Y CombinatorTokenmaxxing: How Top Builders Use AI To Do The Work Of 400 Engineers
EVERY SPOKEN WORD
40 min read · 8,385 words- 0:00 – 0:47
Will you control your AI?
- GTGarry Tan
I think that's like the defining question. Like, will you have control over your own tools or will your tools have control over you? Using OpenClaw these days is like driving a Ferrari, and it's like exhilarating. It's insane.
- SPSpeaker
Mm.
- GTGarry Tan
Like, you get to do things-- Like, it, it figures things out you would never think a machine could figure out, and it does it so quickly. But then it's also like a Ferrari in that you better be a mechanic. Like, it's a Ferrari that will break down on the side of the road, you know, when you most need it, and you need to get out with your wrench and pop the hood and, like, fi-fix it. You know, you're gonna have to fix it yourself. And so this is a very exciting time in, uh, computer science and technology. [upbeat music]
- 0:47 – 1:56
Coding again after 13 years
- JFJared Friedman
Welcome back to a special episode of The Lightcone. In this episode, we're going to talk about how Garry Tan got back to building. If you follow us on Twitter, you'll know that after a multi-year hiatus to become an investor, Garry Tan is back to being a builder, and in the last couple months, he's shipped hundreds of thousands of lines of code and built popular open source projects that have gone from nothing to more than 100,000 stars on GitHub. And he did all of this while having a very demanding job running YC full time. A lot of people on the internet don't even think that this is possible and are somewhat, like, in disbelief. But it actually happened. We know because we were here to see the whole thing. And so today, we're going to talk about how he did it.
- GTGarry Tan
Well, I'm relatively, uh, shocked myself. [laughs]
- JFJared Friedman
[laughs]
- GTGarry Tan
I'm amazed as well. It was 13 years of not coding, and then suddenly, boom, I'm doing about 400x the amount of work that I was that year the last time I was even sort of, like, two-thirds of the time writing code.
- JFJared Friedman
Maybe to start things off, how about we go back to the project that started it all off, which was Garry's List-
- GTGarry Tan
Oh, yeah
- JFJared Friedman
... and just, like, talk about a few months ago how you powered up Claude Code and, like, started to get back to coding.
- GTGarry Tan
Yeah.
- SPSpeaker
And it was right after one of the Lightcone episodes, right?
- 1:56 – 5:50
Rebuilding a startup with Claude Code
- GTGarry Tan
Oh, yeah, definitely. I realized that I wanted to bring together all the people who believed what I believed, um, particularly for California. And so I started a, uh, 501C4, and now it's a C3 and a PAC, which is sort of what a lot of political groups do. Um, it's a very common way to bring people together. You know, everyone focuses on the money, but we're trying to bring together smart people. Um, you know, what I learned in the years of working in San Francisco politics is that bringing together people is so powerful, and, uh, that's what a mass social movement is. And I said, "Okay, well, why don't I just make a website where we start doing that?" And it would just start with, um, why don't I start writing about the issues that I'm worried about? It's like I want children in school. You know, people watching this from all around the world might find it very, very strange, like I find it strange, that, uh, it was not possible and still very, very hard for a seventh grader or eighth grader in middle school in San Francisco public schools to be able to take algebra. And that was, you know, a math education thing. Like, you know, if I didn't get to do that when I was in public schools in the East Bay of the Bay Area, there's no way I would've studied engineering at Stanford. I never would've written code. I never would've been able to do any of these things. So it was close to my heart, and I realized, like, "Hey, it's time to write code," and I ended up building Postrous, my first YC startup from 2008.
- JFJared Friedman
What, what was Postrous for people who don't-
- GTGarry Tan
Yeah
- JFJared Friedman
... remember it?
- GTGarry Tan
Yeah, Postrous was, uh, dead simple blogs by email. It grew to be a top 200 website on the internet, and then Twitter ended up buying it for about $20 million. So that was sort of like my first bag, [chuckles] really. I actually built it again, uh, as Posthaven when Twitter, um, you know, bought it for the amazing people that we had hired, and, uh, they shut down the startup. It would've cost a couple million dollars to buy it back from Twitter, and at the time, I had no money in the world. So the next best thing was, why don't I write it again? And then, uh, in January of this year, I ended up writing it a third time. Um, only, you know, the first time it took about, you know, $4 million and, you know, six or seven people and about a year and a half. And then the second time it, you know, took about, I don't know, 100 grand and two people, me and my co-founder, Brett Gibson, who now runs Initialized, um, and maybe, like, three months or so. And then in this case, it took about $200, which was my Claude Code Max account, and probably five days. Full-featured blog platform, does everything you want, and then on top of that, like, full rag, full, um, agentic retrieval, like, be able to, you know, sort of go out and read all of the internet, like every tweet I've ever done, recursive crawl, deep research of any topic. The algebra thing is just one of a whole lot of different issues that we really, really care about, and to be able to go ingest the internet, you know, see all the arguments for and against, and then to craft incredibly detailed, um, reports on the back end about, um, what are all the quotables. Like, I think people who are big followers of The Lightcone might remember one of our first episodes about agentic, uh, systems with Jake Heller, actually. So Jake created case text, and he described exactly what I ended up building for basically journalistic, uh, long-form articles about any, you know, sort of issue or, uh, you know, piece of news that was happening. And so, you know, anyone can go to garryslist.org today, and, you know, we do aboutTwo or three relatively, you know, researched, all fully sourced, um, articles about what's going on in California and San Francisco and LA, and, like, how do we build a better government?
- 5:50 – 7:09
Software that thinks like a journalist
- GTGarry Tan
And-
- SPSpeaker
Yeah, this is the thing I feel like people missed about Garry's, or don't fully get, is that it's like the classic thing we've been talking about here, which is, like, software was you build software to let people use it. So it was like you build a blogging platform and people, like, write blogs and maybe, like, they'd start their own Substacks eventually or they, like, write articles. But Garry's List is both blogging platform, but it actually does the work of a high-quality investigative journalist. It's not just something that a journalist uses to publish their articles.
- GTGarry Tan
Yeah. I mean, basically the, for the equivalent of, like, five or $10 of Opus calls, I mean, I would estimate that it does the work of, like, you know, a real human being that would have to, like, go painstaking through dozens of articles, read entire books about certain subjects, uh, annotate them. I mean, going back to the case text example, like, the thing that Jake taught me was that you need to think about what a human would do with the context given. Like, what would it retrieve? Like, does it go to the library? What kind of book would it look for? What does it search on for search, you know, on the web? I mean, the great thing now is, like, you don't have to just do that. Like, you can get Perplexity's API and you can do deep research there. You have X's API, you can do deep research there. You know, Groq's API, if you need to, like, do research on X using the Groq API, is actually very, very
- 7:09 – 10:07
The rise of “tokenmaxxing”
- GTGarry Tan
good, and you can just grab all of the context. This is sort of going back to the philosophy of, uh, boil the ocean, which is one of my essays. It's like, particularly when building agentic software now, you don't have to settle for, um, what we did when we were humans writing the code. Like, and that goes for research as well. What if you absolutely boiled the ocean? Like, what is, you know, the total completionist? Like, if you were a human, this would take you about a month to do this research. You can just, you know, zap the rocks harder. Uh, you know, it... You pay more money and you might be token maxing, but you should token max. Like, basically if there is incremental work that makes something more complete, more awesome, more... You know, in the case of, um, this type of writing, like, we want it to be more representative of reality. Like, you know, we don't just settle for one source when we can get 20 sources, and we can cross-reference them. We can figure out, like, well, these 13 sources say this, and these 7 sources disagree with that. And then, you know, you wanna feed all of that context into, like, your core prompt, and then you can basically make a better decision than what you would, like, just, you know, a human being clicking on a link, reading a headline, and that's all you understand. And I think if you token max, like, that's actually the coolest thing you can do now, and it's not just in, you know, generating articles. It's not... You know, it's clearly in, uh, writing code, right? I think now it's, it's going to permeate every part of society. Like, everything that we would call knowledge work could be token maxed. And, um, I don't think that it means that we're gonna get rid of people. I think it means that people need to s- still supply, uh, the agency. Like, I need this. Like, I'm the one who's sitting here caring about algebra. Like, I want kids like me who couldn't afford private school. You know, San Francisco is the one city in the world that has the highest rate of private school attendance, um, probably in the entire country, actually, and that's not okay. Like, you shouldn't have to be rich to have a good education and, you know, I don't know why that's controversial. And so for me, it's like this, you know, mass sort of shift in technology was happening, and then, uh, I had a need and a want and a desire, and it was a burning desire. Like, I... It hurts me and pains me to think about 10, 12, 13-year-old kids who don't know algebra and, like, could have, but, uh, some bureaucrat or, you know, some virtue signaling person in power says, like, "Actually, I don't want that kid who wants to learn algebra to learn it."
- SPSpeaker
So I think in this process of basically solving your own pain and need from the young Garry and building Garry's List, you sort of discover a lot of patterns on token maxing and this new way of building that led you to the next project, which was, uh, GStack.
- 10:07 – 14:21
The accidental creation of GStack
- GTGarry Tan
Like, I actually did not plan to make GStack. All I did was, like, I, uh, realized that I was doing the same things over and over again, and then I got sick of typing the same thing, so I went into my Apple Notes. I typed in all the things that I found myself writing over and over again into Claude Code, and it was pretty simple stuff. It's like, here's the plan review. One of the things I started doing is I really love asking Claude to make ASCII art diagrams. One of the things I discovered is, um, sometimes Claude would just get confused and, like, write bugs or not be complete. But once I started saying, "Actually, before you start your work, make an ASCII diagram of all the data flows, all the inputs and outputs. What are the user flows? What are the error messages?" And you can see this. It's like data flow, state machines, dependency graphs, processing pipelines, decision trees. Once it did that, it loaded all of the context in, and then it just did the work more completely. Like, it boiled the ocean better. And it broke down into a bunch of different sections, like here's architecture review, code quality, test. I mean, one of the things I learned building Garry's List was that when I was writing the code myself, I would always do the minimum amount of testing, 'cause it was just, like, not very fun. I knew I needed to have it, but I'm here to write, you know, fun, new code. I, you know, did not like write, to write tests. And then honestly, like, I hit all the things that everyone else hits when they start vibe coding, which is like, this is slop. It's not working that well. Like, it works fine for the 80% case, but if any users actually touch it, it starts falling over. And then that's when I realized, oh, I can get to 100% test coverage. I've since learned that 100% is probably too much. Like, hitting 80 to 90% is usually the best practice at this point. Um, but yeah, this, this is basically the first version of plan-eng-review. I know, uh, everyone knows the office hour skill, uh, which isYou know what people can use, and I still use when I'm trying to make a brand new product or a brand new feature. It, uh, simulates what a, what we do when we're working with a company. It's like, how do you know that people want this? You know, who's it for? What does it do? And what's the impact, right? But this is like the proto skill. Like this is... I didn't even know skills existed, and I posted this, and it went viral. Like, uh, you know, 200,000 people saw that, and then I made another version of it that was a mu- much more ex- uh, expansive version. I called it the Mega Plan, and then I ended up, um, renaming it to the CEO Plan. We've probably talked about meta prompting before. I used meta prompting here. I took the other review plan that we had, and then, uh, I said, "Okay, well, let's do a version of this, but, like, imagine Brian Chesky sitting with you," right?
- JFJared Friedman
Mm.
- GTGarry Tan
Like Brian Chesky has this great line about, uh, what is a 10-star experience? So... And you know, the point of it is everyone thinks about hotels in terms of like three... This is a two, three-star experience. This is a four-star experience. And he, like, goes, you know, through the list, like five stars. It's like everyone, you know, yeah, cool. Like, he's like, "What's a six star? And what's a seven star? And what's an eight star?" And, like, he goes all through that entire list, and, um, that's one of my favorite, like, product and design exercises to go through, like, as a mental exercise. And then the cool thing is, like, you can do that every single time now, and so that's what this is. You know, this prompt basically tries to figure out what is the platonic ideal of, uh, what this is. These are sort of like the three, the two things that are pretty awesome. One is, uh, what is the 10X check? What is more ambitious and delivers 10X more value, uh, for only 2X the effort?
- JFJared Friedman
Mm.
- GTGarry Tan
Right?
- JFJared Friedman
Mm.
- GTGarry Tan
And so for whatever reason, coming out of latent spaces helps the model, like, really visualize. Like, so I'm... Plan CEO skill I actually really enjoy because I'm an ADHD C- CEO, and I love, um, potential, like pure potential. And so this is, like, the one... Like, I can't believe this is just literally two little sentences, but, like, this unlocks an incredible amount. And so that's how G- GStack started, actually, not as, you know, I didn't want it to be anything other than like, well, I just need to make some skills, and I had heard that people were making, like, skill repos.
- 14:21 – 20:59
The workflow behind 400x output
- GTGarry Tan
But then the third thing I did was I started, um, using these two skills so much that, um, my Conductor instance was getting very backed up. So this is how I use Conductor. Uh, this is actually my real setup. Like, you know, I'm-
- JFJared Friedman
Okay, so this is your, like, daily workflow. This is how you've been shipping hundreds of thousands of lines of code a month. It's all, it's all in here.
- GTGarry Tan
Yeah, that's right.
- JFJared Friedman
Mm-hmm.
- GTGarry Tan
So I dropped like 13 PRs in the last 48 hours, and then, you know, I... You just queue them up. Like, anytime I come up with a new idea, I come in and, uh, here it is. You know, I loved using the CEO skill. I loved using the ENG skill to, like, really make it super well tested. I did that all in plan mode, uh, and then I'd click Approve here, and then, you know, Claude would go and do all the stuff. And then I did that so much that I ended up having, like, 15 different features that were all queued up, waiting for me to manually test it. Like, it passed it, uh, you know, it passed end-to-end testing. It passed, uh, integration. It passed unit tests. But, like, at the end of the day, I still need to, you know, for Garry's list, it's like pop open the rail server and, like, you know, load that user and, like, make it into that configuration for that particular user and, like, manually just make sure it works. And I got sick of doing that, and I was trying to use, um, Claude in code MCP, and it was very, very slow.
- JFJared Friedman
Mm.
- GTGarry Tan
Two to three seconds for every turn.
- JFJared Friedman
Yeah.
- GTGarry Tan
And I was like, this is not usable for QA. But I had heard that Microsoft had released Playwright, which is sort of, um, an alternative testing framework. In retrospect, it's like actually there was, like, Agent, uh, there were, like, Agent Harness and, like, all these other, like, tools that I could have used. But the upside and downside of Claude Code is it's so easy to just start something that I just popped open. Like, I literally went in here, and this is probably what I did. It's like, "I'm so sick of using Claude." [laughs]
- JFJared Friedman
[laughs]
- GTGarry Tan
"Claude in, in Chrome MCP, it's too slow. Let's go ahead and wrap Microsoft's Playwright." [laughs]
- JFJared Friedman
[laughs]
- GTGarry Tan
"Can we do that?"
- JFJared Friedman
[laughs]
- GTGarry Tan
And then I just pressed Enter. And then, you know, one of the things that emerged with GStack is that, like, this is how I create new features now. Of course, you know, what it's gonna do now is like, "Hey, dude, you already did that," which is hilarious. You know, I have bug fixes right next to giant features. And then, um, the way GStack works, there's a CEO, there's a designer. There's actually a developer experience person in there.
- JFJared Friedman
Oh, okay.
- GTGarry Tan
There's a number of design tools, uh, and then plan ENG is the last one. And then I actually usually run /codex, and, um, I recently added a /claude in Codex.
- JFJared Friedman
Mm.
- GTGarry Tan
So one of the cool things that I actually learned from, uh, YC alums, I came to an event and brain totally frazzled, but, you know, went to one of our batch events, and we were just, you know, shooting the shit about what's going on with Claude Code versus Codex. And at the time, I was a total Claude Code only guy.
- JFJared Friedman
Mm.
- GTGarry Tan
And, uh, I realized, oh, a lot of people actually prefer Codex. Why is that? And I discovered that Claude Code is ideal for the ADHD CEO. But once in a while, there's a, you know, Claude Code will just BS a bunch of stuff. Like, Claude models are very, very good, but, like, they are not the smartest, it turns out. And so a lot of people, you know, explained to me that if you have a problem that's much crazier, you need the 200 IQ, nearly non-verbal CTO.
- JFJared Friedman
[laughs]
- GTGarry Tan
So you can just call in a friend, and then that's what, like, /codex is. It's a, you know, GStack skill that takes whatever plan i- y- your plan is, or if you're out of plan mode and you already implemented, it'll take your repo, and it'll run Codex in a command line prompt with the prompt that says, "Find all the problems and all the bugs," and it reports it back to Claude Code, and then you and Claude Code can work through those feed- that feedback. Uh, and then I have since added, if you use Codex as your main coding agent, you can actually go and type /claude and have Claude come and be the CEO briefly, [laughs] if you want as well. The cool thing about GStack is when I run it through this program, like, I always, I do, I start with office hours, CEO review. Like, I do design if there's UI. If, um, I know a developer needs to use it, which is, like, practically all of GStack and GBrain stuff, I run the developer review, and then I do ENG review, and then Codex. Once that plan is done, I've worked through all of the issues. The GStack relies very heavily on ask user question. So, 'cause, you know... And that's, that to me is, like, really important. That's where the human, you know, vibe coder or operator, agentic engineer needs to supply their understanding of what's going on, what are we building. There's not really a substitute to that. It would surprise me very much if someone really truly did manage to make a thing that could just make software without the human in the loop.
- JFJared Friedman
Mm-hmm.
- GTGarry Tan
Like, that, you know, it's controversial take, I think.
- JFJared Friedman
Mm-hmm.
- GTGarry Tan
But, um, I never want to be entirely out of the loop. I just want the machine to do the stuff that I don't wanna do. And so, you know, basically QA is a good example. And, you know, I mean, that's hilarious. Coming back to the demo, it's likeI type something into the modern version of GStack, and it's like, "Dude, what are you doing?" Like, "We already built that."
- SPSpeaker
Yeah. [laughs]
- GTGarry Tan
We have Browse.
- SPSpeaker
Uh-huh.
- 20:59 – 24:35
Thin Harness, Fat Skills
- GTGarry Tan
Yeah. I mean, some of it came out of, uh, being trolled on the internet relentlessly about markdown, and like, I, you know, I'm just, like, peddling a markdown, a set of markdown. And it's like, you know, I guess my lived experience at this point is that markdown is actually code. It's just, like, this-
- SPSpeaker
Mm
- GTGarry Tan
... compiled in a different way. But, like, you can get the computer to do really astonishing things. Like, I mean, even this. It's like, could we have imagined that I would be talking to something that has replaced Visual Studio for, like... I, I don't use Visual Studio at all.
- SPSpeaker
Yeah.
- GTGarry Tan
Like, there's no reason to, like, when I can talk to my agent, and my agent can do this, right? The article actually na- the name actually came from, uh, our partner, Pete Kuman. We have had to build an internal agent, and, uh, you know, we call that the harness, over and over again. And then at some point, using Claude Code all day, we realized, like, you know, why should we rewrite a version of that over and over again? Like, you know, we should just use the things that are really awesome as, you know, harnesses. Like, a harness is the core loop that takes the user input, gives it to the LLM, runs what the LLM does. Like, it can do tool calls and things like that. I mean, why would we build that? Like, what we should be spending all our time doing is thinking about what markdown should there be. And the way to think about markdown is if you're an event planner and throwing a wedding, and you're trying to write down a checklist of how to throw a wedding again, like, what would you, what would you write in plain English to teach the next person who had to do it what to do? All of that should be in the markdown. Whereas, um, all the things that should, you know, be deterministic, like, um, I mean, or is a, is a real action. Like, a, a wedding planner might have to call, like, 20 venues, right? But you wouldn't use markdown for that. Like, you would make a, you know, a call to Twilio, for instance, right? There's, like, a l- you know, sort of all of the difficulty in agentic engineering today is when people try to do things that should be in markdown in code, and it fails because code is brittle. It doesn't understand special cases. It do- actually, you know, code literally doesn't understand what you want or who you are. It is like, you know, executing deterministic zeros and ones in a Turing complete loop, right? Like, it doesn't know. But then now we have LLMs that have latent space, and they know who you are, and, uh, it knows what your motivations are, and it can handle generic cases. And then, you know, a lot of the, the magic right now as an engineer is, like, figuring out, okay, how much of it is over here in LLM land, and how n- how much of it is over there in, um, code land? And then, you know, if you combine that with the other thing I learned, which is, like, get to 80 to 90% tests. Like, if it's not tested and you're just throwing users in there, like, it's slop. You know, 10X worse than, like, human written code, 'cause, like, you just have no idea what's going to happen. Um, and so that's, like, one of the things that people have to do. It's like, all right, not only do you need to figure out what's going on in latent space and deterministic space, you also have to make sure that, like, it's, you know, uni- individually tested, and then the integration is tested. And then going back to, uh, boil the ocean. Like, the machine doesn't care. It'll just do it. It's amazing. Like, just zap the rocks more, and you can get to 90% test coverage. And then you can have a system that, you know, is not quite perfect. Like, you know, OpenClaw right now, um, there are lots of, like, failure cases, but it's 95% there. You know, it's, uh, I feel like using OpenClaw these days is like driving a Ferrari, and it's, like, exhilarating.
- 24:35 – 27:12
AI agents are like Ferraris
- GTGarry Tan
It's insane.
- SPSpeaker
Mm.
- GTGarry Tan
Like, you get to do things... Like, it, it figures things out you would never think a machine could figure out, and it does it so quickly. Uh, but then it's also like a Ferrari in that you better be a mechanic. Like, it's a Ferrari that will break down on the side of the road, you know, when you most need it, and you need to get out with your wrench and pop the hood and, like, fi- fix it. You know, you're gonna have to fix it yourself. And so this is a very exciting time in, uh, computer science and technology, 'cause it's like, this is Homebrew Computer Club, uh, you know, the moment when the Apple I came out. Like, the Apple I created by Steve Jobs and Steve Wozniak was a breadboard inside, like, literally a wooden case hammered together with, like, nails and duct tape, you know?And, uh, if you wanted a personal computer, that's what you had to do, and that's where we're at right now. Like, you have relatively, you know, smart technical engi- you know, people who had to study computer science have to spend, like, two or three hours and, like, maybe, like, 500 or $1,000 in both tokens and cloud to actually get something like that running. But, like, once you get it, it's like we're sort of in the kit car Ferrari phase. [chuckles] It's like, then you can drive, and you can go anywhere and, you know, you want, you wanna shout to the hills like, "Hey, I got a Ferrari."
- SPSpeaker
Even the part about fixing it yourself, I feel people, um... It's just, like, one of those things until you've, like, pushed through, you just don't quite get. If I really zoom out, it's almost just like things have moved so quickly. Like, if you think way back, just having Stack Overflow as a website that you could consult when you got stuck on a programming problem felt, like, amazing. And then it's like a, like, ChatGPT launches, like, oh, now I've got this, like, interactive thing that's way better than Stack Overflow. But you're still sort of doing the same thing. You're, like, asking questions, and you're copy and pasting code, and you're running the code and seeing what happens and copy and pasting it back. And then you sort of, with Claude Code, you sort of push through, and you realize that you don't need to do the copy and pasting anymore. It just, like, actually, like, executes and runs the code. And then even with OpenClaw, I found out when I set it up, yeah, it's annoying 'cause it can, like, effectively brick itself, and it does a bunch of annoying things. But if you actually have, like, Claude Code, like, sort of-
- GTGarry Tan
It'll fix it
- SPSpeaker
... V- yeah, if I just have Claude Code running, it will just-
- GTGarry Tan
Yeah
- SPSpeaker
... like, fix it. And I... It's clearly not the way things will be long term, but there's just this mentality shift of it doesn't actually matter if it's brittle and, and requires fixing, 'cause you can actually just have another agent, like, sat there, like, fixing it all the time.
- GTGarry Tan
Yeah. I feel like this evolution, I was, like, completely Claude Code pilled, uh, and still am, but, like, probably only, like, 50% or 60% of my time, like, building product, um, or agentic engineering is in Claude Code now. At some point-
- SPSpeaker
Oh, wow
- GTGarry Tan
... basically-
- SPSpeaker
Almost half of it-
- GTGarry Tan
OpenClaw
- SPSpeaker
... is through OpenClaw
- 27:12 – 38:37
The future of personal AI
- SPSpeaker
now.
- GTGarry Tan
Yeah, which is very interesting. I mean, then again, I'm also spending a lot, most of my time working on Gbrain itself. So Gbrain came about because I met... You know, obviously we had Peter on the show. Um, and then I finally got around to it, and it was like one weekend I said, "I gotta check this out. Like, what's going on with OpenClaw? Let's get it going." And, um, this was about the time Karpathy wrote his X post about knowledge LLM wikis.
- SPSpeaker
Mm-hmm.
- GTGarry Tan
And so I was like, okay, well, I have a repo full of markdown. All my... You know, I should put all of my context into that markdown. And then at some point I realized, oh, shoot, it's just using Grep.
- SPSpeaker
Mm-hmm.
- GTGarry Tan
And Grep is not that good. Like, it's, you know, wasting context. Uh, it's loading a lot more into context than it needs to, and then I sort of fell into a rabbit hole. I just went into Conductor, clicked Quickstart, and then I had GStack built into-
- SPSpeaker
[chuckles]
- GTGarry Tan
... Conductor already. And, you know, basically this was how I started. I, you know...
- SPSpeaker
[chuckles]
- GTGarry Tan
It was actually much more interesting than that. So, uh, I didn't start off from nothing. One of the things I've learned as you write, like, a larger and larger corpus of code is, like, you have it loaded in your brain. You're like, oh, well, in order to build an agentic newsroom for, um, Garry's list-
- SPSpeaker
Mm-hmm
- GTGarry Tan
... I actually had to learn about, uh, vector embedding and hybrid RRF and chunking. Like, when you're in there trying to make it work, you're just, like, very applied. It's like, I have an output that I want. I want the article to look like this. It needs to be of this quality. It needs to have these citations. Like, you start building up, uh, your, you know, your tests and integration tests, and, like, you end up with, like, a product that's, like, battle tested from, like, the output that you want. And so I sort of put two and two together, and I s- you know, and this is something that, you know, anyone can do, actually. It's, like, this, like, this is why I think we're entering the golden age of open source. Uh, I could just open, you know, this project in Conductor, and then the first thing I write is, like, you know, go look at, you know, tilde/git/garryslist. Like, look at how we do chunking, embedding, uh, you know, hybrid RRF, RAG, like, all of this, and then just, like, extract it. And then I wanna use Postgres with pgvector, and, like, I want a, a, you know, full RAG system for my OpenClaw. And then it sort of, like, one thing led to another. It's like, then I have, you know, 10 windows in Gbrain, and I'm just, like, at it. What's cool about OpenClaw... I mean, maybe this is a good example. This is actually my OpenClaw. I did go ahead and ask. It's, um, how... You know, how did I actually get into it? January 23rd.
- SPSpeaker
Also, all your emails and-
- GTGarry Tan
I had a tweet that was like-
- SPSpeaker
[chuckles]
- GTGarry Tan
... "Claude Code this week has awakened my 25-year-old self, the one that chugged Red Bulls and stayed up till dawn coding. We're so back." [laughs]
- SPSpeaker
[laughs]
- SPSpeaker
The builder identity resurfaces. [laughs]
- GTGarry Tan
Yeah. And then, you know, I'm basically back to, you know, sleeping four hours and, you know, coding 20 hours a day. You know, this is also when I started getting myself into trouble, like, talking about lines of code. I still believe this, by the way. It's just-
- SPSpeaker
Yeah, this might be, like, a good quick aside to talk about, like, this, this idea of, like, lines of code being important measure has been, like, controversial on the internet. There's obviously the counterargument like, oh, lines of code doesn't, like, measure developer-
- GTGarry Tan
Yeah
- SPSpeaker
... product productivity. But what-
- GTGarry Tan
It doesn't, right? But it-
- SPSpeaker
What do you think about this, Garry?
- GTGarry Tan
But it also does. So-
- SPSpeaker
It, it also kind of does, right?
- GTGarry Tan
Yeah.
- SPSpeaker
[laughs]
- GTGarry Tan
Like, it does... It's clearly... And, you know, what's interesting is you can actually, um, there's well-published Git repos out there that you can run to, uh, strip away and, like, standardize what is actual logical lines of code. And so I actually did go ahead and do that. Um, you know, and I got into trouble for saying, like, "Oh, I'm coding at, like, 100x, uh, the rate that I was in 2013." And then after I did the logical lines of code strip down, um-
- SPSpeaker
It actually went up
- 38:37 – 41:28
Buying back time with tokens
- JFJared Friedman
everything.
- GTGarry Tan
Yeah, I, I envy time billionaires.
- JFJared Friedman
Mm.
- GTGarry Tan
You know, sometimes look at... I mean, I'm- look at my kids, and it's like, "These kids are time billionaires right now, man."
- JFJared Friedman
[laughs]
- GTGarry Tan
Like, you know, you could just, like, do thing... You know, you know, we run across people at startup school all the time, and it's like, "You're a time billionaire right now. Like, this is incredible. Like, you could just do anything. You could, like, learn about anything. This is so great." So yeah, I'm, you know, personally, like, I think my philosophy is I am in a crazy rush. In my brain, I'm like, probably live 10 billion lifetimes living in this body right now, and I need every single moment to count. Uh, and then if you can token max, it's like, I mean, you could buy millions of years of-
- JFJared Friedman
Yeah
- GTGarry Tan
... consciousness-
- JFJared Friedman
Yeah
- GTGarry Tan
... of machine consciousness.
- JFJared Friedman
Interesting.
- GTGarry Tan
Now I can be a time billionaire. It's not, you know, my own time. It's the time of a machine-
- JFJared Friedman
Right
- GTGarry Tan
... like, doing work for me and, like, the human entities that I care about working on the causes that I care about, right? I care about YC. I care about builders being able to build. Even in a lot of our internal meetings last year, remember in our off-sites, we would talk about, like, how do we teach the next generation how to use these tools? And so, you know, I'd like to s- I wish that I could say, like, that was a- all a part of the grand plan, and that's how it started. It's not. Like, but, you know, subconsciously, I actually think it was. Like, I think subconsciously from doing Lightcone and, like, talking about this stuff, like, sitting side by side with, uh, Boris Cherny-
- JFJared Friedman
Yeah
- GTGarry Tan
... right here was a very powerful moment for me-
- JFJared Friedman
Yeah
- GTGarry Tan
... because I realized, like, he's- he started saying things that, like, I could do myself. It's like he said, "Our team doesn't write a single line of code." I'm like, "Oh, actually, like, I can do that." And, like, the people who are watching right now, it's like you and I are not different, right? We're the same. Like, we started in the same place. I don't think of myself as, like, you know, in the sky yet, even though people seem to talk like I am. You know, like, I'm just a person trying to do a thing, and if I sit next to Boris, I'm like, "You know, this guy is one of the best engineers I've ever met." But also, like, if I just open a prompt, we have the same prompt. We have the same MacBook Pro, and, you know, there's nothing that stands between, like, me or you or any of us from, like, drawing on millions of years potentially of, like, tokens to, like, serve humanity.
- SPSpeaker
Well, Garry, I think that was a beautiful quote. That should be retweetable. It shows-
- GTGarry Tan
[laughs] Gotta get it on X right away.
- SPSpeaker
You could have infinite time by borrowing the time from the machines.
- GTGarry Tan
Yeah, what a time to be alive.
- JFJared Friedman
That's a beautiful thought to end on. Thanks, Garry, for showing us the future.
- GTGarry Tan
Thanks, guys.
- SPSpeaker
Thanks, Garry. All right, thanks for watching, and we'll see you on the next episode of Lightcone. [upbeat music]
Episode duration: 41:29
Install uListen for AI-powered chat & search across the full episode — Get Full Transcript
Transcript of episode 57lDpTwiW6g
Get more out of YouTube videos.
High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.
Add to Chrome