text
stringlengths 204
6.98k
|
|---|
<human>: Next one, how to be excited about technology. We came up in this weird era, I guess, I didn't think it was weird, but looking back, I guess it was weird, where everyone thought technology was cool and making the world a better place.
<bot>: Yeah. A lot of the way we understand the world is framed via journalism. Yes. And one thing, again, for young people, they don't have context on this, but it used to be journalists were all emphatically excited with no, downsides no reservations no reservations the internet is great yes it's and they would debate how great it was yeah the debate was like yeah yeah we know it's great but just how great yeah and who's making it the best who's making it the better the fastest you know and so it was this it was hard to like see any problems with it yes and um in this current universe we live in it's the opposite
<human>: Yeah, it's, this is bad. A lot of these people are bad. Every new technology, how is it going to try to screw us, exploit us? Yeah. You know, yada, yada, yada. And let's be clear, both extremes are incorrect.
<bot>: That's correct, yeah, there's fair points. It's 100% there are fair points. But sometimes when I talk to young folks, they internalize too much of the current thing. And I think, I don't see how that helps you when you're young. Like your job is to be an optimist. Your job is to believe amazing things about what can you do with your life and what can you do in the world when you're young.
</s> |
<human>: So another thing that happened recently is we sent a letter to YC founders about the economic downturn, which was, happened to maybe get a little bit of exposure to the general public. I'm not sure how that happened. But it was interesting because I've been really impressed with how the YC founders have responded. What have you seen? I think that if you're smart,
<bot>: You know how to look at things like that, as well as just general press or advice, and apply it to your specific situation correctly. Like, if you're a two-person startup with no burn, what's happening in the late-stage fundraising environment in IPOs? Like, if that's what you're worried about, man, you've got bigger problems, okay? And so I think if you were able to say, well, what is my actual situation? Am I default alive? How much cash do I have? What's my runway? And then make the right moves. Because again, for some folks, the actual move is to go on offense. Like we said a moment ago, where they're like, okay, I see. So this is the score, got it. Time to go hard against my competitors who have higher burn. This is a great time if you're the underdog and your large competitor is in trouble. And so I think that smart founders know what applies to them and what doesn't versus overly freaking out about things that have nothing to do with them. What do you think?
</s> |
<human>: I think that the, the challenge nowadays is where will non-conformists go to find their home? You know, it, it used to be as easy as going to tech and, and now, um, it's not as easy to go to tech. And, you know, you brought this up when we were discussing this before, but, you know, PG originally started YC to be a home for this type of people, right? To be a home for people who wanted. to build, who didn't want to wait in line, who really didn't care about status in and of itself. They just wanted to go out there and like challenge themselves. And it's interesting because when we're talking to founders now. um, who are in YC, there are all these things that we hear or conversations that we have that do motivate us, that do make us feel like, oh my God, like you, you actually want to be a builder. And I think it'd be helpful to kind of talk about some of those things, because they might be different than people would think. The first one that immediately comes to mind for me is, you know, now that YC gives $500,000, I'll have conversations with founders all the time where they come to me and they, they're like quiet. They think I'm going to disapprove. Right. They're like, Michael, like, I know I'm not supposed to say this, but I think 500,000 might be all the money we need to like, I don't know, like hit 50K in MRR to like get profitable or like hit this mega milestone. Like, is it okay if we don't raise a bunch of money? You know, I think the other hint and you brought this up, you better describe it in more detail is. They have no idea who the like tech Twitter celeb of the moment is, or the tech Twitter debate of the moment is, right? Like this is not, they don't live in that world. How have you seen that? It's just a sign of what you're focused on.
<bot>: And so when folks are really involved in the scene, in the drama, in the characters, um, and are obsessed with the startup scene, as opposed to their own thing and solving customer problems. Yeah. That's usually a sign of like conformity.
</s> |
<human>: Hey, this is Michael Seibel with Dalton Caldwell. And welcome to Rookie mistakes. We asked YC founders for their rookie mistakes so we could share them with you and help you avoid them. Here's the first mistake that was written in. In my company, we tried to accommodate more than one use case in our product before nailing a single use case and proving out that there even exists a business serving that customer.
<bot>: Yeah, this is super common. It's definitely a problem. We call this boiling the ocean. It's, you're trying to do something that's basically impossible or intractable, and all of your instincts are to build a complete, fully formed product without getting a single user. In your mind, you have this elaborate plan, and so your plan to start the elaborate plan is to build it all at once before getting a single user.
</s> |
<human>: This is Michael Seibel with Dalton Caldwell. And today we're going to talk about cargo culting. We encounter this way too much in our life. So there's classic variety and then there's new age, modern cargo culting. Let's start with classic. What's classic cargo cult?
<bot>: Well, let's start with what is cargo culting? What do we even. What are these guys talking about?
<human>: What are we talking about?
<bot>: All right, so the history of the term, as I understand it, is when you superficially copy something without understanding why you're copying it.
<human>: Yes.
<bot>: That is cargo culting. I think the history, if someone looks this up and Wikipedia is like, folks would create a fake airfield so that the planes came back. And so it was something that looks like a landing strip because they wanted the airplanes to come back. They didn't really understand why the planes were coming. So like, oh, if we make a fake landing strip, then the airplanes will come back. And so in this classic cargo culting mentality, it's just, I'm gonna copy something. I don't know why, I'm gonna copy It, and then I will be as successful as the thing I'm copying. Right?
<human>: Yes.
<bot>: Anything to add there?
<human>: Well, I think in the classic variety, what's essential is the thing that you're copying is good. Yeah. No one would debate whether it's good or not. Right. And so we're just debating how you copy it.
<bot>: Yeah.
<human>: I think what's funny about this modern new age that we'll get to later is that, like, we could even just debate whether the thing you're copying is worth copying at all.
<bot>: Fair.
</s> |
<human>: And that's probably the overarching theme. They had to be contrarian to walk down this path because if they had asked 10 startup experts, 10 investors, 10 fellow founders, eight of them would have told them that they were stupid.
<bot>: And they had to build good products. Like you can't take for granted, you can't, we can't, you know, talk on a whiteboard and plan our strategy and win. All of these founders had to actually do it. And the doing it part was the hard part. Yes.
<human>: Right.
<bot>: Like all, all these people had to execute and build a product that people loved and actually worked. And all these people built products that handled hundreds of millions of dollars and they couldn't lose the money. Right. So the actual execution bits, talk is cheap, execution's hard. Execution's expensive, and they had all these folks how to execute.
</s> |
<human>: Hello, this is Michael Seibel with Dalton Caldwell. And today we want to talk about our secret for learning as much as possible from your early stage customers. One of the things that we have to fight a lot for these founders, early stage founders, we had to fight is this idea that when we started the company, We understand the problem really well that we're trying to solve. We understand the customer really well. We understand the solution really well.
<bot>: Yeah, we have it all figured out, right? Day one, we nailed it. We have our next 10-year plan all lined up. And why would you start a company if you didn't have the plan, like if you didn't know, right? It's true. Overconfident foolishness. is a key part of doing anything ambitious in life. So I do, you're right, you gotta love that. You gotta start there and then immediately switch.
<human>: Wait, maybe we don't know anything. Is that possible? But you only switch after you burn the bridge behind you.
<bot>: Yeah, but you can't quit. You have to be apart enough long, quitting's not an option before you realize you don't actually know too much.
</s> |
<human>: I think this is a neat trick for an early stage founder. Audit the amount of time you spent last week talking to your customers and building product. Right. If that amount of time in your waking day is like 80 to 90 percent, you're probably doing it right. If that amount of time in your waking hours in the last week is more like 20%, you're probably doing something very, very wrong. All right, so here's the next note that a YC founder wrote in. You know, a lot of founders think money is like oxygen and you need it to survive. One of the things that Brian Chesky at Airbnb told The Batch recently is maybe money is more like food. You definitely need food to survive, but in a lot of places in the world, including America, people are dying from too much food as opposed to too little food.
<bot>: If you're afraid that bad things are going to happen, the idea of stockpiling as much of whatever resources you can as much as possible is totally sane and reasonable. The issue is really successful companies, the oxygen they have is revenue from their customers and they're being pulled ahead by customer demand for their product. And that is providing the oxygen of growth is like the pull of customers.
</s> |
<human>: So the next one is Coinbase. So set the scene for Coinbase. What do you think Brian saw when he was getting rolling?
<bot>: Yeah, so I was around back then and I was trying to buy Bitcoin back then too. And I remember the Coinbase YC application really well in the whole historical context. So to set this up for people, circa 2011, 2012, it was really hard to buy Bitcoin. Really hard. I remember looking into it around 2011, and there was a step of sending money orders, like going to Western Union and sending a money order to some foreign country. And that's when I hopped out of it. I wish I would have done it, would have made a lot of money. But I didn't, because it just seemed too much like a total scam. Like if you're ever sending money orders to foreign countries, something is going wrong in your life, right? But anyway, I also was familiar with Mt. Gox. And Mt. Gox was the biggest and largest Bitcoin exchange back in the day. It went down a lot and got hacked and everyone lost all their money. I actually lost some money in Mt. Gox personally. I think I had about one Bitcoin in Mt. Gox.
<human>: I'm not too worried about it. I feel like the reputation for Mt. Gox was like, you can get money in, but you can't ever get any money back out. That was the environment where Kugo Coinbase was coming in.
<bot>: What it's grown out of is that Mt. Gox was an acronym that was Magic the Gathering Online Exchange. It was originally a website to trade magic cards that they pivoted into Bitcoin. And so anyway, the historical insight was buying Bitcoin was something people wanted to do. but all of the options were pretty bad. That's the historical context and Brian wanted to fix that.
</s> |
<human>: So, you know, I think it makes sense to split this up into mistakes that people make setting goals and then mistakes people make trying to accomplish these goals. So I would say like the first one, and maybe I'll start with the simplest, is when people set goals that are so aggressive, they aren't motivational. And they're basically missing the understanding of what the purpose of setting a goal is, right? Like you want to motivate yourself to act smarter, faster, more intelligently than you would otherwise. And oftentimes people are setting goals that are too aggressive because they're motivated by fear. You know, in YC we see this all the time.
<bot>: And what's an example of a too aggressive goal? Like, what do you think? I can give you an example. What do you think?
<human>: Yeah, you know, I'll see a YC founder who comes in to YC just starting to build their product. And they tell me, by demo day, we want to have, you know, 30k in MRR. And we want to do that because some alum told us that like, that's how much MRR you need in order to raise money on demo day. And it's just like, How many errors can be said in three sentences, you know, is my thought. What's an example that comes to your mind?
<bot>: My most common example is someone that believes once they launch a product, it will immediately succeed and take off. And so it's like, we're going to spend three months building this app. We're going to put it in the app store. We're going to launch. and then we're going to get 100,000 DAU. Yeah, yeah.
<human>: Like two weeks later.
<bot>: Yeah, it's always the plan is they're going to put it out and then it's going to immediately take off. Those are always the goals that are rough. And what's funny is we're always like, why don't you launch sooner so you have more time to make it grow after it launches? I'm like, no, no, no, no. We're going to spend all the time making it good And so then when it goes, it's gonna immediately take off top of the app store, 100%.
<human>: Dalton, why would we launch something bad?
<bot>: Then it won't take off, Dalton, Jesus. Yeah, we're gonna talk to some influencers. We're gonna do a social media launch. We've got it all lined up. We have a wait list. So yeah, top of the charts, definitely.
</s> |
<human>: Caring about your customer is a superpower. And I think what's funny, and you made this point, right, is that it's really, really hard to beat a competitor who cares about the customer more than you do. Yes. It's really hard. The customer knows in their bones that you don't give a shit.
<bot>: Yes.
<human>: And I think that if we bring this back down to startups, one of the things that's tricky is that, you know, you get into a startup for a lot of different reasons, right? And like, hey, Dalton, I'm building a B2B SaaS company for accountants. Like, I think it's really good. I have some experience doing accounting stuff at my previous company, but I don't love accountants.
<bot>: Yeah, I'm just kind of like going through the motions. I don't know. I'm looking forward, let me tell you about my next startup idea after this. Like, you know it's not great when they want to pitch you their next startup.
</s> |
<human>: And I think the smartest founders look past that. They look past all these like stupid debates. And one of the things I think they see about the Bay Area is the network effect. So why don't you go like what's going on here? Like why are billion dollar companies just seem to keep popping up after decade after decade here?
<bot>: Well, I think, look, network effects are powerful. We know this. This is the thing that makes things like Airbnb work, Uber work, all the startups. Network effects are really powerful. That's why Facebook has any value at all is network effects. And basically, what's weird about network effects is if you're not benefiting from them, you don't know what you are missing. And a lot of the times when people want to talk about, well, I don't need to live there, blah, blah, blah. OK, that's fair. you won't know what you're missing. It's all the things that won't happen. It's all the people that you won't meet, all the chance encounters you won't have, all the employees you won't have. Like all these surface area for luck. I like to talk about how to maximize luck. Think about how many people, again, let's talk about non-tech. If you wanna make it as an actor, think about how many people their story of their big break is that something happened in like Los Angeles or New York or a band. that moved to Los Angeles or New York. When the actual moment happens, when someone spots them or finds them or like that.
<human>: A lucky moment.
<bot>: Whatever that is, the work that they did before that was to put themselves in that position. And so no one is going to take someone that's outside of this area and tell you, this is what you're missing out on.
<human>: Can I say something that's even more? I think that people here sometimes don't understand the network effects they're consuming. You and I both saw a lot of people leave the Bay Area during COVID. All of them came back. And they all said this. They don't say that as publicly. They don't say that as publicly. They all came back, yeah. And all of them said the same thing, which was basically like, I missed the community. But I never really understood that I was consuming the community. I thought I was working all the time and da-da-da-da. But I actually was consuming a community of people who are really into startups. And when I moved to Seattle, or Austin, or New York, or da, da, da, da, that community wasn't as strong, and I missed it. But isn't it weird?
<bot>: And there is tech there.
<human>: Yeah, but there's tech there.
<bot>: And there is good lifestyle there, but that's not startups.
</s> |
<human>: Well, PB is the inventor of Gmail. And as kind of a side project at Google, he invented something that 1.5 billion people on earth actively use. And he literally did it doing things that don't scale. So I'll start the story and then please take it over. So as I remember it, PB was pissed about the Gmail product, the Google product he was, sorry, the email product he was using. And so Google had this newsletter product. The first version of Gmail, he basically figured out how to put his email into this Google Groups UI. And as he tells the story, his eureka moment was when he could start reading his own email in this UI. And then from that point on, he stopped using his old email client. And what I loved about this is that as he tells the story, every email feature that any human would want to use he just started building from that point. And so, you know, he would talk to the YC batch and he's like, and then I wanted to write an email. And so I built writing emails. And if you know PB, like he could have got a couple of days reading emails without replying at all. So he didn't need writing emails to start. I remember him telling the first time he got his like coworker, like literally like his deskmate or something to try to use it. And his destiny was like, this thing's pretty good. It loads really fast. It's really great. The only problem is, PB, it has your email in it. And I want it to have my email. And he was like, oh, shit. OK, well, I've got to build that. I'm like, I've got to build that. Perfect night-to-night solution. And so then it started spreading throughout Google. And do you remember when it broke? No, what happened? Oh, so he told this story where like one day PB came in late to work, which is, you know, knowing PB every day, you know, and everyone was looking at him a really weird. And they were all like a little pissed. And he got to his desk and someone came over to him and was like, don't you realize that Gmail's been down like all morning? And Peter was like, no, I just got to work. I didn't know. And so he's like trying to fix it, trying to fix it. And then his coworkers see him like grab a screwdriver and go to the server room. And it was like, they were like, Oh God, why do we trust PB with our email? Like we're totally screwed. And I think he figured out like there was a corrupted hard drive. And I remember that point of story. He was like, he says, and that day I learned that people really think email is important and it's got to always work.
<bot>: And like, I think the reason, I think the reason he did it, man, is because he liked to run Linux on the desktop. And he didn't want to run Outlook. The Google suits were trying to get him to run Outlook on Windows. And he was like, I don't really want to run Windows. But yeah, it was the dirtiest hack. And as I recall in this final part of the story, it was hard for him to get Google to release it because they were afraid it was going to take up too much hardware. And so there was all these issues where there was a decent chance I think it never would have been released.
<human>: Well, this part was that everyone thought Gmail's invite system was like some cool like growth hack. Like virality hack. It's like, oh, you got access to Gmail. You got, I think, four invites to give someone else. And these are like precious commodities. And it was another product. It was just another version of things that don't scale. They didn't have enough server space for everyone.
<bot>: They physically did not have enough servers. So they had to build an invite system. Yes. There was not an option to not, but basically there was no option other than building an invite system. It was not like genius PM growth hacking. It was like, yeah, well, we saturated the hard drives are full, so I guess we can't invite anyone else to Gmail today.
</s> |
<human>: Here was the next comment that was written. YC founder wrote, we did not do enough research before deciding what to work on. We now realize the more research you do in your space before you write a line of code, the better.
<bot>: It seems like people go to the effort of starting a company, of trying to raise money for a company, of applying to YC with a company, of making it to YC interviews with a company, and we can tell you haven't Googled it. You haven't typed in like the idea that you're working on into Google or read any articles about folks that have tried it before. And this is such a self-owned. It's free to do research on those that came before you and failed. Cost you nothing. Doesn't take very much time. And to spend years of your life or months of your life or any amount of your life on an idea that you've not done just basic cursory research on is really dumb. Do you understand? Maybe you'll do it better or different, but to not even understand what came before you is kind of a willful ignorance. And I don't get that, right? It's almost like, Michael, do you think it's that they don't want to know or that they just don't think it applies to them or, oh, this time it's different? Why would you obstinately refuse to research related companies in the past?
</s> |
<human>: So I think that so much of this kind of pop entrepreneur Shark tanky advice, right? I actually think comes from a different place. I think it actually comes from like weird branding. And I think that in the branding world, being different, being unique, that is a very, very important thing. And a lot of the examples in the branding world are people who did things radically different and then became successful. What I find funny is that a lot of the examples in the technology world are people who did things 80% the same. and 20% different. At least 80%. 80% was the minimum that they copied. And so I think one of the things that founders screw up is when they take advice that might work in fashion and apply it to software, it might not work.
<bot>: Yeah, this reminds me of usability. If people can't use your thing, like I remember back in the day, people would try to innovate on the website design and how the cursor worked and how you would even click buttons, and that was an example of probably not helpful innovation. No. And so watch out for unintentionally creating risk that you don't need to create.
<human>: Yeah, and I think that if you put your customer first, second, and third. You might look at some of these other things and say, do I really need to do them? Or better yet, let me do it on my second startup. Let's get one successful startup out of the way. And then I can make programming languages. I can hire people all around the world. I can do all kinds of crazy things. I can build rockets. I can do all kinds of cool things. Startup number two. All right, Dalton, good chat.
<bot>: Thanks.
</s> |
<human>: What we also need to attack is this idea that because smart investor invested, my company is doing well. Like I just don't, I think that when you're the press or when you're on the outside having to judge, you have to use these kind of weird secondary, non-primary sources.
<bot>: Yeah, it's not revenue focused. Your only signal as an outsider is fundraising rounds. Yeah. And there can be companies that are still struggling and aren't going to make it. They're still somehow raising money. One trick, by the way, friends out there, that's very common, is a fundraising round may have happened a year ago, but they're choosing to announce it now. Yes. And it looks like they just raised, and that is not true. So watch out for using the announcements of fundraising as a very reliable signal.
</s> |
<human>: So, let's talk about the fatal punches, right? At YC, we deal with a lot of failure. We deal with a lot of companies who fail. And you and I have to have a lot of conversations with founders who their company has failed, and their first thought is, I'm a failure. They personalize that failure. What are some of the things you tell those people when they're dealing with that fatal punch?
<bot>: Yeah, I think as per what we talked about here, a lot of the things that people think are game over aren't. And so our advice is don't give up. You actually have a bunch of customers, you have a bunch of money in the bank, let's look at the facts, you're good. And so a lot of our office hours are let's examine the facts. Fact, fact, fact, fact, great, you're fine. However, sometimes we look at the facts and you're not fine. And it doesn't help you, like you don't need a pep talk to keep going. And it actually is probably the right thing for you to not keep going. Because at the end of the day, this is your life, you only have one of them. And messing up your life in a permanent way, your savings, your family, your friends, whatever it is, you know, don't do that. And again, I know it can be confusing out there, because we get bombarded with messages. Oh, but you say you never give up, or you say, you know, like, yeah, it's confusing.
<human>: It's not that easy. Yeah, it's complicated.
<bot>: It's complicated. So I think you need to actually, with as clear objective ways as you can, be able to know when it's not working, and that it was a fatal punch, and that, yeah, you should not do this anymore. Like sometimes you see people get into like, debt where they owe a bunch of people a lot of money and then they shut down and they ripped off all their suppliers again you know you know i'm trying to say like like you're good you fail in such a way that you hurt a bunch of people not just yourself not good don't do that what i think that this is what's tricky is that i think someone needs to be out there saying that these aren't the things you have to put on the table to win
<human>: Yes, when you're working hard, you're gonna probably have to spend less time with your family or friends. But you don't have to put those relationships, you don't have to sacrifice those relationships to win. In fact, they're a source of strength. You're working hard, you're probably not saving as much money as you would be if you're working another job, but you don't have to sacrifice all your savings. You don't have to go into extreme debt. Like, if you're working hard, like, you might not be able to get the salary that allows you to live in the apartment of your dreams. But like if you have to crash on friends' couches, these things don't tend to have to be sacrificed to win. And so if you're taking these kind of one-way hard life hits, maybe the facts are set up.
<bot>: Yeah. And again, what's tough is when you're one of those folks, sometimes you can even be victimized by people that'll like keep bleeding you because that's their racket. And we see this a lot with struggling startups. All sorts of people will come out of the woodwork to sell you services or promise they'll connect you with the investors or they'll help you fundraise or you name it. And it's like, it's kind of like moving to Hollywood to become an actor and it's not going well. All these people will, like there's a whole underbelly of folks who exist to kind of rip off the people who aren't doing well.
<human>: You know, to me, where I see this happen that's most tragic is with non-technical founders. Because it'll be some dev shop or some, you know, if you give me your last dollar, I promise that I'll solve your problem. Yeah.
<bot>: And you see people writing checks for 20, 30, 40, whatever, 50 grand out of their personal checking account, their life savings to some dev shop. Yes. That's like their whole business model is to rip. I shouldn't say rip off, but like, they're like, yeah, cool. Like whatever. Like just as long as the check clears, we'll do it. You know? Yeah. It's pretty depressing.
<human>: It's really depressing. And, and I think that like those founders, when we have this conversation, the like, Hey, your startup failed, that doesn't mean you failed. Sometimes they just need to hear someone say that. So often we'll talk about, look at this person, their startup failed and they have another one that does well. Look at this person, their startup failed and they're not working as an executive at this really cool company. These experiences you have, are valuable to you, even if your company didn't work. You learned 10x more than you would have learned otherwise, even if your company didn't work. And sometimes when we explain that silver lining, people are like, oh, you're right. That's actually a fun part of the job. So there you go. Step one, how to try to avoid the punches. And step two, when they come, how to recover as fast as possible. Great chat today, Dalton.
<bot>: Thanks man.
</s> |
<human>: And I think the last point we'll give is that I think that until these big companies solve AGI, it's going to be their first, second, and third goal. And so using the existing tools to make people's lives better, their businesses better, it's not on their list. Like getting AGI, one, two, and three most important goals. So that's a huge opportunity for everyone.
<bot>: So look, in conclusion, unless you actually believe in the short term, AGI will be created by OpenAI that will do all the things that's possible for us to predict. Yes. OpenAI is not going to kill all the startups. No. And there's plenty of room to innovate.
<human>: And maybe we would say that the tools that exist now and the LLMs that are being made available, this could be a explosion of new amazing startups. This could be the moment that we've been waiting for since mobile. Yep. Where people can actually do cool new things and there aren't just cog-a-cog culting. So, this should be a moment where everyone's excited. Except for the people on Twitter. They're never excited. Alright, thanks much Dalton.
<bot>: Thanks.
</s> |
<human>: Explosion.
<bot>: You've seen this, man.
<human>: What's going on here? Well, first things first, right? This is why we like teams who know each other for at least a little bit and have some kind of work or personal relationship. Because I always say that when you have some kind of non, if you have some kind of base relationship that you might want to maintain, even if this startup doesn't work, you won't say that thing. Or you'll think really hard before saying that thing that will like shatter the relationship. But when you're like, oh, the only reason why I'm even talking to you is because of this startup and now I'm convinced that our startup's fucked, which by the way, you will be convinced your startup's fucked just continuously. That's like a normal feeling. And then you're like, well, fuck it. Man, you can't, you know, there are things you can't unsay. And, um, Wow, sometimes the original sin was like, you shouldn't have started the company with this person. But like, let's say you are doing a company with your co-founder and it's just really frustrating. What's the advice to give the founders on how to kind of process them?
<bot>: I think it's like, you have to learn how to fight, and maybe fight's the wrong word, how to disagree. It's like, You have to learn how to pull your punches and have a disagreement that's a real disagreement and actually release the pressure of the disagreement in a way that doesn't cross the line so that the relationship is irreparably harmed. And it's a skill you have to learn. And if you've never been through a major disagreement with someone or had the skills for both of you to have a fundamental disagreement and talk it through yet not blow the relationship up.
<human>: Yeah.
<bot>: And again, this is a skill like any other skill, man.
<human>: It's a skill. You know, it's funny because the analogy that I'm thinking in my head is that like, you know, it's a pressure release valve and you don't want to just rip it open.
<bot>: Yeah.
<human>: But if you don't release any pressure, you also have a problem.
<bot>: It builds up and blows up. Either way it blows up.
<human>: Either way it blows up.
<bot>: If you let the pressure just build, build, build by only having superficial conversations for years, one day someone will snap.
<human>: Boom.
<bot>: And on the flip side, if you just leave it open all the time and you fight constantly, that ain't gonna work either. It's sort of like the happy medium thing.
</s> |
<human>: All right, here's the last comment that a YC founder wrote in. I chose a co-founder with whom I could not share my honest disagreement. We didn't know how to fight well or come out of those fights better and wiser. Some part of that was conflict avoidance on my part, and some part of that was him fighting dirty.
<bot>: It's crazy when you speak to founders where they'll spend eight hours a day with someone, 12 hours a day with someone, and they'll be like, I haven't spoken to them in a week. And I'm like, what are you guys doing all day? You haven't talked to them in a week, or haven't talked to them in a month, or I haven't had a real conversation with them in a year.
<human>: And I think when things get that bad, I would argue there's a point where breaking up becomes inevitable. And the CEO's job is now not how to repair the relationship. It's basically how to separate in like the most effective and least destructive way.
<bot>: When you talk to folks about this, they know in their hearts that that's what needs to happen, but they just can't bring themselves to actually do it because it feels bad. And so that's what's, again, when you talk to these folks, they know, they know that it makes, the right thing for the company is to go their separate ways. But they, for whatever reason, They're willing to go through years of pain or actually reduce the chance the startup's going to work than to face that head on. It's really rough.
</s> |
<human>: All right, let's move on to the next one. So the YC founder wrote in, take arguments with your co-founders seriously. it's more likely to kill you than anything else.
<bot>: What I see with a lot of co-founder disputes is that the relationship has never been pressure tested. They've just been friends. They've been like, oh yeah, we chat all the time. And then the first time there's a disagreement, it's just a blow up and the relationship is broken and you'll never be able to put the pieces back together again. Versus if it's someone you've known a while, maybe it doesn't seem as shiny, but you've already had some disagreements. You've already had the relationship ebb and flow over years, right?
</s> |
<human>: I think what's tricky, though, is that there are people who don't think that this is a good time. The people who aren't really into CS aren't really excited by the power of LLMs. And people who don't have experience with ML at all And those are the people who just want to make money. And I think what's interesting is in the last couple of cycles, those people have been very attracted to the startup world. How do I make money fast? Those people are not being attracted to this. I think that's what makes our job so much fun, because working with people who want to make money fast in startups, it's not a great group of folks. Those are harder office hours. Harder, harder. When we're like, yeah, it'll just take a decade. They're like, no, no. Why don't I do my ICO or something? Whereas this group of people, it reminds me when people were nerding out about Ruby back in the day. Like, oh, wow, I'm just excited about what I can build.
<bot>: And when you think about it, a perfect time where if you're a creative person and you're an ambitious person, you can do really cool stuff. And we saw this with the iPhone. Yes.
<human>: You can blow people's minds.
<bot>: Well, again, Uber would not have made sense without the iPhone. And so to me, it's less obvious that everyone's going to build open AI competitors. I am worried that all the low-hanging fruit ideas, open AI will just be able to do well enough. Yes. But if you go deeper to second-level insights, a la Uber after a consequence of the iPhone, Second order effects like this from LLMs are going to be amazing. You get what I mean? It's like, it wasn't the obvious shit. I want to try an analogy on you, right? Like fart apps. Remember when I was making fart apps? That wasn't the big business.
<human>: I would argue, maybe the analogy here was that it was obvious that maps were going to come to the phone. Yeah. It wasn't obvious that Uber was going to come.
<bot>: I agree.
<human>: I never would have imagined. And so I definitely think that if you can think second order, and I'll even be charitable. I think sometimes to think second order, you think first order. It's okay if your thing starts as a toy. Like when people are like, oh, this is a thin wrapper on open AI. I always laugh because I'm like, okay, is that the destination or the starting point? Yeah, it was a starting point. I remember as we had the old Dropbox as a thin wrapper on top of AWS, on top of S3, right?
<bot>: Oh, I can build this in a weekend.
<human>: I can build this in a weekend is a sure sign that the person doesn't know what the fuck they're talking about. So I will say that if you are absorbing, if your thing is a thin wrapper on OpenAI to start, and you're absorbing hate, ignore those fuckers. That's silly. Understand that many good things started like toys and make something that customers really love.
<bot>: Yeah. This is a time to be optimistic. This is a time to build cool stuff. And this is not a time to cargo colt, as I said earlier. So superficially copying AI stuff just because it's hot or raising money. Don't do that. But if you can really solve customer problems in an amazing way, this is the time.
</s> |
<human>: So next, what about employees?
<bot>: What do you think there? I think it's the same sort of situation. Again, the dynamic might be a little bit different, but if you're only ever having easy superficial conversations with people, It's cool until it's not. And sometimes the best way to work with folks at your company, whether colleagues, employees, whatever we want to call them, is to find the right way to have some of these hard conversations. And you know what they are. You're probably, I'm sure someone watching this is like, yeah, I can think of a few hard, I can think of some things I would say if I weren't. afraid of the consequences. You know, like there's a right way and a wrong way to do it. We're not saying go blow people up, but if you're just avoiding hard conversations, no one wins. No.
</s> |
<human>: and getting fired when it doesn't work out, right? Because it's their fault, it wasn't your fault.
<bot>: You have company all hands where you can, you know, like you have all these layers where you're, this is all the stuff that's filtered out from you, man. Like this is not your problem when you have a job. When you're a founder, there is no filter. And I think people freak out because they treat being a founder is on the same, like the same sort of thing as being an employee. They're like, oh, either I'm gonna work at Google or I'm gonna start a startup. It's like, well, No, this is different, right? In one of those things, you're like a worker bee and you can just work on your thing and it's really low stress and you have to worry about your manager liking you and stuff like that. There's no managers, there's no filter. You're just out there dangling in the wind and every breeze that comes your way, you're gonna feel. The inputs that you experience as a founder are like completely unfiltered. And you have to be the person that tells the people working with you that it's all gonna be okay. You're now in the role of the filter. Like you are the filter, not the person being filtered to. Yikes. I think a lot of folks aren't mentally prepared for this. Reality is tricky when it's not filtered.
</s> |
<human>: So Michael, in terms of market timing, one thing that might be interesting to think about if you're currently working at a unicorn, a very late stage company, is now might be a good time to consider going to an earlier stage company as an employee because it's less likely their equity is super overvalued and there's lots of room for advancement. So how would you think about this if you were an employee of one of these companies?
<human>: Well, one, I think that you've gathered a lot of experience, and so you might have an opportunity to have more responsibility to an early-stage company, which would also probably get you more equity. I would say, too, you could use many of the hints that we gave you to judge that early-stage company. And you can actually do a bit of a comparison to get a vibe for like, oh, this early-stage company seems like it's doing better than my late-stage company. And then the third thing is that, What's funny is I think it's a little counterintuitive, right? It's the moment where your friends are gonna be like, that's stupid. Yeah, why would you go to a smaller company that's not a unicorn? Exactly, right? And it's so weird in my life how many times the dumb move at the moment was the smart move later and vice versa. It is just over and over again.
<bot>: Yeah, and so the dream setup is you go to an earlier stage company that has the same revenue as the unicorn you are leaving, and one-tenth the valuation, thus your option strike price is much better. And you have more responsibility. You have more responsibility. That's a pretty good trade.
</s> |
<human>: I think the other thing that comes up a lot around innovation is business model and pricing. I think this, once again, is not putting the customer first. You know, hey, let's say you're selling cloud compute, right? Your customers have probably bought AWS before. Maybe you should charge like AWS does, right? Because maybe your customers will recognize that and that will give them comfort. Yep. No, that's wrong. We hate AWS. We can't do anything like AWS, including pricing. So now your customer looks at this pricing thing, and they're like, well, I really like your product, but I don't understand.
<bot>: Your pricing page doesn't make sense. It's not even that they don't want to pay. It's that they're like, I don't understand what you're saying or how this works. I have to buy floozles, and then I get credits for floozles, and then I transfer them into the, like super real.
<human>: And by the time I'm at that page, I just want to know what it costs. And if I can't figure out what it costs, how do I? I'm walking, you've invited me in your home, and then you've shot me in the leg.
<bot>: No, you've invited me in your home, and I can't open the front door. Like the door handle. I don't know how to use your door handle. And I really wanted to come in. I did. I was game. I had my money.
</s> |
<human>: This is Michael Seibel with Dalton Caldwell. In our last video, we talked about the setbacks that make founders feel like shit when running their startups. And this time we're going to talk about how to prevent these punches to the face, and how to take a punch and recover if you absolutely must. So Dalton, I think the cool way to think about this is a little bit like healthcare. There's preventative healthcare and then there's treatment. So let's start with the preventative and let's set the framework here. A lot of times founders get punched in the face as almost unforced errors. It's like a result of magical thinking or like other parts of their lives not being set up. And so here are things you can do to either reduce the number of punches that come or at least reduce their intensity because you have your other shit locked up. Does that make sense?
<bot>: Yeah, exactly. It's like, as we spoke to last time, you can't think that you're not going to have any setbacks and you're not going to, again, take some punches. It's going to happen to you 100%. The highs are high and the lows are low. And so rather than assuming you can be so smart that you will never have low lows, Instead, plan ahead. Put the infrastructure in place so that when you do have these big challenges or these low moments, you have the infrastructure set up that, you know, you plan ahead for it. I think that's a very good idea.
<human>: So we were joking when we were talking about what to talk about in this video. A lot of these things could be put in the category of adulting. And it might turn out that if you want to be a founder of a very successful company, you might have to adult harder than the people around you. In fact, it almost assuredly requires adulting harder than the people around you. Sometimes I think founders look at us and they're kind of like, well, you know, my roommates don't do this, so why do I have to? And it's like, well, your roommates aren't trying to build a billion-dollar company, then they don't have to. Maybe you need to be better than the people around you to do something extraordinary.
<bot>: It's yet another thing that distances you from your peers. And if your whole thing in life is I'm the same as my peers and I'm the same as my roommates that have jobs at like big tech companies. This is yet another way that you're going to be isolated and different and have to learn to love that. and not feel sad that when they're like, hey, we're gonna go pull another all-nighter, we're gonna go party Thursday, Friday, Saturday. You have to be cool with opting out of that, right? But if you think you can have it all, you can't. We're here to ruin that have it all dream.
</s> |
<human>: I'm going to try to come up with a bad analogy on the spot. Let's say that changing the world is like uprooting a tree, like a big, old, tall tree. Imagine there were two founders. One founder knew that trees have roots. and the other founder had no idea, right? Like the trees with RootsPerson, they have an advantage. They have a very large advantage. The tree without RootsPerson, they're gonna have a lot of very horrible, how do I phrase this? On-the-job learnings. Yeah, it's not moving. Like we don't get it. Like we...
<bot>: We're pushing it, and it won't fall over.
<human>: Yeah, we've done all the math. If the tree ends right where the ground begins, pushing like this, it should work.
<bot>: That's a great way to say it. There's so much under the surface. There's so much under the surface to understand with a lot of these ideas. And if you don't understand it, yeah, you're going to learn. You'll get some on-the-job training.
</s> |
<human>: And I think that what's not spoken about enough, and it's a point you make a lot, is that there are certain cities that are just better, and there are certain regions that are just better. And we can talk about all the reasons why, but if you want to be the best in finance, you're probably going to find yourself in New York. If you want to be in the best.
<bot>: Or maybe London.
<human>: Or maybe London. Yeah. If you want to be the best, no, no, no.
<bot>: OK, anymore.
<human>: We're not since Brexit. Yeah. Brexit kind of fucked that up. If you want to be the best, in entertainment, you're probably going to find yourself in LA. And the reason why is because when you want to be top 0.001%, you want to be around other people who are trying to be top 0.001%. And I think both of us wanted to be top 0.001% in startups. Yeah. You're from Texas. I'm from fucking Jersey. We didn't grow up here.
<bot>: Yeah, that's true.
<human>: We made our way here. And when you're here, you get to consume all the other people like us who were looking to be the best and willing to get in the car and make our way here to do it. So I think that's a huge, huge factor.
<bot>: Yeah, and I just think a lot of the folks that I talk to, they have the opinion from reading Twitter and reading all this stuff. that they all need to agree with you on this point. And that like, if moving to San Francisco means... You have to live downtown, in the Tenderloin. It means you have to make some really serious... You have to protest on the weekends. Yeah, but again, I talk to people when I fund people for YC, and I think they have a lot. A lot of people have like a lot of anxiety about these issues. And again, what they don't realize is Do you know how many people live in East Bay and they live in the peninsula and they like it's a huge area. It's a huge area. Yeah. But we all get to work together. Yes. But we get to make our own decisions. Yes. We get the benefits of living in the Bay Area and having the network effects of the city. Yes. Without all living in like the like our lives are not the Twitter thread.
<human>: No.
<bot>: Showing photos of what's going on in downtown San Francisco.
</s> |
<human>: So you had another story about Facebook early days that is similar in this light.
<bot>: So let me paint the picture. Back when you started a startup a long time ago, you had to buy servers and put them in a data center, which is a special room that's air conditioned that just has other servers in it. And you plug them in and they have fast internet access. And so being a startup founder until AWS took off, part of the job was to drive to the suburbs or whatever, drive to some data center, which is an anonymous warehouse building somewhere, go in there and like, plug things in. And what was funny is when your site crashed, it wasn't just depressing that your site crashed, it actually entailed getting in your car. Like part of being a startup founder was waking up at 2 a.m. and getting in your car and driving to like Santa Clara because your code wedged, you had to physically reboot the server. And your site was down until you physically rebuilt the server. So anyway, I'm just trying to set the stage for people. So this was what our life was like, okay? And so my company, iMeem, We had a data center in Santa Clara, and there was a bunch of other startups there as well. And so something that I liked to do was to look at who my neighbors were, so to speak. There was never people there, it was just their servers, and there'd be a label at the top of the rack, and you could see their servers, and you could see the lights blinking on the switch, okay? So this is what I was like. And so our company was in the data center, in this data center in Santa Clara, And then one day there's a new tenant and oh, new neighbors. So I look at it and the label at the top of the cage next to ours, you know, three feet away, the label said thefacebook.com. And I remember being like, oh yeah, I've heard of this. Like, cool. Like, sounds good. And they had these super janky servers. I think there was maybe eight of them when they first moved in. And they were like super cheap. They were like super micro servers. You know, like the wires were hanging out, like, you know, I'm like, cool, but the lights were blinking really fast. Okay. And so what I remember. was that there was labels on every server, and the labels were the name of a university. And so at the time, one of them, one of the servers was named Stanford, one of them was named Harvard, you know, like, and it made sense because I was familiar with a Facebook product at the time, which was like a college social network that was at like eight colleges, okay? So then I watched, every time we would go back to the data center, they would have more servers in the rack with more colleges. And it became increasingly obvious to me that the way they scaled Facebook was to have a completely separate PHP instance running for every school that they copy and pasted the code to. They would have a separate MySQL server for every school. And they would have like a memcache instance for every school. And so you'd see like the University of Oklahoma, you know, you'd see the three servers next to each other. And the way that they managed to scale Facebook was to just keep buying these crappy servers. They would launch each school and it would only talk to a single school database. And they never had to worry about scaling a database across all the schools at once. Because again, at the time, hardware was bad. MySQL was bad. The technology was not great. If they had to scale a single database, a single users table to hundreds of millions of people, it would have been impossible. And so their hack was the 9-10 solution like PB used for Gmail, which is like, just don't do it. And so at the time, if you were like a Harvard student and you wanted to log in It was hard-coded to the URL was harvard.thefacebook.com, right, man? And so if you try to go to stanford.thefacebook.com, it'd be like, you know, error. That was just a separate database. And so then they wrote code so you could bounce between schools. And it actually took them years to build a global users table, as I recall, and avoid this hack. And so anyway, the thing they did that didn't scale is to copy and paste their code a lot and have completely separate database instances that didn't talk to each other. And I'm sure people that work at Facebook today, I bet a lot of people don't even know this story. But like, that's what it took. That's the real story behind how you start something big like that versus what it looks like today.
</s> |
<human>: Well, and it's so funny, because I love your point around maybe you don't like coffee shops. Everyone can like people. Everyone can like helping another person. That's just a quality of humans, right? You like helping someone else.
<bot>: Yeah, it feels good to provide service. And it feels good to give someone something that, sure, you're making money from it because you're charging for it. But you know that the value that the thing is delivering is big. Way more. You're getting a great deal. And you know in your heart they're getting a great deal. And not just like, hey, they bought the software. We know it doesn't work. We know they don't use it. But I hope they keep paying. They signed the LOI, so I was able to fundraise, but we know the software sucks.
<human>: That makes you feel bad. That makes you feel bad, yes. So if we're going to wrap this up, we've given a lot of advice on how to do all kinds of things around early stage startups. But one of the things that we probably should have emphasized more is it really helps to care about your customers. And if you can use that as a tool, you'll learn more. you'll make more sales, you'll have more fun.
<bot>: And people can tell if you care. They'll want to tell you more about their problems. They'll give you the benefit of the doubt. They'll cut you slack. If they can tell that you care and that, you know, you want to actually solve the problems and not just get money, raise VC dollars.
<human>: With that, thank you very much. See you later, Dalton.
<bot>: Great. Thanks.
</s> |
<human>: The next one that comes up a lot is fake metrics. And we've talked about this a little bit, but for companies who charge their customers money, somehow creating a goal incremented in something that's not money. Hey, my product costs $10 a month, but I'm measuring registered users. I want to hit 1,000 registered users. That's weird. Like, hell, if users is going to be the metric, like, why wouldn't it be active users, right? Like, just like if we're going to be in that world. Well, that's too hard, Michael. That's why. Well, fair. But if we're charging them, why wouldn't it be the amount of money we make? Like, that seems even simpler. But I think you've seen a wide variety of fake metrics that goes way further than users, right?
<bot>: Yeah. Okay. Counting hits on your website. That's an oldie but a goodie. Yeah. Counting downloads but not registrations is a good one. Yeah. Counting users as people that started the registration process and didn't finish it. Counting users as people that downloaded your product, opened it, closed it after five seconds and never opened it again as users. Yes. Yes. We've heard that one. Just basically like a thousand and one different ways to avoid the actual meaning of the metric, which is to capture if it's working or not. It's like every which way. People are so creative in finding ways to like not actually measure the thing that they know they're supposed to be measuring. And I can never tell if they're doing it to fool themselves or to fool investors or authority. You know what I'm saying? It's hard for me to tell when someone is practicing self-deception that number of downloads is the right metric or if they think that no one else realizes that that's obviously... No one else can tell what they're trying to do.
</s> |
<human>: I think what's really interesting about this is we come back towards he wasn't the first mover, was not the first mover, but the product that existed was so bad that a 10x better product was actually within reach, like it was actually possible. I think the other fun insight here is that like portable online gold, is valuable, like it is 10x better than gold. And so as something you might want to have, if you think gold is something that you might want to own and seems like the market does like owning gold, portable online gold, strictly better. So I think Out of maybe all three of these founders, Brian was exposed to the most shit takes, the most people saying this was not gonna work. So break that down for us. Explain all the reasons why Coinbase is not supposed to work and Brian should not be a successful founder today.
<bot>: Well, at the time, people saw Bitcoin as a tiny market, that it was going to crash, that it was a bubble. Investors didn't like it. It was synonymous with a lot of actual fraud. It didn't have a great reputation. Also, getting a bank deal was impossible. It's not like other founders didn't want to start something like Coinbase. U.S.-based exchanges were incredibly hard to start. And this is the reason why all the exchanges at the time were offshore. was the regulatory environments were different in different places, right? Another thing I want to note is even Brian in his YC application didn't really believe in his own idea because what he basically applied to YC with was the P2P transfer parts. It wasn't buying Bitcoin and holding it. It was the idea that he could build something like PayPal to do P2P transfers. And that the buying Bitcoin part, that was just part of it. And so isn't it funny that even he kind of undercounted the simple promise of buying Bitcoin in a non-sketchy way with a debit card in the U.S. and not getting hacked and losing all your money, that was enough of an insight to be the basis for like a $100 billion company. He didn't need to do all this other stuff.
<human>: He didn't know that. No one knew that. And following the pattern, a valuable insight that he learns after starting the company, right? Like, you don't have to have all the valuable insights before you start.
<bot>: Well, you remember what the Coinbase product was back in the day, right? It was a website, you logged in, you put in how much Bitcoin you wanted to buy, and you push the button and you buy it. And that was, you could sell it too. There was no social network, there was no comment feed, you know. It's probably the simplest product. There were no graphs. It was one of the simplest products I've ever seen. But it doesn't solve the right single problem at the time.
</s> |
<human>: And the last one on our list, playing the game of using your position as a startup founder to become an amazing investor. And I think this one's like really tricky because for one thing, you definitely see a lot of famous startup founders have written kind of angel and checks into companies that that tend to do well. And so I think sometimes people confuse that for, oh, I should be spending a significant amount of my time looking around and trying to be an angel investor instead of making my company work. And I think that what, if I can try to explain to you what's actually happening, when you're a good founder, oftentimes you know other good people and the opportunity you have to give them money requires almost no time or effort. And so you just, and like, if you're a good founder, oftentimes people are offering you deals, and so you're spending five minutes saying, yes, this is an obviously good thing, I use it, or this is my friend, I wanna support them, and the amount of time and effort you're spending writing these angel checks is basically nil. I remember when I was starting SocialCam, I emailed Brian Chesky saying, do you wanna angel invest? He was like, sure. That's it. That was the entire time that he spent, probably less than 15 seconds. I think people don't see this so they think, oh, I need to copy what I see investors on Twitter doing. I need to go network. I need to go meet founders and advise them and do office hours and like all these things. And it's like, ah, like classic example of cargo culting, right? Like not really understanding what's going on.
<bot>: The stupid game you're playing is a status game. Like if you play status games where what you want to do is level up, you want to, put angel investor in your Twitter bio or something. Okay. You're playing a status game. Fair enough. The prizes that you win playing the game is congratulations. Now a bunch of your money is tied up in illiquid investments that may or may not show up. So now maybe you're like financially strapped. Maybe you're worried about other stuff. You're worried about your startup. So maybe you're performing worse because your money's tied up somewhere. you have spent a bunch of time and stuff, you've totally pissed off your employees, whether or not they would say it to your face, that is not a great way to win awards with your team.
<human>: Yeah, you're a scenester. Congratulations. Yeah. So I think to wrap this up, right, Sometimes founders don't think enough about the bad consequences of the games they're playing. And once they really do the whole logic tree down to the end, they'll realize that maybe it's not worth playing those games and you might as well just build a good business. And even if that's a tricky message for you to internalize, Think about what you're teaching your team if you're making these mistakes. They will copy what you're doing because you define success in your company. And so even if you're like, oh, for me, this is cool. A perfect example, if becoming a status-seeking angel investor is what seems cool in your company, people in your company can start trying to do it instead of doing their work. And so make sure... yeah, people in their company start doing it. It's kind of like a little bit, we're both parents, it's kind of like, hey, if you don't want your kid to be a screw up, you don't do screw up shit in front of them. It's like a pretty simple one to one here. And on the flip side, to kind of end with a positive note, some of our best companies get so good at goal setting and accomplishing goals that they They move faster than we would ever imagine possible. They are just machines at doing this well. And I would argue that most people don't start doing this well. Most people who focus on setting goals and accomplishing them get better at it over time. But man, the rate of improvement is sometimes shocking. Sometimes there are founders who are kind of fooling themselves, who are thinking like, hey, I'm smart, so I can coast on this stuff. Man, outliers are smart and great executors and great trainers, right? Like they have multiple things they're great at. They don't sandbag themselves. Any other thoughts here, Dalton?
<bot>: I think we're good. I think it's well said. Thanks, man.
</s> |
<human>: I think another really interesting thing about Stripe was that it was a problem that they saw their peers in YC have. So literally, they were seeing all of their friends in YC going through all of the pain of Authorize.net, and they were hearing this story over and over again. And that's a good hint for people out there looking for ideas. If all of your smart technical friends are complaining about the same thing, maybe it's a real problem. Now, last insight that I think that they had, talk to me about their go-to-market and specifically about understanding that their customers were developers and not business guys. Because I think that was revolutionary at the time.
<bot>: Yeah. The really clever brand promise or marketing stance or whatever you want to call it they had was to try to make the most beautiful website they could with the most beautiful documentation that was every programmer's dream. They constantly asked themselves and pushed themselves to say, what would I want? Or what would a programmer want? And this is so different than every other processing company, because it was built for basically business people. The programmer who had to implement Authorize.net was not the customer. It was someone getting paid $20 an hour or something to implement the code. Whereas this was like, they went nuts at making something that developers would just freak out about. And everyone copied it, by the way. Every developer would copy the Stripe documentation, copy the Stripe website. It was like the Apple. It was like if Steve Jobs had to design a payments company, it would be Stripe. And they totally did this on purpose. But what this created is a lot of buzzed on Hacker News and around nerds, basically, that, hey, have you seen this Stripe thing? Oh, are you in the beta? Also, they did a beta invite program. And so it was a hot commodity to be able to get into Stripe and be able to use it. You were seen as well-connected if you got the pleasure of getting to use Stripe. It was like a favor they were doing you to let you use their product. That's what a great job they did in making the website and documentation excellent.
</s> |
<human>: This is Michael Saibel with Dalton Caldwell. Today, we're going to talk about setting goals. More specifically, all of the pitfalls involved in setting or trying to accomplish goals that startup founders we work with tend to fall for. Dalton, why don't you set this one up?
<bot>: Yeah, you know, when we were talking about it this morning, the phrase or the meme that came to mind was the one, play stupid games, win stupid prizes. And again, what I think it means in this context is if you set goals or if you start playing one specific game that is silly to begin with or that's clearly a bad call, yeah, the prizes, the implications of that, the things that you win are going to be equally silly or nonsensical or nonproductive. And so we see a lot of people who set goals to in effect play kind of stupid games.
</s> |
<human>: So what's the grand takeaway here, Dalton?
<bot>: I think the grand takeaway is the following, which is just to remind people that it's okay slash good to be a nonconformist. If you're not currently a founder, one tip is to join an early stage startup instead of a big company, because it's more likely you'll find like-minded people. Being the first 10 employees somewhere is going to be weird, and the people that tend to like working at the first 10 employees tend to be nonconformist. Right? Cause there's no structure. It's like chaos. So that's like a really good move versus going into like the, the big tech treadmill. And I think the other big takeaway is just to remind people like, you know, don't play status games or, or maybe you can, but maybe some, you know, do it inside of a big tech company instead of trying to play status games and startups.
<human>: Yeah, my final thought is I come back to what I say to every founder when they come in, which is, you know, congratulations for being in YC. The average YC company dies. Like you, you literally have accomplished in the scale of making any impact on the world, getting into YC means you've accomplished nothing. I think there's a lot of people who think that they're nonconformist, but they are actually secretly following some thesis of tech Twitter or yadda, yadda, yadda, you know, and like, they tell their sums like they're, they're nonconformist, but they really are just trying to fit in with a pack. And I would just say like. for the real non-conformists out there, just find your people. Like you're going to be so much happier when you're surrounding yourself with other people like you. And, you know, we think YC can be a place like that, but like, even if you don't think YC can be a place like that, you'll be more productive when you surround yourself with a group of people like that. And I can say personally going through YC, that's why we got better was because we were surrounding ourselves with these non-conformists who all thought that they were amazing. And we all were like, well, I guess we got to level up. We think we're better than them. So how do we, what are we going to do? You know? So for the nonconformists, good luck. Great talking to you, Dalton.
<bot>: Sounds good. Talk to you later, man. Bye.
</s> |
<human>: No, I'd like that. I would love to say, I'd be Facebook's biggest fuck. I'd be like, I don't know what you think about Facebook.
<bot>: You would want to tell people, hey, I actually met Mark Zuckerberg and he came to my house and I guess they really like, it would be a story. It'd be a story. I was a early customer of Stripe at my startup. And it was invite only and very few people were using it. And my customer experience was Patrick, the founder of Stripe. I had a chat with him, like in Google talk. That's a long time ago. And he would message me all the time. And they had a big mistake where they overcharged a bunch of my customers. And it was a problem on their end. And so what happened is Patrick DMed me, told me that it happened, said that they fixed it, and apologized. Do you think that I like Stripe more or less after that experience, even though they messed up? Exactly, exactly.
<human>: Isn't that wild? It's wild. And what's funny is that sometimes big companies can pull this off too. I remember early days at AWS, we were blowing up. We actually, like, there wasn't enough time to buy and rack servers. So, like, we literally needed, to use EC2 and it was in beta, like you just couldn't sign up for it. And we randomly tweeted, can anyone help us get on EC2? Just like into the world. And like this guy, Jeff Barr, tweeted us back, he was like, yes. And it was like Amazon had a face and a human and a hero, and he hooked us up and saved our company. And that's Amazon. They did it. And you remember that. You're telling the story now. I'm still telling the story. It planted in your head. So if you can create that experience for customers. Oof.
<bot>: Yeah. If you can blow people away. by how much you go the extra mile to care and solve their problems and not emulate the big company stuff. You're giving away your power if you don't do that. You got to use that move. Got to do that.
</s> |
<human>: Historically, seed funding could dilute companies 25, 30, even 35%. I would say in more recent years, that number was around 15 to 20%. But we really saw a lot of founders able to get the money they need, raise their seed round with 10%, some even a little less, dilution. which was like huge. I mean, we all know those earlier rounds are where most of the dilution of the company happens. So that was awesome to see. The other thing, and I know you saw this in your group too, it's just founders going into fundraising with confidence. You know, we talk about this all the time. We tell the founders be confident, but it's hard to be confident when you only have six months or three months of runway when you go into fundraising. It's a lot easier to be confident when you come in with half a million bucks. What did you see in your group?
<bot>: Yeah, I think the best founders were just very logical and non-emotional in the way they handle this. It's business, right? Like the best way, imagine any financial transaction, you want to buy a house, you want to buy a car, you name it, the more that you can be just not manipulated into being emotional or to be FOMO, like there's all these things. If you could just be like, hey, I wanna buy a car, this is my budget, this is what I wanna buy, okay, let's work it out. All right, I bought the car. That's how you wanna approach any kind of financial business relationship, right? Is just to be non-emotional. And so that's having this extra money helps people not be quite as susceptible to being told to be afraid basically, right?
</s> |
<human>: Hey, this is Michael Seibel with Dalton Caldwell. Today, we're gonna talk about what does it mean to do things that don't scale, the software edition. In this episode, we're gonna go through a number of great software and product hacks that software companies used to figure out how to make their product work when perhaps they didn't have time to really build the right thing. Now, Dalton, probably the master of this is a person we work with, a guy named Paul Buchheit, who in front of this term, the 90-10 solution.
<bot>: He always says something like, how can you get 90% of the benefit for 10% of the work? Always. This is what he always puts on to people when they tell him it's really hard to build something or it takes long to code it. He'll just always push on this point. And, you know, founders don't love it. Right, would you say that's a fair assessment, Michael?
</s> |
<human>: What I will say, though, to kind of finish this point, is I think one of the slightly dangerous things that kind of sneaks into this startup game that also causes people to not want to come here is that people don't realize that they need to be aiming for greatness. I always like to equate this back to sports where it's like, there are so few spots in the NBA, let alone on the all-star team, let alone the hall of fame. The bar is so high to get into the NBA that anytime you're a basketball player anywhere, you want to be the best basketball player. on your high school team, on your AAU team, on the invitational invite, you want to be the best basketball player anywhere because you know that the average NBA player was the best basketball player anywhere. And I think that sometimes startup founders miss this point. And they're kind of like, I want to be in the game versus I want to win the game. And I think that like, it's really easy to say, well, you know, I can be in the game in Austin. I can be in the game in Seattle. There are investors there. There are people there. I can be in the game in New York. And I wish that we were more honest that like, yeah, you can play basketball for your high school team, but that's not, that's necessary, but not sufficient to make the NBA. If you want to be a great founder who really impacts the world and helps lots and lots of users, you have to aim for great.
<bot>: You can't just aim for being in the game. And I actually just bring it back to statistics and odds. So let me be really precise, because I can imagine how some people will respond to some of these you're saying here, and they're going to throw anecdotes at us. They're going to say, there's this, and there's this. Shopify is in Canada. Yeah. And it's true. It is. I have nothing to take away from those things.
<human>: MongoDB is in New York, and I've been told that by every fucking New York founder for a decade. MongoDB? Yeah, great.
<bot>: And again, good for them, like rock and roll. They're doing well. The point is we're actually trying to impart advice to increase your odds of success. Because just like with people that want to become Hollywood celebrities or rock stars, there's certainly anecdotes of people that were discovered and everything slipped into place for them. But if you actually just look at the numbers of how you increase the odds of success, moving to an area, moving to the big leagues was a key part of it. And so I would just encourage folks that are unsure about this debate or they don't have their mind made up to realize that the anecdotes are true. that you can do a startup outside the Bay Area. And maybe there's a really good reason you want to do that. I don't know. Sure. Maybe there's health reasons or family. Great. But if all you want to do is play to the odds and optimize for success, I can't really understand why you wouldn't want to be here. And that's not anecdotes. That's numbers. That's just numbers.
</s> |
<human>: Maybe the other message is if you've got a friend who's doing the positive some game, give them a pat on the back. Give her a pat on the back. Like they're probably taking it on the chin right now, but like, man, at least they're trying to play the game the right way.
<bot>: Yeah. I think what you want to do in every situation you're in, whether it is, okay, let's extrapolate this. Whether it's a startup, whether it's a job, even if it's a relationship, Like, we can frame a lot of things with this. Is this a zero-sum situation or positive-sum situation? Like, in a relationship, imagine if you make each other better, one plus one equals three. Like, with great friendships or romantic relationships, you make each other better. That's positive-sum, right? And so I think this is just like a helpful framework to look at everything through of zero-sum versus positive-sum. And, you know, life's short, man. Try to put your energy into interacting with positive sum situations as much as you can. And it'll pay back in ways you can't even possibly imagine. And the externalities of it are much better. Like the impact you're gonna have on other people is gonna be better if you always choose to play the positive sum games, you know?
<human>: And even if you say, screw that, be careful with the zero sum games because today you're taking money from a dummy and tomorrow, You might be the dummy.
<bot>: Yeah.
<human>: All right, man. Great chatting, Dalton.
<bot>: Sounds good. Thanks.
</s> |
<human>: I think the second thing that people do is they ask their friends here. This is a situation where like Googling is probably a hundred times better than asking your friends because like if you're a young person whose internet history is like four years old, your friends are probably in the similar position. And then I think the last thing is a bit of a psychological thing. I think that's what you were getting to, which is, if I'm so excited to do this, why would I want to learn something that would defeat it before it started? Can I live in the illusion and the dream for a little longer? And again, let me be direct on this one.
<bot>: During the dot-com bubble in the 90s, a lot of people started companies, and a lot of them tried pretty much every idea you can imagine. Every idea that you see today has some analog from the 90s. So dig in, look into it, see if people have tried this before. Same deal, in the 2000s, people pretty much tried every idea. And again, maybe in the example of something like Instacart, people had tried Instacart before and it didn't work, but the founder of Instacart knew that and they intentionally designed it to be better. You understand what I'm saying? Like they stood on the shoulders of those that came before them. Smart. Versus if you're the founder of Instacart and you didn't realize that Webvan existed, How does that help? You're not helping yourself to not know about it. Same in the 2010s. Think about how many startups we funded that have tried stuff before. And so from our perspective, we see patterns in the ideas people start constantly. We get it, you're better, smarter, faster. You have a better programming language or whatever it is. You're better. We get better.
<human>: Better UI, Dalton. I got better UI.
<bot>: Oh, mobile. I remember in our era when we were young founders, it was like, oh, we're an app. We're an iPhone app. iPhone changes everything, which is both true, but doesn't mean we should have discounted history.
</s> |
<human>: A WeWork is a classic example of this.
<bot>: So you should actually be looking at senior management and the founders and make a judgment if you think they seem like they're Competent. Yeah. And again, this is different. Sometimes the press lionizes people that aren't super competent The press shouldn't be involved in this decision.
<human>: So you should make your own decision Yeah, it should be like is the message in the all hands line up with the facts that you see.
<bot>: Yeah, does it seem credible? Yeah, I also would look at what the rest of the people that work at the company seem like? And do they all seem busy? And do they have enough work to do? And do you just feel like your colleagues are good? Because one signal of a company that's not going well is that Everyone good is kind of left and the people that are left are just doing make work to try to not get laid off. It's kind of a malaise. Yeah. And often the founders of these companies won't want to, you know, do layoffs or whatever to keep the fiction going that the company's going well. Yeah. And so, again, I think you can make judgment. you know, hopefully you're correct, but of just how good do your colleagues seem and how much do they have really important work to do that's serving customers versus going through the motions making pitch decks or slide decks or whatever it is that people do at companies that aren't quite well, right? And so I think these are really, you have the information if you're inside of the company.
<human>: You have all the information.
<bot>: Way better than anyone else does. Yes. And again, if this could all check out, and you're like, you know what? This is going great, and I really like my colleagues, and I'm learning a lot, and I'm doing well. And I should double down. You should double, yeah.
<human>: I should work harder. I should try to get more equity.
<bot>: Yes.
</s> |
<human>: You want to talk about this kind of social media piece because I think that a lot of people don't understand how toxic social media is.
<bot>: Yeah, I think you just want to look at your information diet. The metaphor I think about this stuff with is the same way we have a food diet. And like, of course, what we eat and drink affects our moods and how we feel. I actually think the information we consume affects us. And if you think about, again, like myself, all of us, you know, when it's a really heavy time in history, when there's a lot going on, when I'm doom scrolling all the time, reading about pandemic news or war news or whatever, Of course that affects my state of mind, okay? And so to some extent, you can't completely stick your head in the ground about what's going on in the world. No one's saying to do that. But to the extent your social media habits make you feel bad or compare yourselves to people, or say you follow a lot of like investors and everything they're talking about is the investment market and who's raising and all of that. And this is just every day you're bombarding your brain with stuff about investor shit. Why? Why is that good? How is that helping you actually run your startup? Reading what a bunch of investors say about the market all the time.
<human>: And I think people are surprised that successful founders explicitly block social media. They do crazy things like they grayscale their phones so it looks less interesting. They turn off notifications. They're aggressive users of screen time tracking. They actually pretty aggressively audit this stuff.
<bot>: So that illiquidity saves you all. And so again, so if you're consuming media every day and you're reassessing the value, like if you're too paying attention to this stuff, it doesn't make you make better financial decisions, does it? No.
</s> |
<human>: So yeah, so just understand that game and I have to be honest like I like games like this like I don't like games where you have to like convince people to like you or to align with your views. Those are games that are way harder to play. I like games where it's like, hey, if I want to serve this customer and you can be a good legal partner to me, and I give you money and you give me legal services, you can be a good funding partner for me. I give you a check at my company, you give me cash, right? If you can be a good partner to me, a simple to understand partner to me so that I can spend my time working with my customer, That's what I want. The customer's complicated enough. I like the idea that the money people are like, so if I give you this money, maybe give me a lot of money back? Yes? Yes? Okay. Okay, we're good. End of conversation. I give you money, you don't give me any money back? No. No good. Come back when this is out of my way. Hopefully, This helps clear up the debate, but I secretly hope this like, I don't know, like doesn't at all. Cause this is like so silly. I hope we get somehow flame award for this. Anyways.
<bot>: Great.
<human>: Good chat.
<bot>: Love it. Okay. Sounds good. Thanks.
</s> |
<human>: I also think there's this element of like, You're not exploited if you're part of the problem.
<bot>: Yes.
<human>: Again, this is a subtle point.
<bot>: Let's see if we can explain it. It's basically. If it's not working and you have a seat at the table, it's on you, man. You can't just blame, hey, business guy, you're not pulling your weight because no one wants our thing. But if you have a seat at the table, you're equally culpable. If you have equal equity with someone and you have a seat at the table in decision making, just because it's not working doesn't mean you get the right to blame other people. That's not cool.
</s> |
<human>: All right, so here's another one that comes up a lot. Dalton, I'd like to spend two hours really going deep on this problem. But our office hours don't go that long. How do you how do you deal with me? I want to do a deep dive.
<bot>: Yes, this is another one of those question behind the questions. And again, it can be different things depending on the people. I think sometimes what's going on is you're an idiot and I don't have confidence you can give me advice unless I spend two hours showing you a slide deck so I can explain everything to you. Sometimes it's, it's not really about the meeting. I just want a lot of face time so we can build a relationship or whatever. And so this is, yes. Yeah. Okay. That's fine. But you see what I'm saying? There's usually when someone asks that there's something else going on. And again, it's usually the first one for me where they think we don't understand. Yeah, maybe we don't, I don't know. But like, instead of them directly saying, I am concerned that you do not sufficiently understand our business. And so I wanna make sure you do X, Y, and Z. Okay, that's a hard conversation. But then I'm like, okay, I know where you're coming from. All right, I hear you. Yes. But some weird like, can we meet for three hours? Yeah. I'm always like, why?
<human>: I want to know the question behind the question, you know? Yes. Well, and what's so funny is if they just said, I don't think you're smart about this particular thing, we would get to the, we would get to the meeting, right? We would get to the meeting. Now, I think there's a couple others that I see. One is this assumption that we are like godlike advisors with complete understandings of every user base and every problem in the world. And like, they can kind of like shortcut talking to users if they just spend enough time talking to us. And so that one is just like, folks, like, so often in this one, I'm just like, you're having a conversation with me that you should have with your customers. Like, talk to them. Like, I don't use your product. Talk to the people who do. I think the other one which I really try to push back on is I'm lazy and I didn't come up with the agenda. I wanna like roam my random thoughts. And over the course of two hours, we will have 20 minutes of productivity, but I don't wanna organize my thoughts. And I want you to accommodate that. And for that one, I'm always just like, that's like, you're not training yourself for success here. Like you expect more from yourself, like, If your competitors can get 20 minutes of input, 20 minutes of output, they will do way better than two hours of input, 20 minutes of output. And just, you know, that seems to kick people into gear. What's another one that you're excited by?
<bot>: I think we can shift gears to a couple other contexts for hard conversations.
</s> |
<human>: Well, and I think that this is a big, there's a big difference. And we've now seen both, right? I think that we've seen the kind of fintech boom and the crypto boom, where the people attracted to them were slightly different. And as tools, they just weren't as useful. Whereas giving everyone a neobank for every single flavor. Whereas we also saw, literally during our lifetimes, launching a website with closed source expensive tools would cost $5 million. And then with the similar tools that were better and open source would cost like $50,000.
<bot>: We built our companies on MySQL.
<human>: Both of us did. Yes. Postgres.
<bot>: You did Postgres?
<human>: We did Postgres, yeah. regardless like that shift happened and then I remember when like You had to buy servers and then wait for them to come and then configure them and then have to get more space in the cola like the speed of actually building software was Incredible.
<bot>: Some people were like, we're going to keep buying server. Like some people rejected that. Yeah. And so there was a moment in time where it did make sense to jump on the bandwagon and start using it. We were on the bandwagon. But it was actually smart.
<human>: It wasn't just bullshit hype. It wasn't bullshit hype. It was real. And so I think it's obvious that now AI is clearly going to be a tool as impactful as mobile or open source backends or cloud computing. And then we'll see from there. Like LMs are clearly that useful. And so it's stupid to not think about how you can make your users more happy, more productive.
<bot>: And again, I think what's funny about this is you and I were in the room. when OpenAI was created, because we were working at YC with Sam, and we had YC Research, and it was a non-profit. It was meant to be an enabling technology. The vision here, you were in the room, it was to be a non-profit so that all these startup flowers could bloom, and all these people could be enabled to create value. And so again, I think sometimes people are afraid of a narrative that OpenAI, maybe that will happen, But the vision was about creating the technology that would be harnessed by other people, and by ideally creating AGI, which is kind of what his goal was, as opposed to, I want to create AI-powered CRMs, and I'm going to destroy every startup that's going to create AI-powered CRMs. That was not what we understood. No.
</s> |
<human>: Hey, this is Michael Seibel and Dalton Caldwell and welcome to Rookie Mistakes. We've asked YC Founders for their Rookie Mistakes so we can share them with you and help you avoid these common errors. Let's start with our first anonymous story from YC Founders on Mistakes to Avoid. At the beginning, when everything's going well, you don't know how you're going to handle disagreements or bad actions by the other person. It's extremely hard to deal with a bad situation after the fact if you don't have anything written down.
<bot>: It's awkward to talk about things like who gets what percentage of the company or do you have founder vesting and you know how human beings are. We don't always remember things quite the way they went down, right?
<human>: And so write it down. I think the biggest error that I see is founders looking for someone with a skill match versus someone that they actually maybe have had a fight with before, like a friend. A lot of founders assume that whatever skills their co-founder has at the moment they join the company are the only skills they'll ever have. And in my experience, almost everything you learn, you learn on the job. So you rather work with someone you really like and learn together than work with someone you don't know at all and get into fights and then break up.
<bot>: I mean, to put some facts on that, how many founder breakups have we seen? where the founder says, my co-founder is excellent A+, they just don't have the skills that we need versus my co-founder is a living nightmare and I can't take it anymore. Right? Like how many people are like, what a great person that I like a lot, they just didn't end up, I shouldn't have made them my co-founder because they just didn't have the right skills, Michael. Do you ever hear that?
</s> |
<human>: All right, let's stick with hard ones. We're talking to an early stage company, and it's becoming obvious that they're not going to be able to raise the amount of money that they want to raise, and they're not going to be able to execute this magical explosion of spending that they want to execute, that they've convinced themselves is what's required to get product market fit. What do you do in those situations?
<bot>: You know, that's a, that's a really tough one because you want people to be optimistic as we've spoken about before. And it's hard to, you never want to be short on someone's startup. And so what I would usually say on this one is think about what a great life philosophy it is to set your expectations low. and prepare for the worst, and then if you get surprised, you get surprised on the upside, not the downside. And so the key in this hard conversation is not to debate someone that their plan is bad. Keep the optimism, you know? But isn't it better to sort of have a plan for the worst and not be surprised on the downside? And if you're surprised on the upside, fantastic. Right, man? And again, people don't want to hear this. This is a hard conversation to have. It's like going up in the airplane. Do you want to bring the parachute with you or not? Like, I'm not trying to be grim by saying bring a parachute, but wouldn't you want to bring the parachute? Yeah, if you had the choice. What's the downside of bringing the parachute?
</s> |
<human>: I think what's interesting as well, when you think about this game, is that there are very, very, very well-paid people. And you were pointing this out. Very well-paid people who are leaving their jobs and who are starting startups right now, because they believe that LLMs are a powerful tool.
<bot>: Yeah, the way I think about this is opportunity, cost, and life. There's people that I've been funding, and they have a great job, and they actually like their job, and they're choosing to leave because they know at this moment in history, because they become domain experts at AI, that this is the moment to do a startup. Like this is that, imagine if you worked on, I don't know, cloud computing for years, and then all of a sudden Amazon Web Services comes out. You'd be like, oh, this is my, they're calling me in, this is my moment in time. And so it's really cool to see these people with all this vast domain expertise that they did before this stuff was cool, realize that this is the moment in time to work on this stuff.
<human>: Well, and I think that we see a second group of people, too. And I feel like those are the people who got the first iPhone when the App Store came out and said, I'm going to build an app. And it was weird because at that moment, everyone had zero years of experience building apps.
<bot>: That's exactly right. Well, remember the Brex founders, what they did when they were like 15 was jailbreak iPhones. Remember all the kids that were doing jailbreaking? Like this was like a rite of passage to be into this stuff and learn about it because no one knew anything about it.
</s> |
<human>: So let's talk about situations where things are going well, right? Signs that this is great.
<bot>: I think one sign is from an opportunity cost perspective, you realize that you're at the best possible place in the world for the risk-reward ratio. And however you're being comped, you're like, wow, I'm getting a smoking deal. And I know there's no better deal I could be doing. And I'm proud, I feel privileged to be working on this team I am because they care just as much. Like if everyone feels like they're getting a great deal, that's a sign of a good culture.
<human>: Yeah, I also think if you feel like you're being given a lot of responsibility, you have a lot of opportunity to learn. I think most people don't realize that like, You can learn at a startup pace, or you can learn at a Google pace. And a startup is an amazing option to learn. So if you're getting better faster than your peers who are in big tech. you might be getting a really good deal. Especially, we see this a lot with people who learn a ton and then they go start their own company. And it's like, well, that startup was incredible for you. Even if it didn't work, you didn't get rich from it.
<bot>: That was like the best education you could have ever gotten.
</s> |
<human>: And the other thing is you have to remember, if you want to raise a lot of money, but you can't explain to the investor why you might IPO and give them a lot of money back, then you can't raise VC. We want to be explicit. It is a business transaction. It's not a faith transaction. Correct. It is, I give you money now, you give me a lot more money later, or at least you try really hard to. And if you can try really hard, but the result can't be a lot of money, I shouldn't logically give you money now. Not because I don't like you or because you're not a great person or these users you're trying to serve aren't great. It's just because it's not a good business transaction. It's literally nothing personal. And I think sometimes founders kind of are very confused when VCs say no.
<bot>: Well, it's because, again, if we're trying to stoke outrage. Let's stoke some outrage. You point at something silly that raised a lot of money. Yes. The most extreme silly thing in the world.
<human>: No, no, no, no.
<bot>: You always point to Juicero. That'd be one. Right? Or we were, whatever. You point to something that is like on face silly. Yes. And then you say, well, If they funded that, why won't they fund my social network for dogs? And so it causes a lot of emotions. And I understand, I relate, but it's don't fall for the rage pill. Don't let yourself get enraged by obvious engagement bait, which is to cherry pick the craziest, silliest thing and use that to get all worked up and take that personally, like that somehow hurt you.
<human>: Like you were hurt by that thing over there happening. Well, and what's so funny is like you are actually included on the real truth, which is that they screwed up. Like you're right, they shouldn't have gotten that money. Like you nailed it. That person who funded that company is an idiot. And you're exactly right. But like, hey, that doesn't mean We should better. Oh, yeah, it's like, okay this dumb thing happened.
<bot>: Therefore up is down black like like forget everything we know. Yes Those are those that doesn't follow that logic doesn't make sense.
</s> |
<human>: So where I like to start is audit how you live. Like, think about where you're waking up in the morning. Did you get enough sleep? Are you in a place that's a home? Are you living in a place that makes you more powerful or less powerful? Are you sacrificing, like, are you losing hit points at home? And if that's happening, man, that's unforced error, right? So that's who you're living with, what you're eating, do you have easy access to exercise, are you living in a place with a bunch of alcohol and drugs everywhere? I'm not helping you. At the minimum, your home should be neutral, but I think for the most successful people, the home's actually a plus. The home is like... where they're making points, where they're winning points. And I think that a lot of founders in their early days don't understand how much they could be losing based on just how they're living.
<bot>: Yeah, I think almost from a clinician's perspective, when someone is having issues, the first thing you look at is sleep disruption, diet, and exercise, right? If you go look at research depression or anxiety and things, that's usually where the 80-20 solution is for a lot of folks that are struggling, is you look at their sleep patterns. Are they sleeping okay? Are they eating okay? Are they getting exercise? Are they getting sun? All these sorts of things. And so if you don't have your house in order on those fronts, you are not even if you don't currently have depression, you are not well-situated to deal with really hard things that might happen to you, right?
<human>: But Dalton, I went to an Ivy League school, and it was really hard. And I went to a really challenging high school. And I didn't have to change these things to get good grades or to get the good internship. I was able to work hard and play hard. Why do I have to change now? It's working. It's working for me, this lifestyle.
<bot>: I think it can work for people. You and I know people that certainly don't follow this advice and they still did okay. I just think you and I also know the same people. where eventually you've got to pay the piper. Like at some point, no matter, it's almost like you're going into debt, like personal health debt or whatever you want to call it. And man, you can go pretty far into debt. You can go five years into debt. You can go 10 years into debt. I don't know. But at some point the debt comes due. where you can't hold it all in anymore. You can't hold the whole world on your shoulders. And I think what we're just trying to say is if you start off with good habits early, you're not gonna incur this massive debt that one day causes you to have like a breakdown or a meltdown or again, whatever you wanna call it.
<human>: Well, and to double down on that, I might argue that like, you probably can sacrifice these things for five years, like maybe even seven years. The tricky thing is that like the best companies last multiple decades. The tricky thing is the shit that you can get away with in your 20s, you can't get away with in your 30s. And company running just gets harder. And so I think sometimes people are like, oh, this is gonna be a relative sprint. But it's like, what I like to talk to you about with YC founders a lot is like, what happens if this works? Like, are you set up for this to not work? Or are you set up for this to work? Because if this works, like, Woo, you're gonna be in it. You're gonna be in it for a while. And I think sometimes people set their lives up for it to not work and then wow, self-fulfilling prophecy.
<bot>: And when you think about it, this isn't an age thing. This is a lifestyle thing. Because you'll see 19-year-olds with all the good habits and you'll see folks that aren't 19 that still live like 19-year-olds. And so this isn't an age thing at all. This is a habits thing, man.
</s> |
<human>: So I think what I would say is this is that, you know, this is tricky, right? I think that when we made the video about Fang, fortunately or unfortunately, I think that, you know, Google is going to look very similar five years from now as it looks now. And I think that for those of you who are at unicorns, it can really go either way. So you have to be careful, right? You could leave a unicorn and that company could do great." And you could look back five years from now and say, like, I made the exact wrong decision. On the flip side, you could be the person, you know, shutting the lights off and five years from now being like, I'm not making the right decision. Make sure that you're actually doing your own analysis here, I think is the point I want to make. Make sure you're doing first principles analysis, you're looking at data, you're not believing any hype.
<bot>: I think another point to make is the concept of job hopping. Job hopping is not good either. So sometimes you'll see people that swap. They go to a new unicorn every 12 months or 18 months. It is very hard to ever build a good career or to build expertise. Or even make a lot of money. Or make a lot of money doing that kind of stuff. So again, I don't want folks to interpret what we're saying as, hey, you should be a job offer and just switch jobs. To the extent you are working at a place where, as far as you can tell, the metrics are excellent, the founders are extremely focused, your colleagues are very smart, and you are very impressed continuing to work with them. You should probably stay a really long time. Yeah.
<human>: I mean, that's kind of what Google looked like, what Facebook looked like.
<bot>: And so again, let me just go through things I would look at if I were someone in one of these companies trying to decide if my company was doing well. All the stuff Michael said.
</s> |
<human>: You know, Dalton, as you were saying this, something occurred to me. The platforms change faster than the human problems. So like you and I have lived through Web 1.0, Web 2.0, mobile, and whatever the hell you call it.
<bot>: The Facebook platform.
</s> |
<human>: And I think that what's so tricky is that it's so obvious the society we live in today was built by people who were playing positive sum games. So what it really is, is those people created a little bit of excess capital that the zero-sum game people are like harvesting. They're kind of like slowly degrading society and as long as like the positive-sum game folks stay ahead, society progresses. But in times where the zero-sum game folks kind of get too far ahead, I mean, we lived through one of those financial crisis, the last financial crisis, maybe the current one. The second the zero-sum folks get ahead, the world literally goes to shit. It's quite funny how the world starts looking really bad when the zero-sum games take over. It's interesting because this is something you brought up, the idea that people are getting rich out there and I'm missing out. Like, I think that we've been in the last four or five years in a zone where like, people are kind of seeing people out there getting rich with games that seem too easy. If stocks only go up, it is easy. It is, yeah, you know? And you might as well buy a margin because it'll only go up faster, right? I think that if I can predict the future a little bit, when everything's going up, it's easy to think you're the smart person. When things start going down, you start realizing who the real smart people are. And it tends to be a way, way smaller group than you might think. And it turns out that they're taking money, like, they're playing the zero-sum game 10x better than you are, and they start taking money from you. And then you start losing faith in the system. Because you ask yourself, well, why did the system not protect me? Like, I didn't do anything wrong. Why am I punished? And it's like this negative feedback cycle that only exists on the zero-sum side. Because our friends who tried and failed to do positive sum games, they almost always learned something or advanced in some way. They almost always took something from that game with them that made them better off, even if they didn't win. Whereas the folks who are playing the zero-sum games, if you don't cash out, that was the only thing you could take out. That was the only win, is getting out of the game. They never get the lessons in little dabs along the way. As kids, we're used to getting these little lessons along the way. For these zero-sum games, often the lesson just comes fast and hard at the end. It's like, boom.
<bot>: And then you're blowing up. I mean, you do these office hours with companies where it's just game over. Like, it's like, it's good, it's good, it's good. Okay, we're dead. There's no warning, especially when you deal with debt and leverage, which is, again, related to this stuff. When you are gambling with money that's not yours, and you're heavily levered, it's rough. So, so let's make, let's take this positive. So again, like we're seeing all the, what is the advice? Like, how can you make sure what you're doing is positive some, and like, how can you build enduring value and not accidentally.
<human>: You know, what's the move? You know what, Dalton? I don't think people are confused whether they're gambling or building houses. I think that they know whether they're gambling or building houses. But they're so good at fooling themselves, do they? I think they know. I think that the thing they have to resist is the FOMO. I think the more deep question is how do you build houses when you see a lot of people getting rich gambling all around you? How do you kind of stay strong and build a house? when you see people getting rich getting around you. And, you know, it's funny because I had a friend who was a sports gambler and I think I learned this lesson through him. He would always tell me when he won that weekend and he'd always bring in like stacks of cash and it was like, I'm way up. And then the weekends he didn't win, he was just silent. And I think I always assumed that like, oh, like he must not have gambled that week. What do I know? I'm not paying attention. And I think that like for those people who are looking at the folks who look like they're winning in those zero-sum games, I think if they looked a little closer, and they ask themselves, like, are those people actually cashing out? Are those people actually doing something sustainable? Like, are those people drinking the Kool-Aid so hard that when the turn comes, they won't be ready for it? I think we'll start realizing that they should feel less FOMO. That's how I feel. Like, how do you feel about it?
<bot>: Yeah, I think, look, I think People can convince themselves of anything. In fact, this is definitely something I've learned over the years is like, no matter how crooked someone is being, they have a story that they cling to, and they refuse to see it any other way than that. I think you kind of want to look for external validation that you're building something of value that's enduring for people and be able to articulate that in a very simple way, what that is. What is the leave behind value that is being created as a consequence of my work? Am I winning because someone else is losing or is something real? I mean, we're seeing this right now with a bunch of our startups. A lot of folks, okay, you know, it's hard out there. We can't raise whatever, but our startup is still running. Like they're still growing. They're still like, like the company is just doing the same thing. And the stuff happening in the external world is noise. Those people are doing a real thing. That's a positive. Some people were there like, well, we're done. You know, like the people were immediately the music stopped that. That's rough. Like if you're that sensitive to like market conditions that literally you don't have a company anymore the minute the markets drop.
</s> |
<human>: So I mean, to kind of wrap this up, right? Like this idea of do things that don't scale. One, it's gonna be counterintuitive. Two, expect people around you to not understand. And to actively think you're stupid.
<bot>: Not just not understand, but actively tell you, you are being an idiot. Why are you delivering burritos? What on earth are you thinking? They'll stage an intervention for you. You're screwing up. Your friends will come together. They'll set you down and be like, what are you doing, man? This is a mistake. This is not what you should be doing.
<human>: Expect it to look way different than what your larger competitors are doing now. Expect it to look way different. And expect yourself to be the primary actor. You're not acting through others. You are the doer. Anything else to add though to wrap this up?
<bot>: I think if you look at other companies that raise a lot of money, you're inclined to copy that strategy. of what they're doing. So again, if you see someone, all these companies are doing, I don't know, 10 minute delivery, right? Like that's the hot new thing. And so they're like, oh, this company raised 50 million. I better raise 50. Do things that don't scale is cool. Yeah, not for you. Go do one delivery. Like when I see people fail a lot, it's that they want to get a thousand customers and they can't get one. Just being able to say one, we've delivered one burrito separates you from the pack. And so again, maybe this is an inspiring thing. Actually doing something is much better than average. Congratulations, you're in the top half of startup founders if you can get out of your own way enough to do one thing.
</s> |
<human>: So to wrap it up, we have a strong disagreement. I think the suburbs are horrible. You clearly like them. By the end of the day, there's room for both of us.
<bot>: Yeah, we're both in the same ecosystem, right? Who knew? We're both working together. Who knew? Yeah.
<human>: And we're recording this video in the frickin' suburbs, too, which is hilarious.
<bot>: We are. You're right. We came to my zone to do this video. We came to your place to do the video.
<human>: Oh, man.
<bot>: All right.
<human>: Great chat, Dalton.
<bot>: Thanks.
</s> |
<human>: So what's the takeaway for founders?
<bot>: Well, the takeaway is you look at these big companies, and you can easily decide to emulate this stuff. Again, if all I'm doing is from first principles trying to look, how does the world work? Why does the world work the way it does? It's easy to look at these very successful, very valuable companies, know the story of Facebook, and actually attempt to emulate the end state of these companies, which they're so big. The people that work there are very isolated from their customers. The customers are sort of like, only a small percentage of those companies employ people whose job it is to talk to their customers? Yes. And most people, if you work at those companies, you would never talk to the customers.
</s> |
<human>: Like I thought, like, isn't that weird, man? Like why? We have a grand, nefarious strategy of giving founders what we wish we had when we were founders. I mean, isn't that like so funny? Because it's kind of one of the core guiding principles of YC when we think of what we're going to do. Yeah. It's like, what would I have wanted? Yeah. Like, that's certainly how I think about this. Yes. And the opposite, too. Like, what would I have thought of as bullshit? Like, how do we not do the stuff that I would have just like been like, that's bullshit. Who cares?
<bot>: I mean, it's hard to do in practice. It's just, at the end of the day, more leverage for YC Founders, good. More options for YC Founders, good. That's the game.
<human>: Obviously so.
<bot>: Anything more on the standard deal?
</s> |
<human>: And I think that the way that this is kind of embodied was that, fully embodied how bad of an idea people thought this was, is that he had an impossible time raising money on Demo Day. And so if he had taken the Demo Day signal, the investor's signal of, oh, we don't want to give you money, and quit, we wouldn't have Coinbase. Correct. All right, last one, Stripe. So you had dabbled with payments pre-Stripe. How easy was it to accept credit cards online pre-Stripe? Share the story with everyone.
<bot>: I have set up, before Stripe existed, I set up accepting credit cards for my companies twice. Once in 2002 or so, believe it or not, when I was very young, and then once again in 2007. And to get a merchant credit card account was like applying for a mortgage. You had to fill out lots of paper. You had to fax in stuff. You had to personally guarantee things. They had to do fraud checks on you. It was rough. It was expensive. There was minimums. And so it was a possible thing to do. But I would call it gnarly and the opposite of easy in every way. And I also remember when Stripe came out. I was actually in the Stripe beta. I was one of the first 100 customers of Stripe way back in the day for my third company, the third time I went to accept credit cards. I really wanted it, in terms of make so many people buy it. When it came out and I read about it on the Hacker News, I immediately wanted Stripe. And I hadn't even seen it yet. I just knew I wanted it. So that's the historical context.
</s> |
<human>: I would argue that like there were two fundamental facts that made the existing products not good. The first is that VRBO and Craigslist did not facilitate payments. So when you arranged a house share with someone or staying in someone's apartment, you still had to pay them either in cash or check or wire. And there was a lot of friction because it's two people who don't know each other having to trust each other to transmit payments. I think the second problem that VRBO had was they charge hosts to list. And if you think about the core insight of this market, it's that hosts are the game. If you can get the most hosts, you win. You have the best inventory. But if you charge them upfront to be on your site, you're probably doing it wrong. So to me, timing was huge. Existing product did not, there were 10x improvements that could be made. I think the second thing that was really interesting was that they were solving their own problem. Most people don't realize that Airbnb started because Joe and Nate needed to make rent money. And there was a big conference going on in San Francisco, and they basically rented out room on their floor to host people so that they could make some money. And it's funny, because we always talk about personal problems, but not being able to pay rent, that's a real problem, right?
<bot>: And that doesn't sound like a vacation rental, which was what I was used to seeing on VRBO, which was vacation rentals.
</s> |
<human>: Okay, so here's another one that I see a lot, especially with fundraising, stupid comparatives. So like, in 2021, Tiger gave this company $100 million funding when they accomplished blank 500,000 of ARR. Therefore, we will be able to raise $100 million of funding when we accomplish 500,000. Right, Michael? There's no difference between summer 2022 and summer 2021 at all.
<bot>: Well, and that's how it works, right? As investors, what they do is they just are always consistent and they always make the same decisions. And it's easy for you to tell, reading the TechCrunch announcement, why the investor made the investment. Right? It's clear. Like I read the article, you know, this VC invested in this company. We're kind of like that company in some superficial ways. It's in the bag. We got it.
<human>: And then the other one that I love about it is like, no, Michael, like that round was announced last week. That just happened. And it's like, sorry, but lots of things are announced way after they happen.
<bot>: Way, way after. And so again, I think what we're saying about what's the stupid goal in this case, playing the stupid game here is trying to create superficial resemblance to other things. Yes. as opposed to deep, the thing is working, or maybe there's a deeper analog to the other thing. But if you're just focusing on the very surface level stuff, yeah, that is not a smart game to be playing.
<human>: One other example, maybe an old one, we talked about in the past, you know, with Facebook, where you might be able to argue, well, they raised money when they only had a small number of users, right? And then you completely punt on the fact that like, that small number of users were 95% two hour a day Facebook users. So the engagement was like incredible.
<bot>: If you can replicate Facebook's engagement, then you've got something versus replicating, I don't know, it's for college kids or I don't know, people have very superficial stuff there.
</s> |
<human>: Here's another one that's in the news more and more lately. Defrauding your customers. Selling your customers something and telling them it's one thing and you know it's not that thing and your customers lose money or your customers are in some way extremely harmed. What's the prize for doing that, Dalton?
<bot>: No joke. It seems like there's people going to jail and getting arrested and people whose actual lives are now irreparably harmed by the games that they were playing to get growth or to get money. And yeah, they're gonna spend, you know, best case scenario is spending years and years and years in court and in the court system and just having your life changed.
<human>: Like this isn't making a mistake. We gotta be clear here. Like your state of mind is extremely important here. This is like knowingly pursuing a strategy that you know is harming your users. And I think what's tricky is that oftentimes people don't think this is happening.
<bot>: I think sometimes people forget they're not playing a game. And I think especially in COVID land, I don't know, like one of my explanations is if you spend all day on Twitter and Discord and everything's a game and everything's a joke, everything's silly, you can kind of, I just have noticed some folks lose themselves and not realize that the numbers in the spreadsheet are real dollars. And I don't know, it's like, we're not playing Monopoly. We're not playing sellers of Catan. And I think that the prize that you win is the knock on the door from the police. And that's when you're like, oh, wow, this was real life.
</s> |
<human>: This is kind of a fake disagreement, because if you kind of have been parsing our words carefully, we're talking about living in the Bay Area. So I'll ask you straight up, Dalton. Would you recommend someone starts a startup outside of the Bay Area?
<bot>: Yeah. Well, I genuinely would not. We agree. So the part we're agreeing with. is that, again, think about it. We're working together. We're in the same room right now. We get to live in the same area, even though our personal decisions about where we live are wildly different. We have very different lives. I don't have a yard. I have kids, too. And so what's cool is we get to work together, and we get to work with all these amazing people, and yet we have very different choices on how we want to live.
</s> |
<human>: So in the case of Twitch, if not all, most of the examples of this came from this core problem. And it's why I tell people to not create a live video site. A normal website, even a video site, on a normal day will basically have peaks and troughs of traffic. And the largest peaks will be 2 to 4x the steady state traffic. So you can engineer your whole product such that If we can support 2-4X to steady state traffic, and our site doesn't go down, we're good. On a live video product, our peaks were 20X. Now, you can't even really test 20x peaks. You just experience them and fix what happens when 20x more people than normally show up on your website because some pop star is streaming something. And so two things kind of happened that were really fun about this. So the first hack we had was if suddenly some famous person was streaming, On their channel, there'd be a bunch of dynamic things that could load, like your username would load up on the page with their channel, and the view count would load up, and a whole bunch of other things that would basically hit our application servers and destroy them if 100,000 people were trying to request the page at the same time. So, we actually had a button that could make any page on Justin.tv a static page. All those features would stop working. Your name wouldn't appear, the view count wouldn't update, like literally a static page that loaded our video player and you couldn't touch us. We could just cache that static page and as many people as possible want to look at it. Now to them, certain things might not work right. But they were watching the video. The chat worked because that was a different system. The video worked. That was a different system. And we didn't have to figure out the harder problems until later. Later, actually, Kyle and Emmett worked together to figure out how to cache parts of the page while make other parts of the page dynamic. But that happened way, way later. Dude, that reminds me.
<bot>: Let me give you a quick anecdote. Yes. Remember Friendster before MySpace? Yeah, of course. Every time you would log in, it would calculate how many people were two degrees of separation from you. And it would fire off a MySQL thread, where you would log in, it would look at your friends, and it would calculate your friends and friends and show you a live number of how big your extended network was. And the founders, you know, John Abrams, he thought this was like a really important feature. I remember talking to him about it. Guess what Myspace's do things that don't scale solution was? If they were in your friends list, it would say, this is in your friends, you know, so-and-so is in your friends list. And if it wasn't, it would say, so-and-so is in your extended network.
<human>: There it is.
<bot>: That was it. That was the feature. And so, so Friendster was like trying to like hire engineers and scale MySQL and they're running into like too many threads on Linux issues and like. updating the kernels, and MySpace was like, ah, so-and-so is your extended network, that's our solution.
</s> |
<human>: Yes. Well, and the second thing is, if they do end in acquisition, and many will end in acquisition, oftentimes, you have to re-interview for your job. Oftentimes, they don't want to bring everyone over in the acquisition, and so that's tricky. And also, you might end up at the big tech company you were running away from. That's right. When you're joining a startup. So I think I'd love to put in a little bit of a, A note here, I think that those 30% that will do well will probably do counterintuitively well. Like really well.
<bot>: Yeah, like very well. Extremely well.
<human>: Yeah. Even going to work at those companies now is probably a good idea. Absolutely. Yeah. And so I think that's what's so tricky about this is you have to be smart. You can't really be like following the bullshit press or stuff.
<bot>: Yeah, or like the memes on Twitter about what's doing well and not doing well.
</s> |
<human>: You know, I see another one, because corporate governance, that covers your investment docs and where you're incorporating and all that kind of stuff, your vesting, blah, blah, blah, your classes of shares. I sometimes see founders doing crazy stuff. I see another one that you brought up, though, which I really love, is the, like, I'm going to make this startup, but I'm also going to disprove every piece of startup advice. Like, I love this, like, I'm only willing to help my customer if I can simultaneously prove that all of the startup advice is incorrect. And it's like, what?
<bot>: And so, yeah, so the example of that is just to take something that is like widely considered useful or true and try to prove the opposite of it. You know, like my thing will be reliant upon making the small town that I live in the center of the startup ecosystem or something. Like somehow there'll be some other bet they're making that involves a super contrarian thing that has nothing to do. Actually, I can think of an example of these, by the way. One of these was, I remember a founder doing something unrelated, again, I'll keep this anonymous, but they were like, the real thing, the real bet we're trying to make is the hydrogen economy and that no one will use gasoline or solar or wind or, or, or, But then in the future, we're gonna use hydrogen everywhere. And I was like, hey man, maybe don't mention that. We'll keep this between us. Maybe when you're- That's the real secret sauce. Maybe you should keep that on the down low. And the case was, maybe he's right, but that had nothing to do with the actual bet of the startup.
<human>: No.
<bot>: And to try to throw in this long shot bet that we're all going to be using hydrogen for everything, again, maybe he's right. I don't know. That seemed like a completely unnecessary risk or thing to innovate on.
<human>: Yeah. And I think that what's so sad about these things is that I think there's a misunderstanding of how hard it is to make something that people want, where people think that they have these extra points, this extra juice to spread to do other things with. And I just, I always like to tell people, it's like, this game is so hard. Without this stuff, I'm like, why do you want the game to be harder? Like I never understood that. Is it fun?
<bot>: Yeah, okay. Let me give you an example of something that's fun. Okay, sure. Like nerd bait kind of stuff. Sure. Again, this is my recollection. My recollection is that when, I believe it was Asana, when they started, they wrote their own programming language. Of course. First. Of course. And why would you do that? Because it's fun. I believe they back that out. Again, someone will correct me if I'm wrong on this. But a lot of times choosing very idiosyncratic programming languages or text stacks, people choose to do it because it's fun. And who am I to fault them for that? But it's like they're optimizing for like, wouldn't it be cool if we wrote our entire thing in this new, idiosyncratic programming language?
<human>: Yeah, that's such a weird, it's like, I get it on one hand, and your startup should be fun, right? Like you're doing it for a while. I get it on one hand, but I've never seen a founder who didn't have the most fun by helping their customer.
<bot>: Do you remember in the Reddit versus Dig wars, Dig made a lot of technical bets. along these lines, meaning they made a lot of very high-risk technology choices, while Reddit was just like, not. Let's make a social news site. Well, I don't think they were taking any high-risk technical choices. And so this, again, is an example where Dig was taking on all this extra risk on something that had nothing to do with dig.com loading news stories. It was literally about the technologies they were choosing to power the website. Yes.
</s> |
<human>: Do you have any more on the preventative side before we move to treatment?
<bot>: I think it's just this expectation setting. I think so much of life is expectation setting where setting expectations for yourself, setting expectations for people you work with about what to expect. If you are good at that, people can deal with all sorts of stuff. And when you get into the biggest trouble, both with yourself, managing your own brain, as well as working with other people, is when you say a bunch of stuff that turns out to be really not true, and you set expectations poorly, and you have to dig yourself out of this deep hole that you dug yourself into, because you promised a bunch of shit, or you set expectations in such a way that just weren't true. And so expectation setting is key for prevention.
</s> |
<human>: I see this hiring all the time. I see the hiring startup applies to IC, and the thesis is always the same. I'm an engineer. I'm a genius engineer, and I am being assessed by a non-technical recruiter. This is a crime. This is a crime against humanity. It's dehumanizing that I have to go through this experience. And if only the hiring manager was empowered with software, the entire recruiting team and all recruiters would just go away, disappear off the face of the earth through the hiring manager and software. And what's weird is that I kind of believe the premise. I believe An engineer is better at determining whether another engineer is good or bad. However, I also look at the way the world is organized and I ask myself, well, if it seems consistently organized that these massive teams of recruiters exist at all these companies, there must be some efficiency going on that I don't understand, right? And the one core thing that I've learned is that even though engineers are better, at creating other engineers. There are two other facts. One, they don't tend to enjoy doing it. And two, it doesn't tend to be the greatest way to extract value out of a great engineer.
<bot>: Yeah, it's not the best use of their time. Like if you're employing engineers, you don't really want them to spend all their time doing this. You want them to be doing their jobs.
</s> |
<human>: Dalton, before we close, what are some tactical tips you'd give folks who are looking for co-founders now, who are extremely early in their journey or thinking about starting a company?
<bot>: I hear from a lot of folks starting companies where they want to come up with the idea first, maybe they want to raise money first, and then they want to add a co-founder. And I actually think that's going about it in a less than ideal way and actually might cause more problems. I would recommend figuring out who the co-founder is first, and then if you come up with the idea together, and perhaps you fundraise together, then you'll have collective ownership that it's your idea and it's your company versus a lot of times when you add co-founders later, in their mind, it's your company. It's not their company. And even though you worked on the company an extra month than the other person did, which is so silly, right? You'll always have this like, well, this wasn't my idea. This wasn't my company. which isn't great from our retention perspective. If you can both really feel like you shepherded the idea through the earliest stages, you're going to see a lot more ownership and people stepping up when you go through hard times.
<human>: To reiterate what we talked about at the beginning, I don't want to say co-founders are essential, but man, they're so helpful. It's such a powerful tool. especially in the hardest part of the startup, the pre-product market fit startup. We still encourage everyone to have a co-founder. But like the startup game, right? It's not about doing it well, it's about doing it great. Like having a great co-founder can be a superpower for your company. Having a okay co-founder, not taking this seriously, can be the seed of big problems.
<bot>: Absolutely. And sometimes people, they end up with co-founder issues and like, well, I guess I'm just gonna quit and start a new company and we'll, it's so easy to start a new company and then, It's like, well, good luck. And then you speak to them a year or two later and it's really hard to get back to where they were in the moment. And one of the regrets is they wish they would have spent the time to set up the co-founder relationship well and choose the right person first, then think they can just blow everything up and get a do-over. That's just not how life works. And so the more you can front load this the first time around versus having hard earned lessons.
<human>: Yeah.
<bot>: Would recommend.
</s> |
<human>: This is Michael Saibo with Dalton Caldwell. And today we're going to talk about how OpenAI is going to kill all startups. This is our last video.
<bot>: Might as well pack it in. We're done. OpenAI is going to do this. They're going to make the videos next.
<human>: They are, yes. We're the next video.
<bot>: The next video will be SkyNet. AI Dalton and AI Michael.
<human>: You're right. Doing our video for us. And do a better job than us.
<bot>: Yes.
<human>: What do they call it? It's not a deep fake.
<bot>: It's like a complete AI recreation.
<human>: Yes. We're done. Well, it's been fun, so let's talk about how that happened. So I think to start, people need to understand that companies like OpenAI, Anthropic, et cetera, They're actually trying to build AGI. They're not trying to build the AI-powered CRM or better search. They're trying to build AGI. And this is not a debate. We're not going to talk about whether they're going to succeed at building AGI.
<bot>: Yeah, there's plenty of videos and there's plenty of experts that are better experts than us to debate whether AGI is about to be created. And I kind of bring this up. I've heard of Godwin's Law. Please. In an internet debate, when there's people arguing with each other, and one person calls the other person a Nazi, the debate is over, and no good discourse is productive after that. It just means it's over. And so where I'm going with this is, once we start talking about how AI could become God, and we have a Skynet, and take all the things, and we're going to be uploading to the Matrix, I'm arguing nothing useful will happen. That conversation is over with that person. We can't help you.
<human>: in this video about that. Whether or not Skynet is coming is outside the scope of this video. And we would love to talk about it, but we just don't have the expertise.
<bot>: Someone else is the expert on that, not us.
</s> |
<human>: This is Michael Seibel with Dalton Caldwell. At YC, we often have to have challenging conversations with founders when giving them advice. Today, we would like to talk through some of the hard conversations that founders don't want to have.
<bot>: Dalton, why don't you set this up for us? Well, look, let's start by trying to define a hard conversation. By definition, if it's a conversation you're looking forward to having, it is not a hard conversation. A hard conversation sucks.
<human>: Yeah.
<bot>: That's why it's called a hard conversation. You don't want to have them. They're bad, right? Or they don't feel good.
<human>: They don't feel good.
<bot>: They don't feel good. You dread the hard conversations. And so a hard conversation is when the stakes are high. Like it could go bad. It could go off the rails. It could be you're saying something risky or you're making a point. Maybe you're doing something that's impolite or saying something that's impolite. Because again, think about an easy conversation. Easy conversation is superficial. You just agree with someone. You're just like, hey, you're great. Way to go. That's an easy conversation, right?
<human>: Yes.
<bot>: Hard conversation is not that. A hard conversation is when you're vulnerable. You're putting yourself out there. You're saying something that someone in the conversation is uncomfortable.
<human>: You know, it's funny, as you set that up, What's tricky being a startup advisor is that you know it's gonna help someone to have hard conversations with them, but you also know that they're not going to enjoy it. And I think as a YC partner in the early days, I think I measured my effectiveness based on how much fun founders had talking to me. And only after a couple batches did I realize that doesn't really do anything, And then when I started having honest conversations and talking about my actual opinions about their product or about how hard they were working, oof, the job changed. Did you experience that?
<bot>: Yeah.
</s> |
<human>: How should the CEO set up a company so that if this battle, you know, if there is a co-founder fight, it's not fatal to the company?
<bot>: The closest to equal you can get, the better, because it avoids this, oh, this person has 10% more, so it's their company. You see all this drama that happens over equity splits. So equal is good. However, here's a pro tip for you. A straight 50-50 deadlock is rough, and we see that kill companies a lot. And so it might be reasonable for the CEO to have one extra share. So you effectively have the same ownership, you're equal co-founders, but that one extra share is you agreeing in writing early that in the event of a 50-50 deadlock, there's a tiebreaker vote.
</s> |
<human>: You can't just sprinkle software on the product.
<bot>: Yeah, or like realtors, like buying a house. Why is it so hard to buy a house? Well, you know, I don't even know how to summarize that. But like, like a lot of founders want to believe they can just like start a company and revolutionize the home sales process. Right. So I feel where it's coming from. But in practice, The simplistic engineering efficiency arguments don't always work when applied to the real world.
</s> |
<human>: I would say one that I see on the YC application that I love is when it's like some kind of weird incorporation. Yes. We incorporated it as a Wyoming LLC. And I'm like, this was a voluntary red flag. This is like, why would you do that? And sometimes they'll even write, well, because, blah, blah, blah. And you're just like.
<bot>: Well, I think my theory is there's a lot of smart people. Again, they want to invent it in different ways. And they'll look at something like, corporate law in the existence of the Delaware C Corp and be like I Someone that knows nothing about this could do better. Yes And everyone else is doing Delaware C Corp. Yes, that's not for me. I'm gonna do a and then crazy things happen. Yes, right and so Probably corporate governance is not the best place to innovate one thing that's been funny Headline ripped from the news is yes people looking at the corporate structure of open AI. Yep, and being like oh This is an interesting. This is an instruction manual a Nonprofit that owns a for-profit would not recommend that strategy even the people that work working there I mean even Sam himself has suggested that that was perhaps not the wisest choice. And so again the point here is is the miracle of making something you want is the hard part. But if you're just doing like a startup, you know, Delaware C-Corps are pretty good.
</s> |
<human>: Let's say the punch happens, bam, and you need some treatment. something really bad happens or you suspect something really bad happens. I think the first point that you brought up that I really love is this idea of like, do I have to do anything right now? Like, talk about that a little bit more.
<bot>: Yeah, I think I learned this as a founder the hard way, which is when something bad happens, you want to immediately like make a move. You want to like, call a meeting or you wanna, you get an email with bad news in it, you wanna hit respond and like, in the moment of fight or flight when your adrenaline's pumping, you're like, how dare you, sir? You wanna start writing emails with that tone? Dear sir, in response to your query about, like if you're ever typing an email with that tone, Don't do it. And what I've noticed is you can just like not respond or like let stuff sit a little bit and sleeping on it is the minimum thing I would do. This is what I always tell founders is when they have something to happen to at least sleep on it. Because I just noticed the next day You have a whole new amount of clarity on the situation.
<human>: And I often find myself in my best moments. In my worst moments, I'm exactly like you said, I'm like, act now, go, send that email, like punch back. In my best moments, I'm always like, if there's ever a decision that feels like it's action one or action two, There's always a third option, which is don't act. And it's almost never presented to you. I find a lot of times lawyers fuck companies with this. It's like, you gotta do this or that. And it's not like, how about we don't respond?
<bot>: Yeah, what if we do nothing?
<human>: What if no action is taken? And then what's really funny is that the best founders no action becomes one of their like key plays. Like they use that play way more than you think. It's a great play. Such a good play. Um, and it's amazing that like for the best founders, no action is like, you know, 20, 30, 40% of the time what they do, maybe more. But for other founders, they don't even know the play exists. Like they don't even know the play exists.
<bot>: Yeah, maybe just archive the email.
<human>: Whatever the email says. Yeah, that's true. Just hit archive. You know what's a really big deal? They'll probably reply back. I've noticed that. It's a really big deal. And of course, don't do this in the case where someone's health is on the line or someone's going to go to jail or whatever. That's different.
<bot>: Yeah, it's more of the stuff where it's interpersonal or someone, I don't know.
</s> |
<human>: I think the first thing I'd be thinking about is revenue. I would say that at the end of the day, when a company goes public or when a company is acquired for a lot of money, the market is looking at how much revenue that company is making and is that revenue growing. And I would say that, for example, if I'm at a company right now that's making 50 to 100 million in revenue or more, that's a unicorn. Like, that's pretty good. Yeah, it's reasonable that it's a unicorn.
<bot>: If they have $100 million plus in revenue, OK, that pencil's out, right?
<human>: Yeah, that's pretty good. I think that if I'm working a company that has like $50 million or less in revenue and is a unicorn, now I'm starting to ask myself the question, do users like the product? What's retention look like? Are we charging as much as we could? Could we charge more? Do we actually have product market fit?
<bot>: Do we actually have product market fit? Again, not likely to be a popular question in management, if you ask management this, but worth considering.
<human>: And I think a lot of these questions can really be answered by looking at what are the customers doing? Right? I think what's so funny is that if you're an employee inside of a company, most likely the information you need to tell whether the company's doing well or not is like literally available to you.
<bot>: Yeah. Well, and I can imagine there actually may be some folks out there that work at companies where the information is not available to them. Is that OK? Like, what do you think?
<human>: Is that normal to not be told these numbers? I would say that, like, what's interesting is that Maybe there are certain financials or certain cash on hand or something that it's important for the company, or a founder might decide to keep private. But I would say in most companies, product analytics in some way or another is available, is widely available. And so you can tell whether the users who are paying for your product are actually engaging with it. And man, I think that's like hilariously the simple leading indicator of whether you have a good product is you sold somebody the product, they've successfully onboarded, and they're actively using it.
<bot>: And then they renew. And they do it on the business model of the company.
</s> |
<human>: This is Michael Seibel with Dalton Caldwell. And today we're going to talk about the problem with zero-sum games. So we were chatting, Dalton, and we've seen a lot of zero-sum games kind of in our lifetimes. It seems like it's something that comes and goes pretty, pretty often. Why don't we start with kind of the first time you've encountered a zero-sum game and almost like how you got trapped by it?
<bot>: Yeah, so just to start with definitions, a zero-sum game is a game that you play where the upside that you're getting comes directly from the other player. So if we're talking about money, a classic zero-sum game is we make a bet. And so say we bet, you know, 20 bucks, something will happen and you win. The money that you win comes out of my pocket. There's no new money that's created in the system. It's zero sum. So whatever you gain, I lose. And it all equals out to zero, okay? That's zero sum. A positive sum game is where something happens and as a consequence of it, value is created that lasts for a while. So say that we decided to do something for fun and we built a house. We're like, it would be fun to build a house. So we do the thing and then when it's all said and done, the house exists. Our labor produced something that will last – that wasn't there before.
<human>: We can charge rent for it and maybe generate some income.
<bot>: Yeah, exactly. And so we were entertained in both scenarios where we, you know, made a bet versus built something. And in one of those scenarios, it was a, we made something that lasts and the other one, it was just a zero sum form of entertainment.
</s> |
<human>: It's fair. And here's why you're wrong. OK. So I live on Market Street in downtown San Francisco. Fair? Just to be clear. OK. For me growing up, living in a city was aspirational. So I spent my high school and middle school years in a suburb of New York. And when you do that, you know.
<bot>: That means New Jersey, right? Whenever someone says a suburb, I'm from New York. Well, where exactly?
<human>: They're like, well, you know, upstate. Middle school and high school in New Jersey. And when you're growing up in a suburb of New Jersey, you know where you are is not where the action is. It's true. You know, almost by definition. And at least for me, I perceive getting to the city as part of growing up, becoming an adult. That was a big part of my mentality. Two, I like nice restaurants and nice bars. And those things don't exist in the suburbs. I know someone's going to be in the comments saying, well, in my suburb, there's like, no, no, it doesn't. Sorry. It's just good for where you live. Another thing that I like, especially as a startup founder, I liked having a chip on the shoulder. I liked being in a place where there were things I couldn't afford, where there were places I couldn't go unless I was more successful, where I could kind of see what success could get me. And I always felt like the suburb tried to hide that away. Like everyone was in the same kind of house, in the development, and we all have our own space, we can't see each other. seeing what if we were to make it, what I might be able to get. That was really amazing. Also, I spent my first kind of nine years living in a city in Brooklyn. So I was used to living in an apartment. That was never weird for me. And there are a bunch of amazing newer companies, Uber, Airbnb, DoorDash.
<bot>: I don't know those companies. Well, DoorDash was Palo Alto Food Delivery. That was their original name. So they didn't move there. They didn't start there. And they moved. They moved. OK.
</s> |
<human>: And honestly, that's gonna be kind of the theme of this whole setup, right? Super dirty, but it worked. You had a couple of these in iMeme, right?
<bot>: Yeah, there was a couple that we had in iMeme. So one of them, so at the time, again, like to set the stage, the innovation of showing video in a browser without launching real player? No one here probably knows what that is. But it used to be to launch a video, it would launch another application in the browser that sucked and it would like crash your browser and you hated your life, okay? So one of the cool innovations that YouTube, the startup YouTube had before it was acquired by Google, was to play video in Flash in the browser that required no external dependencies. It would just play right in the browser. At the time, that was like awesome. Like it was like, it was a major product innovation to do that. Um, and so we wanted to do that for music and I mean, and we were looking at the tools available to do it and we saw all this great tooling to do it for video. And so rather than rolling our own tools that was music specific, we just took all of the open source video stuff and hacked the other video code that we had. so that every music file played on iMeem was actually a video file. It was a .FLV back in the day. And it was actually a Flash video player. And it was basically, we were playing video files that had like a zero bit in the video field. And it was just audio. And we actually were transcoding uploads into video files. You know what I'm saying? Like the whole entire thing was, it was a video site with no video. I don't know how else to explain it. And it works. And I do think this is a recurring theme is a lot of the best product decisions are ones made kind of fast and kind of under duress. I don't know what that means. But it's like when it's like 8 p.m. in the office, and the site's down, you tend to come up with good decisions on this stuff.
</s> |
<human>: This is Michael Seibel with Dalton Caldwell, and today we're gonna talk about caring about your customers. Well, first, I guess. Yeah, let's be meta. Here we are. Does this look different? Yes.
<bot>: We're in person.
<human>: We're trying this. Where's your art?
<bot>: I know.
<human>: But we are really, literally in person. This is us.
<bot>: We're in person. We're not avatars. We're not in the metaverse.
<human>: We're not in the metaverse right now, people. Maybe next year. We're upgrading. This is an upgrade. Great. We had so much fun last year, we decided to do this in person. So let's set this up. We're in the beginning of a YC batch, and there are a lot of companies who are trying to get sales, trying to get new customers. Always a good thing. And we might describe some of them as flailing. So what is the sign of a startup that is flailing when trying to get new customers?
<bot>: You know, it's like the old aphorism when all you have is a hammer, everything's a nail. And so they'll have a product, they'll have an idea, and they want to like bully customers or beg, some strategy to like cram it down people's throat. And they're like, why won't they? Take it. Why won't they take this thing that I'm trying to get them to buy?
<human>: I'm trying to help you. I have this thing and it's good.
<bot>: What's wrong with you? You're making a mistake to not want this thing. And so that's a lot of people's first experience with sales. That was my experience. These people are dumb. Don't they realize how brilliant my software is?
</s> |
<human>: You know, the next topic is on, you know, acquiring companies. And I think that This comes in a number of flavors. One is once again, we're finally grown up. We can make our first acquisition or like we want to get good at this acquisition thing. So we got to start doing it.
<bot>: There's a lot of talent out there, Michael, and some really talented, failing startups would love to be acquired by us. And this will help us grow faster. So we're going to acquire them.
<human>: And by the way, that doesn't mean that acquiring companies is bad. It just often means the folks who are thinking about it in startup land tend to be thinking about it too early. This is another example of taking later stage advice too early. when the advice you should be taking is make your core business work. Just make your core business work.
<bot>: Yeah, if you're a pre-PMF, if you don't have product market fit yourself, probably you're not gonna buy one. Probably not a great idea. You're laughing, but people are probably like, wait, really? Yeah, really.
</s> |
<human>: Oh God, you brought up one on our list about sandbagging. Let's talk about sandbagging a little bit.
<bot>: Yeah, so sandbagging, I don't know how much people are used to that term. I think it's, I think it's a golf term. But sandbagging is basically where you set goals that are intentionally way easy to hit. with the goal of blowing them out of the water, right? So say you know you can accomplish something in one week. The sandbag version of the goal is to give yourself a month. And then when you go around and you hit the goal, you like look like a genius. And what's funny is when you are working for the man, When you are working at a company, like office space, you know, you're in a cube farm somewhere. It makes sense to sandbag goals. And that's actually great career advice, I suppose, is that you, you know, you set really, you convince people that something's really hard to do, and then you exceed their expectations. What a great way to get promoted or whatever. However, there's a problem. If you're used to doing that, and that's how you think all things should work, when you start working for yourself, when you are your own boss, you are screwing yourself. And what may be a good strategy to rest and vest working at Google or Facebook and to just do as little work as possible by sandbagging goals and working three hours a week or whatever people do, when you're the boss, do you see how that's not great?
</s> |
<human>: Then I think the last thing is they used their own product. Airbnb didn't realize the insight around facilitating payments, around accepting payment when they launched. They didn't have that insight when they launched. Brian came and spoke to YC recently and he shared the story that when he used his own product and he forgot to bring money for payment and the host thought he was a fraud, he realized, oh crap, like our site needs to allow people to pay. Like we have to solve this problem. So it's funny, because these insights seems obvious now, but Dalton, back in the day, put your investor hat on. What were the shit takes? Why did everyone think, oh, this is dumb, you should do this?
<bot>: Well, look, there's two extremes. One was renting a house when someone is already home. Renting a room in a house with a host there was the ultimate, unappealing, scary, bad thing that no one wanted to do, especially older folks, you know, like investor folks.
<human>: Like investor types. You know, who have a lot of money and can afford nice hotels.
<bot>: Why would I want to go stay in a stranger's apartment in Manhattan? No, thank you. Right. So it was extremely unappealing idea of people worried about those sorts of things. And then like the other the other insight I have for you on this one is it was seen as uncool and impure when you're building a community at this time in history to charge money for it. Like the couch surfing ethos was a very like communal, community-based, pay it forward, social collective action, decentralized goodness thing. And to be commercial, was extremely in poor taste. And remember, Michael, you and I both were the founders in this era. All of the messaging that was bombarded from us, from everyone, all of our peers, is that making money isn't cool and being commercial isn't cool. And what they should have done is get as big as they could and get 100 million people on Airbnb and then charge once they built the network. And so to charge, That's a horrible idea, guys. Build a network first and then charge, right? Again, you went through this as a founder, man.
<human>: Isn't this what you would have been told? It's what we were told. I mean, Twitch became big when we started diversifying our business model and started accepting direct payments from users in addition to ads. But that was seen as dumb back then. So clearly, and of course this is gonna be a common theme, if they had listened to most of the investors, or most of the founders at the time, Airbnb wouldn't exist.
<bot>: Yeah, it'd be like, well, couchsurfing is free, so your plan is to build something like couchsurfing, but with no users and you're just starting and you're going to charge money for it? Good luck. That sounds like a suicide mission.
</s> |
<human>: Hey, this is Michael Seibel with Dalton Caldwell. Today, we're going to talk about where do great startup ideas come from? We've picked three successful YC companies to unpack this question, Airbnb, Coinbase, and Stripe. And there are three common themes that we've seen through all three of these companies. The first, timing was important. For each of these companies, there was a pre-existing product, pre-existing competitor, dominant, you might say, but there was an opportunity to make something that was 10x better than what existed. Number two, most people, founders and investors, thought these ideas were horrible, either because they were too hard to execute or because they just were bad ideas. And then number three, and I think the coolest one of them, is that each of these opportunities turned out to be bigger than the founders even knew when they started. They turned out to be way bigger. All right, so let's talk about Airbnb. One of the things that I think is really interesting to set this up is that existing products did exist, right? Airbnb did not come up with this idea. So what were you using before Airbnb to Airbnb, Dalton?
<bot>: Yeah, for context, I think if you've only seen Airbnb, you think they came up with the idea. That's probably if I talked to my mom, she'd say, oh, Airbnb is a great idea that those founders dreamed up. But back in the day, I was already using VRBO before Airbnb was even funded by YC or existed. There was also a very popular startup called Couchsurfing, which was quite similar to Airbnb and it had a lot of mindshare, was a big network. And so it kind of felt like the third-rate entrant to a crowded space at the time. I remember when they were in NYC, that was my perspective. Do you remember that, Michael? Had you used any of those? Because I had used VRBO personally, and I thought it was pretty good.
</s> |
<human>: So another way that people screw up the accomplishing goals is not understanding how to take the L. OK, maybe you set the wrong goal. And instead of, Realizing that and setting a new goal, you cheat or do one of these other tactics to try to accomplish it because you feel as though not accomplishing your goal is a failure in and of itself. Man, I find founders screw this up constantly. It's like, you don't have to assume you're gonna be good at setting goals. Like, you can give yourself some slack. Assume you're gonna be bad at it. And like, you can adjust over time. You can set better goals over time. You can not accomplish your goals and learn from it. There isn't this, you know, sometimes in YC, I think people feel this like, oh, we're grading them on whether they accomplish their goals. And it's like, first of all, we're not grading, we're not your teacher, we're not your boss. And second of all, like, your job is to work on the hardest problem in your company. Like that, like, if you've made progress on the hardest problems in your company, you're doing well. That's the whole gist of this. It's not like, oh, did you like, Release that feature when you said you were going to, you know, that no one's going to use. Oh man. And then you talk about excuses a lot. How do people screw that up when they don't accomplish their goal?
<bot>: I just noticed a lot that when folks set goals and are not able to hit them, that's okay. But when folks are in a position where they really think it's important to make a lot of excuses on why it's not their fault and everyone else's fault, and they just have this like inner desire to tell me all the excuses. I think that's not helpful in that – again, I'm not the boss. I don't care. OK. You didn't hear a goal. Great. Let's move on. It's like they want redemption and so I just think that it's good if something doesn't work to accept it, to acknowledge it, to look at it, but realize you're the boss of yourself and you should just not feel a need to make a million excuses or have like, like create this long narrative where you're the victim and everyone else, it's not your fault and your heart was in the right place and you did everything right but everyone else was wrong. This is usually stuff about sales cycle. Well, you know, the sales cycle is just long. Like this is just too hard. And it's just when people do this, my message to them is like, hey, that's fine. I'm not saying your excuse is wrong, but like why are you spending all this energy trying to plead a case like you're in court? that the thing didn't work, as opposed to like, well, move on and make something that does work. How about that? Spend energy in a positive, proactive direction than weaving the narrative of yourself as the person who did great, but you're misunderstood by the universe.
</s> |
<human>: Here's the other one. I love this one. Dalton, I need an executive team. It's time for my company to become a real serious company. And to do that, I need an executive team. And so I'm gonna spend the next year recruiting the executive team, like it's time. I'm ready to grow up, Dalton. I'm ready to grow up. What do you think about this one? How many great executives have we encountered over the years?
<bot>: I mean, look, I think if all you do is consume like VC content, this is an idea that gets introduced into your brain. And I think maybe there is a time where this is a good answer. But it's like so much of the VC content is aimed at late stage founders, which is pretty weird. It's like putting out content that's like, you know, how to care for your your Ferrari or something. Like again, I don't really know who a lot of this stuff is aimed at. The majority of the people that consume it are like two or three person startups. And if you, if all of your advice is like hire an executive team and you have like a 3% pre-PMF startup, like, oh man, like you can get someone to leave. You can get someone with a title to leave Google or Facebook or somewhere really impressive. And you think you're like a big winner that you got someone from this cool company to join your company. But then you wake up and you're like, wow, what did I do? Like what usually happens is they either are, either they joined your startup because they weren't doing well. I'm trying to think of a nice way to say it. Either there's a reason they joined your startup and left Google, or they had expectations that you were farther along or more successful than you actually are. And they get very upset with you when they realize that your startup sucks.
</s> |
<human>: All right, we got two more types here, so two more types. Type, one is other founders. So this is becoming a lot more common nowadays, right? Like founders investing in each other's companies. It's, you know, some people have seen success doing this, others not. But what's the advice that most often you're going to get from another founder to help you when they're on your cap table?
<bot>: Usually when you get advice from other founders, it's heavily based on their personal experience. Duh. But the downside of that is if they really struggle with fundraising personally, all their advice is going to be them basically telling you, don't do what I did. Or if they struggle with distribution, all their advice is going to be around, you know, like they're almost like they have a lot of feelings about what happened to them. Again, this is, we were founders do, dude. Like a lot of my advice was heavily based on my personal experience and it only, it took years of me working at YC to sort of break out of that trap, which is to not be so autobiographical. And the things that I'm telling people.
</s> |
<human>: When we were in this situation with the founder, you know, very recently this started clicking in my head where I'm like, oh shit, like, Can we take a big step back? Do you like your users? Do you like them?
<bot>: Yeah. And people think that's weird. That's not what they expect you to say. No. Why are we talking about if I like my users? Is that relevant?
<human>: Where are you going with this? These people you're trying to build things for. Do you like them? Now, you brought this up. A lot of companies don't like their users, right? Any examples?
<bot>: Well, look, to speak from personal experience, Comcast, who dislikes their users so much, I think they renamed to Xfinity.
<human>: That's part of the rebranding. Let's try again. I don't know. Maybe they won't remember.
<bot>: Every experience I've had with them, and again, maybe you have the same one, you can tell that the whole thing was designed with the implicit assumption that they don't like their customers, and their customers are bad. And everything that you try to do they wanna make it bad. Yeah. And it seems to be baked into the whole thing, right? It's pretty weird. Well, they don't have a lot of competition. We can talk about why that is, that's probably a different topic.
<human>: It helps that they're running a wire to your house. Right. That's a big part of it.
<bot>: Yeah, I'm still a customer, let's be real.
<human>: I still pay for it. Yes, they figured out that their customer was the government that gave them a monopoly. Yeah. So that's one example. Are there others you think about?
<bot>: I mean, look, there's other stuff like that, like phone companies. But let's talk about another one we've used more often. Social media companies. Let's talk about Facebook. Facebook is known to do some user-hostile stuff. What's the term for it? Dark patterns. There's a whole field of research.
<human>: Yes.
<bot>: And again, maybe someone would say watching this, oh, well, they kind of like their customers.
</s> |
<human>: Yes.
<bot>: That is not evidence of original thinking.
<human>: No, No.
<bot>: Versus, you go read a bunch of places.
<human>: Yes.
<bot>: You digest the information, you synthesize it into your own original work. You maybe cite the sources of what you're learning from, but you actually took the time to digest and process these things. Same thing with the music industry where if you plagiarize a song, that's a problem.
<human>: Yeah.
<bot>: Like, if you just rip off someone's music, you will get sued. Right. But if you listen to a lot of music and you get influenced by some of the sounds you hear and you integrate these new sounds into the new music that you want to put out.
<human>: Yes.
<bot>: Totally cool.
<human>: That's literally, that's the game, that's music.
<bot>: That's the music business is that everyone's being influenced by everyone else. And so again, the really important thing to tease apart is copying completely without thought or anything original thinking or original work, versus being influenced and borrowing good ideas to integrate into your own thing. Right?
<human>: Doesn't the thing that suck about startups is that you do have to think about a lot of things. There isn't just, you can't just copy and paste. There's a checklist. You do have to think carefully, but I think that's why really smart people are attracted to it. Yeah. Because you have to think really carefully.
<bot>: Yeah.
<human>: It's an amazing test of your skills. All right, great chat.
<bot>: Great, thanks.
</s> |
<human>: But, yeah, you know, it comes back to that. Like, the best founders are disciplined. What you talked about is that's discipline. Right. That's doing the right thing when no one's forcing to you or no situations forcing you to. And I think that too often, genius is mistaken for discipline. It's like, you know, a lot of people think, oh, this person out executed all their peers because they were smarter. And it's like, that assumes the peers were actually working on the thing they said they were working on, as opposed to, like, hiring and going to conferences and talking to reporters. Discipline to avoid the distractions. I mean, that should be comforting to a lot of people. It's like, yeah, for every ounce of discipline you have, you can probably lose 5, 10 ounces of intelligence and still outperform, you know?
<bot>: Yeah, that's a great point. It's funny how many people that we see, again, let me think how to phrase it with, like, you'd think they'd be really good at a lot of things, but they. I'm not sure what they do with their time. They have a great resume, but it appears they just don't really do work. And the people that sit down and do the focused work. And again, we all know what this is like. And think back to college. Lots of reasons to not work on something. If you could bottle up those moments where you're actually doing focused work, the people that succeed just seem better at that. That's actually the criteria that they seem better at. If you looked at their calendar, if you shadowed them or something, the folks that are really good at this are just better at doing focused work, and it's kind of nothing else. I mean, or at least.
<human>: Yeah. And by the way, you can't. You can't really change your raw intelligence, but you can get better at this. Like, this is a little bit like, working out like you can. You know, if doing focus work for someone who likes to procrastinate is a little bit painful, the more they do it, the less painful it gets, you know? And so, hey, you know, smart people certainly have an advantage, but, man, hard workers. Oof. Hard workers are dangerous. Hard workers are dangerous. Lazy people are, you know, as a startup founder, lazy people, lazy competitors are your friends.
<bot>: Yeah. It's good when your competitors are focused on the wrong things.
</s> |
<human>: Tell a Google story because I think this one's like the like really like.
<bot>: So look, for the Facebook story, that was firsthand where I personally witnessed the servers with my own eyes. So I'm 100% confident that is what happened because it was me, right? This Google story is secondhand. And so I may get some of the details wrong. I apologize in advance, but I'll tell you this was relayed to me by someone that was there. All right. You ready? So look, The original Google algorithm was based on a paper that they wrote, which you can go read PageRank. It worked really well. It was a different way to do search. They always didn't have enough hardware to scale it, because remember, there was no cloud back then. You had to run your own servers. As the internet grew, it was harder and harder to scale Google. You still with me? Like there were just more webpages on the internet. So it worked great when the web was small, but then they kept having more webpages really fast. And so Google had to run as fast as they could to just stay in the same place. Just to run a crawl and re-index the web was like a lot of work. And so the way the work at the time is they weren't re-indexing the web in real time constantly. They had to do it in one big batch process. back in the day, okay? And so, there was some critical point, this was probably in the 2001 era, again, this is secondhand, I don't know exactly when it was, but there was some critical point where this big batch process to index the web started failing. And it would take three weeks to run the batch process. It was like the, you know, reindex web.sh, you know, it was like one script that was like, do Google, you know, and it started failing. And so they tried to fix the bug and they restarted it and then it failed again. And so the story that I heard is that there was some point where for maybe three months, maybe four months, I don't remember the exact details, there was no new index of Google. They had stale results. So anyone, any user of Google, they didn't know that, you know, the users didn't know this, but any user of Google was seeing stale results and no new websites were in the index for quite some time. Okay. And so obviously they were freaking out inside of Google. And this was the genesis for them to create MapReduce, which they wrote a paper about, which was a way to parallelize and break into pieces all the little bits of crawling and re-indexing the web. Hadoop was created off of MapReduce. There's a bunch of different software use. And I would argue every big internet company now uses the descendants of this particular piece of software. And then it was created under duress when Google secretly was completely broken for an extended period of time because the web grew too fast.
<human>: But I think this is the most fun part about this story. When the index started getting stale, did Google shut down the search engine? Like that's the coolest part. Like people just didn't realize.
<bot>: They didn't know. And did they build this first? Again, in terms of do things that don't scale, did they build MapReduce before they had any users? No. Like they basically made it this far by just building a monolithic product and they only dealt with this issue when they had to.
</s> |
<human>: Like what are some other examples of quote-unquote gambling out there?
<bot>: Well, think about it. Okay, so poker is a game I played a lot. I'm sure you have too. And in poker, the rules are it's okay to bluff. and you're rewarded. Like the game is to manipulate other people around you to do dumb things. It's not hard to take one extra step to do that kind of behavior outside of poker. And so there's a whole variety of both legal and non-legal confidence games where essentially the way you win is to manipulate people and get them to do what you want when you want them to do it through any means necessary. And Yeah, I think that is rough. And a lot of people do some version of that. I guess maybe we all do to some small extent, but some people really take that to the extreme of making their entire living by fooling other people more or less, right?
<human>: Well, it's crazy because you're talking about legal versus illegal, but back in the day in the US, I was reading this biography of Morgan Stanley and like, One of the things that happened in the early 1900s before a lot of the financial regulation is that banks would regularly kind of sell really bad paper, really bad debt to unassuming normal Americans, make a lot of money in the transactions, I think the one example I read, it was some country. Some country was speculating, they sold a bunch of debt, they couldn't pay it back, and a bunch of Americans just lost the money. The bank for selling the transaction did fine. The country, well, they can always print more money. It's interesting because in that time, doing that was not illegal. Like it wasn't illegal for the bank to resell something to normal people when they had knowledge that it was bad paper. But those people didn't. And it's funny how many of the financial regulations today come from people in the finance world basically doing zero-sum games and like harming normal Americans. And harming them so much to the point where they're like, you know what we should do? We should like get a law passed because this is crazy. Like this doesn't scale. Like this can really screw a country if you let people play these zero-sum games to the extreme.
<bot>: Yeah. And there's some amount of like lack of empathy or viewing of intentionally wanting to victimize other people. There's some dark stuff along that whole line of thinking. I think if you feel that you are smarter than other people, and this is something we encounter sometimes in our jobs, I think if you feel that you are more intelligent than others, perhaps you can end up on the slippery slope of moral arguments that it's okay for you to make a living off of other people's work because You use your intelligence, your superior intelligence to get them to go along with this, right? You've seen this a lot. They kind of feel like that's freedom.
</s> |
<human>: The next area of prevention, you have to learn how to have hard conversations with your co-founders and for everyone to be okay afterwards. Everyone has to go through this and it's going to suck. But if you have some of those in the bag, when you get punched in the face, you all know a little bit more how to interact with each other. And to me, the biggest challenge that I've seen on this front, and we've talked about this at YC quite a bit, is this anxious, personality type versus avoidant personality type. You know, when people are challenged, people are frustrated, and this is way over simplification, but sometimes people are anxious, they wanna deal with the problem right now, they're leaning in, they wanna talk for, they've talked for two hours with you, and they wanna talk for another two hours with you. And sometimes people are avoidant, and, you know, after five minutes, they're done. They wanna think about it for a long time. They'd rather talk asynchronously. And I actually see that most problems between co-founders The root cause isn't whatever went wrong or whatever they're debating. It's actually their style of dealing with their frustration. And if you can have a little empathy if the person who you're working with has a different style of dealing with frustration than you do. and you can just take a beat, right? I'm the anxious type. You know this, Dalton. I wanna talk about it for six hours, then six more hours. I wanna plan, I wanna write it down right now. Go, go, go, go, go. And I always get into trouble when I'm interacting with someone who reacts negatively to that. And I always have to kind of be like, fuck, I gotta take a beat. In this situation, I gotta take a beat. And so, in my experience, If you can figure out that dance with your co-founder, it's so much more helpful when you're dealing with these external challenges. And like, the startup's going to present many opportunities for frustration with your co-founder, right? Like infinite opportunities.
<bot>: It's like the whole topic today, which is eventually you're going to take punches. You're going to have setbacks with your startup. Eventually you're going to have conflict with the co-founder. 100%. And the thing that you're disagreeing about isn't even the thing. Who cares? It's noise. It's like roommates. Did you put the dishes away? It's not about the thing. It's not about who's right or who's wrong. It's funny because a lot of people want to ask us advice about co-founder stuff. But what they want is us to agree that they were right and their co-founder's wrong.
<human>: You love that.
<bot>: They're like, Dalton, can I tell you about this situation? Basically, I'm smart. My co-founder's dumb. What do you think I should do about it? And it's like, no, no, no, no, no, no. I'm not going to take the bait on that. The actual thing that you need advice on, a thing to work on, is the meta conversation, which is like, how do you deal with conflict? so that people feel good when it's over. Otherwise, whatever the, you know, not cleaning up your dishes or taking the trash out, whatever the equivalent of that is in your co-founder relationship, eventually it's not gonna work out, man, right? You gotta have tools, because there's gonna be more issues.
</s> |
<human>: Welcome to Dalton and Michael. Today, we'd like to do a follow-up on a video that we recorded a year ago. That video was why you should leave your fang job.
<bot>: We all know these people that want to just tell you their darkest secret, which is they wake up every day and they like dream of quitting. Like they have fantasies of quitting every day. Those are people that probably should quit.
<human>: This video is why maybe you should leave your failing unicorn startup. Oof. Tricky topic.
<bot>: And let's say signals. We don't know. We don't have all the information. But there might be some hints. There might be some signs you want to be looking for that it might be time to reach greener pastures.
<human>: And if you're an employee of one of these companies, you probably have the best perspective, a better perspective than investors, maybe sometimes even better perspective than founders on what's really going on. So maybe we should start this by saying there are 1,400 unicorns now. Is that right? Yeah. Wow. Well, I'll ask you. I don't know what you think. Do you think all 1,400 will go public successfully?
<bot>: I think the odds are pretty slim that they're all doing amazing. Yeah. I think that's a fair statement. I think that's a fair statement.
<human>: And so if you kind of divide this out, even if you're really optimistic, what do you think an optimistic count What percentage of the 1,400 were being super optimistic, they do an IPO, and everyone's really happy? A third? I'm just making this up. A third? A third. Great. So in that case, two-thirds of that 1,400, it's not going to work out. And I think what's unfortunate is that when things don't work out, employees usually don't.
<bot>: They are. Yeah. And the who takes one for the team, they're usually in the category of the team. Right.
</s> |
<human>: Cruise, perfect example. I remember getting into a cruise car with Kyle, driving down 101. And he said to me, uh-oh, there's a shadow in the road. Let's see how we handle this. And I'm like, oh, fuck. This is an MVP. Shadows, eh? Haven't thought about that. Yeah, haven't thought about shadows in ever when driving. And I remember when Cruise did their kind of first open launch, and I got into a Cruise car with my wife, and it just drove us to where we were going. And I remember for the first minute 30 being like, I can't believe this is the same. I can't believe this is on a continuum that started with me being afraid of shadows and now it's like.
<bot>: I actually care about that stuff a lot. If I just think about growing up about just the number of people that I knew that died in car accidents and the number of people that every day get seriously injured or die in car accidents. I think we're going to look back and be like, that was crazy barbaric. That was like having surgeons that didn't wash their hands. Literally. In that era. Yes. Is, I think, how we'll look at some of this transportation stuff. Yes. Right? And we're right on the precipice. It's happening now. It's not like everyone's even excited about self-driving cars. No. It's like, oh, I don't know about this whole self-driving car thing. Drunk drivers aren't that bad, are they? Yeah, yeah.
<human>: It's only tens of thousands of people who die a year in America.
<bot>: It's like, whatever. And so you should, I would expect people to be pretty excited about this. Yeah. But it's seen as sort of this neutral or divisive issue instead of something that's kind of awesome.
</s> |
<human>: Taking a big hit to your growth rate in order to get to default alive. It sounds a lot like bankruptcy. It kind of sounds a little bit like personal bankruptcy, where it's like you take a hit on your credit score to kind of clear your debts. And the benefit though, is you clear your debt like you are now living sustainably as opposed to unsustainably. Now, here's why it's better than bankruptcy. I think in a traditional bankruptcy, it takes seven years for your credit to kind of get repaired. The startup world works a lot faster than that. So at any given time in your startup, you're being judged on the last six to 18 months. And so if you take this hit, you cut your revenue in half, but you get to default alive. And the result of that is you get to spend the next six to 18 months building a better product, getting closer to product market fit, or getting product market fit. You're going to be judged on just that last six to 18 months. You're not going to be judged on when you had a horrible business that was burning more money than it was making structurally, and you're going to have a huge advantage. And what's tricky was this was kind of our story at Justin tv and twitch almost exactly like.
<bot>: Yeah you had the choice, you looked into the precipice, you guys could have jumped in, you could have just let it go.
<human>: Like, right, you could have let it go. So, I mean, we had raised about seven or $8 million. We had grown to about, I don't know, let's say like 30 million monthly. People were watching content, we were making about $750,000 a month in revenue, but we were, we had a million dollars a month in expenses. We were burning $250,000 a month. And I swear to God, like, the come to Jesus moment was with half a million bucks in the bank. And I always love this, because as YC founders, we don't talk about these mistakes and want to give you the impression that we didn't make them. Like, we made this exact, we were right there.
<bot>: That's what you love about investors, is they're like, oh, I know everything. They taught me this at McKinsey and Harvard business. Like, like, that's what's nice about being former founders, is. Yeah, man, we got all this shit wrong.
<human>: Yes. Like, no one is actually playing right towards the mountain. Like, straight up, like, deep, deep mountain, not top mountain. And we, I remember we had this meeting with a lot of our employees, and we were like, look, we got three options. We can die in two months. We can try to get to break even, or we can try to get this thing profitable. And I remember, like, I had to call this meeting, and it was one of the most embarrassing things I've ever had to do upfront because I'm just, like, talking about admitting defeat. I'm like, here's the thing. We're gonna die.
<bot>: We messed up. We blew it. I'm bad at my job.
<human>: Exactly. I'm raising my hand. I suck at this.
<bot>: Hey, guys, I led us astray.
<human>: Yes. And I remember thinking, and I think this is the silver lining. I remember thinking, I have no idea whether everyone's just gonna quit or whether they're gonna rally. And everyone rallied, and it shocked me. But then, like, I thought about it more, and I was like, what kind of person joins a fucking startup, right? It's not the kind of person who's like, well, I don't see any risk here. Like, this seems like smooth sailing all the way, right?
<bot>: These are very mature veterans.
<human>: Absolutely not, right? And so, you know, we selected for the right people on the pirate ship, right? Like the pirate ship. They knew they were on a pirate ship. And I remember everyone was like, we are going to get this thing profitable. We had to do some bad stuff. We definitely had to let go of some people. Our version of raising prices. We had to put ads on everything. Like, we put pre roll video ads on anything that moved. I remember it was, we had this, we literally had this easel with a big piece of paper on it. And I was like, on this side, we're going to write down everything we can do to cut costs. On this side, we're going to write down everything we can do to make more money. And we're not going to leave this shitty little conference room until there's $100,000 of revenue somehow of profit here. And what's crazy is that we had that meeting in August. By October, we were breakeven. By the end of December, we had generated $1.2 million in profit, and we saved the company. And I remember the feeling of not needing VC's anymore. And let's be clear, that's not the last time we pitched VC's but just, it was the last time that I feel, well, it wasn't the last time. There was a nice little window where for a second, we didn't need VC's to like us in order for our business to be alive.
<bot>: And like, and what's funny, man, is that was the moment you were actually tested. And you guys, like, you, your co founder, like, that was it in retro, in hindsight, you guys had a choice and you did. You took the l, you took the hard, hard, but now here you are and that was like really smart. And we just see so many folks that don't do it. They have that, it's like sitting there in front of them, the hard move, and they don't do it for whatever reason.
<human>: Well, and what's crazy is the idea for twitch happened after that. And like, I, it makes sense in hindsight, why, like we were, if you're not just freaked out about dying all the time, maybe you can apply your brain to like, how to make this thing work. I think sometimes it's okay to do a startup bankruptcy. Like, sometimes it's okay to take that l get to sustainable and figure shit out. And especially if you've raised, like, you.
<bot>: See people that raise and again, like, let's keep picking on fast. Like, they could have just not spent the money. No one forced them to.
<human>: Seven months in, they could have stopped spending the money and they'd still have a ton of money.
<bot>: Yeah. And so there's some amount of like, playing along, like, there's some amount of like, founder choosing, making a proactive choice to not course correct, because they believe the fundraising to come in. And again, this is the point of PG's blog post, which is don't do that. Right. And sometimes, you know, this is what happened at my startup and this would happen. This is what happens to the delivery ones is you have contractual, like, lease obligations. Kill people. I had deals with the music industry and there's nothing, literally nothing I could do about that. And that sucked, you know, and so to the extent you have a startup that doesn't have contractual requirements to burn lots of money like WeWork or something, you know, I'd recommend not starting one of those, but if you're in one, you should be really careful of this stuff.
<human>: Yes. Well, by the way, venture dad is similar. Right. We're like, damn. Like, right when you're hurting, you gotta start paying more money out.
<bot>: And they can very, very similar.
</s> |
Subsets and Splits