going to feel threatened by this. And the first thing that she did was that she had DALL-E design a cross-stitch pattern that then she could do in real life. And I was like, oh wow. These are tools that actually help bring out our creativity if we use them right.
Dan Shipper (00:06:26)
What's the thread that turned you into someone that can be a tinkerer and wants to make all these different types of projects with AI? Tell me about that.
Matt Cynamon (00:06:32)
Sure. If I had to guess, I'd probably get it from my dad who was the type of person who always had some broken down piece of machinery—either a car or a computer that he was building from scratch or a ham radio. I remember he went through a real ham radio phase. So he was a real tinkerer. So I think it was always in my nature to want to make things. And the problem is like, I just had so few skills. I was quite the generalist always. I mean, my whole career, I worked in startups, but in weird general managerial kinds of positions, even when I was really young. And so there were all these things that— In my spare time, I'm trying to learn piano and I'm trying to learn all these different hard skills that I never sort of gained growing up. And then all of a sudden these tools came about where I wouldn't say that you need no skill, but you can develop the skill alongside seeing your creativity come to life. If you want to learn how to play a Beatles song on the piano it's going to take you a long time of learning your scales and then building up to the position where, to the point where you can actually play it credibly, and then if you want to sing on top of that—my god. We're talking about three years of lessons and whatnot. But with AI, you can kind of learn alongside the creative process, which has been super rewarding, and the sort of the feedback loops are so fast. And so a great example of this is I'm not a software engineer, but I had made something—I had made a custom GPT and I was like this would really work so much better if it read off a live spreadsheet, but I don't know how to connect to APIs so that the GPT can read off the live spreadsheet. But then because you're already so far down the process, it's just adding another little element to it. And the GPT can walk you through how to do that. And it just has been this magical experience for me.
Dan Shipper (00:08:35)
Yeah, this is one of the things that I see a lot too in AI stuff. I teach a programming course— Programming with AI—and one of the things that's very different about that course, for example, the way I learned to program, which is the way I learned to program is the exact same way you're talking about learning to play piano. It's like, yeah, okay. What's a variable? What's a function? And you're like, I want to make a website. I want to make an app. And you're like, okay, no, no, no. You have to spend a year learning about these really basic building blocks—you don't know how they translate into the full thing. And what I can do with my students and what anyone can do, regardless of whether they're taking a course with AI, is that within the first 30 minutes, you can make something that looks pretty much the thing that you want to make. And then you can be like, whoa, wait, how does that even work? And then you can go down into the, okay, here are the nuts and bolts of details of how it gets built up. And I feel like there's a whole generation or crew of people who have not been able to, for example, program because they don't want to go through that whole thing, learning all the basic things before they're, before they see something that’s buildable. They connect to and now they can connect to that and then they can go back and learn. I think that's so powerful.
Matt Cynamon (00:10:00)
It reminds me a lot of the personality archetype who, as a kid, takes everything apart to learn how it works. They take apart the clock radio to learn how it works. And you can actually do that. Now you can build the clock radio. And then you can take it apart to see what it is that you just did and then sort of build your skills that way. And I think a lot of people learn much better that way.
Dan Shipper (00:10:14)
Totally, totally. I know I do. And I feel like I have a similar thing where I have all these different interests. I have all these different things I want to make and build and with AI, I can now do it. And yeah, it's just the best.
Matt Cynamon (00:10:27)
Literally the only thing holding you back is time and patience at this point.
Dan Shipper (00:10:30)
Yeah, exactly. I want to get into some of the practical stuff that you're making, because I think it's so cool. We could start with The Librarian, but I don't know. What do you think is the best thing to start with?
Matt Cynamon (00:10:42)
Well, there's like six different ways that we can sort of talk about The Librarian, because I feel like that's sort of the persona that's taken off—and I'll pull it up. You know, when we first started working on all of these projects, I think like a lot of people, my imagination just exploded and it was like, oh my god, we are going to build this all-in-one monolithic super app that's going to live where we are with us, wherever we go. And it's going to have a name and a face and a personality because we all believe that metaphor is really powerful in helping people understand things. And I think over time, what we realized was that if we wanted to build things that work. Now, rather than trying to build a monolithic app, let's use the tools that already exist. Let's break them down into their component parts and let's build individual agents that do different things. And so there is a version of The Librarian that we're still building that still kind of resembles that, but honestly, my favorite version of it is just a simple GPT that we cloned and called The Librarian. And I can pull that up if you want.
Dan Shipper (00:11:45)
Yeah. Pull it up and give us some background on what it is and like, and where it came from and all that kind of stuff.
Matt Cynamon (00:11:54)
Okay. So, where to begin? Well, when I first sort of moved into this position, the most obvious thing for us to build would be a chatbot built on top of our entire history of writing. So as a firm, we've been around for about 20 years and we've been relatively prolific writers. I think between all of the partners as well as the USV blog, there's about 15,000 articles that we've written. A lot of that has been driven by one of the partners—Fred wrote every single day without fail for 13 straight years. And I was talking to Albert, another one of the partners here, and he's like one of the biggest impediments to me writing is: I sit down, I'm halfway through a blog post, and then I realize, oh my god, I've actually already written that. And so what I wanted to do as a starting point was just build a bot that allowed them to be conversational with their writing.
And I shared it and everyone sort of looked at it and they played with it. I think the original name I gave for it was called Conversations because we like to say that USV is a conversation. And everyone's like, okay, but what does it do? And I couldn't really give a good answer. And then I renamed it to At the Edge. Because I was like, you can ask questions about our thesis and really try to synthesize and advance our thinking. And everyone's like, but can you explain what it is? I was like, I don't know. It's kind of a librarian. And then it was like this light went off —oh, librarian. Well, that's interesting. And that was sort of this moment, I think, where we realized how powerful metaphor can be and sort of explained what it is that these chatbots can do for us. And so I started building out what was The Librarian, and initially, I said, we had sort of put everything into this one chatbot that was sort of its own standalone application that I actually used No Code MBA to build, which was an awesome program. And then a lot of help also from Ben's Bites. but just maintaining our own UI was such a pain in the butt. So, at least for between now and November, I was like, you know what, let's break down all the component parts of The Librarian and to the individual things that The Librarian was doing, let's make them all their own standalone GPTs and give them very specific names, so people know exactly what they do. So this is an example of The Librarian. So, one of my favorite things to do, and I did this recently. We can do it live—Consensus is a company that we recently invested in. And so, we can go to the about, I'm just going to copy everything on this page. I'm going to type here and say, “Below is the about page of a company we're considering investing in to pull out any relevant blog posts that we've written that might pertain to this company.” And then this is going to take a little bit, so, I can show you— Ah, here we go. So this was one that I did the other day. It was the same thing with Consensus. And sort of it brought back these are the major themes that we've written about that would be relevant for Consensus.
Dan Shipper (00:15:25)
Can you stop for one second? I just want to go back and read it. So, if you go to the top— Okay, so basically what you did is you put in just the About page and you're like, what are the relevant? What's the relevant writing from USV? And this GPT has in its knowledge base all of the blog posts you guys have published, right? And so it says, here are a few key insights from USV’s writings that are highly relevant. “AI unlocking knowledge: one of USV's core beliefs is that I can unlock vast amounts of knowledge from data, making it easier for people to access and synthesize information. This aligns closely with Consensus’ mission.” And then it keeps going. “Democratizing Science: USV has supported platforms that democratize access to scientific resources.” “Trust in AI Systems: for AI powered systems to gain widespread adoption, they must earn users trust.” So this seems pretty good, right? Tell me about your reaction to this response.
Matt Cynamon (00:16:21)
Oh, I think it's spot on, right? And these are all things that we've both talked about and written about. And these are things that we've written about really recently—trust in AI systems. So, in this instance, I think it did quite a good job of interpreting what it is Consensus does, what their core brand promise is and how that relates to both things that we've written about that might be relevant to the tech they're building, but also to the brand they're building as well.
But maybe I'll pause just for one second and explain so why is this even important? Why do we need to pull up our writing about a company that we're considering investing in. And I think for us, we don't chase after deals at USV. I think we're quite patient, and we like to sit around. We like to talk about ideas. We like to talk about them some more. We like to go out into the market and do our research. We like to formulate ideas over time. And sometimes we can spend six, seven, eight years finding the right company that fits within the thesis that we're looking for. And so a lot of the time we're trying to prove to entrepreneurs like, hey, we're not just chasing the hot thing. You are actually what we've been looking for for a long time and we have the receipts. And so that's kind of what this tool allows us to do.
Dan Shipper (00:17:30)
That's interesting. And one thing that I noticed though, is in these summaries, it's not saying, Fred wrote in 2015, blah, blah, blah.
Matt Cynamon (00:17:47)
So, I said, can you just share the URLs to those posts? They don't seem to be working, right? Because that's obviously the first thing that always happens with any of these bots is it gives you back— It cited the articles for me and then it gave me these actual URLs. And this is a little trick I've kind of learned about ChatGPT. One of the ways that it likes to hide the fact that it's lying to you is, it'll give you a fake URL and if your cursor is showing up like this, it means it's a fake URL that doesn't exist.
Dan Shipper (00:18:14)
Really? Yeah. That's so interesting. Okay. So if the cursor shows up as the same cursor that you see when you're highlighting text that you can type in instead of that mouse hand, that means that it's lying.
Matt Cynamon (00:18:29)
Yeah. Let's go look. Oh my god. That is a completely made-up link. So, then you can see I said, none of these are real, let's try again—with a smiley face. And now look at these, you see how my mouse cursor is changing? Trust in AI, Science Exchange, and then this one's still fake. “AI and Crypto.” But this is a blog post about that time we invested in Science Exchange. “I Trust in AI.” This is a blog post that Andy wrote about trust in AI, as it says, and these are real links.
So, you can now use links to the Consensus team and I was like, well, let's get a couple more—maybe something that's more about search because in this case I'm using my own knowledge about what we've done, which is that I know we've written a lot about search in the past. I know we've invested in search. So let's try to pull some of those in as well because you can't— I say this all the time, but if you're relying on the AI to produce the final product for you, you're always going to be disappointed. But if you're relying on the AI to help you get to a final product, then I don't know. I find it extremely powerful because normally this type of work would have actually taken quite a long time.
Dan Shipper (00:19:40)
That makes sense.
Matt Cynamon (00:19:43)
So here we have the fragmentation of search—our investment in DuckDuckGo. And I was like, okay, now let's rewrite the email, but include these articles, the real ones. Leave out the AI and crypto one, because that wasn't really relevant. And then also make sure to differentiate between the blog posts you pulled around DuckDuckGo and Science Exchange, which were relevant investments we've made, and then the other articles which are more like kind of what we're actively looking for. And I had instructed it earlier to write it in the voice of one of our partners, Jared Hecht. And I think it did a really great job. “I’ve been following what you're building with Consensus, I'm really impressed by their mission, and we are long believers in the transformative potential of AI to unlock knowledge and make it more accessible,” which, by the way, was a core part of our thesis for a long time. It did a good job of pulling that in. “We've made investments in companies like Science Exchange and DuckDuckGo, both of which share an ethos of lowering barriers to specialized knowledge and rethinking how people engage with information in terms of what we're actively thinking about. Here's a couple of other examples.”
Now, I don't think anyone on the team would ever allow the AI to write the email for them. I kind of did that just to show what's possible. But, basically demo this to the team. Hey, these things that you do to sort of prove to an entrepreneur that you're aligned with them that take you a long time, we can now do it way quicker and kind of in a fun way. And then I added one extra step to this, which I'd love to show you. I have this other GPT, which again, this used to be folded into The Librarian and I separated it out—called Portfolio Tracker. It categorizes all the companies that we've invested in, when we invested in them, what our ownership percentage is, all of that. And so in this Consensus example, I asked the Portfolio Tracker, build a chart that plots out all the companies we've invested in education, search, and AI over time. Because those are sort of the three areas that were most relevant to this team. And you kind of have this chart that goes all the way back 12 years of us investing in these spaces. But from my own, again, first-party knowledge of what we've done, I knew that Indeed, which was job search, which is a big part of the disaggregation of search early on, was missing here. But, first, actually, I asked it to make the colors more pronounced so that it was clearer what was going on. And then I said, the only company that isn't there that falls into the search category is Indeed. Make sure you include that one as well. But the reason why I didn't, Indeed didn't have a date, so I gave it the date, blah, blah, blah. And now we have this chart dating back to 2005 of all the relevant investments that we've made in the space that this company is working in. Again, I don't think we would actually send this chart to them, but this is all knowledge that would have probably taken a really long time to gather up. But now we can do it really quickly.
Dan Shipper (00:22:41)
Would you send the GPT to them and be like, hey, you can ask questions about what we think?
Matt Cynamon (00:22:48)
Yeah, absolutely. We haven't done that yet. But I think it is highly likely that if you come to our website at some time before the end of the year, that’s going to exist as The Librarian.
Dan Shipper (00:23:00)
I think that's really cool. I want Andy and Fred voice mode. And just get to ask them questions about ideas that reference all their blog posts.
Matt Cynamon (00:23:17)
Yeah. To date, everything that I have built has been more for internal use. And when it's internal use, you have a certain level of tolerance for information being wrong because, you know, it's all first-party data for you. So, for instance, Indeed didn't show up, but I knew we invested in Indeed in 2005, so I could correct it in that way. And so we're just thinking through how to get this to a place that it's just a tool for public consumption. I mean, what I really want to do, not just get Fred's opinion on things— And I think this is also on the roadmap for relatively soon is that you can just dump your deck into here and it can equip you with what we've written about in the past and that sort of enables you to be able to come to the meeting also ready to have a conversation in the way that we're sort of thinking about it as well. Kind of get aligned before you even walk in the door.
Dan Shipper (00:24:14)
And what are you thinking about? The place where my mind always goes for this kind of thing is: investing is this activity that you can talk about in terms of rules or maxims, but really it's a highly intuitive, pattern-matching type thing where Fred or Andy has developed, over many years, the ability to select the kind of opportunity and the kind of person that they have a taste for. And to some degree tools like this might be able to replicate some of that taste. Probably not all of it, but some of it. Have you explored that at all? If I wanted to get a rough idea of what Fred would think about this, I could throw it in there like for internal use. Or is that not really on your radar?
Matt Cynamon (00:25:08)
No. And there's two reasons why. Number one is the team is highly accessible here. So if I want to talk to Fred, I'll text Fred right now and ask him his opinion. And that's sort of how we operate. And so, there isn't really a need to internally, at least, abstract away the way that the different partners like to think about deals and then build a bot to sort of get their opinion because they're so accessible.
Dan Shipper (00:25:30)
What if they're gone? You know, I hope this doesn't happen, but Andy could get sick and I don't know—whatever. People don't last forever.
Matt Cynamon (00:25:50)
Yeah, I would then say, look, we can always query Andy's writing history. And we've talked to a lot of companies that are building digital clones for whatever reason—it's just not what we're interested in. And I think we believe that in general, venture capital is a highly relational business and we don't necessarily want abstractions of those relationships to replace or even augment the real relationships themselves. And in general, our approach to AI has been enhanced, not replaced. So knock on wood, if someone were to disappear it's not our intention to be able to build something that can replace them. We would just mourn them.
Dan Shipper (00:26:46)
That’s a very good answer. I will say I think that there's room for there to be compatibility between embodying someone's perspective in an AI like this and strengthening human relationships. I don't think it's an end or a question of augment or replacement. I think you can use that—even Fred or Andy could use that—and what would Fred have thought about this five years ago and how has he changed or whatever. There's lots of different ways to use that tool.
Matt Cynamon (00:27:20)
I’m going to augment my answer a little bit, which is to say, I don't think we would ever build that tool to help us decide what to invest in. I think we would build that tool to help our companies more. And so what do I mean by that? Every week we get together and we discuss all the potential new investments that are on the table. And then we walk through the portfolio and each partner gives an update on not necessarily every company in their portfolio every week, but for any company that there's something newsworthy or something that they need help with. We'll have those conversations and that stuff—the sticky situations that get thrown around in there are worth 30 MBAs. And so what we are working on right now is how to capture how Fred handles this particular situation. So we don't have to have that conversation 6,000 times, right?
Dan Shipper (00:28:20)
That's really interesting.
Matt Cynamon (00:28:26)
So, for example, a CEO wants to step down or sell the company. Have you ever gone through this before? And then there's a wealth of knowledge that gets passed back and forth in that Monday meeting that isn't necessarily captured and is not something we ever want to lose.
Dan Shipper (00:28:44)
Yeah, that makes sense. This reminds me of one of the one of the core ideas that I think is coming out of this particular era of AI. For me, it particularly applies for me to creative work, but I think it applies in all areas of business, which is it starts to reveal how much we actually repeat ourselves. Because it's very good at when something has happened before in a similar context, bringing it back and changing and giving the answer for that particular context. And so when you have a tool for that, you start to see the world through that lens. And I think it's there all the time in creative work. It's doing headlines or making a tweet out of an article or whatever. And that's why we built this tool Spiral to do that. But I think it's the same thing in investing. When a CEO wants to step down from a company, that feels a very unique situation. And there probably are some unique variables, but if Fred has seen that 5,000 times, he pretty much knows the three cases and three ways to respond or whatever. And having that available is helpful.
Matt Cynamon (00:30:03)
Yeah. I mean the actual idea that the actual conversation that comes to mind that happens a lot is like, say the CEO steps down. We need to bring in a replacement CEO. Should that CEO’s goal be to retain the entire executive team or bring in their own team?
Dan Shipper (00:30:19)
Can I try to answer that question? I'm curious what the USV perspective is.
Matt Cynamon (00:30:22)
Yeah, sure.
Dan Shipper (00:30:23)
I would say bring in your own team. I would say get rid of everyone.
Matt Cynamon (00:30:31)
I think it depends. So actually the way that you answered the question is kind of right, but I think the answer is you have to bring in your own team, but that doesn't mean that the people who are there aren’t your team. So that's what you have to suss out pretty. That's what it seems like you have to suss out pretty quickly. The team that's remaining—are they ready to ride with you as well? And if the answer is yes, then you keep the team. And if the answer is no, then for better or for worse, the only way you're going to be successful is probably bringing in your own team. And of course there, there's nuance to all of this and that's where I've been throwing this idea around with my colleague, Nick Grossman. We're calling it Playbooks. And there are all these Playbooks for these really tricky situations that we've never written down before. And so how do we trigger our AI transcribers to make notes of when those sorts of conversations are happening. And then recording those as Playbooks is a project that we're working on right now.
Dan Shipper (00:31:30)
That's really cool. I love that. I worked at an incubator before Every and we had a similar thing of trying to write down playbooks of how we made decisions. I think it's really interesting about all of this is that, USV can have a playbook for something like what to do if you're an incoming CEO of a startup that just fired their CEO, but the playbook that you would write is different from the playbook that Founders Fund would write.
Matt Cynamon (00:31:55)
Yeah, sure.
Dan Shipper (00:31:56)
And what I think is so interesting about that is, even though they're quite different, they both work, but they probably work in slightly different contexts. And USV is probably going to attract founders and types of companies that work for US Vs worldview and kind of advice—not always, but more likely. And Founders Fund is going to kind of be giving advice in a context that's more suited to the Founders Fund style of advice. And I don't know, because I think I've always been sort of fascinated by, if you ask five successful people how to handle a situation, you get five different answers, and they all kind of work, but they're all very contextual. And I think AI helps you kind of see that a little bit.
Matt Cynamon (00:32:48)
Well, I would say this. I mean, one of the things that we like to say is it's very much a marriage. At the end of the day, the product that we sell is money—and our money is just as green as Founders Fund, as a16z, as whoever else. Everyone's selling the same product. Sure, you can dress it up with all these sorts of value-added services, which a lot of funds do. I think Founders Fund, if I'm correct— Sorry, well some provide none, and that's actually what they believe is the value add that they get out of your way. But at the end of the day the real differentiator is the relationships and perspectives and do you align with the people that you're doing business with? And so, yeah, I think obviously, you can suss that out through the diligence process and reading historical writing and whatnot. But that stuff happens so fast. Founders sometimes are making decisions over the course of two weeks about people that they're going to be in business with for the next 10 years. And they don't even make decisions that fast when it comes to hiring. And hiring is not as permanent sometimes as adding someone to the cap table, which is kind of a lifelong commitment to the company. And so, yeah, I think conversational tools that can really help you get a sense of the type of person you're going into business with, how they think, how they like to work, I think could be really helpful for founders making that decision.
Dan Shipper (00:34:25)
Totally. Okay. I want to keep going. I know you have a ton of different tools. Let’s keep going. What's the next thing you want to show us?
Matt Cynamon (00:34:31)
Well, I mean, my favorite thing that I've made recently was Meeting Notes. So we've started transcribing— I mean, we've been doing this for a while. We've been transcribing all of our meetings for the last four months. It's actually not true. It's not all of our meetings. We do these sort of special topical meetings around things like AI, crypto, climate and then we do sort of this miscellaneous one and that's sort of where we hash out ideas and discuss specific companies. And so we've been transcribing those and now we're sort of porting automatically pulling those into this GPT so that you can ask questions to the meetings. I kind of want to make two separate points. One is, well, why are we doing this all here when there are better purpose-built tools. And I think one of the main reasons, for instance, we could do all this in Granola. You don't need to build a spectral GPT in order to ask questions to meeting nodes. But what I think is really nice, and I can't necessarily show this to you because I'm recording myself on my phone. But if any member of USV opens up like their ChatGPT or their cloud on their phone, there's a conversational interface with every part of the business in the left-hand column that they have access to right there without having to toggle between a million different apps. So, I actually really preferred NotebookLM for instance, for analyzing meeting notes. But sometimes ease of access is the best feature and I think whether it's Claude Projects or whether it's you know GPTs on ChatGPT, for our purposes, I think that just works a little bit better.
Dan Shipper (00:36:16)
Wait. I gotta go back. Well, shots fired on NotebookLM. Why do you prefer it for meeting notes?
Matt Cynamon (00:36:22)
So there's three reasons why I like NotebookLM better. Number one is I think it comes up with really insightful questions to ask the notes. I think number two is, by the way, are you saying this is shots fired on Spiral?
Dan Shipper (00:36:46)
No. Shots fired on ChatGPT.
Matt Cynamon (00:36:48)
Oh, I was going to say, I mean, all these products are amazing. So, number one is I think it prompts you with really thoughtful questions about the meetings that I sometimes would have not come up with myself. Number two is I think it does a much better job of citing the transcript or the things that have happened in the meeting so I can verify whether or not that actually happened. And then the third thing is: my new favorite thing in the world is not to read meeting notes or read meeting recaps, but to listen to meeting podcasts. And so anytime we have a really important meeting, I mean, I can just pull one up. We had his guy, Gary Hustwit, who directed the Eno film, it was a generative AI film about the life of Brian Eno that was running at the film forum in New York. And he came in and just talked to us about his process. Obviously, I attended that meeting, but it was super fun to just also turn that meeting into a podcast and then give it to my wife and be like, how cool was this meeting that we just had?
Dan Shipper (00:37:48)
Dude, yeah. I love that.
Matt Cynamon (00:37:55)
Or we had a really, really dense AI meeting on Monday. And I shared the notes around. I was like, I would honestly recommend listening to the podcast because it's a lot more fun and it's all 10–15 minutes long, so you can do it on a subway, you can do it on a city bike. And what I like about podcasts as a meeting recap is you can do it while you do other things. I can't read and do other things at the same time, but I can listen to two people talk about a topic while I'm responding to emails or riding on the subway or whatever it might be.
Dan Shipper (00:38:32)
Totally. We're so on the same wavelength here. So I think you've probably seen this, but two days ago we launched our studio where we do product incubations. And one of the ones I'm most excited about is we built something that— We record all of our meetings and we use Discord instead of Slack, but it takes all of the messages that happen in important channels. And then it creates a podcast of what happened. And it's the notebook on style thing. And it's so good. We're at a scale now where I can't be in every meeting, which is fucking wild to me because I'm like, I write a newsletter and do a podcast. That's weird. But yeah, we're at a scale now where I can't be in every meeting. And I just love listening to a podcast about a meeting that I deeply wanted to go to, but didn't have time to attend. And it's so helpful. And one of the things I love most about it is you feel so good when the host mentions your name.
Matt Cynamon (00:39:38)
I'll tell you what, do you know what makes you feel even better?
Dan Shipper (00:39:46)
What?
Matt Cynamon (00:39:50)
When the host is like, whoa, that's a good idea.
Dan Shipper (00:39:55)
It's so good. I'm so excited for this product. So I think we're going to do something external where you can listen to every meeting. But I think we're going to just release it as a product or use it. I would love to have you guys try it. Because I think you're the perfect place to give it a shot. But it's really cool. And it seems like you're doing it already. Can we listen to a little bit of a podcast?
Matt Cynamon (00:40:18)
Yeah, for sure.
Dan Shipper (00:41:01)
That’s so cool. I love that. I honestly would keep listening to that.
Matt Cynamon (00:41:07)
I'll send it to you.
Dan Shipper (00:41:14)
Yeah, send it to me. Send it to me, please.
Matt Cynamon (00:41:15)
Well, I actually really want to start because what we're trying to do is let people into a lot of our processes earlier. Because we're sitting in our office and we're talking about ideas and it sometimes can be months before we really communicate it to the public. And so we're trying to find interesting ways to let people in a little bit sooner. And so I might just start releasing all of our meetings as a podcast that people can listen and—
Dan Shipper (00:41:38)
You should totally. I love that idea.
Matt Cynamon (00:41:39)
I think I’ll release one today then.
Dan Shipper (00:41:42)
Perfect. Let's do that. One of the things I feel really strongly right now is— Do you remember the startup Justin.tv?
Matt Cynamon (00:41:50)
Yeah, of course.
Dan Shipper (00:41:52)
So I think that Justin.tv would actually work now because the reason why Justin.tv didn't work is, if you're recording yourself 24/7— And for people who don't remember Justin.tv was Justin Kan, who eventually started Twitch, was just wearing a video camera around and streaming videos of himself, doing his whole life, basically. And the reason why that doesn't work is because of any given day for a normal person, there's like 12 interesting minutes. AND you have to string those minutes together into a story in order to make them compelling and tuning into any given minute of a person's life is not that interesting. And one of the things that I think is the cost of good storytelling is going down dramatically. And what that will do is you're not going to necessarily read novels written by AI. It's not going to necessarily just replace all human novelists, but we will be able to tell high-quality stories about places that we normally would not be able to afford to tell stories about. And one of those places is your company meetings. or whatever Justin.tv was now, Justin Kan, when he was 20 and not a billionaire can afford to have incredible stories told about his life. Because I can pick out the interesting things and leave the rest out.
Matt Cynamon (00:43:09)
It's funny that you say that because we talked at the beginning about the little overheards that we do. I mean, a lot of that was born from this idea that, hey, we're not producing enough content. And I was of the opinion that, well, actually we're producing a ton of content. Every day we are getting together and we are producing a ton of content and just not capturing it. And we're not necessarily curating it enough. And so that was really the impetus behind that. It was like, there are these great stories that are happening in our meetings. That just ends up sitting in our heads for weeks on end until we can put pen to paper to get our ideas out there. And for us, nothing is ever going to replace writing as our primary mode of getting our thoughts and ideas out into the world for a variety of reasons. But there's a lot of things that we can do to tell stories in the meantime. And then there are lots of things that we can build that will help us write quicker and easier than we've done in the past. And I think that's kind of where our focus has been.
Dan Shipper (00:44:22)
That's really cool. I know that you said we could get an OH at USV out. I would love to see you go through that process.
Matt Cynamon (00:44:29)
Well, I'll start by saying this process has changed so many times since we started doing it. It used to be fully automated, then it was super hand done and now it's kind of somewhere in the middle, but let's do it as automated as possible. So I'll go back to share my screen again. We'll open up ChatGPT. Let's do our Meeting Notes. So I'm having a little bit of an issue with Meeting Notes understanding what the most recent meeting means. So I've been a little explicit recently. “Let's produce five OHs from the AI meeting on October 15 and the three meetings on October 18. Don't explicitly mention any companies or anything specific to a company.” Because when we were doing things a little more automated, sometimes companies would come in and pitch. And we wouldn't really want their pitch to go out into the world and make it look like, hey, these are our ideas. So let's see how we do.
Dan Shipper (00:45:39)
So it's saying, “Here are the five OH posts based on the AI meeting on October 15, and the three meetings from October 18. 1. Commoditization is coming: The race for dominance in AI models may lead to a future where foundational technologies become a commodity. It's a reminder that differentiation is key to survival to decentralize to survive. We debated if decentralized AI models can compete with their centralized counterparts. It might be the only way to break free from the current tech China's hold.” I think that's a really good debate. “3. Hydrogen risk or reward as we push for greater tech hydrogen. The potential for clean energy remains controversial, both promising and dangerous safety concerns. Keep the debate heated for uncorrelated bets matter. The unpredictability of AI as evolution means diversifying investments is crucial,” interesting. And then, “5. Microgrid revolution. Our microgrids are great and gaining traction. Their potential to revolutionize local energy is undeniable.” These are cool. What's really interesting is I want the ability to be, okay, tell me more about uncorrelated bets, you know?
Matt Cynamon (00:46:38)
I mean, I can tell you more about unrelated things. Well, I guess I'd throw this question back to you. How do you think we should release this into the world so that people can ask follow up questions into our meetings. We tweet these out and they get some engagement, but I don't know if it's that people would rather have a private conversation with our meeting or whether they want to have a public conversation with our meeting. How can we get people to ask us more questions about uncorrelated bets?
Dan Shipper (00:47:05)
I think the key thing is when you read this— So, uncorrelated bets matter in venture, the unpredictability of AI is evolution means diversifying event investments is crucial. The real question, which bets will prove to be the game changers. So, that is posing a question, but it's not giving me any hint at all about what your take might be, right? USV’s perspective is completely hidden there. So I know the topics, but I don't have any concrete idea of, oh, you think that if you're going to invest in AI, you also have to invest in the Japanese whaling industry. Because they're completely uncorrelated or whatever. So that would be my guess is that the summaries are. And I think this is just a problem generally of AI-generated summaries. they're good at finding interesting topics, but they're very good at telling you things without saying very much at all.
Matt Cynamon (00:48:12)
Oftentimes, if something pops up as if overheard at USV, which means it's something that we're discussing in a meeting, the reason why we're discussing it in the meeting is because we don't always have the answer yet. Typically when we feel like we have the answer, that's when we write about it. Now, with uncorrelated bets, I could be at a point in our thinking where I think we have a strong idea of the direction where we are, where we want to go, which is that there's this X and Y axis of different things that could happen in generative AI. On one end of the spectrum is, we could be living in a world of an oligopoly when it comes to models, where all the power is within four companies, or we could be living in a multi-model world, so that's one access. And then another access is: we reach a plateau in terms of AI's ability vs. we get runaway AI or self-improving AI, and that's another axis. And so there are a range of different outcomes that can happen based on the answers to those two questions, which are questions we don't necessarily have the answer to yet. And as a venture firm, it's important that you make bets that occur sort of within each scenario. So that if one of those scenarios does happen, you've made the right bet and hopefully you've backed the right team. And one of those scenarios doesn't happen then and you won't, and you put all your eggs in one basket, then that's not really good portfolio management.
Dan Shipper (00:49:45)
Yeah, no, I think that makes sense. I think that, even if you don't have a particular perspective, if I knew, okay, Andy brought up uncorrelated bets because he's concerned about X, Y, Z. And so that became an open question. Or if I knew Andy and Matt argued about what it means to be uncorrelated and any position was this and that was this, but it's an open question. Even if it's not a statement about what your full perspective is, even that gives me enough detail to be, oh wow, that's actually really interesting. And I don't know the answer to that question or here's what I think, you know?
Matt Cynamon (00:50:18)
Yeah. So I think because we said that we were going to push these events this week, we should do that. But I think what I'm hearing from you and we'll do this next week is let's alter the system prompt a little bit to make sure whether we're identifying whether something is a topic where we have a really strong opinion on. And if so, let's say it. And if it's one where it's still an open question, let's say it. Let's leave it as an open question.
Dan Shipper (00:50:40)
Do you think we could try it? Not necessarily even modify the system prompt, but just follow up and see if we can make these better. Or if you want to modify the system, you probably can.
Matt Cynamon (00:50:49)
Oh, well, I mean, I'm happy. What would you like me to ask?
Dan Shipper (00:50:55)
Okay. I think that I would say, none of these tell me anything about the positions that were actually taken by anyone in the meeting. Can you be more concrete about what the different positions were, what people thought?
Matt Cynamon (00:51:12)
So I can tell you now, it will not be able to tell you who said what.
Dan Shipper (00:51:17)
That's okay.
Matt Cynamon (00:51:18)
And that's not for privacy reasons. That's just limitations on the technology.
Dan Shipper (00:51:27)
Yeah, I think that's totally fine. It doesn't have to have names. I just want to know what the perspectives were. Okay. So it says, “Commoditization is coming. The concern about commoditization of foundation models was voiced by multiple participants. One side argued that these models driven by high burn rates are becoming indistinguishable. Leading to a race to the bottom. Another perspective emphasized the need for differentiation, particularly through proprietary data to escape this trend. Consensus leaned towards cautious optimism for companies that can find unique data sets or applications.” See, that actually I'm like, wow, these are the two ideas. and then now I kind of understand where the conversation went. And then the thing that I would maybe think about is how to express that as part of the headline but yeah, I mean that I'm more interested in that personally. I don't know what you think.
Matt Cynamon (00:52:25)
So in this case, you think it's better to re-prompt a few times until you get something that's extremely valuable vs. publishing the unfiltered results of the LLM.
Dan Shipper (00:52:38)
Yeah.
Matt Cynamon (00:52:40)
Let's do that then.
Dan Shipper (00:52:42)
Great.
Matt Cynamon (00:52:48)
So I mean, decisions get made here too.
Dan Shipper (00:52:50)
I mean, because the first one, which is publishing the unfiltered results to me, that's more like a barometer of AI progress than it is what's going on at USV, right? And I think the idea for you guys is not necessarily creating a barometer of progress directly, but more actually just getting out what are we actually thinking about? I'm using this cool technology to tell that to people, but you tell me.
Matt Cynamon (00:53:17)
No, I mean, so here's where it gets tricky for me. When we look at this one, decentralized AI, it actually got this very slightly wrong because we were not talking about decentralized AI models. We were talking about specifically decentralized training, which is different. And it doesn't really, because the general idea here is that the really big companies are well suited to win because they build out these enormous facilities, these enormous clusters where they're doing all their training. But if you can figure out a way to do decentralized or distributed training, then you don't necessarily need the same tool, high capital investment, to get started, in order to compete. And so, that seems a really important area to be looking for investments so that we can build towards a multi-model world. And that isn't really captured here. But it's close.
Dan Shipper (00:54:24)
I think you're totally right. I wonder what it would be like if it wasn't a one-shot thing. And it was like, each time you did it for one topic, as opposed to all of them at once. But yeah, I think that that makes total sense and that, at least for me, would be something that would annoy me. I would need to get this right. And that's such an interest. That's so interesting. No one's talking about that. No one is talking about that. And it's really important that more people do like it. The thing that I think about is all those people that were mining bitcoin should just be financing AI training runs and that's cool.
Matt Cynamon (00:55:05)
Yes. And that’s where our head is at with number two.
Dan Shipper (00:55:10)
Okay. Got it. cool. Well, I guess we're on the same page or at least I can follow your line of thought once you explain it to me.
Matt Cynamon (00:55:18)
It's this fine line. And I guess the conclusion that I've kind of reached and I think you've kind of helped me see it here as well is that I think that the market for purely AI generated media is the size of your largest group chat. And I think any time we do something new, what people are actually interested in isn't necessarily the content that was produced, but how we did it. And so I tend sometimes to over index on let's keep as many hands off as possible. But in reality, if we go back to sort of our first principles of “enhance, not replace,” when it comes to our own internal AI projects, we should be using these tools in partnership with humans to create better content that's actually valuable for the people who are consuming it. And so I think you changed my thinking a little on this.
Dan Shipper (00:56:17)
I love that. I love the value of purely AI generated content is the size of your biggest group chat, which at work is your Slack channel—your whole Slack. And that's why I think the work podcast thing is really interesting because to your point, you don't have to read all the emails you want to read while you're sitting at your desk, you can listen to that, listen to all the things you missed while you're doing the dishes, which is another point that I was talking about. I was talking to someone else a few days ago on this podcast about—do you know Yohei Nakajima?
Matt Cynamon (00:56:55)
Yeah, of course. My inspiration for everything.
Dan Shipper (00:56:59)
Yeah, he's absolutely amazing. And obviously he does all these really cool AI side projects, has a similar tinkerer vibe to you, to me, to a lot of the people I really like hanging out with. And one of the things that he said that I think is so interesting is that, because I asked him, how do you do all this stuff? You have a day job as a VC, you have kids and you're programming all the time. How is it even possible? And he was like, well, first of all, I only do it at night after they're in bed, which makes sense.
Matt Cynamon (00:57:32)
I mostly do it in the morning.
Dan Shipper (00:57:34)
So, okay, there you go. But also because it's doing a lot of the coding for me, I can do it with divided attention. I can do it with fractured attention. So I can say, okay, go build this thing. And then I go do some dishes and I come back and I see if it did it. And then if it did, I say, okay, do the next thing. And he doesn't necessarily need to be in that full flow state all the time. And so I think a lot of these tools are, for example, AI-driven storytelling . You can listen to stories about content that wouldn't have necessarily been storied before. And that means you can consume that content in places that you wouldn't ordinarily have been able to consume it, listening to your meetings that you miss while you're doing your dishes or and in programming cases. You can create things in situations where you wouldn't have been able to create them before because you don't have to do all the work in this super zoned-in flow state.
Matt Cynamon (00:58:32)
Yeah, though the one counter is: Should I just do the dishes?
Dan Shipper (00:58:35)
That's a really important question, which I think is really interesting. And it's an extension of a question that we've had to ask ourselves, since cell phones or since the internet or whatever, we're bringing all this stuff into an integrating into every aspect of our lives. I think one of the things that I feel that makes me sort of optimistic is because you can now talk to computers, you can express with much more, fine-grain control what you want to see and when. And so, for example, I really think we're going to get to a world pretty quickly where instead of seeing the trash Twitter algorithm that everyone else sees that's optimized for the most amount of engagement possible on a mass scale, I'll be able to say here, I only want to see, if you show me an article on Twitter and it's about science, I only want to see articles where, if it was not just a mouse study—don't show me any finance articles unless the market has moved more than 3 percent. Stuff like that where, as things get more integrated, we also have the ability to have more fine-grain control about what we see when, which hopefully is healthier, but also people do dumb stuff and yeah, there's trade-offs here. It's not all good.
Matt Cynamon (01:00:18)
Yeah. I mean, the challenge there is that so much of our internet lives are owned by these handful of data monopolies—Meta, Twitter. And it requires either breaking those monopolies or behavior change on their part in order to kind of build a more customizable internet, in my opinion. And so I think it's worth backing lots and lots of businesses that can potentially break those monopolies. And in addition to that, I think kind of forking over full control of LLMs to four or five major tech conglomerates is really problematic for society in the long run.
Dan Shipper (01:01:05)
I think you're totally right. And the thing I will add to both of those things is I also think there should be a social movement to ask large tech companies to establish data trusts where they make all of their data open to researchers, because I think it's so silly to me that people like researchers at universities are doing studies with a sample size of 16 people when Facebook is sitting on trillions of terabytes of the most valuable behavioral data ever to understand what it is to be human and what works and what doesn't. And I think people hate tech companies right now. I think there should be a social movement for them to donate it for the public good. And also, while we're at it, to make sure that all data can be exportable by an individual, because suddenly, the sequence data, for example, that I get from my WHOOP— If I can throw that into an AI model, it can make predictions about what is good for me or what I might want to do with my health that I can't make unless I have that data. And I don't think any company should be able to keep that away from me.
Matt Cynamon (01:02:25)
Yeah, I mean, this is and has been a major, major part of our firm's thesis for 10-plus years when it comes to web3 applications, which is composable data that can exist anywhere you want it to exist and that blockchains can enable that. I think there's a long way to go on sorting out the UX of a lot of those applications. So in the meantime, let's push the big tech companies to make our data at least available for research purposes.
Dan Shipper (01:02:54)
You're here to hear first folks—grassroots movement, data trusts. Cool. We're getting close to time here. And there was one thing that you showed me before we started recording that fucking blew my mind. And I would just want to make sure that we get some time to show it to people. So, set the scene for us. What are we about to see?
Matt Cynamon (01:03:18)
Sure. So, I am actually sitting in front of a 120-something—maybe, I don't know how big it is—a really big television. And hooked up to this television, there's a bunch of different things, but one setting is hardwired directly into a piece of machinery that is locally running a visual diffusion model, that is connected to the Whisper API that listens to what we are saying and then in real time generates moving images based on what we're talking about. It's called The Dream Machine. And it was developed by an artist who I only know as Humin. I think it's H-U-M-I-N. You can follow him on Twitter. He was a member of a group called the Bright Moments DAO, where he developed this, which was an investment of ours. And this kind of just sits in the background in our office from time to time. And it's one of the coolest things because it is one of the few things that we have here that both visiting CEOs or whoever or other investors will come and have their minds blown. But then also I very often catch the building super bringing his friends up to kind of play with it. So I'm going to turn it on. The one caveat I'll say is that this thing tends to get pretty backloaded. So sometimes it's a little slow in terms of its responsiveness. But let's just throw it on and see what it's doing anyway.
Dan Shipper (01:04:49)
Great. Perfect.
Matt Cynamon (01:04:51)
There we go.
Dan Shipper (01:04:51)
Ooh, we've got an aquarium. Okay. So I'm just going to name some things and see what it does. Yeah, I've been reading Moby Dick and it's really good. I've actually just finished it. And I just love all the whales, and oceanic iconography—he gets really into the whaling industry. It's such a detailed account of how whales work. And I guess we've got the aquarium, so we're getting close to whales.
Matt Cynamon (01:05:10)
Well, what I was going to say is every once in a while you have to reset this thing's memory because it becomes so backlogged with things that people have talked about in the past. That it can sometimes take a minute or so before what you're talking about actually shows up, but there's our whales.
Dan Shipper (01:05:25)
Here they come. Look at that. That's so fucking cool, dude.
Matt Cynamon (01:05:30)
By the way, if we had wiped its memory before we started, those whales would have just popped up immediately. And one fun thing I'll say is that, we had some event here with Sen. Gillibrand and she allowed us to have this going in the background while she was talking. So it was basically transcribing a senator's speech with visual imagery.
Dan Shipper (01:06:05)
So here’s what it reminds me of: The way fiction works is when you're describing the setting around a character, typically the way that you describe it will be a reflection of the character's internal state. And that's why, it's a cliche that when something bad happens in a movie, it's raining outside. It always reflects how they're actually feeling and you can create this real sense of drama, and concreteness. And that's Gillibrand behind you, which is crazy. I'm sorry. This real sense of drama and visceral— I'm there kind of in connection to the character with that. And that's what this feels like to me is it's reflecting this in our internal states and our conversations in this visual way that reminds me a lot of fiction.
Matt Cynamon (01:06:53)
Well, I would just say compliments to the chef. But also I think this is one of the first like truly native AI artistic forms that could not exist in a world prior to AI, which I think makes it really fun. And obviously there's cats coming up and, I don't know. It's just like, ooh, geez. I know I have such a hard time communicating when this is on because I'm just looking at it. I tried to have a serious meeting here the other day with someone while this was running and it did not go well. I don't know. Bring your ideas to life. I feel like that is kind of what the lesson of The Dream Machine is and sort of my perspective on everything that's happened over the last six months of my life is just make stuff because the tools are there to do it.
Dan Shipper (01:07:56)
Fuck yeah, dude. That's exactly how I feel. I love it. And I think that's a great place to end. Thank you so much for coming on and showing us all this stuff. It was amazing.
Matt Cynamon (01:08:07)
No problem. And by the way, if we meet again in a year, my hope is that The Librarian will be here with us because that is what we're working on.
Dan Shipper (01:08:11)
Let's book it. I definitely want to have you on in the coming months and years.
Matt Cynamon (01:08:17)
Cool. Thanks so much, Dan.
Thanks to Scott Nover for editorial support.
Dan Shipper is the cofounder and CEO of Every, where he writes the Chain of Thought column and hosts the podcast AI & I. You can follow him on X at @danshipper and on LinkedIn, and Every on X at @every and on LinkedIn.
We also build AI tools for readers like you. Automate repeat writing with Spiral. Organize files automatically with Sparkle. Write something great with Lex.
Find Out What
Comes Next in Tech.
Start your free trial.
New ideas to help you build the future—in your inbox, every day. Trusted by over 75,000 readers.
SubscribeAlready have an account? Sign in
What's included?
- Unlimited access to our daily essays by Dan Shipper, Evan Armstrong, and a roster of the best tech writers on the internet
- Full access to an archive of hundreds of in-depth articles
- Priority access and subscriber-only discounts to courses, events, and more
- Ad-free experience
- Access to our Discord community
Comments
Don't have an account? Sign up!