Y Combinator Startup Podcast
00:36:58 · Garry Tan
[00:36:58] S1: I mean, dynamic retrieval is pretty clearly going to happen the second you have really, really smart cogen. Yeah. So, I mean, for now... I mean, I use it for OpenClaw, so then I use my production instance, and then the traces from that, I extracted out, like, an eval dataset. And then I have a separate repo called gbrain evals, and it's got 40 different categories of, like, specific types of retrieval, retrieval efficiency, like cost efficiency, latency. And then the cool thing about evals is then you can just tell the agent, like, loop. You know, just auto research and loop, and anything that improves your stats on this eval, like ship it into master on by default. Yeah. And anything that you tried that didn't work, write a markdown file that, you know, explains why you think it didn't work, and then file it away in g brain evals. I use Capi. There's a... You know, Capi has this concept of captains, which is kinda like similar to Grockbots bots. Uh-huh. And so you can just give it a context. And so I have one that is always going, that's like come up with new categories. And I have another captain that's always going, that's like, go through all the categories in evals and auto research, and every single day, try to find a way to improve our scores on our own internal evals. And that's just going all the time. It's a very, very primitive version of RSI for, particular use case. But I guess if you, like, go up one level of abstraction, you know, you could do that, you know, not for my use case, which is from... For OpenClaw or something. Like, it could just be for generically, like, anyone's retrieval use case. Like, the only thing that changes is, like, the use case and the traces and the dataset.
00:38:42 · Paul Copplestone, Garry Tan, S3
[00:38:42] S0: You obviously know about eval's, and you can improve your software because you're, like, wrapping this framework around it. Like, do you think that in the future, builders will have to actually know about these type of things? [00:38:54] S1: Or... Maybe not. I mean, honestly, I feel like we're so early that, you know, I'm just messing around. Yeah. And, you know, I like doing it in open source, and someone else... You know, I hope someone looks at that and says, like, oh, I can apply that. You know? Like, we're... I think we're literally coming up with the primitives on how to use this stuff right now. Yeah. I mean, I remember earlier in the year, you know, reading about Steve Yegge's software factories and things like that, and then not being able to totally figure it out. And it's like, oh, no, I feel like now I've cobbled together something that works for me at least. [00:39:24] S0: Yeah. [00:39:25] S3: Yeah. When we had Boris Cherny here, his vision of the future of coding was more like, you just talk to Claude like a friend, and you don't have to know about evals and all all this all this stuff. And, like, Claude just, like, figures out how to build the thing that you have in your mind.
00:39:25 · S3, Paul Copplestone, Garry Tan
[00:39:25] S3: Yeah. When we had Boris Cherny here, his vision of the future of coding was more like, you just talk to Claude like a friend, and you don't have to know about evals and all all this all this stuff. And, like, Claude just, like, figures out how to build the thing that you have in your mind. [00:39:41] S0: I've got this domain name, openusd.dev, and it's because there's actually a file format called open usd, and I collect domain names. And then suddenly, Stripe and Visa and everyone Yeah. Announced open usd. And I was like, oh, I better put this domain to use now. But I never had time to to use it. So I was chatting to the dot and it's like developed this, like, developer site with the ecosystem and everything. And I was just chatting to it on my computer and then like, as I was winding down my day, I called it on my phone, like, as I'm getting to bed, which sounds sus, but I'm... I promise I'm [00:40:17] S1: just Checking in.
00:40:17 · Garry Tan, Paul Copplestone
[00:40:17] S1: just Checking in. [00:40:18] S0: Just coding with it. And I was, like, saying, I don't like the information architecture of how, like, the ecosystem links to the the use cases. Can you make some suggestions? And it did. And I said, okay. Yeah. Implement them. And then twenty seconds later, it said, oh, yeah. Okay. I've done it. Do you wanna refresh? And I refreshed the site, and it was really well written, and everything was linking together, and it's hooked up the SEO type stuff. And so I haven't done all the classic stuff that I'd have to do traditionally. I've just been chatting to it, and it really felt like one of those moments where I was... I I sort of saw a glimpse of the future. [00:40:56] S1: I mean, you can do that because you know what you want to build. [00:40:59] S0: That's the thing. Yeah. So, like, I obviously have a background in engineering. So I kind of know how to prompt it, but I'm trying to not say anything. I'm trying not to, like, point it towards GitHub or anything like that. And I'm trying to code like a like a normie or someone will do next year so that I know it's basically so I can dog food Supabase and know that, oh, is it going to have a good time with Supabase in one year's time?
00:40:59 · Paul Copplestone, Garry Tan
[00:40:59] S0: That's the thing. Yeah. So, like, I obviously have a background in engineering. So I kind of know how to prompt it, but I'm trying to not say anything. I'm trying not to, like, point it towards GitHub or anything like that. And I'm trying to code like a like a normie or someone will do next year so that I know it's basically so I can dog food Supabase and know that, oh, is it going to have a good time with Supabase in one year's time? [00:41:27] S1: Yeah. It's funny for Boris to say, like, oh, I I just wanted to do it automatically. And like, certainly, once it's into distribution, like, literally the model has it, you know, in its weights, it can do it. But until then, it needs, like, some markdown or something. You just... Like a lit... Like, not even a lot of prompting, like, small amounts of prompting. It can just do it. I... We're entering this very strange moment in society, I think, where, like, it sounds like RSI really is here, and it's like going from the 20% to 80% moment of like, AI research is just happening in sort of these... Inside these loops, inside, you know, Claude Code or Codex or wherever it is. And then simultaneous to that, like, society doesn't really have enough people like you, Paul, who, like, know what to build and how to ask it. And so it's like unstoppable force meets immovable object right now. Like, the capabilities, the models are, like, going parabolic, and then the number of people who know how to actually have an impact on society with it is, like, more or less constant.
00:42:36 · Paul Copplestone
[00:42:36] S0: Yeah. And want to be kind of excited by it. I I think that's the other thing. I think a lot of people are getting paranoid, but I'm genuinely excited about what the future could be for a lot of people. A lot of my previous startups were focused on like blue collar workers and, like, people who... I was wrapping tech around a lot of people who just had to work a lot of their life, you know. And I... The thing that I really love about Supabase is that it's, like, see a lot of entrepreneurship because of the platform. And so I can see this future where actually there is going to be so much more entrepreneurship, and it's actually quite a fulfilling lifestyle for a lot of people. So I'm pretty pumped about 2027, actually. As long as we can keep this cadence up and avoid a few few crazy events, then then it should be a fun ride for a lot of people.