为什么每个人都可能拥有自己的数据库？Supabase CEO 谈智能体与个人软件

简要描述Brief Description

为什么每个人都即将拥有自己的数据库Why Everyone Is About To Have Their Own Database

目录Table of Contents

• 简介
  Intro
• 增长与收入增长至 4 倍
  Growth and 4x Revenue
• Supabase 的三个时代
  Three Eras of Supabase
• “构建者”与传统开发者的区别
  “Builders” vs. Traditional Devs
• 个性化应用程序
  Personalized Apps
• 个人数据库与数据所有权
  Personal Databases & Data Ownership
• 扩展至数十亿规模
  Scaling to Billions
• Supabase 的 AI 应用情况
  AI Adoption At Supabase
• 一路走来的经验教训
  Lessons Learned Along The Way
• 为个人智能体构建并亲自试用
  Building For Personal Agents, Dogfooding
• 代理优先设计与评估
  Agent-First Design and Evals
• 编程的未来
  The Future Of Coding
• 开启更多创业可能性 + 结语
  Opening Up More Entrepreneurship + Outro

简介Intro

嘉宾：我真心为许多人的未来感到兴奋。我特别喜欢 Superbase 的一点是，我觉得这个平台催生了很多创业活动。我当然认为，未来世界上每个能使用 AI 的人都会成为某种意义上的创造者。你可以构建任何东西，也可以按自己的需求定制。Guest: I'm genuinely excited about what the future could be for a lot of people. The thing that I really love about Superbase is that like I see a lot of entrepreneurship um because of the platform. I certainly think that it'll be the case that everyone in the world with access to AI will become a builder of some sort. Like you can build anything, you can customize it.

你想对某个应用或界面做些调整，就不必受制于别人了。说实话，我对 2027 年还挺期待的。You want to make tweaks to some app, some UI, then you don't have to be beholden to someone. I'm pretty pumped about 2027 actually.

主持人：欢迎回到《Lightcone》的新一期节目。今天我们请到了 Supabase 的联合创始人兼首席执行官 Paul Copplestone。Supabase 是一个开源的 Postgres 后端，如今已成为 Claude Code 和 Codex 等工具的默认数据库。Supabase 目前拥有 1300 万用户，每周创建超过 100 万个数据库。Host: Welcome back to another episode of the light cone. Today we're joined by Paul Coppstone, co-founder and CEO of Superbase, the open-source Postgress backend that's become the default database inside tools like Cloud Code and Codeex. Superbase now has 13 million users and it's spinning up over a million databases a week.

保罗，欢迎来到 Lite Cone。Paul, welcome to the Lite Cone.

嘉宾：感谢邀请我。Guest: Thanks for having me.

主持人：那么，先从这里说起，你知道，YC 很有名的一点是会在第一天给你一件 T 恤，上面写着：“做出人们想要的东西。”但我们越来越意识到，现在要做的是做出智能体想要的东西。你们公司确实很好地体现了这一点。你知道，大约 70% 的新增活动都来自智能体。这不是很疯狂吗？Host: So, to start off, uh, you know, famously YC gives you a t-shirt on the first day of YC that says, "Make something people want." But increasingly, all of us are realizing it's make something agents want. And your company really exemplifies that. You know, something like 70% of the new activity is from agents. Isn't that crazy?

增长与收入增长四倍Growth and 4x Revenue

嘉宾：是啊，真是不可思议。太不可思议了。我觉得尤其是今年，从数据上看，趋势明显发生了巨大转变，大家越来越青睐智能体。Guest: Yeah, it's wild. It's wild. I think like this year especially what we've seen in terms of the numbers the inflection is just a huge shift towards agents

主持人：我们想了解一下你们到底发展得有多快，因为这简直令人难以置信。嗯，你们关注哪些数据？去年这个时候你们处于什么规模，现在又发展到什么程度了？Host: just so we can understand just how much you guys have grown cuz it's kind of mindboggling. Um yeah like what are the numbers you care about and where were you like this time last year and where are you now?

嘉宾：我想应该是去年这个时候吧，所以，是的，我们现在有 1300 万注册用户。大概 12 个月前，可能也就三百万左右。嗯，今年收入会增长到四倍。嗯，我们已经……我想想是什么……Guest: I think this time last year, so yeah, we're 13 million signups now. Probably 12 months back, we would have been around three perhaps. Um, this year, like revenue will grow, 4x. Um, we've got trying to think what

主持人：你们现在每周大概会创建一百万个数据库。Host: you got like a million databases being created per week at the moment.

嘉宾：对。对。对。Guest: Yeah. Yeah. Yeah.

主持人：去年这个时候是什么情况？Host: What was it this time last year?

嘉宾：我觉得，实际上目前托管的数据库数量已接近 5000 万，而去年这个时候只有 800 万。所以这真是一个巨大的转折点。Guest: I think actually if um databases under management now are approaching 50 million and this time last year it was 8 million. So it's just a huge inflection.

主持人：是什么导致了这种情况？Host: What's been driving that?

嘉宾：第一，人们正在借助被弃用的软件工程师构建东西。第二，我认为有越来越多的构建者正在涌现。过去，通常只有具备软件工程背景的人才能做这些事；而现在，非工程师也开始能够在 Superbase 上构建东西了。Guest: First people are building with abandoned software engineers. Second I think that there are a lot more builders coming online. So what was traditionally uh someone with a software engineering background is now uh it's now becoming possible for non-engineers to actually build things on top of superbase.

Supabase 的三个时代Three Eras of Supabase

主持人：所以这是一个非常大的转变。呃，你们实际上做了些什么来促成或鼓励这种转变？显然，软件工程师会继续选择 Superbase，但你们是怎么让这些智能体一开始就转过来的呢？Host: So this is a really big shift. Uh what have you guys actually done to facilitate or encourage this shift from you know obviously software engineers are going to keep choosing superbase but you know how do you get the agents to come over in the first place?

嘉宾：是的，我们大致经历了 Superbase 的三个阶段。起初我们是一家仪表盘公司，后来转型为 API 公司，而现在我们则是一家非常注重代码优先的公司。因此，我们努力提供智能体真正想要的开发方式，也就是代码优先。他们大多数时候确实想使用 CLI。Guest: Yeah, we largely have seen like three chapters in Superbase. We started as a dashboard company, then we went to an API company, and now we're very much a code first company. So, we try to have the modalities that the agents really want to build with, which is code first. They really want to use CLI most of the time.

另一件事就是被 LLM 选作默认选项。嗯，我认为我们受益匪浅，尤其是受益于我们开始成为数据库默认选择的时机。The other thing is just being chosen as a default uh in the LLMs which I think we were a huge beneficiary of our of our um the timing of which we started to become a default choice for databases.

主持人：你觉得开源也在其中发挥了多大作用？因为智能体都很喜欢开源的东西？Host: How much do you think being open source played a role in it too cuz the agents love open source things?

嘉宾：你知道，很难知道反事实会是什么样，但我认为这至关重要。我的意思是，我们做的一切都是开源的，这似乎给我们带来了巨大的好处，而且我们采用了非常开放的开源方式，比如我们努力支持现有工具。我们支持的不只是 Supabase 的工具；比如 Postgres，它是 Postgres 生态中非常知名的工具，我们也在帮助维护它。所以，我们的业务也就遍及了许多社区。Guest: You know it's hard to know the counterfactual but I think it was critical. I mean everything that we do is open source and it seems to have been a huge benefit to us and we do it in a very open- sourcy way like we tried to support existing tools. It's not just superbased tools we support like Postgress is a very um famous tool for the Postgress Ecosystem and we help to maintain that. So we kind of got sprawl across many communities.

主持人：我猜这些智能体其实很喜欢开源，因为出了问题时，它们可以直接查看源代码。Host: I would guess that the agents actually really like open source because when something goes wrong, it can just look at the source.

是的。Yeah.

嘉宾：是的。我注意到，智能体确实很喜欢掌控感，也很喜欢数据。嗯，没有什么比碰到一堵高墙更让人沮丧了：你不知道发生了什么，也无法解决问题。我认为这也会变得越来越重要，因为如今安全问题如此重要，我想很多企业都会希望检查源代码，以确认它是安全的。如果代码是闭源的，他们可能就不会选择这类供应商。Guest: Yeah. I mean, I noticed the agents really like feeling powerful and they love data and uh there's nothing more frustrating than hitting a brick wall and then you don't know what's going on and you can't fix it. I think it's going to be increasingly important as well because now with you know security being so important I think a lot of the say enterprises are going to want to inspect the source code to know that it's secure and if you've got closed source code then you probably won't want to adopt them as a vendor.

“构建者”与传统开发者的区别“Builders” vs. Traditional Devs

主持人：开发者现在仍然算是你们要重点面向的核心用户吗？或者说，你们在 2026 年是怎么考虑这个问题的？Host: Is developer even still sort of the core user that you're going after or how you know how do you think about it now in 2026?

嘉宾：是的，我觉得我们正在迈向的那个世界，至少从我们今年看到的情况来看，就是越来越多的构建者开始上线，而且人数多得惊人。今年不可思议的地方在于，通常我们漏斗顶端的注册量在加速增长时，其他很多指标都会开始下滑，比如激活率、转化率。但今年实际上这些指标都在不断向上增长，这有点疯狂，因为模型在构建方面变得越来越强了。Guest: Yeah, I think that the world where we're moving and at least what we're seeing this year is like um kind of builders are coming online and it's like a crazy amount of people coming online. The crazy thing about this year is usually when you're um like our top of funnel, our signups are accelerating. And usually when this happens, you see a lot of the other numbers start to decline, activation, conversion. But actually this year, all of them are kind of going up and to the right, which is a bit insane just because the models are getting so good at building.

我们开始看到，传统上没有软件工程背景的人也能够参与进来并构建东西。And we're starting to see people who traditionally wouldn't have a software engineering background able to come and build things.

主持人：这个区别就像 builder——他们可能并不是真正的软件工程师。他们可能只是需要做出某个东西的人，然后就打开 Cloud Code，结果发现光靠文件能做的事终究有限。Host: That's the distinction is like builder as in they might not be actually software engineers. They might just be someone who needs to build a thing and they're just, you know, popping open cloud code and then it turns out files only get you so far.

嘉宾：是的。从某种意义上说，这类人积攒了很多想法，以前他们怎么也说服不了软件工程师帮忙把这些想法做出来，而现在他们不需要说服任何人了。他们有一大堆想法，正不断把它们变成现实。软件工程师仍然占很大一部分，但开发者群体的增长速度相当快。Guest: Yeah. And in some ways like this category of people have all these pent up ideas that they could never convince a software engineer to like help them build and now they don't have to convince anyone. They've got all these ideas that they're churning out. Software engineers still make up a huge portion but the rate of the growth of the builder segment is pretty big.

而且我也不知道这件事的上限在哪里。我记得早期投资人曾说，啊，PLG（产品驱动增长）这种模式的增长到这个营收水平就会触顶，你们就得开始转向市场的这个细分领域。但到目前为止，似乎完全没有上限，我也看不出它会在哪里停下来。Also like I don't know where the ceiling is on this one. Like I remember our early investors were saying ah PLG product like growth is going to tap out at this revenue and you'll have to start moving into this segment of the market and there just appears to be no ceiling so far and I can't see where it stops.

主持人：我是说，这在两年前或一年前基本上还是真的，但今年肯定不是这样。Host: I mean that was basically true like two years ago or one year ago but definitely not true this year.

是的。上周末我刚好和一个人聊到这个话题，如果说的是 builder 这一类的话。他算是个金融科技领域的创始人，刚以超过十亿美元的价格卖掉了自己的公司。他一直算是和产品沾边：本科读的是数学，勉强能拼凑出一些 Ruby 脚本，但总得找工程师来开发软件。现在做副业项目时，他开始自己动手开发各种东西。他具备创建金融科技公司的全部知识，所以能为自己的个人财务开发相当复杂的软件，比如资产负债表和追踪工具；他也知道怎么接入银行，而且正在从头编写所有集成。这类软件甚至在两年前都还不可能有人开发出来。Yeah. I was just talking to someone actually this last weekend if it's the builder category. It's like a fintech founder just exited his company of like over a billion dollars and um he's always been sort of product adjacent like studying math at like as an undergrad and sort of like kind of could pull together some Ruby scripts but like always need an engineer to like build the software and now side projects he's just building his own stuff and he has all the knowledge from how to build a fintech company so he can actually build pretty sophisticated just like for his own personal finances like balance sheets and tracking software and knows how to like integrate in with banks and he's wring all the integrations from scratch and it's just like the kind of software that would never have been built um even 2 years ago.

嘉宾：他们也是非常理想的创作者类型。像我这样的开发者，脑子里有很多以开发者为中心的想法，想做各种东西；但你们这里还有这些领域专家，他们很清楚自己所在的细分领域有哪些尚未解决的问题。所以现在他们真的可以直接深入这些细分领域，不必先说服别人加入自己。我记得你们之前也聊过这个，对吧？是在纽约市的时候？比如说，就连你们招进这个群体的人选画像都在发生变化。Guest: These are the perfect type of builder as well because like developers like me I have very like developer focused ideas and things that I want to build but then you've got all these domain experts and they know exactly the niches of oh this is an unsolved problem in my niche and so they're actually able now to like dig right into those niches without having to convince someone else to join them. I think you guys were talking about this, weren't you in NYC, like the profile shifting even from who you're bringing into the cohort.

主持人：我觉得，如果你看看2022到2025年左右这个时期，会发现一种真正的思维转变：人们开始觉得，AI要来了，于是突然之间，大家认为软件工程是核心能力，也就是说，无论如何你都需要一位技术联合创始人。这个观念在那段时间里成了YC上一个非常重要的观点。Host: I think that if you look at the sort of era of what 2022 2025 there's sort of this real shift thinking like well AI is coming and suddenly um having software engineering as uh you know core you know you need a technical co-founder no matter what that was like a mega idea that you know really came to the four at YC during that time period.

这一直多少都是真的，但我们算是把这一点又强调了一遍。呃，过去这一年里，我们才真正开始说：其实没错，建设者——我们开始看到一些人能够……我是说，更难做到的是知道该构建什么。如今，任何人都多少可以随时动手构建了。这其实是一件很棒的事。is always sort of true, but like sort of doubled down on that. Uh and then really in the last year, we sort of said actually yeah, builders like we're starting to see people who are able to like I mean the much harder thing to do is to know what to build. You know, being able to build is something that anyone can sort of have on tap now. And that's actually a really cool thing.

你能想象有多少东西根本就不会被开发出来吗？这正是你刚才说的那种情况。就像是：“哦，我们知道人们会买这个。我们知道这里存在一个问题。”但对于那些边缘需求，这些人却没法说服工程师来解决。Like can you imagine all the things that never would have built exactly for what you said? It's like oh we know that people would buy this. We know that there's a problem here, but at the margins, those people couldn't convince an engineer to work on it.

个性化应用程序Personalized Apps

Paul，你能举一些例子吗？比如人们用 Superbase 搭建的应用，可能只是自己用的，那种以前根本不会有人开发的东西？Do you have some examples, Paul, of like apps that people have built on Superbase, maybe just for themselves, that are the kinds of things that would have never been built before?

嘉宾：嗯，一个挺酷的例子发生在我们的会议上。会议在这里举行，之后有个来自巴西的人走过来跟我说，他用手机开发了一整套出租车应用。嗯，这有点像面向当地市场的小型 Uber。我当时就想，他自己就是个出租车司机。我其实不知道他为什么要开发这个应用，但他居然真的做出来了，而且他走过来时特别感激，觉得自己竟然能做到这一点。他身上还有一种活力——他大概五十岁吧，但那种突然开始动手开发的劲头，就像个青少年一样。我觉得这挺酷的，因为现在似乎正到了这样一个阶段：我觉得未来的工作会是什么样子，仍然存在很多不确定性；但在这群开发者当中，人们对未来充满期待。这正是我喜欢 Superbates 的地方：人们可以加入进来，而那些如今感到迷茫的人，正在发现这套技能和这些机会。过去，他们只是蓝领工人，是这类背景的人。Guest: Well, one kind of cool example was at our conference. We had the conference here and afterwards this guy from Brazil came up to me and he's built an entire taxi app uh from his phone and it's um kind of like a little mini Uber for his local market and I just thought he's a taxi driver himself. I don't actually know why he built it, but the fact that he could build it and he came up extremely grateful and that he could do this and also like with the type of energy he's he was like 50 years old or something like that, but he had the energy of a like teenager building suddenly, which I think is kind of cool because now it's kind of getting to that stage where I think it's a little bit there's so much uncertainty around like what is the future of work going to look like but in this category of builders there's that excitement of the future and that's really what I love about superbates it's like something that people can come in and those who are uncertain now are discovering this skill set and these opportunities where previously they were just blue collar workers these type of profile

主持人：最近你一直在艰苦地开发一些自己的个人软件，能聊聊你正在捣鼓些什么吗？Host: hard you've been building some of your own personal software recently you talk about what you've been cooking up

它就是这么发展起来的，是的，有点像一件事走到了尽头，但其实是因为我越来越沉迷于 OpenClaw。大概是六个月前吧，现在想起来我都不好意思承认当时说过的话。我说以后不会再有 UI 了，一切都只会通过 OpenClaw 聊天来完成。但后来发现，实际上……而且我之前也特别坚持很长一段时间不使用数据库，只想把所有东西都放在 Markdown 里。不过后来发现，确实到了某个阶段，数据库会很有用，而且你也确实需要 UI。所以过去几周我一直在搭建这些东西。嗯，我管它叫“控制塔”，但它其实就是涵盖我生活各个方面的界面。比如我有一个 UI，用来筛选处理所有邮件，这样我就不用看收件箱了。it's just grown yeah it's sort of like the end of one stuff but it's just grown out of um getting really addicted to open claw actually like maybe 6 months ago now I'm embarrassed I said it I said like there was going to be no UIs and it was all just going to be like chat through my open claw but it turns out actually and I also was really determined not to use a database for a long time I just wanted everything to be in markdown um but yeah it turns out actually you hit a point where like a database is useful and you do need UI so I've just been building that over the last couple of weeks in particular and so it's like um I mean I call it control tower but it's just like sort of every section of my life like I have like a UI I to like triage all my emails so I don't need to read my inbox.

嗯，财务、支出追踪，还有健康方面，比如记录体重、锻炼等，全都放在一个地方。但它神奇的地方在于，有时候这想法简直令人难以置信：我会想，我给自己做的这个应用里的财务模块，我觉得至少在功能上不输 Mint、Monarch 或其他这类产品，而且在某些方面其实更好，因为你可以加入非常个性化的上下文。比如，它可以通过查阅我 Gbrain 里的名字，弄清楚一笔交易对应的是谁。哦，你知道，就是这样，然后还能正确地分类。而这本来足以支撑一整家公司，有好几家初创公司都在专门做个人理财；可你只要给自己做一个就行了，而且我不需要它适用于其他人，也不需要在意别人的看法。Um, finances, tracking like spending, health, like both like tracks my weights and my workouts and everything is all in like one place. But I like the magic of it is sometimes it's a mindboggling thought actually is like I think about like the finance section of like my one app for myself is better I think is at least feature parity to mint or monarch or all of these things but in some ways actually better because you can start doing really personalized context like it can figure out what a transaction is by looking up in my like the name in my Gbrain to figure out who that person is. Oh, like you know that's like and categorize it correctly. And that was like a whole company like several startups just doing personal finance and then you just like build it for yourself and I don't need it to work for anyone else or like have anyone else's opinion on it.

这就像是，我的东西还挺棒的。It's just like kind of like my thing is like it's kind of awesome.

嘉宾：我们经常看到这种情况，比如金融和健康这两类领域，基本上都是你希望拥有自己的数据的领域。所以我们看到很多人都在这么做，而把所有设备同步到一个数据库里，算是一种很神奇的技能。然后你就可以提示它，让它建立这些关联。Guest: We see a lot of that one like where it's finance and health are basically the two like ones where you want your own data. So we see a lot of people doing that and syncing all the devices to a single database is kind of a magic skill. And then you can like prompt it to like build these correlations across.

个人数据库与数据所有权Personal Databases & Data Ownership

主持人：真正糟糕的是这些关联。比如再拿健康这个例子来说，没错，所有这些数据都在我的 two base 数据库里，但它也能访问我的日历，所以它知道一些事情，比如：“哦，你的体重最近涨了，不过你当时在旅行，所以没关系，下周再回到正轨就行。”它掌握的这类背景信息非常有价值。我还发现，开始使用个人代理之后，我有点儿担心自己把所有的日常习惯之类的东西都放进了一个代理里，CRM 也变得像是被锁定在这一个代理里了。所以现在我正慢慢把它们提取出来，这样如果我想在上面接入不同的代理，就知道自己可以用任何代理。CRM 也是另一个非常关键的东西。Host: It's the correlations that are really bad. Like again like if you just take the health example, it's like yeah all of that data is in like my two base database but then it also has access to my calendar so it knows things like it's like oh like your weight I know your weight went up recently but like you were traveling so that's okay like you can just like get back on track um next week. And it just has like this context that's really valuable. I also found as I started to use the personal agents like I'm getting a little bit paranoid that I'm putting all of like all of the um like routines and everything and the CRM is becoming like um boxed into one agent. And so now I'm slowly extracting it out into one so that if I want to attach different agents on top then I know that like I can use any agent. So the CRM is another really critical one.

主持人：是啊，这就是为什么你们这么有价值。实际上，它有点像数据库的权威数据存储。真正有价值的就是这个。你肯定想拥有自己的数据库，然后在它之上构建所有应用或智能体，而不是把这一切都放在别人的数据库里。Host: Yeah, that's why you guys are so valuable is like actually like it's like the it's sort of like the store of record. to the database is actually the thing that's valuable. Like you don't you want to own your own database and then build all the applications or agents on top of it versus having that all in like someone else's database.

这想法简直太疯狂了。你想想数据库的发展史：过去世界上只有相对少数几个规模很大的数据库，由大公司运营。我记得 Subbase 刚起步的时候，你们有个想法，觉得应该让所有人都能非常轻松地创建数据库。当时这想法几乎让人觉得说不通：那么多人为什么会想这么做？毕竟，除非你会写代码，否则你能拿数据库做什么呢？而且真正会写代码、能搭建这样一个个人 CRM 的人也没那么多。Which is a totally wild idea like if you just think about the history of databases used to be the case that like the world had only a relatively small number of very large databases run by like large companies. And I remember like when Subbase got started, you kind of had this idea that they should be like really easy for everyone to like make a database. And it almost like didn't make sense at the time why so many people would want to do that because unless you can write code, what can you do with a database? And there's not just not that many people who can actually like write code and build a personal CRM like that.

就像，这对大多数人来说实在太费劲了，preI。Like it's just like too much work for most people preI.

再举一个例子吧，Super 对我来说特别有价值的地方，就是我还有一个板块，功能就是上传文件。听起来非常简单，但不管是什么文件，我都可以通过邮件转发，或者直接丢到这个界面里，然后我的智能体就会弄清楚那是什么、它和我的生活有什么关系，以及该怎么处理它。嗯，不过所有这些内容都存储在 Superbase 上。所以总的来说，Superbase 最终会把所有与我生活有关的数据都集中存放在一个地方。大概一年前，我根本不会想到自己需要一个个人数据库，因为那时这完全说不通。Like another example actually where super is really valuable for me is like the other section I have is just like a file upload. Sounds very simple, but like any file I can sort of either forward via email or just like dump it in this UI and then like my agent like figures out what that is and how it's relevant to my life and like what to do with it. Um, but that's all being stored on Superbase. And so yeah, in general, it's just like Superbase is actually going to end up having like all of the like data about my life in a single place and like I would I would never have thought about wanting a personal database like a year ago because it wouldn't have made any sense.

但现在我觉得，那其实才是最有价值的东西。But now I like that's actually like the most valuable thing.

是啊。你有个类似 S3 兼容的 Supabase 文件存储的东西，我所有东西都在里面。Yeah. You have like an S3 compatible superbase files thing and all my stuff is in that.

客人：哦，真的吗？不错。是啊，是啊。Guest: Oh, really? Nice. Yeah. Yeah.

是的。Yeah.

主持人：这是 Gbrain 中的默认设置。Host: It's default in Gbrain.

访客：太好了。谢谢。Guest: Great. Thank you.

主持人：Paul，你觉得这就是未来吗？基本上世界上的每个人——不只是每个开发者，而是每个人——都会拥有一个 Superbase 数据库，里面存着他们生活中的各种信息，比如健康状况、财务状况和人际关系。Host: Do you think this is the future, Paul, where like basically everyone in the world, not every developer, every person will have a superbase database that has stuff about their life in it, their health, their finances, their relationships.

嘉宾：是的，我们很乐意。我是说，我当然认为，世界上每个能使用 AI 的人，最终都会成为某种创造者。你可以构建任何东西，也可以按自己的需要定制。你想对某个应用、某个用户界面做些调整，就不必再受制于别人。Guest: Yeah, we'd love that. I mean I certainly think that it'll be the case that everyone in the world with access to AI will become a builder of some sort. Like you can build anything, you can customize it. You want to make tweaks to some app, some UI, then you don't have to be beholden to someone.

当然，我们一直把自己看作一家索引公司。加入 YC 时，我们只专注于 YC 的公司。我们想拿下所有 YC 客户，因为我们知道，企业刚起步时，我们就必须在第一天出现。使命没有改变，只是覆盖范围大幅扩大了。Of course, like we think of ourselves as an index company. We when we came into YC, we just focused on YC companies. We wanted to win all YC customers and like now that was because we knew that we had to be there on day one when businesses were getting started. The mission didn't change just the aperture has like increased significantly.

现在，随着越来越多的建设者上线，我们知道需要为他们提供服务。这实际上是一个完全不同的问题，但也挺令人兴奋的。Now as more builders come online we know that we need to service them which is actually a whole different problem to solve but kind of an exciting one.

主持人：显著的意思是，比如说 1000 万倍。Host: Significantly meaning like 10 millionx.

嘉宾：是的。比如说，我们现在每周上线一百万个数据库。但如果做个简单的算术题，假设 ChatGPT——我记得他们说有 12 亿周活跃用户——而且假设每个人都想每个月上线点什么，那就是每月 12 亿个数据库。这就是我们正在迈向的规模，也是我们需要构建相应架构来应对的规模。在数据库领域，以前从未出现过这种情况。Guest: Yeah. Like so what we launch now a million databases every single week but I mean if you do some basic arithmetic let's say with chat GPD I think they said they've got 1.2 billion weekly active users and let's say all of them want to launch something every month that's 1.2 two billion databases a month. And so that's like the scale that we're moving towards architectures that we need to have so that we can actually cater for that scale which is something that has never had to happen before on the database realm.

扩展至数十亿级规模Scaling to Billions

主持人：用 Postgres 你真能做到这一点吗？要想扩展到每周新增 10 亿个数据库，你是不是得自己构建数据库引擎？Host: Can you even do that with Postgress? Are you going to have to build your own database engine to scale to 1 billion new databases per week?

嘉宾：我觉得是的。嗯，如果我们能和 AWS 谈出更好的条件，也许就可以了。事实证明，现在大家都想要计算资源。其实，对于很多这类工作负载，我也不知道你是否需要那么高性能的“法拉利”。我们最近进行了一项收购，Turso 的架构兼容 Postgres，也兼容 SQLite。我认为 SQLite 是一个非常出色的数据库，所以我们会提供一个名为 Supabase Spark 的套餐，主要面向刚起步的工作负载。我们的想法是，用户可以从同样的体验开始使用，并一路扩展到数 PB 的规模。我们的宣传语大致是“从原型到数 PB”。作为一家公司，我们需要确保能服务所有用户；如果他们的业务不断增长、规模不断扩大，我们也要确保他们能获得出色的体验。Guest: I think yeah. Well, if we could negotiate better with AWS, then maybe we could. Turns out that uh everyone wants computers at the moment and actually like I don't know if you need like such a Ferrari for a lot of these workloads and we made an acquisition recently terso they've got an architecture that's um compatible with postgress and actually it's compatible with SQLite as well. I think SQLite's a phenomenal database and so we'll provide this tier which we call superbase spark which is basically for these getting started workloads the idea won't be the same you get started with the same experience you can scale up to pabytes so our tag lines kind of prototype to pabytes and we as a company need to make sure that we can provide for everyone and if they do scale up and their business keeps growing then we make sure that they have a great time.

主持人：是的，这其实正是我很好奇你怎么看的问题。传统的软件公司大概都是这样起步的：比如从 YC 某一批的早期初创公司做起，然后一只眼睛盯着企业市场。我觉得尤其是像 AI 之前的数据库公司，通常的看法是，你想成为 Oracle，就得尽快打入企业市场，因为钱都在那里。所以你就开始开发各种企业级功能。而你们似乎是反其道而行，专注于 SQLite。你们是怎么考虑这件事的？你们是不是两边都在看？Host: Yeah, that's something I was curious about how you think um about this actually is like the classic sort of software company. you start with, you know, maybe early stage startups like in a YC batch and then you sort of have one eye towards the enterprise and I feel like especially if you're a database company like preAI the convential wisdom as well like you want to be Oracle so you got to get to the enterprise as quickly as you can because that's where all the money is and so you start building out like enterprise features you sort of leaning into SQL light is sort of going the opposite direction like how do you how do you think about it like are you sort of looking both ways?

嘉宾：是的，是的，我们两边都得兼顾，这真的非常难。嗯，基本上我们有两款产品，分别面向两个极端。一款是 Multigres，可以扩展到 PB 级；另一款是 Turso，则适用于原型开发和 SQLite 这类工作负载。Guest: Yeah. Yeah, we're having to do both which is like incredibly difficult. Um, basically we've got two products that cater on the two ends. So multigresses scale up to pabytes and then terso scale down to like these prototyping and SQLite type workloads.

所以，想要以这样的速度增长，还得雇更多人。即使有了 AI，这也正在成为——或者说一直都是——一个真正的挑战，不过也挺有意思的。So trying to do this uh at the rate of growth with like having to employ more people. It's just even with AI is becoming or has been a real challenge but a fun one.

Supabase 的 AI 采用情况AI Adoption At Supabase

主持人：所以你们最近做了一项调查，嗯，发现有 10% 的工程师用编程智能体编写了 80% 的代码；而最近这个比例在短短 6 个月内升到了 60%。这是怎么发生的？到底发生了什么？你觉得接下来会怎样发展？Host: So you ran a poll recently uh where people went from 10% of your engineers were writing 80% of their code with uh the coding agents and then that number recently got up to 60% in a matter of 6 months like how did that happen? What's happening? Like you know where is this going from here?

嘉宾：所以我们内部没有 AI 政策。大家想怎么用就怎么用，我们也让他们使用任何想用的工具。我觉得现在大家都确信这些模型能做出好得多的成果，也能做更多事情。所以采用速度快得惊人。是的，他们在内部构建的东西不只是那种 vibe-coded 类型的东西，而是相当复杂的项目。Guest: So we don't have an AI policy internally. we just let people do whatever they whatever they want and we give them access to whatever tools they want to use. And I think now it's just that they're convinced that the models can do so much better work and so much more. So the adoption has been crazy and yeah the things that they're building internally are not just viodated type stuff. They're pretty intense.

嗯，随着我们逐渐转向 AI 编程领域，我们所做的测试以及采用的测试工具确实相当有用，能确保他们确实知道最终结果会不错。Um, and as we're like shifting into this uh like AI coded realm, like just the amount of testing that we're doing and the tools that we're adopting for testing is being pretty useful to make sure that they actually know that the end result is going to be good.

主持人：是的，我们看到 YC 的初创公司，比如 Blacksmith Depot、Ubie Cloud 这些，都是垂直领域的，因为大家都在做 CI。Host: Yeah, we're seeing that across YC the YC startups like uh Blacksmith Depot, Ubie Cloud, like they're all vertical because everyone's doing CI.

是的。Yeah.

而且你们针对大概三个……所做的测试数量ેણAnd the number of tests that you have for just like three

用于类似评审的爬行动物。reptile for like review.

所以老实说，看到这个还挺不可思议的。是不是某种特定的……就是现在模型已经足够好了，人们只要花足够多的时间，就会觉得，哦，实际上这挺不错的？So that's pretty wild honestly to see. Was it like a partic like it's just the models are good enough now and like you just people spend enough time where they're like oh actually this is quite good

嘉宾：而且需要说服人们，尤其是，呃，工程师，我是说，他们可能不会……Guest: and people need to be convinced especially uh engineers like I mean they might not

年初的时候，我就觉得这非常好，模型也变得越来越强了；而且人们开始意识到，哦，实际上，借助这些模型可以实现很多了不起的事情。再加上纳维-斯托克斯方程之类的各种进展，以及这些事情，都在让市场相信，没错，我们确实能在这里开辟新天地。所以我认为，我们正走向这样的世界，而现在人们已经相信，这就是未来的发展方向。at the start of the year I've thought that it was very good and the models have gotten better but also they're starting to see oh actually you can achieve some great things with these models and all the stuff with Navia Stokes and all these stuff like convincing the market that actually yeah we can break new ground here. So I think that's the world that we're moving towards and now people are convinced that this is the way that it's going to be.

一路走来的经验教训Lessons Learned Along The Way

主持人：你们经历了 Superbase 的三个阶段。最初有点像是一家仪表盘公司，在 YC 期间用 100 天打造出来；然后是 API 公司；现在嘛，可以说是进入了代理时代，到了打造代理想要的东西的阶段。嗯，每个阶段有没有一两件特别让你印象深刻的事，让你觉得：“哦，这就是我们当时成功的关键”？Host: You've seen Superbase like through three eras. First kind of like a dashboard company um built in a 100 days during YC then the API company and then now it's you know sort of this agent you know make something agents want sort of moment. Uh was there like one or two things like in each era that really jump out at you like oh that was the thing that made us in that moment?

嘉宾：我觉得那些转变确实发生了。所以第一个其实……对。我想你是在说，我们加入 YC 的时候，为什么会有一家数据库公司？我们其实……Guest: I think like those shifts happened. So the first one actually Yeah. I think you're saying like why would a database um company exist when we came into YC? We actually

主持人：当时这确实像是个相当反主流的想法。Host: it seemed like such a contrarian idea at the time actually.

嘉宾：对，对，对。我觉得我们看到了，即使对开发者来说，使用数据库也有多难，所以一开始我们想做的那个仪表盘就是：哦，咱们在 Postgres 上面做一个看起来像 Airtable 的 UI，因为我其实也很喜欢 Airtable。Guest: Yeah. Yeah. Yeah. I think like we saw how hard it was to use a database even for developers and so that dashboard first was like oh let's build a UI that looks like air table on top of Postgress because I actually loved air table as well.

我当时就想，要是后端只是一个 Postgres 数据库，那不是挺酷的吗？嗯，那件事让我看到，就连软件工程师也会遇到困难。后来我们转向 AI 的时候，我想我们在另一档播客里聊过这件事。AI API 的转型是因为有人在和我们集成，他们说：“哦，我们想启动很多数据库。我们需要一个 API 来完成所有这些事情。”那大概是 2021 年吧。I was like wouldn't it be cool if that was just a Postgress database on the back end. So um that one was just seeing that even software engineers struggled. And then like when we moved to AI, I think we talked about this on the other podcast, the AI uh API um shift was because we had someone integrating with us and they were like, "Oh, we want to launch lots of databases. We need an API to do all of this." And that was like 2021 maybe.

结果证明，到了 2024 年，这恰恰是正确的做法。当时，Bolt、Lovable 等团队都开始基于我们的平台构建产品。And it turns out that was exactly the right move for 2024 when the likes of Bolt and Lovable and all of these people started building on top of us.

然后今年我才发现，其实根本没人来控制面板了——没人，真的没人再看控制面板了。那么，智能体要怎么构建呢？这次我只是给团队发了一份产品备忘录，大意是必须以代码为先，走原生路线。Superbase 必须转向以代码为先。Then this year I just saw that actually no one's coming to the dashboard like no one no one visits dashboards anymore. So um how are agents going to build? In this one I just kind of put out a product memo to the team that said it has to be code first get native. Superbase just has to shift to code first.

因此，如果某个功能存在于仪表盘上，它基本上就必须与代码中的基础设施即代码实现同步运行。我们重新架构了 CLI 的很多部分，以及其他所有东西，使它们能够在代码沙箱中运行。So if it exists on the dashboard, it basically has to work in lock step in code infrastructure as code essentially and we rearchitected a lot of the CLI and everything to work in sandboxes in code.

主持人：你们当时可能落后太多了，不过你们有没有受到另一家白人公司的启发？Host: Were you guys maybe too far back but were you ever inspired by par another white company?

嘉宾：是的。是的。是的。Par 和 Firebase。Guest: Yeah. Yeah. Yeah. Par and Firebase.

我喜欢那两家公司，而且这些浪潮挺有意思的，对吧？因为它们做的是后端：Firebase 被 Google 收购，Parse 被 Meta 收购。但在某种程度上，我觉得它们为我们后来进入这个领域开辟了道路，让我们能够真正做成一家正经的数据库公司。因为在 2014 年，如果不用 RDS 来做数据库，那简直不可思议。后来它们出现了，人们开始转向 Atlas，这些数据库公司也在某种程度上证明，你不必只用三大超大规模云服务商之一。你完全可以拥有一家正经的数据库公司。所以，对我们来说，时机至关重要。I liked both of those companies and it's funny these waves, right? because they did the back end and Firebase acquired by Google, pars by Meta, but in some ways I think they like blazed the trail for us to come along and actually have a legitimate database business because in 2014 it would have been ridiculous not to use RDS for your for your database. Then they came along, came along, u started moving to Atlas and a lot of these database companies kind of showed that you don't need to just use one of the three hyperscalers. You can actually have a legitimate database company and um so that timing was crucial for us.

主持人：是啊，人们似乎有点忘了，它其实是一款构建得非常好的产品。他们推出产品的时候，正好是我第一次开发 iPhone 应用，那时候能转而使用一个不错的 RESTful API，感觉挺好的。Host: Yeah, past sort of forgotten that it was like actually a really well-built product. They launched like just when I was building iPhone apps for the first time and it was like quite nice to switch to like a nice restful API that I was trying to deal with.

嘉宾：这些转变总是伴随着某种拐点，对吧？当时市场上发生了两件事。不知怎么的，MongoDB 让所有人都相信，NoSQL 应该是一种非常棒的呃数据存储方式。第二件事是移动端。Guest: These shifts always happen with like inflection points, right? So at that point there were two things that happened in the market. Somehow MongoDB convinced everyone that NoSQL was supposed to be like an amazing uh way to store your data. And um the second was mobile.

所以你知道，我们很幸运，也经历了几波这样的浪潮，而现在我们正身处其中。然后……And so, you know, we're fortunate that we had a couple of these waves as well and now we're right in the thick of it. And

主持人：是啊，我的意思是，[清了清嗓子]我想问的其实是，你怎么看企业级市场和早期阶段？因为我觉得，往前追溯的话，Heroku 算是第一个这么做的：先提供最好的开发者体验，然后再扩展。但实际上，要靠人手把规模做大可能相当困难。我觉得你知道，Heroku 好像没能很好地跨过这道坎——随着应用变得越来越大、对性能的要求越来越高，怎样才能让用户继续留在你的平台上？不过从历史上看，每家公司都得自己想办法解决这个问题。我知道你们也在往这个方向看，但说实话，或许你们不必这么做；如果光是面向我姑且称之为 0 到 10 这个阶段的市场，就能以这样的速度不断扩张，那规模会非常庞大。Host: yeah, I mean, this [clears throat] is what I was asking about sort of like how you think about the enterprise versus early cuz I think I mean you go even further back. This is sort of like Heroku was the first where it's like hey like just start with like the best developer experience and then scale up. But it is actually can be quite hard to like scale up with people and I think like you know Heroku sort of I don't could quite bridge that gap um to how do you keep people on you like as the apps get bigger and need to be more performant etc but like historically every company's had to figure that out and like I know you guys are looking that way but you might not have to like honestly if the like the market for just owning like I don't know call it 0 to 10 whatever like keeps expanding at this rate it's going to be huge.

客人：是的。嗯，我们全都想要。所以，Guest: Yeah. Well, we want it all. So,

所以我们可能不必这么做，但呃，我们肯定会这么做。还有，要给 Heroku 点赞。我觉得是他们让 Postgres 流行起来的，但那时候 Postgres 还相当呃新，扩展性也仍然有一些限制。所以，是的，我们不得不围绕 Postgres 搭建一些工具，让它能够无限扩展。so we might not have to, but uh we'll definitely do it. And like kudos to Heroku. I think they popularized Postgress, but at the time Postgress was pretty uh it was still pretty nent and it still got some scaling um limitations and so yeah, we've had to wrap Postgress and some tooling that will allow it to scale indefinitely.

主持人：但我的意思是，我觉得对你们来说，更贴切的类比可能是 AWS 当初很早就吸引到了用户，并且实现了规模化。所以，你们从中学到了什么？比如，你们会如何确保自己能够规模化？Host: But I mean I guess a better analogy for you guys is more like AWS was able to actually like get people early and like scale and so do yeah like what are the lessons maybe like how do you think about making sure you can scale

无限地？infinitely?

嘉宾：我觉得这里的教训是，我听说过一个数据，对方告诉我可能记错了，所以请帮我核实一下：亚马逊 AWS 的收入中，大概有 40% 来自那些最初在 AWS 上起步、后来发展壮大的初创公司。我们想争取的就是这类客户。你知道，我们很清楚，要说服人们从一家数据库供应商迁移到另一家，几乎是不可能的。所以我们只想从第一天起就陪在他们身边，确保他们用得很愉快，也确保他们真的不想离开。Guest: the lesson I think that they I heard a stat and was telling me I might get it wrong so fact check me but something like 40% of AWS's revenue comes from like startups that started on them and then scaled up and like that's the category that we want you know like we know that to convince people to migrate to from one database provider to another is near impossible and so we just want to be there on day one make sure that they have a great time and make sure that they actually don't want to leave.

主持人：同样的商业模式可以剥离。我是说，如果你能做到，这基本上就是世界上最好的商业模式。但你从第一天起就拿下客户，然后随着全球增长最快的公司一起扩张，而且可以无限扩张。Host: The same business model to strip. I mean, it's like basically the best business model on earth if you can get it. But you get them on day one and then like scale with like the fastest growing companies in the world infinitely

你只要专注于一代人，最终就能打造一家世代相传的企业。差不多就是这样。and you just do that for a generation and you become a generational business. That's pretty much it.

嘉宾：是的。这对我们来说很难，因为Guest: Yeah. It's hard for us because

第一天会是什么样子？它正在迅速发生变化。过去，对我来说，第一天总是意味着：为什么要见客户？而现在，第一天开始变成：好吧，每个人都是构建者，他们会用什么工具？有哪些模式？他们会如何选择数据库？这些都是棘手的问题。what does day one look like? That's rapidly shape changing. So in the past day one for me was always like why see customers and now day one is becoming like okay everyone's a builder what are they going to use what are the modalities what how are they going to choose their databases these are tricky questions

主持人：新一批申请现在已经开放了。如果你心里有个创业项目，就去 y combinator.com/apply 申请。永远不嫌早，填写申请表也能让你的想法更上一层楼。好了，回到视频。……这是一个相当不同的客户群体。比如你们刚起步的时候，数据库还没有面向个人用户的市场；数据库公司直接面向消费者做生意这种想法，听起来简直就像语法错误一样。Host: next batch is now taking applications got a startup in you apply at y combinator.com/apply it's never too early and filling out the app will level up your idea okay back to the video it's kind a different customer segment like initially when you started like there was not an individual market for databases like the idea of a database company being a direct to consumer business would have just like sounded like a syntax error.

访客：是的。Guest: Yes.

主持人：嗯，但现在你实际上有两个业务板块。一个是那些处于早期阶段、采用这种强大 Stripe 商业模式的公司；但你也在直接向消费者或可能是他们的代理销售。Host: Um but now you actually have two segments. You have the like early stage companies that has this powerful stripe business model, but you're also like selling directly to consumers or to their agents perhaps.

嘉宾：是的，是的。Guest: Yes. Yes.

主持人：而这些用例大概不会像初创公司那样扩张，但他们可能会一直使用你们，甚至用一辈子，因为你们为某个应用提供支持，而这个应用运行着他们的个人理财软件、出租车公司之类的业务。Host: And those use cases presumably will not scale the way startups will, but they might just like continue to use you for like for the rest of their lives because you're powering the app that like runs their personal finance software or their taxi cab company or something like that.

嘉宾：随着他们的生活不断发展、积累的信息越来越多，这基本上就是我们自身成长的一个指标，你知道。所以他们只是存储得更多。人们正在收集更多数据。这种产消者市场本质上是推动我们增长的一个良好方向。Guest: And as their lives grow and they accumulate information, that is basically an index of our own growth, you know. So they just store more. People are collecting more data. this kind of proumer market is essentially a good growth vector for us.

为个人智能体而构建，并亲自试用Building For Personal Agents, Dogfooding

主持人：我想问，你是从这个角度看待个人智能体领域的吗？如果说编程智能体需要 Supabase，这一点很明确。那你会把下一阶段设想为：假设我们都有个人数据库？你需要做些什么，确保个人智能体能轻松地与你交互吗？这有什么不同，还是说本质上就是同一回事？ 是的，现在我非常看好个人智能体。我的行政助理离开了一周，我也因此确切地了解了它们能做什么。现在我有点沉迷于为个人智能体打造产品这个想法。确实，我跟公司里的人说过，我们是代码优先的。嗯，我们是为那些以代码为先的人打造产品的，但实际上，我们是为智能体打造产品的。Host: I guess do you think about the personal agent world in that through that perspective then if sort of coding agents want superbase it's very clear like do you think about the next phase as being assuming we all have personal databases like do you need to do anything to make sure that it's easy for personal agents to talk to you is that any different or is it basically the same thing? Yeah, I'm very bullish now on personal agents after a week of my EA being away and uh me learning exactly what they can do. And now I'm just kind of obsessed with the idea of building for personal agents. And it's true that I said to our company like we're code first. Um like we're building for humans that are doing code first, but actually we're doing it for agents.

那些人类很快就不会真的再进行交互了。所以，我现在的构建方式是使用 dots。嗯，我一直和它打电话聊天，告诉它：“哦，你能做这些改动吗？”而我用来确保自己是在正确地构建东西、正确地进行自用测试的一种启发式方法就是：我不看代码，也不允许自己检查架构，除非我想确认它确实在正确地构建东西。Those humans pretty soon won't actually be interacting. So like the way I've been building is I'm using dots. Um I just sit on a phone call with it all the time and I'm chatting to it and saying oh can you make these changes and my kind of heristic to make sure I'm building or dog fooding correctly is that I just don't look at the code and I don't allow myself ever to check the architecture except when I want to check that it's actually building things correctly.

但我在做这些改动时，只想跟它聊聊，看看它能改些什么。所以，But when I'm making these changes I just want to talk to it and see what it can change. So,

主持人：我们中的一员。Host: one of us.

嘉宾：这也太不可思议了。它做的事情简直令人惊叹，我觉得就像是两年前科幻电影里的场景。可现在，我经历了这么多这样的时刻，简直惊呆了。要是六个月前把这个展示给别人看，他们肯定会觉得这根本不可能。Guest: It's crazy as well. Like, it's doing some phenomenal stuff that I just it feels like something out of a sci-fi movie from like 2 years ago, but now like I'm having so many of these moments that I'm just mind blown. If you had shown someone this 6 months ago, they would have just thought it was impossible.

主持人：是的。你……几周前我参加了你们的 Supabase Select 大会，顺便说一句，那场大会真棒。我当时突然冒出一个有点疯狂的想法。我坐在那里，听你介绍 Supabase 正在推出的各种很棒的新功能，就想：如果我在用 Supabase 开发应用，也许我根本不需要自己去了解这些很棒的功能。我想把我的智能体派去参加 Supabase Select，让它听听这些新功能，再想办法把它们集成到我的代码库里。Host: Yeah. you I was at um your Subbase select conference a couple weeks ago which is awesome conference by the way and I had this like kind of crazy thought. I was sitting there and you were talking about all these awesome new features that Superbase was putting out and I was like you know if I was building an app on Superbase maybe I wouldn't even care to understand all these awesome features myself. I want to like send my agent to Superbase Select to like listen to all the awesome new features and figure out how to integrate them into my codebase.

嘉宾：哦，真是太不可思议了。一场真正的虚拟会议。我们应该办一场。专为智能体举办的会议。Guest: Oh, that's wild. A truly virtual conference. We should do that. A conference just for agents.

面向代理人的会议。一个为代理人举办的会议。For agents. A conference for agents.

他们都会现场亮相。They all turn up live.

直播。他们[清了清嗓子]可以互相聊天，交流一些技巧，比如在 Facebook 直播上之类的。Live. They [clears throat] can like talk to each other, exchange tips on like, you know, Facebook live.

主持人：哇。嗯，你可以把它传过去。你可以通过隔空投送之类的方式，把 Markdown 文件发给大家，但大家得在现场、身处观众席才能收到。Host: Wow. Well, you can bridge it. You can sort of airdrop like the markdown file for everyone, but you have to be there in like the audience to get it.

嘉宾：我们就称它为制品库吧。Guest: We'll call it the artifactory.

主持人：天啊，我还挺喜欢这个的。我们之前聊过，你一直在做不少事情，确实能让智能体更喜欢你们，比如错误消息之类的。你知道，那个关键洞见是什么？还有没有其他你们正在做的事情，一方面看起来挺显而易见，另一方面却还没人做？Host: Oh man, I quite like that. We talked about before this like there's just a bunch of things that you've been doing that like really make agents like you better like error messages you know you know what was that key insight and like are there a bunch of other things that you're doing that kind of obvious on the one hand on the other hand like nobody's doing yet?

智能体优先设计与评估‌Agent-First Design and Evals

嘉宾：对，就像错误消息。是的，昨晚我去了一个开发工具中心，很惊讶这件事竟然没有那么显而易见。不过我们确实深入研究了错误消息，这样你就可以设想这样一个使用场景：比如，我想构建一个应用程序。通常，开发者看到的错误消息可能只是“500”之类的基本信息，让你知道出了问题。但现在，你实际上希望智能体能够自行修复问题。因此，在错误消息里，你会直接告诉它们如何修复这个错误，或者让它们去阅读相关文档来解决问题。Guest: Yeah. So like the error messages. Yeah. I was at a dev tool center last night and I was surprised that this wasn't so obvious, but we really dug into our error messages so that you can take a use case like oh I want to build an application and generally like developer error messages are like 500 um something basic and you just know there's a problem but now you actually want the agents to like remedy themselves. So inside the error messages, you are literally telling them how to fix this error or to go and read some docs to fix the error.

所以很大一部分就是选定你的使用场景，然后反复迭代、改进自己的错误提示，这样你基本上就能一次性搞定任何想做的事情。So a lot of it is just picking your use case and just trying to do these loops on improving your own error messages so that you can oneshot basically anything that you want.

主持人：对，这说得通。基本上，你知道，如果一个智能体在使用你，它会遇到一条错误消息。过去，人得去 Google 搜索，然后做一堆事情，但在这里你可以直接说，哦，比如说，你只是节点用完了，所以你可能该去做这个。Host: Yeah, that makes sense. Basically, you know, if you're being used by an agent, the agent will encounter an error message. In the past, a human would have to go Google that and do a bunch of stuff, but here you can just say, oh, like you're just, you know, out of nodes, so you should probably go do this.

嘉宾：对，因为要赢得智能体的青睐，大致分两个阶段。第一是被模型选中；第二是如果它们卡住了，你不希望它们转而使用别的工具。所以，它们肯定会在某个时候卡住。你只要给它们提供解决问题的工具就行。Guest: Yeah, cuz there's like two stages to winning the agents. The first is being picked by the model, and then the second is like if they get stuck, you don't want them to switch away. So, guaranteed they'll get stuck uh at some point. You just want to give them the tools to remedy.

所以，呃，其实没那么复杂。他们现在已经足够聪明，能弄明白很多事情，但你确实得把以前只是面向人类和开发者的许多东西，重新设计成适用于智能体的。So, uh, it's not actually that complicated. They're smart enough now that they can figure out a lot of stuff, but you do have to re-engineer a lot of what previously was just for humans and developers for agents.

主持人：你会针对智能体测试你的项目或产品吗？比如让智能体尝试使用 Superbase，然后报告它们遇到困难的地方？Host: Do you test your project, your product for agents? Like, do you have agents like try to use Superbase and then like report all the places where they had trouble?

嘉宾：是的。是的。是的。各种不同的模型。Guest: Yeah. Yeah. Yeah. All the different models.

我们有一个评测网站，可以查看哪些模型构建得最好；我们内部也有自己的评测套件。我们还会评测哪些模型在使用 Postgres 时表现最好。这对业界来说很有意思，我们也在围绕它培养技能，让大家能够采用这些模型，并真正用 Postgres 进行开发。所以，是的，我们做了很多测试。事实上，现在我们很大一部分工程工作都投入到测试特定用例上，而不是构建本身。We've got an eval um website where we see which models are building the best and we got our own eval um suite internally. We eval as well which ones are best just with Postgress. So that's interesting for the industry and build skills around it so that they can adopt them and actually develop with Postgress. So yeah, it's a lot of testing and in fact pretty much now a lot of our engineering effort is going into like testing specific use cases rather than the building.

我们想深入探讨人们如何围绕这一点进行构建，以及如何打造相关套件。We want to think through how people are building and build suites around that.

主持人：Gary，你开发 Gbrain 时，是基于 Superbase 构建的。能聊聊你是怎么决定基于 Superbase 来构建它的吗？作为用户，你的体验如何？嗯，我想，Gbrain 可以说是我写过的一堆东西的提炼版。我最早做的是 Gary's list，它有点像智能体式的新闻编辑部。我基本上得搭建一个研究系统，用于 RAG，也用于政策和论文；它会阅读所有关于某个主题的报纸文章，然后尝试综合归纳。后来我把这些东西提炼成了面向 OpenClaw 的开源检索系统，因为当时的想法是：好吧，我用 Rails 搭建了它，那有点像是一个为智能体服务的富士康工厂。Host: Gary, when you built Gbrain, you built it on top of Superbase. Can you talk about like how did you decide to build it on top of Superbase? What was it like for you to be a user? Yeah, I guess I mean Gbrain was like a distillation of a bunch of stuff I wrote like I first worked on Gary's list which was like agentic it was like an agentic newsroom and I had to build up like basically a research system for rag and for like policy and papers and it would like read every newspaper article about a given topic and then try to synthesize um and then I took that and then distilled it into uh open- source retrieval for openclaw cuz the idea was like, okay, I had it in Rails and that was kind of like a Foxcon factory for agents.

就好像我把每次调用 LLM 都看得成本极高、危险至极。It's like I treated every LLM call as very expensive and incredibly dangerous.

后来我看到 OpenClaw 时，它就是，你知道，有点像 Eselin。它是一种截然不同的、呃，你知道，你与 AI 协作的方式，因为这时你会觉得，哦，AI 很聪明。呃，它并不是想伤害你，所以你就应该让它去做事，只要给它数据和能力就行。于是我意识到，一百万个 token 实际上是一种惊人的工作记忆。大多数人脑子里能记住的东西也就七个左右，上下浮动两个。And then when I saw OpenClaw, it was this, you know, it was kind of like Eselin. It was just like a very different way for uh you know, you to work with AI cuz then it's like, oh, the AI is smart. uh it's not trying to hurt you and then you should just let it like do stuff and you should just give it data and capabilities. And so I recognized a million tokens is actually an incredible working memory. Like most human beings only have like seven plus or minus two things that they can keep in their head.

而一百万个 token 基本上大概相当于三本《哈利·波特》。但即便如此，对智能体来说还是有点局限。比如，随时都把正确的三本《哈利·波特》放在上下文里，确实很有挑战。所以感觉在公司的“大脑”和我个人的东西之间，好像还存在这么一个中间地带。Whereas like a million tokens is like basically uh like three Harry Potter books. But then even that is like a little bit limiting for the agents. Like keeping the correct three Harry Potter books in your context at any given time is a real challenge. So it felt like there was this thing in between for a company brain or like my personal stuff.

就像你一样，我有五十万个 Markdown 文件，记录着我曾经进行过的几乎所有交流。所以这个东西确实掌握了关于我以及我在意的一切的上下文。不过，在任何一个特定时刻，代理可能只需要其中两页左右。这是个检索问题。所以到了那个阶段，你知道，数据量可能有三四十 GB，你就需要 pgvector，需要 Postgres。你知道，用 SQL 很容易就能搭建图数据库。所以 Gbrain 就是这样：RAG 检索，再加上一个能把非结构化数据组织成结构化数据的图数据库。It's like you I have half a million markdown files on like every communication I've ever had. And so this thing really does have context on me and everything that I care about. Uh but then at any given moment like the agent it might need like two pages or something. it's a retrieval problem and so uh at that point you know at many I think it's like 30 40 gigabytes you need PG vector you need Postgress you know you can do graph databases very easily in SQL and so that's what Gbrain is it's like you know rag retrieval um plus like a graph database that creates like structure out of unstructured data

所以它就像动态模式，有点像我记得 Palanteer 当年那样。and so it's like dynamic schemas like a little bit like what I remember uh Palanteer was back in the day.

然后，你知道，整个想法就是，当中间有这么一个环节时，智能体会强大得多：智能体只要说出自己要找什么，它就会遍历图谱，执行所有这些向量搜索，然后回来告诉你：“这是报告，把它加载到上下文里。”这就是 Gbrain。然后 Superbase 就非常直接了。And then, you know, the entire idea is that agents are much more powerful when um there's sort of this intermediate thing where the agent can just say like this is what I'm looking for and it'll traverse the graph. It'll do all of the uh you know uh vector search and it'll come back and say like here's a report and like load this into context. And so that's what Gbrain is. And then Superbase was just like very straightforward.

我需要托管的 Postgres，它得能很快支持一个 50、100 甚至 300 GB 的数据库语料库。它一直表现得特别好，自动扩缩容也运行得很出色。现在最有意思的是，配合 Browser Use——我现在用一个侧边浏览器来使用 Browser Use——它就像是：哦，对，OpenClaw 可以接入 Supabase，使用数据库或你们新做的 API，而且它能自己把这一切管理好，甚至可以自我管理。It's like I need I need hosted Postgress and I need it to be able to support like a 50 or 100 gig or 300 gigabyte you know database uh corpus really fast and uh it's been great like you know the autoscaling works really well and now the funniest thing is like with browser use like I use a side browser now for browser use and it's like oh yeah like open clock can go into superbase and you know use the database or the new APIs you made and it just like managed it itself it can like self-manage

嘉宾：你当时是不是得提示它，让它去理解像图这样的数据结构，或者 RAG 之类的东西？还是……Guest: Were you having to prompt it to like figure out the data structures like graphs or like rag or anything like that or

主持人：呃，我是说，有意思的是，我记得我当时打开 Cloud Code，就直接说：“用 Exa 下载并整理你能找到的所有 AI 研究论文。”嗯，今天我可以用 Alpha Signal 之类的工具，不过也可以说：“去找所有关于 RAG、图数据库，还有文本检索的研究，然后根据我的使用场景做个总结。”我的使用场景就是：我该怎么帮助一个智能体访问这些东西？等它做完之后，它就说：“哦，好吧，那我们就这么做。”Host: uh I mean what's funny is like I remember going into cloud code and just saying like use Exa and download and diorize uh every paper you can find in AI research. Um, today I could use like alpha signal or something, but it's like go and find every piece of research about rag and graph databases and like you know text retrieval and then summarize it for like my use case which is like how do I help an agent get access to this stuff and then after it did that it's like oh okay well here's here's how we're going to do it.

嘉宾：是的，前几天晚上我参加了一场晚宴，讨论的主题大概是数据库的未来。有一种观点认为，数据库本质上是一种数据检索机制，你可以建立索引，让它们按照特定格式搜索数据，比如图数据库或 RAG。还有一种特别有意思的想法，就是让智能体不断循环运行，创建出最适合搜索的数据结构。Guest: Yeah, I was at a dinner the other night on like the future of databases and one idea was like databases essentially are like a retrieval mechanism for data and you know you can put indexes so that they'll search across the data in certain format. So a graph or rag and then one of them which was super interesting was just like putting an agent on a loop to create the perfect data structure for the search.

比如说，如果你要在这个数据集中搜索这么多次，而且每次都要花 10 秒，那为什么不让一个智能体循环运行，创建一种新型索引，或者找出最适合的索引，让它能在一秒内返回结果呢？Like if you're searching this data set this many times and it's taking 10 seconds, then why don't you just put an agent on a loop to create a new type of index or like find the best index for returning that in less than a second.

主持人：我的意思是，只要你拥有真正智能的代码生成，动态检索显然马上就会出现。Host: I mean dynamic retrieval is pretty clearly going to happen the second you have really smart codegen.

嘉宾：是的。Guest: Yeah.

主持人：所以我是说，目前我用它来做 OpenClaw。然后，呃，我会用我的生产实例，再从中提取轨迹，整理成一个评测数据集。然后我还有一个单独的仓库，叫 Gbrain evals，里面有 40 个不同类别，涵盖各种特定类型的检索，比如检索效率、成本效率、延迟等等。评测很棒的一点是，你可以直接告诉智能体：“循环执行，自己研究并不断迭代；只要能提升这项评测的指标，就把它合并到 master，并默认启用。”对。Host: So I mean for now I mean I use it for open claw. So then uh I use my production instance and then the traces from that um I extracted out like a eval data set and then I have a separate um repo called Gbrain evals and it's got 40 different categories of like specific types of uh retrieval uh retrieval efficiency like cost efficiency latency and then uh the cool thing about eval is then you can just tell the agent like loop you know just auto research and loop and anything that uh improves your stats on this eval like ship it into master on by default. Yeah.

对于任何你尝试过但没成功的事情，都写一个 Markdown 文件，说明你认为它为什么没成功，然后把文件归档到 Gbrain evals 里。我用 Cappy。Cappy 有个叫“captains”的概念，有点类似于 Grockbots 的 bots。所以你只要给它提供一些上下文就行。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 Gbrain evals. I use Cappy. There's a you know Cappy has this concept of uh captains which is kind of like similar to Grockbots bots. And so you can just give it a context.

所以我有一个一直在运行的，负责想出新类别。还有另一个队长也一直在运行，负责遍历评测和自动研究中的所有类别，每天都试着想办法提升我们内部评测的分数。And so I have one that is always going that's like come up with new categories. And I have another captain that's uh 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

而且它一直都在运行。这是一个非常原始的 RSI 版本，适用于某个特定用例。不过我想，如果你把抽象层级提高一点，也可以这么做——不是针对我的用例，也就是用于 OpenClaw 或类似工具的用例，而是泛指任何人的检索用例。唯一会变的就是用例、轨迹和数据集。and that's just going all the time. It's a very primitive uh version of RSI for like a 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 uh 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 uh the traces and the data set.

编程的未来The Future Of Coding

主持人：你显然懂 eval，而且你可以改进自己的软件，因为你就像是把这个框架套在软件外面。你觉得未来的开发者也必须真正了解这类东西吗？还是……Host: You obviously know about eval 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 or

嘉宾：也许不是？Guest: maybe not?

主持人：说实话，我觉得现在还处于非常早期的阶段。我就是随便折腾一下，而且我喜欢在开源项目里做这些事。我希望别人看到后会想：“哦，我可以把这个用起来。”我觉得我们现在其实是在摸索如何使用这些东西的基本方法。没错。我记得今年早些时候读到史蒂夫·亚吉（Steve Yaggi）关于软件工厂之类的文章，当时完全没搞明白。可现在我觉得，嗯，我至少已经东拼西凑出一套适合自己的办法了。Host: I mean honestly I feel like we're so early that you know I'm just messing around 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 Yaggi's uh software factories and things like that and then not being able to totally figure it out and it's like, oh, no, no, I feel like now I've cobbled together something that works for me at least.

是啊，是啊。Boris Turney 来我们这儿的时候，嗯，他对编程未来的设想更像是：你只要像跟朋友聊天一样跟 Claude 说话，不用了解 eval 之类的这些东西，Claude 就会自己琢磨出怎么把你脑子里的想法做出来。Yeah. Yeah. When we had Boris Turney here, um 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 eval all this all this stuff and like Claude just like figures out how to build the thing that you have in your mind.

嘉宾：我有一个域名 openusd.dev，这是因为实际上有一种叫作 OpenUSD 的文件格式，而我会收集域名，然后突然……Guest: 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、Visa，还有其他所有人都宣布了 Open USD，我就想，哦，我最好现在就把这个域名用起来。但我一直没时间用，所以我就跟那个 dot 聊了聊，它就这样开发出了一个带有生态系统等内容的网站。我当时在电脑上跟它聊，后来快结束一天的时候，我又在手机上给它打了电话——就是我准备上床睡觉的时候。听起来可能有点可疑，但我保证我只是在跟它一起写代码。我跟它说，我不喜欢生态系统链接到使用场景的这种信息架构，能不能给我一些建议？它给了建议，我就说，好啊，那就按这些建议改吧。20 秒后它就说，啊，好了，已经改完了，要不要刷新一下？我刷新了网站，内容写得真的很好，所有东西也都串联起来了，还把 SEO 这类东西也配置好了。所以，传统上那些我本来得做的常规工作，我都还没做呢。stripe and visa and everyone announced open USD and I was like oh I better put this domain to use now but I never had time 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 just coding with it and I was like saying I don't like the information architecture of how like the ecosystem links to the use cases can you make some suggestions and it did and I said okay yeah implement them and then 20 seconds later it said ah yeah okay I've done it do you want to 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.

我刚刚一直在和它聊天，真的感觉就像那种时刻——我仿佛瞥见了未来的一角。I've just been chatting to it and it really felt like one of those moments where I was I sort of saw a glimpse of the future.

主持人：我的意思是，你能做到这一点，因为你知道自己想要构建什么。Host: I mean you can do that because you know what you want to build.

嘉宾：问题就在这儿。对。所以，我显然有工程方面的背景，也算知道怎么给它写提示词，但我正努力什么都不说。我尽量不把它引向 GitHub 之类的地方。Guest: 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.

我想像普通人那样写代码，或者像某个人明年会写的那样，这样我就能实际使用 Superbase 来测试它，并看看一年后用 Superbase 会不会顺利。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 um Superbase and know that oh is it going to have a good time with Superbase in one year's time.

主持人：是啊，鲍里斯这么说还挺有意思的，比如“哦，我只想让它自动完成。”当然，一旦它进入分发阶段，模型就真的把这项能力写进权重里了，你懂吧。但在那之前，它还需要一些 Markdown 之类的东西。你只要给它一点提示，不需要很多，稍微提示几句，它就能做到了。Host: Yeah, it's funny for Boris to say like, "Oh, I just want it 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 so. You just like a like not even a lot of prompting, like very small amounts of prompting, it can just do it.

我觉得我们正在进入社会中一个非常奇怪的时刻：呃，听起来 RSI 确实已经到来了，就像从 20% 走到 80% 的那个阶段——AI 研究正在发生，嗯，基本上是在这些循环里进行，你知道，在 Claude Code 或 Codex 之类的工具里，或者其他什么地方。与此同时，社会里又没有足够多像你这样的 Paul，知道该构建什么、该怎么向它提问。所以现在就像是一股不可阻挡的力量撞上了一堵不可移动的墙。模型的能力正在呈抛物线式飙升，而真正知道如何借助它对社会产生影响的人数，基本上还是不变的。I we're entering this very strange moment in society I think where like uh it sounds like RSI really is here and it's like going from like the 20% to 80% moment of like AI research is just happening um in sort of these inside these loops inside you know cloud code or codeex 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.

开拓更多创业机会 + 结语Opening Up More Entrepreneurship + Outro

嘉宾：是的，而且希望能对此感到兴奋。我觉得这是另一件重要的事。我想很多人都变得有些疑神疑鬼，但我真心期待未来能给很多人带来怎样的可能。Guest: Yeah. And want to be kind of excited by it. I think that's the other thing. I think a lot of people were getting paranoid, but I'm genuinely excited about what the future could be for a lot of people.

我之前创办的很多初创公司，关注的都是蓝领工人，以及那些我为他们提供技术支持的人——很多人一辈子都得辛苦工作，你懂的。我真正喜欢 Superbase 的一点是，嗯，因为有了这个平台，我看到了很多创业机会。所以我能想象这样一种未来：创业的人会多得多，而且对很多人来说，这其实是一种相当充实的生活方式。所以说，我对 2027 年挺期待的。只要我们能保持现在的节奏，避开几件疯狂的突发事件，那很多人都会度过一段有趣的旅程。A lot of my previous startups were focused on like blueco 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 superbase is that it's um like I see a lot of entrepreneurship um 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 crazy events, then it should be a fun ride for a lot of people.

主持人：我们正看到这样一个阶段：垂直 SaaS 领域的创始人实际上在融资 A 轮时有些吃力。你知道，当你的规模还比较小，比如 ARR 只有 500 万到 1,000 万美元时——即便如此，按过去的标准，这也是相当可观的 ARR，甚至在 9 到 12 个月前，这样的成绩基本就能确保拿到 A 轮融资；但现在嘛，我也说不准，投资人似乎不太感兴趣。横向 SaaS 和 AI 投资看起来则完全是绿灯，但垂直 SaaS 领域的人确实很难融资。不过，这种情况恰好发生在另一个时刻：你往往只需要 10 到 15 个人，就能做到 1,000 万到 1,500 万美元，甚至 2,500 万、3,000 万或 5,000 万美元的 ARR。到了那一步，你的盈利能力就已经很强了。Host: We're seeing this moment where vertical SAS founders actually are kind of struggling with raising series A's. uh you know when you're subscale at like you know five to 10 mil ARR even which like historically is a lot of ARR like that's like a guaranteed series A even like 9 or 12 months ago and today it's like uh I don't know people are kind of like not really into it um for vertical like horizontal and AI investments like seems like it's uh totally green light but like vertical SAS people are really struggling but it's also sort of happening right at the moment where you can get to 10 to 15 mil, you know, often 25, 30 mil, 50 mil with like 10 or 15 people. And so at that point, like you're very profitable at that point.

嘉宾：对，对，对。比如你有15个人，每人200万美元的AR，利润率是50%，那你们每个人一年就能赚100万美元。Guest: Yeah. Yeah. Yeah. With like if you got 15 people, 2 million AR per head and with 50% margins, you're all making a million a year.

我是说，对很多人来说，那真是个了不起的结果。I mean, that's an amazing outcome for a lot of people.

主持人：对。同时，我们也会给很多人做办公时间辅导，他们觉得自己已经拿到了梦寐以求的大奖，结果却因为融不到 A 轮而沮丧。所以，你知道，我很多时候都会跟他们说：你以后回头看这件事，可能会觉得这是因祸得福，因为你根本不需要这笔钱。以前，你得融个一亿美元，才能做到年收入三千万美元，因为你不得不雇一大堆人；而现在，你不用这么做了。Host: Yeah. And simultaneous to that, we just do a lot of office hours with people who do like they got the brass ring and then they're bummed out that they can't raise the series A. And so, you know, many of my office hours there are just like you're probably going to look back on this as a blessing cuz you don't need the money. Like time was you had to raise like a hund00 million to get to like 30 million a year in revenue cuz you just had to hire all these people and now you don't have to do that.

嘉宾：是啊，是啊。在创业公司里，融资确实像是一种勋章。我是说，我一开始也是这样，拿到融资时，感觉自己好像成就了一件了不起的事。但实际上，你知道，现在在我看来，真正了不起的事应该是不用融资。所以我有点羡慕那些已经走到这一步的公司。Guest: Yeah. Yeah. There's a real thing in startups like the badge. I mean it was the same for me like to get funding at the start like feel felt like you know I was achieving something great but actually you know to actually not fund raise now would in my mind be like oh that's achieving something great so like I'm a little bit envious of these companies that are getting to that point.

主持人：是啊。我也说不准。我的意思是，世界变化非常快，但你为所有公司打下的坚实基础，确实让它们成功经受住了每一波浪潮。你有什么建议，能给那些试图效仿你的人吗？Host: Yeah. So, I don't know. I mean, it's a super changing world, but um your super basease of all the companies has really been able to ride high through every single wave. Um do you have any thoughts for people as they try to emulate what you've done?

嘉宾：有一件事让我晚上能睡得很踏实，那就是这有点像林迪效应。数据库已经存在了 50 年。我想它们还会再存在 50 年。无论人工智能最终如何，我相当确定，数据库都会一直存在。Guest: One thing that helps me sleep well at night is that it's kind of the Lindy effect. Databases have been around for 50 years. I'm I think they'll be around for another 50 years. And this is one that at the end of AI no matter what I'm pretty certain they'll be databases.

除此之外，你喜欢什么都可以。呃，你得选择那些非常经得起时间考验的类别。如果你要押上自己的一生——我基本上就是这么做的——那就选一个你觉得值得投入的类别。我觉得另一个问题是，事物变化得太快了。所以，作为 Supabase，我们不试图掌握所有答案，而是努力确保自己总能以最快的速度适应变化。你知道，对我来说，我评估过，也关注过很多我最喜欢的开发者工具。呃，它们往往都是从关注开发者起步，然后不断向上发展，变得非常企业化，也就逐渐停滞下来，失去了那份热爱。So apart from that whatever you will like uh you got to choose categories that are very durable and if you're going to bet your entire life which is basically what I'm doing you choose the category that you feel is worth investing in. I think the other one is like things are changing so fast. So we don't try to have all the answers as superb base, but we just try to make sure that we're always adapting the fastest. And you know, for me, I've evaluated or like watched a lot of my favorite dev tools. um they kind of start with the developer focus and then they always move up and they become very corporate and they kind of stagnate a lot and they lose that love.

从我们的角度来看，至少从我个人的角度来看，像 Stripe 这样的公司，确实有这么一类人，比如创始人，他们真正关心的几乎就是专注于新的构建方式。所以，如果你是在为下一波浪潮做准备，就得始终留意未来会出现什么，而现在的时间窗口非常短。变化太快了，不过，关键是要保持高度灵活，并确保团队有能力迅速调整。这就是我们明年要重点关注的事情。And from our point of view, at least from my point of view, companies like Stripe for example, they have this real like someone like a founder who just cares about like almost focusing on what the new ways of building are. And so if you're like building for this next wave, you just always need to be one eye on the future of what is next, which is a very short timeline now. Things are moving so fast, but um being super adaptable um and making sure you've got capacity within your team to shift very fast. That's the thing that we're that we're focusing on for the next year.

主持人：你从中学到了什么？有没有什么具体的经验？比如，你可能经历过最初的氛围编程转折点，之后又遇到了 Opus 48 的转折点，还有代码生成。等下一波到来时——希望接下来会有很多个转折点——你会做些什么不同的事，让自己为此做好更充分的准备？Host: are the things that you've learn maybe any specific things you've learned there like because you've had you know maybe had the initial vibe coding inflection point and then the opus 48 inflection point and just codegen like when the next sort of wave hopefully next like many inflection point hit for you but like are there things that you'll you'll do differently to be better prepared for it

嘉宾：嗯，首先，内部试用自己的产品是最重要的事情之一，至少从我们的角度来说是这样。所以我总是会拿我们的工具来试用，看看还有哪些差距。没有什么反馈比自己用工具时卡住更好了。嗯，然后还得留出人力和时间。所以我们会尽量和这个领域的关键参与者合作，而这位生态伙伴一直很有帮助，因为他们会给我们反馈，告诉我们他们正在构建什么。我们也会尽量在团队里留出一些余力，这其实也很难。这样他们有想法时，我们就能试试看。不过，实际上很多尝试并不会成功。即使看起来我们是在合作做一些新鲜酷炫的事情，我们其实也不知道最后会怎么样。Guest: well first of all like dog fooding is one of the most important things at least from our um perspective so I'm always trying these tools with ours to know where are the gaps there's no better feedback than you getting stuck on your own tooling. Um, and then having capacity. So we try to partner with the key players in the space and this ecosystem player has been really helpful because they give us feedback on what they're building so that and we try to leave some capacity within the team which is also very difficult but um so that when they have ideas we can we can give it a shot and not a lot of the bets actually win. Even when they seem like we're partnering together to do some new cool thing we actually don't know.

它们听起来可能很酷，我们也会试试看，结果却不太成功；但那些真正奏效的点子，最终会让我们一起乘上这股美妙的浪潮。They might sound cool and we try them out and they kind of flop, but the ones that do work then end up meaning that we ride this awesome wave together.

主持人：这是一个很棒的收尾。保罗，非常感谢你，伙计。我们下次再见。Host: That's a great note to end on. Paul, thanks so much, man. We'll see you guys next time.