Y Combinator Startup Podcast
00:08:14 · Garry Tan
This applies to product management. This applies to growth. This applies to every part of what you might want to do. The multiplier for coding is not just for coding. It's for every piece of knowledge work. And it's not just me. At YC, we get to watch this at portfolio scale. A year and a half ago in the winter twenty five batch, a quarter of the companies had code bases that were 95% AI generated. Those companies use AI agents for everything now, not just code. And that batch is on track to becoming one of the fastest growing, most profitable batches in the history of YC. Now I know what a correlation is, so let me say it carefully. I cannot prove that the AI generated code and everything else caused the growth. But what I can tell you is that the fastest growing founders we fund are not treating AI as autocomplete. They are treating it as a workforce. There are two x people and there are 100 x people who are using the same Claude, same weights, same context window size, same API. But the leverage is not in the weights. It's in what context you give it, how relevant it is, and does it happen at the right step. We'll come back to this. Now, Spinoza has a definition I think about every single week. In ethics, he defines joy as the feeling of your power of acting increasing, which is why the first time an agent does a week of your work in an afternoon, it doesn't feel like a convenience. It feels like joy. And that's not me being poetic. That's the technical term. Your power of acting increased. Your canatus just got bigger. He defined the opposite to you, by the way, sadness, the feeling of your power of acting decreasing. If your Sunday nights have a specific heaviness, like your ability to influence the world is receding, that you feel like you're quiet quitting, then this is what you feel and hold that thought because we're coming back to this in the second half of this talk. And it gets political. So here's the equation for the next decade of your life. A frontier model, which is rented and a commodity and getting cheaper by the quarter, plus your context which is owned by you and unique. No. And ideally nobody else on this earth has it. Plus a harness that wires them together. That harness might be Open Claw, Hermes agent, Claude code, or Codex. Add that up, and that gives you an agent that acts like a very fast version of you.
00:10:59 · Garry Tan
Model quality is rented, but your brain is owned ideally by you. Marshall McLuhan said that technology is an extension of man. Steve Jobs called a computer a bicycle for the mind. And if you have what I'm describing here, then you have a self driving rocket. Paul Graham taught every founder in this building two things. Make something people want and do things that don't scale. Both still govern everything. What's new is the multiplier on the second one. Agents are how one founder now does unscalable things at scale. The advice didn't change, but the physics of all startups and of what you can do did. Spinoza ground lenses, instruments that let people see past the limits of their eyes. I wanna spend the next fifteen minutes showing you what grinding lenses for the mind looks like. This is the machinery I actually run my life on, and every concept travels to whatever stack you use. Let's start with working memory because it explains everything. You and I, as human beings, hold about seven things in our head at once. Seven plus or minus two. It's the most famous paper in cognitive psychology. It's why local phone numbers are seven digits and why you forget the eighth item on a grocery list. That is the entire working memory of a human being. And every institution humanity has ever built, every checklist, every org chart, every filing cabinet, every stand up meeting is a prosthetic for that limit. An AI agent though holds a million tokens. That's about a thousand pages. Three Harry Potter books sitting open on its head all at once. And it can find a needle in any of them and synthesize across all three in seconds. Three Harry Potter books versus seven digits. You could argue that's not quite AGI yet, but it is already a different operating regime. And almost everyone on Earth is still running their life on an org chart and a way of doing things designed for the seven digit brain. Run that number in the other direction. A thousand pages is a lot, but it is also very little. Your life is not three books. Your life is a library. Every email you ever sent, every meeting, every decision, and every reason behind it, every conversation with every person you know. The question that determines whether your agent is a genius or a goldfish is this. Who decides or what decides which three books are open on the desk. And that's what a brain is.
00:13:44 · Garry Tan
That's what g brain is meant to be, the library plus the librarian. I've been building g brain in the open. My personal Open Claw has a Karpathy style knowledge wiki with about 220,000 markdown pages. Twenty five years of my life diarized. Every email, every meeting, my notes, my photos, my drafts, the things I got wrong. Compiled mostly by agents, curated by agents, searched for by agents. But I never re ask a question I already answered. And the lived experience in the system is the point. A founder emails me about a crisis before I finish reading the email. My agent has already pulled every prior conversation I've had with that founder. Three portfolio companies that hit the same wall and what actually worked for them. When my agent does anything, it does knowing everything I know. And that's the difference between an assistant and a colleague. Let me walk you through an actual day because that matters more than an architecture diagram. While I slept last night, my agent processed my inbox. Not sorted it, processed it. It knows which emails are from founders in trouble, which are from people trying to sell me something, and which are from the 17 mailing lists I never quite unsubscribed from. The ones that matter are triaged with context pulled from the library, who this person is, my whole history with them, what they're really asking under what they wrote, and what that might mean for me. I wake up to a briefing, not a pile of emails. Before every meeting, a prep doc, who I'm meeting, what we said last time, what changed since, and what I should ask. Research I was curious about at midnight is finished by morning. And when something interesting happens in the world, my agent has usually read it cross referenced against what I care about and filed it before I've had coffee. On top of this library sits my agent coding framework g stack, a 123,000 stars now, which put it in the top 100 open source projects in the history of GitHub. And what's actually in the punchline of this full architecture? It's mostly skill files plus a browser that the agents can drive. Pages of English and a way to act on the world. Markdown, not magic. Fat skills, then harness. Let me show you what a skill file is because I keep saying this phrase, and I want you to see how unmagical it is. Here's a real one, lightly redact is.
00:16:27 · Garry Tan
It says, when a meeting recording lands from circle back, transcribe it with speaker labels. Pull out the commitment made, who made it, and the deadline. Cross check every person named against the library and link their pages. File the summary here, full transcript there. If anything contradicts something we already believe, flag it. Don't overwrite it. That's it. That's a skill. It's a page of English. A smart intern, anyone really who could read could follow it. And that's the test actually. If a smart intern could follow it, an agent can run it, which means actually a kind of profound thing. I know I caught a lot of flack for talking about this, but I think it's more true than ever, especially now. Markdown is actually code. If you can write clear instructions in English, you're a programmer. The compiler is a language model. And that's why it's not just for engineers anymore. At YC, our media people, events staff, finance team, people who never open a terminal in their lives are building skill files and scheduled jobs. One of our finance folks compiled about a 100 Excel workbooks into a single app she built with an internal agent. She is not a programmer. She is a manager of agents now. Everyone is about to be. The most important question to ask here is where is the computation happening? And there are exactly two answers, and confusing them causes every agent failure I've ever seen. Some computation belongs in latent space. Taste, judgment, reading what a human actually wants from a vague request, that lives in the model and you steer it with a markdown file. And then some computation belongs in deterministic space, the arithmetic, the SQL query. For instance, the seating chart for what sessions you're going to go to today for your breakouts. All of that needs to be stored in a SQL database used by the markdown files. Being smart about this goes a long way. Ask an agent or human to seat five people around a table. That's easy. Do it in latent space. Ask it to make custom schedules for 6,000 people in an arena like we just did for you, and your latent space agent needs to write some code to keep track of it. Your experience at this conference had to be markdown files calling code in exactly this way. And you can't do it without the code. The model fails where we fail. The fix is having the model compute the way humans compute.
00:19:12 · Garry Tan
The latent and the deterministic, Markdown files calling databases and scripts. Simple, but it's what everything is actually built on. And I'll give you one more receipt, my favorite one because you're sitting inside it right now. Five days ago, I decided this talk needed Spinoza, one of my favorite philosophers, especially because of how canceled he got. So my agent went and acquired three of the best biographies about the man, books by Nadler, Goldstein, Stewart, about 1,500 pages. It read all three. It built me a synthesis, a dated chronology of his life, every place the three biographers disagree with each other, and the best verbatim quotes with chapter citations. And because it knows what I need, the 10 most tellable moments of his life ranked with delivery notes, The knife attack, the bribe, the desk. Every beat of our opening that might have given you some chills twenty minutes ago came out of that overnight run. 1,500 pages became a stage ready story that I could edit. I call it a compendium skill, and I use it daily. It's a personal skill that is a mega mega version of deep research, only deeper than anything the corporate AI products will give you. The spine of this talk you're watching was inspired by the machine we're describing now. And if you're wondering where my... Mine actually started, it was not 220,000 pages. It was a folder. It was a few markdown files about the companies I was working with and the people I kept emailing. And the library got big the same way anything gets big. A little everyday compounding with agents doing the filing. Nobody builds the warehouse first. First, you build one shelf. When you sit down with an agent tonight, you're not coding. You're managing a workforce made of markdown. A skill file is an employee. It has one capability, one job written down clearly enough that someone new could execute it. A resolver is an org chart. A task comes in and it decides which markdown file or who handles it. Which means that before you ever incorporate anything, before you have a co founder or a logo or a deck, you can already be running an organization. An organization of one plus your agents. You are the founder and the entire management layer of You Incorporated and the headcount under you is now whatever you decide it is. This already produces companies that break the old math.
00:21:56 · Garry Tan
Emergent out of our summer twenty four batch went from public launch to 9 figures of revenue in eight months. When they crossed $15,000,000 in annualized revenue, they were 15 people. Retail, winter twenty four, hit 60,000,000 annualized with about 40. That revenue per person did not exist before, not in software, not in oil, not in railroads. And these aren't freaks of nature. They're the first companies built natively on the new physics, and every one of them started as one or two people wired the way I just described. Now picture our batch room in the dog patch, Hundreds of founders every single day, each one of them doing what used to be a person's entire year of work. That is not the future. That is the bar right now with this batch. If you're not doing it, your competitor is, and they will eat your lunch politely and thank you for it. It also changes what software even is. Software doesn't have to be precious anymore. You can build exactly the tool you need for the audience of one in a weekend. The old advice was scratch your own itch and hope it's a market. The new version is much better. Scratch your own itch because scratching itches is nearly free, and some of your tools for one will turn out to be entire companies. You'll know because other people start begging for them. And one honest caveat before the how to because you catch me out in any way. A brain nobody curates is a garbage dump with great search. Retrieval will surface a stale fact with total confidence. A bad skill file encodes a bad process forever. So the primitive is memory plus hygiene, provenance on every fact, contradiction checks when new information collides with old, and a librarian whose actual job is pruning. Treat the brain like production infrastructure and it compounds. Treat it like a dumping ground, and you get a very confident agent that is wrong in ways nobody can trace. Everything so far is philosophy and receipts. So let's get into some how to. If you do what I describe in the next six minutes, you'll be ahead of 99% of people who watched this talk and just nodded. Step one tonight, pick a harness and run an agent on your own machine. I use OpenClaw and Hermes agent with g brain. A hosted version of this is at gbrain.io. It's free. G brain itself is free and open source. I always recommend the Ferrari. But I'll be honest, the Honda is really good too.