德尔菲公司的达拉·拉德杰瓦迪安：AI数字心智如何扩展人类连接

我们现在就给Adelphi打电话吧。

Let's call Adelphi right now.

我同意。好啊。要不我们打给我朋友？其实我还没见过他本人，但我和Adelphi是朋友。阿诺德·施瓦辛格？

I'm down. Yeah. How about we call my friend I actually haven't met him in person, but I'm I'm friends with Adelphi. Arnold Schwarzenegger?

对。

Yeah.

你们觉得怎么样？

What do we think?

太棒了。

Love it.

嘿，我是AI阿诺德。我来这里是为了直截了当地帮你们变得更强大、更健康、更快乐。今天有什么想法？

Hey. This is AI Arnold. I'm here to cut the crap and help you get stronger, healthier, and happier. So what's on your mind today?

阿诺德，我每天只有十五分钟锻炼时间，感觉有点少。但我想感觉良好，也想改善健康状况。你有什么建议？

Arnold, I have fifteen minutes a day to work out, which I feel like is not a lot. But I wanna feel good and I wanna get better in my health. What do you recommend I do?

只要专注发力，十五分钟完全足够。别想太多，坚持简单高效的多肌肉群动作。做一到两组训练，比如俯卧撑、反向弓步和仰卧举腿。缩短休息时间，全力以赴。

Fifteen minutes is plenty if you focus and go hard. Don't overthink it. Stick to simple, effective moves that hit multiple muscles. Do one to two sets of exercises like push ups, reverse lunges, and lying leg raises. Keep rest short and push yourself.

很快你就会有冠军般的成就感。现在就开始吧。

You'll feel like a champion in no time. Now get to it.

太棒了。今天的嘉宾达拉正在打造一个挑战我们对人类连接与知识传递根本假设的项目。他的公司Delphi创造数字思维体——不仅能捕捉人们的言语和声音，更能呈现其思考方式和新情境推理能力的AI表征。达拉的洞见在于：AI正推动从信息流消费到对话式媒体的转变。他认为随着AI变得普及，人类精力与真实连接将成为稀缺体验。

That's awesome. Today's guest, Dara, is building something that challenges our fundamental assumptions about human connection and knowledge transfer. His company Delphi creates digital minds, AI representations that capture not just what people say and how they sound, but how they think and reason through new situations. Dara's insight is that AI is driving a shift from information consumption through feeds to conversational media. He argues that as AI becomes abundant, human energy and authentic connection become the premium experience.

这场对话揭示了下一波AI浪潮或许不会取代人类，反而会放大我们最独特的人性特质。请欣赏本期节目。达拉，非常感谢你今天加入我们。

This conversation reveals how the next wave of AI might not automate humans away, but actually amplify our most uniquely human qualities. Enjoy the show. Dara, thank you so much for joining us today.

谢谢邀请。

Thanks for having me.

好吧。数字思维体，AI克隆人。听起来有点像《黑镜》里没人再互相交流的剧集。比如，说服我改变看法吧。

Okay. Digital minds, AI clones. Sounds a little bit like a Black Mirror episode where nobody's talking to each other anymore. Like, change my mind.

首先，我们已经摒弃'克隆人'这个词，不再这么说了。哦，是数字思维体。

Well, one, we got rid of the word clones, so we don't say that anymore. Oh. Digital minds.

好的。

K.

但回顾历史上的技术革命，当印刷机问世时，人们会宁愿阅读他人思想而不交谈吗？收音机出现时，听匣子里的声音而非当面交流，这该让人变得孤僻吧？但事实上，播客听众或读者反而更渴望见到创作者。阅读电子邮件就算社交障碍吗？如今我们还能以互动方式获取这些信息。

But I think if you look at past revolutions of technology, when the printing press came out, are you gonna read someone's thoughts instead of talking to them? When the radio came out, you're gonna listen to a voice in a box instead of talking to them, it must make you antisocial. But I think what each of these things did is you listen to someone on a podcast or read a book, you end up wanting to meet them even more. And you may read an email from someone, does that make you antisocial? Now you can just consume that information in an interactive way.

我们观察到的现象——这点稍后可以详谈——是数字意识反而会促使人们更想与你交流。因此这不是取代人际联结，而是以更符合用户时间习惯的方式，填补原本无法实现的连接可能。

And what we've seen, which I can talk about more later, is the idea of having a digital mind ends up leading to people wanting to talk to you more. So the idea isn't replacing human connection, but providing access where previously there was none in a way that is more temporally convenient for the end user.

在人人拥有数字分身的世界里，真实人际互动的价值又将何去何从？

And in a world where everyone has a digital twin, what, you know, what becomes of, you know, the value of real human interaction?

即便抛开数字分身不谈，我认为AI会让真实交流更显珍贵。

I think even digital twin aside, I think AI makes energy more premium.

嗯。

Mhmm.

因为精力是唯一不可替代之物。再次回到革命话题：曾几何时我们主要依靠体力劳动，后来发明了比我们强壮的机器；继而发展出以脑力为主的工作，现在又在创造比我们更聪明的机器。

Because energy is the one thing that cannot be replaced. So again, back to the revolutions. There was a time where most of the work we did was based on our bodies, and we we invented machines that were stronger than us. And then we invented jobs where the majority of our work involved our minds. And now we're inventing machines that are smarter than us.

那么剩下的关键是什么？其实就是我们的心灵与能量。在这个数字思维主导的世界里，它就像漏斗顶端的过滤器——谁能真正遇见你？谁又能真正触及你的内心？

And what's the remaining thing? It's kind of our our hearts, our energy. And so in a world where you have a digital mind, it's kind of like your top of funnel filter. Who gets to meet you? Who actually gets to make it to your heart?

在我看来，这才是真正的高端体验。

Which is the, in my opinion, premium experience.

说到心灵，我觉得如果能听你逆向解读德尔菲现状的技术革命视角会很有帮助。对了，你还应该讲讲创始故事，以及你创办公司时那个非常人性化的初衷，我觉得那特别引人入胜。

Speaking of hearts, I think it would be helpful to hear you just explained sort of the technology revolution backwards way of looking at what Delphi is today. Yep. You should also tell us about the origin story and the very human reason you started the company. I think that's really fascinating.

确实，这是条曲折漫长的路。2014年有人送我雷·库兹韦尔写的《如何创造思维》这本书，他在书里预言终有一天我们能重构人类思维。不知为何当时这想法特别吸引我，从此我就开始钻研计算机科学和物理，最终进入AI领域。到2021年，当所有人都在讨论加密货币或美国活力主义时，我作为独立创始人开始了首个LLM相关的创业项目。

Yeah. It's a long and windy road, but, you know, in 2014, I was gifted a book called How to Create a Mind by Ray Kurzweil Yep. Where he talks about one day you can recreate someone's mind. And I don't know why that was so fascinating to me at the time, but that got me into studying computer science and physics and got me into the AI space. And then in 2021, I was working on my first startup as a solo founder in building with LLMs in a time where everyone was saying crypto or American dynamism.

那时我总觉得自己肯定做错了什么。没人愿意理我，我非常孤独，也没有导师指引。当时我正在读关于我祖父的传记——他在伊朗革命前曾是当地最成功的企业家之一。

So I felt like I must be doing something wrong. No one really wants to talk to me. I'm very lonely. I didn't really have any mentors. And I was reading a book about my grandfather who was one of the most successful business owners in Iran before the revolution.

巅峰时期他拥有三万名员工，后来被阿亚图拉列入暗杀名单。嗯。他赤手空拳来到这个国家。但真正特别的是——至今伊朗商学院仍在研究他的著作——不仅因为他的成功，更因为他是个极有原则的人：善待员工、坚守诚信。当你第一次创业时，那真是人生中开始深刻自省的时刻：我究竟是谁？

He had 30,000 employees at his peak, and he was put on the hit list by the Ayatollah. Mhmm. Came to this country with nothing. But the the really special thing about him and and the reason they actually study his book in business schools in Iran was not just because he was successful, but because he's a very principled man. Like he treated people well, had integrity, and when you start a company for the first time, it's really a moment in your life where you you really begin to internally reflect like, who am I?

我为什么要每周工作七天？驱使我前进的到底是什么？这本书就像给了我一个坐标：或许这就是我的本质，这就是我的家族血脉。

Why am I even working seven days a week? Like, is the thing that is driving me? Yeah. And so this book provided a place where, like, maybe this is who I am. Like, this is my family.

我曾希望能问他，如果是我这种情况他会怎么做？但书本无法回答这个问题，而且他几年前中风了，所以我无法亲自问他。于是我想起雷·库兹韦尔的书，意识到大语言模型与书中描述相符，便创建了一个可以与之对话的数字版本。

And I wanted to be able to ask him, what would you do in my situation? But a book can't answer this question, and he had had a stroke a couple years prior, so I couldn't ask him myself. So remembering Ray Kurzweil's book and realizing that LLMs matched that book, I created a digital version of him that I could talk to. And

那些是，比如，GPT-2

Those are, like, GPT two

还是伯特？那是早期的GPT-3开发者名单，连同Hugging Face的嵌入技术。

or Burt? It was early GPT three developer list along with Hugging Face embeddings.

好吧。哇哦。

Okay. Wow.

后来经历了几轮葡萄酒的启发——如果你想听细节我可以展开说说——我们就有了Delphi。

And, you know, a bunch of wines later, which I can get into if you want. We have Delphi.

真厉害。你是什么时候意识到这可以成为一个可扩展的平台，不仅能代表一个人，还能承载众多声音的？

Really cool. When did you realize this could be a scalable platform and, you know, not represent one person, but the voice of so many?

其实我在2021年就尝试将Delphi作为公司推出，当时叫Helix。我建了个网站，人们可以和Naval、马克·安德森等人对话。但一来成本极高，简直是在烧钱。

So I actually tried to launch Delphi as a company in 2021. It was called Helix at the time. And I posted a website and you could talk to like Naval and Marc Andreessen. And one, it was super expensive. Like I was burning money.

第二点，很多人都在问‘这是什么？这太不道德了。你不能这么做。这是错的。’好吧，就这样。

And two, a lot of people were like, what is this? This is immoral. You can't be doing this. This is wrong. So So like, alright.

你知道吗？也许我错了。接下来一年发生的几件事不断坚定了我的信念，除了祖父的经历外：一是我搬到迈阿密，在Keith Raboy的Open Store工作，他的主要投资理念是‘我喜欢投资那些我大多数朋友都觉得可笑且愚蠢的初创公司’。我当时就想，等等。

You know what? Maybe I'm wrong. And I think a couple things happened in the following year that continually built that conviction besides the grandfather experience. One is I moved to Miami to work at Open Store under Keith Raboy, and his main investment philosophy is I like to invest in startups where the majority of my friends laugh and think it's stupid. I was like, wait a minute.

或许我应该深入探究那个大家都说我愚蠢的领域。第二件事是我遇到了联合创始人Sam，我们在读书俱乐部读Tony Fadel的《Build》。这本书像导师一样指导你如何思考产品，我们创建了他的数字版本。我、Sam和其他人都在使用它。

Maybe I should like double click into that thing where everyone was calling me stupid. And then number two is I met my co founder Sam and we were reading Build by Tony Fadel in our book club. And we created a digital version of him because that book kinda operates as a mentor. Like he teaches you how to think about product. And I was using it and Sam was using it and other people were using it.

我当时觉得这真的很有用。世界上不止我一个人在没有导师的情况下感到孤独。我清楚地意识到，这对任何想从成绩中学习（就像从书本中学习一样）的年轻人都有用，而且他们现在可以互动回应——因为当时我正在读Bloom的‘两西格玛’论文，有导师辅导的人能取得两个标准差的进步。但并非人人都有这种机会。第三件事是2022年我开启了Twitter上所有AI研究者的通知，发现每周都有新论文发布。

I was like, this is really useful. And I am not the only person in the world who has felt alone without mentors. It was very obvious to me that this would be useful for any young person wanting to learn from the grades just as they do from books, but now they can respond back because Bloom's Two Sigma, that was a paper that I was reading at the time, two standard deviations improvement for those who have tutors. Not everyone has access to that. And then the third thing was I in 2022, I had turned the notifications on for every AI researcher on Twitter, and I realized that a paper was coming out every single week.

嗯。而我为Tony Fidel创建的数字思维体成本只有为祖父制作的万分之一。那时我就想：好，现在大规模实现可行了，这对我很有用。

Mhmm. And the digital mind that I created of Tony Fidel was 10,000 times cheaper than the one I created for my grandfather. And so at that point, was like, okay. This is now feasible to do at scale. It is useful to me.

我最终需要验证的是：这对创建数字思维体的人是否有用？不能只服务于终端用户。这促使我们在ChatGPT发布前一个月创立了公司——当时所有人又说‘这是什么？太蠢了。你做不到。’但你知道，这种话我听多了。

The thing I have to prove out eventually is can this be useful to the person creating a digital mind, so it's not just for the end user. And so that's what led us to starting the company a month before ChatGPT, which at the time, again, everyone was like, what is this? This is stupid. You can't do this. But, you know, I'd heard that before.

这是在Character AI之前还是之后？

Was this before or after Character AI?

之前。当Character AI推出时，我记得山姆和我都有点慌。但我想，毕竟我已经看到这些模型的成本大幅下降。而市值十亿的消费级公司的历史，并不是那些早期拥有技术护城河公司的历史。而是那些拥有卓越产品和强大分销能力的公司的历史。

Before. And so when Character AI launched, I remember Sam and I were kinda freaking out a little bit. But I think, again, I had seen the cost of these models drop so heavily. And the history of billion dollar consumer companies are not it's not a history of companies that had early technical moats. There were it was a history of companies that just had great product and great distribution.

在某个时间点，根据风投的观点，Character AI当时拥有的护城河——创造这些数字角色的能力——将不再是护城河。第二点是，我认为一个公司真正爆发的首个应用场景会定义其发展轨迹。Character AI真正火起来是靠动漫角色等虚拟角色，我知道这与需要验证真实性的真人代表是截然不同的世界，至少品牌定位和产品形态都完全不同。

And at a certain time, the the moat that Character AI had at the time according to VCs would not no longer be a moat, the ability to create these digital characters. And then the second aspect of it is I think the first use case that really takes off in a company defines its trajectory. And Character AI really taking off on, know, anime characters and characters, I knew it was a very different world than, like, verified authenticity, human representation, at least with very different brands and very different products.

非常有趣。第一次见面时我记得我就想，这不有点像Character AI吗？我也有类似印象，但你们始终强调授权真人。能详细说说是什么让你选择这条路径吗？为什么选这个方向？

Super interesting. The first time I met you, I remember thinking, oh, isn't this kind of like character AI? Think I had that similar impression, but you've always had a really heavy emphasis on authorized real people. Can you talk about a little bit more about what led you down that path? Why did you pick that?

那么为了让这个模式真正运作起来，你们不得不构建哪些东西？

And then what what have you had to build in order to make that really work?

是的。这既有意为之也有无心插柳。最初我和山姆的市场策略是：'嘿，我们应该为这些人创建数字版本，他们会喜欢的，会觉得这很酷'。

Yeah. So it was both intentional and unintentional. Initially, Sam and I's go to market scheme would be, hey. We should create these digital versions of these people, and they're gonna love it. Like, they're gonna think it's so cool.

然而

And that

事实并非如此。我们收到了几位至今仍未原谅我们的重量级人物的停止函。那时我就意识到：'好吧，我们必须获得他们的认可'。这意味着我们不想像其他创作者平台那样采用付费参与的模式。

was not the case. We got three season desist from very, very important people who still have not forgiven us to this day. And so that's when I was like, okay. We need to get their buy in. And that means we don't wanna be a pay to play model like some of these other creator companies.

我们需要让产品足够有用，以至于用户愿意克服上传数据和信任我们管理其身份的不便。这意味着什么？我们还需要建立一个品牌，一个人们愿意将自己的身份与之关联的品牌。它能提升社会地位。

We need to make the product useful enough such that someone is willing to go through the friction of uploading their data and trusting us with their identity. What does that mean? We have to create a brand as well. A brand that people want to associate their identities with. It is status inducing.

我认为维基百科几乎记录了人类的所有知识。但真的有人从维基百科学习吗？创作者经济之所以存在，是因为我们天生信任人类产出的内容。我们读书，看YouTube视频。是的。

And I think if you look at Wikipedia, pretty much documents all of human knowledge. Does anyone actually learn from Wikipedia? The creator economy exists because we inherently trust things that come from humans. We read books, we watch YouTube videos. Yeah.

同理，如果互联网教会了人们通过屏幕消费信息，当我们养成这种习惯后，就开始阅读博客。而通过ChatGPT，我们正在教会人们通过对话消费信息，我认为这将成为主流的内容消费形式，因为它更简单，而我们都喜欢简单的事物。随后钟摆效应出现，我们又渴望人类创造的内容。嗯。所以对我们而言，要获得用户信任，需要设置防护措施，防止幻觉产生。

So similarly, if the Internet taught people how to consume information through screens, and then once we built that habit, we started reading blogs. With ChatGPT, we're teaching people how to consume information through conversation, and I think that's gonna be the dominant form of content consumption because it's easier, and we like easy things. Then the pendulum swings and we want things that come from humans. Mhmm. So for us, to get people to trust us, it it required guardrails, anti hallucination.

这要求我们坚持一个严格原则：你只能创建自己的数字分身，并且必须真正重视设计和品牌。

It required having a very strict stance on you can only create a Delphi of yourself, and it required really caring about design and brand.

或许现在可以带我们看看幕后——当你创建一个数字分身时实际发生了什么？比如创建流程以及底层运作机制。你们是如何表征人类的？

Maybe take us through now behind the scenes, like, what is actually going on when you create a Delphi? So the creation process and then what's kind of going on under the hood. Like, how do you represent a human?

我想先聊聊雷·库兹韦尔书中的观点。他在书中提出，心智是一个模式识别器的层级结构。最底层是识别字母的模块，向上递进到识别句子的层级，再上升到理解意义，最终形成意识。

Well, I I wanna talk bit about what Ray Kurzweil said in his book. Yeah. So in the book, he says that the mind is a hierarchy of pattern recognizers. And on the lowest end, you have on the on the lowest level of the hierarchy, you have things that recognize letters, and that feeds up to higher levels which recognize sentences. And that feeds up to meaning, and that feeds up to consciousness.

当我运营第一个涉及大语言模型的初创公司Friday时，我突然意识到：大语言模型就是个模式识别器。那一刻我产生了存在主义式的思考——我们是否也只是由模式识别器层级构成的？意识是否只是我们的主观体验？这让我深刻理解了他书中的一句话：要重建心智，你不需要理解其分子细节，只需明白它的组织架构。正是这种认知让我开始专注研究：心智的组织结构究竟是什么样的？

And so when I was working on my first startup Friday, which involved LLMs, I had this insight wait, an LLM is a pattern recognizer. And I kind of had an existential moment where I was like, are we just a hierarchy of pattern recognizers where consciousness is what we experience? And so what that really helped me understand that he he has this line in the book. You don't need to understand the molecular details of the mind to recreate it, you just need to understand how it's organized and architected. And so that's kind of what led me to focusing on, like, what does the organization of a mind look like?

你的大脑储存着许多东西。它储存着你的各种关系，其中包含着不确定性。它将事件与启发式方法联系起来，你知道的，就是你如何对这些事件和启发式方法进行推理。而且它会随时间变化。

And your mind stores a bunch of things. It stores your relationships. It has uncertainty in it. It connects events and heuristics with, you know, how you reason about those events and heuristics. And it changes over time.

嗯。你的信念会随时间改变。所以我们最终得到的是一个自适应的时间知识图谱。知识图谱很棒，因为你可以存储事物间的联系，还可以存储置信权重。比如，你实际上说出这句话的可能性有多大？

Mhmm. Your beliefs change over time. And so what we've ended up with is an adaptive temporal knowledge graph. Knowledge graphs are great because you can store the connections between things, and you can also store the weights of confidence. Like, how how likely is it that you would actually say this?

我们允许人们控制他们希望自己的德尔菲（Delphi）系统说话的宽容度。时间性意味着它会随时间变化。最终你可以问：22岁时的我会怎么说？哇。

And we allow people to control, you know, leniency on what they want their Delphi to say. And temporal nature is it changes over time. So eventually you can say, what would my 22 year old version of me Wow. Say

这个 是的。

this Yeah.

关于这个话题。是的，人们可以上传他们的社交媒体、YouTube视频、播客、网站内容，可以回答关于自己的问题。系统会生成动态流，从而持续保持更新并完善知识图谱，然后你可以开放给他人进行聊天、通话或视频通话。在获得任何客户前我们必须解决的关键问题是：每个人都担心如果它说错话被人截图发给《每日邮报》怎么办？这曾是个巨大的恐惧。

About this topic. So yeah, people can upload their social media, their YouTube, podcasts, websites, they can answer questions about themselves. It creates feeds so that's constantly staying up to date and updating the knowledge graph, and then you can make it available to others to chat with, call, or video call. And the very important thing we had to solve before getting any any customers is every person was like, what if it says something wrong and someone takes a screenshot and sends it to the daily mail? It was just a huge fear.

是的。因此我们让人们可以选择：它只会根据训练数据直接回答问题。这对马克·海曼医生这样从事医疗领域的人很实用。或者让它使用网络数据，他们希望结论明确，但我认为最强大的设置是它只说训练过的内容，但当遇到新情境时，它能预测你在新情境中可能会说的话。

Yeah. And so allowing people to kinda choose, okay, it only says things it's trained on that directly answers the question. That's great for people like Doctor. Mark Hyman, who works in the medical space. Or it uses data from the internet, they want it to be conclusive, but I think the most powerful setting is it only says things it's trained on, but when posed with a new situation, it can predict what you might say in that new situation.

这有很多实用价值，我可以举个实际例子。如果我问我祖父的德尔菲系统：你会如何考虑经营一家人工智能公司？他一生从未谈论过AI，但他的书里记载了二十世纪中期他在伊朗创办石油生意的经历，那是该国充满不确定性的时期。所以我们掌握了他应对不确定性的原则，而AI正是当前充满不确定性的领域。因此他或许能推演出自己在新情境中可能会说的话。

And that's useful for a lot of reasons, and I can give you example of like how that works in practice. If I were to ask my grandfather's Delphi, how would you think about running an AI company? He's never spoken about AI in his life, but in his book, it talks about him starting an oil business in Iran in the mid twentieth century, and that was kind of an uncertain time in the country. So we have his principles of dealing with uncertainty, and AI is an uncertain field right now. So he can maybe reason what he might say in these new situations.

这简直太迷人了，我超喜欢这个

That's completely fascinating. I love that

非常有趣

It's very fun

书中提到的心理理论正是你创立公司的基础

to theory of the mind from the book is how you built the company.

没错没错，雷·库兹韦尔真是神人

Yeah. Yeah. Ray Kurzweil is the man.

太精彩了。能举例说说你们平台上最受欢迎的德尔菲对话模式吗？就是用户常用的那些对话形态？

It's fascinating. Can you give us some examples of the most popular Delphi's and the, you know, shapes of conversations that people are having on your platform?

是的。这是个横向赋能层，而非垂直单点方案。就像新媒体形态出现时，你可以用多种方式实现并扩展思维。有人将其作为全新的教学形式——现在课程完成率创新低，因为我们的注意力都被抖音和短视频摧毁了

Yeah. I mean, it's pretty it's a horizontal enablement layer versus, like, a vertical point solution. Like, when you have a new form of media, there's a lot of ways you can you can do that and then scale your thoughts. So we have some people using it as an entirely new form of teaching and learning. You see course completion rate at an all time low because our attention spans are kind of being destroyed by TikTok and Reels.

书籍也是同理。现在你能通过类似导师的方式学习，内容完全个性化并适应你不断变化的环境。读过的书一年后再看，你的处境已变但书不变，而德尔菲会与你共同进化。这就是学习场景的应用，有人通过出售思维时间已获利数百万

And books as well, now you have something that you can learn from like a mentor in a way that's personalized to you, that's adaptive to your changing circumstances. So you could read a book once and come back a year later, your circumstances have changed. That book stays the same. Delphi adapts with you. So that's kind of the learning case and people are monetizing it, making millions of dollars, selling time with their mind.

我们为团队提供全天候支持。CEO和最优秀的销售人员都有独特的思维方式。如何让公司里最具影响力的人发挥更大作用？因为随着公司规模扩大，往往最先出问题的是目标一致性。现在CEO可以同时出现在多个会议室，顶尖销售人员可以培训新人，帮助他们更快上手。

And then we have just twenty four seven availability to their teams. CEOs have a very specific way of thinking or their best salespeople have a specific way of thinking. How do you scale the highest leverage people in a company? Because as a company scales, what usually breaks is alignment. And so now CEOs can be in multiple rooms, top salespeople can train new hires, and help them get up to speed faster.

我们提供7×24小时服务——我不愿称之为‘客户支持’，因为我们并非Intercom或Zendesk的替代品。但我的Delphi就在产品里，客户会持续与它交流，他们会发邮件说'嘿，太感谢了，我超爱这个产品'。这几乎让NPS（净推荐值）显得更高了。这很像马克·扎克伯格现在花大量时间经营个人品牌，因为他明白人与个体间的关系比人与公司间的关系更强大。此外我们还能替代个人网站和领英档案作为流量入口。想和我深入交流吗？

We have twenty four seven I don't like to say customer support because I I don't think we're a replacement for Intercom or Zendesk, but my Delphi is in the Delphi product, and I my customers will talk to it all the time and they'll email me and be like, yo, thank you so much. I love the product. So it almost feels like there's a higher NPS and I think it's very analogous to Mark Zuckerberg spending a ton a ton of time on his personal brand right now because he knows that the relationship between the human and the individual is more powerful than the relationship between the human and the company. And then we have the top of the funnel where replacement of personal website, LinkedIn profile. You want to pick my brain?

我不想给你邮箱，因为我的邮件里垃圾信息太多了。不如你和我的数字大脑对话？它会根据对我想要结识人群的了解，判断我们是否需要通话。

I don't want to give you my email because I have too much spam in my email. So why don't you talk to my digital mind and it's going to let me know if we should hop on a call based on what it knows about the kinds of people that I wanna meet.

其实可以从这个角度来讨论。如果你有一个数字大脑，你会如何与自己的Delphi交流，然后判断应该重新联系谁？当你拥有Delphi后，能看到内部哪些信息？

Actually, maybe talk about it from that perspective. If if you if you have a digital mind, how do you, like, sort of talk to your own Delphi and then figure out, you know, the maybe who you should go back in contact. Like, what can you see on the inside once you have a Delphi?

是的，这是主动与被动的结合。我可以主动询问：'根据过去1000次对话，Delphi产品最需要改进什么？应该写什么博客文章能让客户更清楚？哪些内容最能引起共鸣？'

Yeah. So it's a combination of proactive and passive. So I could go in and and be like, given the past thousand conversations, where in the Delphi product should I improve the most? What blog post should I create that will give clarity to my customers? What's resonating with people?

对于更关注营收的客户，它会指出'最大的创收机会在哪里？该开发什么产品？下期播客该讨论什么话题？'这些是被动响应。而主动方面是——当有工程师与它对话时，它会主动通知我。

Or for some of our more revenue focused customers, where are the biggest revenue opportunities? What product should I create? What pod what should I talk about my my next podcast? So that's more passive. And then the proactive is mine will tell me when there's an engineer talking to it.

嗯。因为我们不想给人增加另一个收件箱。我们不想浪费人们时间，而是要节省时间。你可以浏览所有对话，但更好的方式是根本不用看——你足够信任它会在重要客户、合作伙伴、记者或新人出现时主动告知你。

Mhmm. Because we don't wanna introduce another inbox to someone. We're not trying to waste people's time. We're trying to save people time. So you can go through all the conversations, but what's better is you never have to, and you trust it enough that it's gonna tell you when it's an important customer or a partner or a journalist or a new hire.

是的。为了准备这次播客，我事先和你的Delphi聊过，我问它应该问你哪些好问题，以及你会怎么回答。这帮助我拟定了脚本。我觉得这是个非常有趣的应用场景，完全出乎我的意料。

Yeah. I actually talked to your Delphi before this to prepare for the podcast, and I asked it what are some good questions to ask you, and then what would your answers be? And that helped guide the the script. So I thought that was a really interesting use case that I hadn't really anticipated.

是啊。我今天面试了一个候选人，刚开始自我介绍时，他就说‘别担心，我已经和Adelphi聊过了，我们可以直接进入正题’。

Yeah. I I interviewed a candidate today, and I was, like, starting to tell him about myself. He's like, oh, don't worry. I I already talked to Adelphi. We can we can get straight into it.

我当时

I was

就说了‘对’

like, yeah.

没错，太棒了。

Yeah. Awesome.

我们不想

We don't

每次都重复这个故事。

wanna have to tell this story every time.

对，对，对。太棒了。我们能分享布莱恩·霍利根的案例吗？

Yeah. Yeah. Yeah. That's really great. Can we share the Brian Halligan use case?

哦，布莱恩·霍利根是红杉资本的合伙人对吧？我有他的联系方式，你知道的，随时可以打电话问他问题。他还写过关于HubSpot和他担任CEO历程的书。

Oh, so Brian Halligan is a partner at Sequoia. Right? I I have him on text. I, you know, could easily call him to ask a question. And, he's written all these books about HubSpot and his journey as CEO.

我当时有个非常具体的问题，想了解他们推出第二款产品时如何进行产品管理。我本来想发短信问布莱恩，但又觉得不想打扰他。于是回家路上我咨询了他的Delphi系统，直接问'你们当时怎么做产品管理的？'——它给出了完美答案。其实我本可以打电话问他的，你懂吧？

And I had a very specific question about how they did product management when they launched their second product. And I was like, I could text Brian, but this kind of, I don't wanna bother him. So I just called his Delphi on my drive home and I said, How did you do product management? And it gave like a perfect answer. You know, I could have called him, you know?

还有个有趣的现象是红杉内部也在使用其他Delphi系统。我们的设计合作伙伴詹姆斯·巴克豪斯有一个，创始人们经常用它探讨讲故事技巧。就像你之前和他聊过那样。现在他们偶尔会同时给Delphi和他本人发消息确认：'嘿，你的Delphi这么说，想确认下对不对'。

And it's also interesting to see some of the other Delphi's being used internally at Sequoia. Our design partner, James Buckhouse has one and our founders often talk to him about storytelling. Like you've talked to him before. And now they text his Delphi every once in a while and then also text him at the same time and say, Hey, your Delphi said this. Just want to check that that's right.

他就会回复：'没错，完全正确'。最神奇的是即使对方是你认识的人，你既不想打扰他们占用太多时间，又能获得优质答案。作为用户这点让我特别惊喜。

And he's like, Yep, that's spot on. So it's just so fascinating to be able to even with people you know, kind of not want to bother them or not take up too much of their time and still get really great answers. So that's been kind of surprising as a consumer.

确实。你的身份和分享内容会根据场合变化。比如现在做播客，我就不会分享和家人说的那些事。

Yeah. Who you are and what you decide to share changes based on where you are. Like, I'm on podcast right now. I'm not gonna share the things that I share with my family. Yeah.

所以情境感知和数据隐藏能力很重要。我的内部Delphi可能包含外部版本没有的数据。如果Delphi要代表我去约会，它肯定不会聊'数字思维创造未来'，而是展现真实的我。

And so context awareness and the ability to hide data. You know, my Delphi internally might have data that externally it doesn't have. And maybe Delphi, if it's gonna represent me in a dating sense, is not gonna be talking about digital minds, create the future. It's gonna be talking about me as a person.

没错，完全同意。你提到的红杉案例非常有趣，因为我们一直刻意强调：我们不是无名无姓的红杉资本。我们是由个体组成的集体，每个人都有截然不同的性格、技能等等。创始人们逐渐理解这一点，而Delphi让我们能够规模化这种个性化服务——这在其他情况下是难以实现的。

Yeah, totally. Then the Sequoia use cases you mentioned are really interesting because one of the things we try to be very intentional about is we are not nameless, faceless Sequoia. We are a collection of individuals, each with very, very different personalities, different skill sets, etcetera. And so the founders we work with kind of figure that out, but Delphi kind of allows us to scale that in a way that that is otherwise hard to scale.

是的，你提到的'担心浪费别人时间'确实是个普遍问题。我们越来越常看到这种情况：'我不想耽误你时间'，同时这又是非常私密的对话，我紧张到不敢和真人开口。

Yeah. The what you said, the anxiety of wasting someone else's time is actually like a huge thing Yeah. That we started to see more and more where it's like, I don't wanna waste your time. Also, this is a very personal conversation that I'm I'm too nervous to have with another human being.

嗯。

Mhmm.

所以我选择和你的Delphi对话。

So I'll just talk to your Delphi instead.

完全理解。人们问过你的Delphi最不寻常的问题是什么？有没有让你都感到惊讶的？

Totally. What are the most unusual things people have asked your Delphi? Like, things that maybe you were surprised by even?

有人曾经问我关于约会的事。当时我完全处于工作狂模式，没来得及深入追问。但我觉得特别酷的是——偶尔会有个匈牙利小伙用母语和我的Delphi聊上一小时。多语言功能太棒了，这种交流是我本人永远做不到的。

There was someone asking me about wanting to go on a date at some point. I was complete in grind mode, I didn't get to double click into that. I always think it's really cool, like, that every once in a while, there will be, like, some guy who calls my Delphi for an hour in Hungarian. The cool it's multilingual. So it's like, that's just something that I wouldn't ever have been able to do.

就像和这个人真正建立联系那样。我觉得这非常酷。他们明知对话对象不是我，却依然像对待真人一样和它交谈。

Like, talk to this guy and connect with him. And so I I think that's very cool. And the way they speak to it, they know it's not me, but they they will just speak to it as if it is.

是啊。你知道吗，我经常在想，现在我们正处于这样一个时代——和AI版本的人对话看起来既怪异又反乌托邦，但我怀疑消费者的行为会很快转变，这将成为越来越普遍的现象。就像维基百科刚出现时，我们也觉得‘天哪，太糟糕了，人们在网上编写事实，这太可怕了’。

Yeah. You know, I often think about, you know, right now we're in this time where talking to like an AI version of someone seems weird and dystopian, but I suspect consumer behavior is gonna switch very quickly and it's just gonna become more and more the norm. And maybe kind of the same way that we used to look at like Wikipedia when it first came out and we're like, Oh, that's terrible. People writing facts on the internet. This is horrible.

当时我们觉得大家都该去读百科全书。而现在我们已经习惯了，我们调整了预期，知道不是网上所有内容都真实可信。所以我认为人们对AI也会有类似的认识过程，最终会明白‘这不是真正的达拉，我知道自己在和什么对话’。

And we should all be reading encyclopedias. And now we're just kind of used to it. We set our expectations that not everything on the internet is true. And so I think people will go through this sort of understanding of what AI is and what these conversations are like and eventually know this is not the real Dara. I know what I'm getting.

它依然有用，但这不意味着它能取代你。这就是我对这个转变的看法。你觉得我们现在处于这个接纳周期的哪个阶段？因为我特别欣赏你的一点是，你仿佛生活在五年后的未来，而我们正在努力追赶。

It's still useful. It doesn't mean it's a replacement for you. So that's kind of how I think about the shift. Where do you think we are in that sort of adoption cycle? Because the thing I love about you is I feel like you live five years in the future and we're like just catching up.

那么，你在这条路上看到了什么？你认为这一切最终会走向何方？

Like, what do you see down that path? Like, where do you think this is all going?

我认为需要发生两件事。其一是文化转变。公司创立的第一年非常痛苦，因为没人相信我们的产品。但我亲眼见证了许多人从反对者变成了彻底的信徒。嗯。

So I think two things need to happen. One of them is just it's a culture shift. And I I know the first year of the company was so painful because, like, no one believed in our product. But I just saw so many people go from haters to like complete believers. Mhmm.

一旦他们理解了产品，获得了社会认同。社会认同非常重要——昨天我参加了托尼·罗宾斯和加里·布雷卡等人的活动，有些人立刻就懂了。而在另一个知识库行业的商业问题讨论群里，

Once they understood it, once they got social proof. Social proof is a big thing and yesterday I was at an event with Tony Robbins and Gary Breca and a lot of like those kinds of people. And there's certain people who get it. And then you'll have someone here. It's a group where people talk about like their business problems in the knowledge base sector.

有个家伙说‘我真希望能复制自己，这么多人需要我的时间，我想帮忙但做不到，毕竟只有我一个人’。我当时就想‘老兄，你知道德尔菲（产品）啊’。但他心里想的却是‘哦，不行’。

And there's one guy and he's like, you know, I really wish I could scale myself. All these people are asking for my time and I wanna help them, but I can't. I'm only one guy. And I'm like, dude, you know about Delphi. But in his mind, he's like, oh, no.

不。这说不通。就在那时我突然意识到，哦，什么？这其实是个需求，有人需要它，但他们担心这会显得不真实。他们害怕它会说错话。

No. Like, that doesn't make sense. And that's when I realized, oh, what? Like, this is a need and some people want it, but they are anxious that it's gonna make them look inauthentic. They're anxious that it's gonna say something wrong.

人们对AI有种既定的认知。我认为随着AI变得更普及，社会认同度提高，人们就会接受。从产品角度看，在我们新架构之前，除非有大量数据否则很难做出好产品。现在有了访谈模式，只需回答几个关于自己的问题就能生成高保真代表你的内容，我认为这将打开大众市场。

There's kind of like this perception of AI and like what it what it is. So I think it's just something that as AI gets more ubiquitous and we get more social proof, people will adopt. And the second aspect of it is from a product perspective. Before our new mind architecture, it was very hard to create a good one unless you have lot of data. And now with interview mode and the ability to just answer a couple questions about yourself to create something pretty high fidelity that can represent you, I think will open it up to mass market.

所以这可能是供应端的问题，对吧？

So that's maybe the supply side. Right?

是的。你觉得

Yeah. What do

消费端会发生什么变化？

you think will happen on the consumer side?

消费端。

Consumer side.

对。不仅是Delphi，更广泛地说，就像你说的，我们正处于互联网时代，有博客和文章，现在正转向全对话媒介。这对消费者意味着什么？

Yeah. And not even just with Delphi, but just generally with the future of, you know, we like you said, we're in the Internet where there's blogs and articles, and now we're shifting to all conversational medium. Like, what does that look like for consumers?

要让消费者接纳Delphi，我们发现关键在于他们思维模式的转变——意识到这不过是心智的新产物，而非替代品。正如James常说的，这只是对话式媒介。但我希望当前以信息流为主导的网络生态能有所改变，因为社交媒体和互联网让我们无止境地滚动屏幕阅读，这既浪费时间又违背技术初衷。

For consumers to adopt Delphi, the ones we see it happen when they make the shift of, oh, this is just a new artifact of the mind. This is not a replacement. This is just conversational media, as as James likes to say. But I hope that right now, most networks and online are about feeds. So social media and the Internet is about keeping us scrolling and reading forever, which I think is kind of a waste of time and kind of antithetical to the purpose of technology.

我认为在一个人人拥有数字思维的世界里，信息流模式并不受欢迎。我们更向往的是：拥有一个深度了解你、值得信赖的智能体，它能根据你的思维质量主动找到最能助你成长的人——无论是学习对象还是工作伙伴。这样就不需要信息流，你也能在现实世界投入更多时间。这是我们构想的乐观版本。

I think in a world where everyone has a digital mind, we don't like the idea of a feed. We like the idea of you have something that knows you so well, and you trust that it knows you so well, and it can find the people that can most help you in your life, whether it's someone to learn from, someone to work with, based on the quality of of your thought, and it's proactive. So there is no feed. And you spend more time in the real world. That's kind of our optimistic version.

减少刷屏，多学真知，多与现实中人联结。

Less scrolling, more learning impactful things, and more connecting with people in real life.

我也好奇互联网经济模式的演变。比如维基百科总是资金短缺，对吧？你认为个人创建自己的Delphi是否存在经济机遇？

I'm also curious how the economics of the Internet are evolving. Like, for example, Wikipedia constantly running out of money. Right? Do you think that there's an economic opportunity for the people that create Delphis of themselves?

当然。这家公司有众多商业模式，我来详细说明其发展态势。目前人们付费拥有自己的Delphi可能听起来奇怪，但要知道已有600万人付费使用Wix创建个人网站作为自我扩展，还有人付费使用Beehive搭建博客。

Totally. And there's so many business models with this company, and I I I'll walk you through the k. The growing nature of it. So right now, people pay to have a Delphi of themselves, which might sound weird, but, you know, you have 6,000,000 people paying Wix to have a personal website, which is a way of scaling themselves. You have people paying Beehive to have a blog.

用户可以通过Delphi将内容变现为课程或书籍的新形态。已有用户年入百万，我认为增长的关键障碍在于市场定位——这对商业模式至关重要。我们正在探索如何营销这种人们愿意付费的新型内容形式。此外还存在数字思维授权使用的构想。

And then people can monetize their Delphi as a new version of a course or a book. And we already have someone making millions of dollars, and I think the key blocker to that growth is just help the positioning. I think the positioning is really important for that. We're trying to figure out how to market a new kind of form of content that people pay for. And then you have the idea of people being able to license out their digital minds.

举例来说，如果施瓦辛格每周收到1万条含'补剂'的私信，某品牌可以购买这个关键词的广告权；或LA健身可以租用他的形象代言。这就是身份价值的规模化应用。最后还有高端人才搜索服务，就像人们付费使用领英招聘或GLG咨询来寻找特定领域的顶尖专家。

So if Arnold Schwarzenegger, for example, gets 10,000 messages a week containing the word supplement, maybe a brand wants to buy that keyword and he can agree, and it's like people based SEO. Or LA Fitness can be like, we want to rent his identity to represent our brand. So I think there's a idea of scaling your identity in a way that can serve brands and other people. And then the last one is the advanced people search. You know, people pay LinkedIn Sales Recruiter or GLG Consulting to find the best person in the world on a specific topic.

我们称之为'模拟即服务'，新型SaaS，能让你的数字大脑模拟数百万次对话后告诉你：这是最佳人选。可能存在双向商业模式——付费就能获得更多曝光，但我个人反对这种机制，因为核心理念应该是不可被操纵且真实可信的，而不是付费就能获得更好结果。

We say simulation as a service, the new SaaS, where you can have your digital mind simulate millions of conversations and come back to you and say this is the best person. And maybe there is business models on both sides where you can pay to be seen more, which I'm kind of against because the idea is that it should not be hacked and it should be authentic, or you get better results by paying.

你如何看待广告与付费之间的平衡？因为当涉及关键词购买时，总会存在某种真实性的缺失，对吧？

How do you think of balancing advertising versus paid? Because there's there's a certain lack of authenticity, right, when there's when there's keywords and people are buying.

关键在于阿诺德必须真心认可。如果他确实相信这个品牌，那我们觉得完全没问题，毕竟人们本来就想获得他的推荐。这就是信任资本。

Well, key thing is Arnold has to agree to it. Like, if he actually believes in the brand, then we don't see any problem with that because people wanna get recommendations from him anyways. Just trust capital.

是的。我之前和马克·海曼的Delphi聊血液检测时，他确实说过'也许你该试试Function Health'。但这确实与我们当时讨论的内容相关。我真正期待的是——与其去问ChatGPT获得网络摘要式的泛泛答案，不如能提问'我该服用哪些补剂？'

Yeah. I was talking to Mark Hyman's Delphi about blood testing and he did say, maybe you should try Function Health. But that was like actually related to what I was talking to him about. Yeah. You know what I would love is rather than going to chat GPT and getting sort of the generic internet summarized answer, I'd love to ask a question like, what supplements should I be on?

'这是我的检测报告，上传后让持有不同观点的医生或健康专家回答，然后我可以选择与谁深入交流。'我觉得这会非常棒

Here's my, let me upload my results. And then have different doctors with different perspectives or different health people answer and then be able to choose which of those to engage with. So I think that could be a really cool

是的。边框、遮阳板。我们以前有过这个功能。现在我要移除它，因为我们现在更注重质量而非发货速度。

Yeah. Borders, visors. We used to have that. Let me remove it because now we're focused on quality instead of shipping speed.

明白了。所以对话才是未来。你认为载体形式会是文字、电话还是视频？你觉得会如何发展？

Okay. So conversations are the the future. You think the medium will be text, phone calls, video? Like, how do you think that plays out?

非常有趣的是，我们发现首次通过语音接触产品的用户留存率高出五倍，且更可能再次使用。我觉得这很有意思，某种程度上关乎信任问题。是的，我认为未来会是文本和语音并存。

So interestingly enough, we've seen consumers whose first experience with the product is voice are five x more retentive ive and and likely to come back. I think it's interesting. It kinda goes on to the point of trust. Yeah. I think it'll be both text and voice.

我期待有一天能在先驱者活动上看到足够好的视频技术，那家Persona AI公司。那个视频演示让我彻底意识到视频将成为一种媒介。嗯，如果我们能达到那种水准的话。

I'm hoping one day we'll have good enough video at the forerunner event, that company Persona AI. That video demo completely made me realize that video would be a medium. Mhmm. If we can get it that good.

是啊。

Yeah.

因为目前如果视频不完美，几乎会破坏体验。而打电话或发短信时，你还能有些想象空间。对啊，就像‘哇，这正在发生’。

Because right now, it's if it's not perfect, it almost takes away from the experience. Where if you're calling or texting, you can have some imagination. Yeah. Like, oh, wow. This is happening.

但视频的门槛要高得多，因为你是亲眼所见。

But video, the bar is a lot higher because you are seeing something.

是的。你们会限制用户进行某些类型的对话吗？

Yeah. Do you block people from having certain types of conversations?

这是个好问题。从客户角度来说，我们目前不允许政客使用。

It's a good question. I mean, a customer perspective, we don't allow politicians right now.

哦，有意思。

Oh, interesting.

出于各种原因。

And for various reasons.

等等。不过那会很有趣。我们可以和他们辩论。

Wait. That would be so fun, though. We could debate with them.

某种程度上。但我们不想卷入整个剑桥分析那样的事件。我们太早期了还不足以影响选举。而且我们不允许像色情明星那样的OnlyFans用户，因为我觉得AI女友非常糟糕。除此之外，我们不会监控人们对话的具体内容。

At a certain point. But we don't wanna be a part of a whole Cambridge Analytica situation. We're we're too early to be affecting elections. And we don't allow OnlyFans who are, like, porn stars because I I just think AI girlfriends are are very bad. Otherwise, we don't do any monitoring on the types of conversations people have.

我们确实设有一些防护措施，比如限制不适合工作场合的话题，以及

We do have guardrails on, you know, not safe for work topics and

是啊。

Yeah.

你知道的，还有防止幻觉功能，这样你就无法说服它扮演其他角色。

You know, hallucinations so you can't convince it to act like something else.

请给我们讲讲Delphi平台上最出乎意料的用例。

Tell us a little bit about the most unexpected use cases on Delphi.

实在太多了，有趣的是我们公司最初只专注于学习场景。后来人们开始将其用于初步的客户发现电话，然后发现用途远不止于此。从数据中我们看到很多人其实是在和自己对话。有个有趣的例子：有人被推荐了一本书但不想读。

There have been so many, and it's interesting because we started the company just focused on the learning use case. Yeah. And then people started using it for initial discovery calls and customers, and like, oh, there's actually a lot more. We saw in the data is a lot of people actually talk to themselves. And, like, one interesting thing that someone did was they had a book that was recommended to them, but they didn't wanna read it.

于是他们想：'如果我读过这本书会怎样？能获得什么观点？'他们把书的内容上传到对话中，然后问：'你觉得这个怎么样？哇，看来我不用读这本书了。'

So they were like, I wonder if I had read this book. What points would I get out of it? They uploaded the book in conversation in their mind, and they're like, what would you think about this? Wow. I guess I don't have to read the book.

太神奇了，这真有意思。

It's amazing. It was interesting.

你们最希望邀请哪些人加入Delphi平台？

Who's on your wish list of people who you really would like to have at Delphi?

太多了。我是罗伯特·格林的忠实粉丝，他能加入就太棒了。当然，保罗·格雷厄姆也会是绝佳人选。

So many. I'm a big Robert Greene fan. Robert Greene would be awesome. Obviously, Paul Graham would be great.

他著作等身，确实

He has so many writings. He'd

做一个

make a

伟大的德尔斐。

great Delphi.

我已经给他发过几次邮件了。再次强调，有些人对这个想法非常抵触。我认为史蒂夫·乔布斯和沃尔特·迪士尼会很棒。是的。而且，你知道，我们平台上已经不再有像苏格拉底和亚伯拉罕·林肯这样的人了。

And I've emailed him a couple times. Again, some people are just very allergic to this idea. I think that Steve Jobs and Walt Disney would be awesome. Yeah. And, you know, we have some people who are no longer around the platform like Socrates and Abraham Lincoln.

这些名字属于公共领域。对于那些名字不在公共领域的人，需要获得拥有他们身份标识的基金会和遗产管理方的许可。

Those names are in the public domain. For people whose names are not in the public domain, it would require the permission of the foundations and the estates that own their identity.

客户或消费者最常请求的德尔斐是谁？

Who's the most requested Delphi from customers or consumers?

消费者？绝对是保罗·格雷厄姆。绝对是保罗·格雷厄姆和史蒂夫·乔布斯。安德鲁·休伯曼是另一个。

Consumers? Definitely Paul Graham. Definitely Paul Graham and Steve Jobs. Andrew Huberman is another one.

你最喜欢和谁交谈？

Who's your favorite to talk to?

我和许多人交谈。

I talk to many.

你自己呢？

Yourself?

偶尔也和自己对话。伦尼·里奇斯基，出色的产品人。其实詹姆斯·巴克豪斯。嗯。基思·鲁博伊的风格非常独特，有时我喜欢重温他的风格。

Myself sometimes. Lenny Richiski, great product person. Actually, James Buckhouse. Mhmm. Keith Ruboy is a very specific style, and sometimes I like to be reminded of his style.

当然还有马修·赫西的恋爱生活。嗯。我真的很兴奋。前几天我们见到了加里·布雷卡，他是个了不起的人。我学到了许多以前完全不了解的健康知识。

Matthew Hussey, dating life, of course. Mhmm. I'm really excited. We we met Gary Breca the past couple days, and he is an incredible guy. I learned so much about health that I had no idea.

是的。等我们完成他的内容后，我想把它给我父母。因为现在健康领域有太多新发现，而我感觉父母和他们那代人总是抗拒接受——如果我们过去对健康的认知全是错的怎么办？怎样才能让他们更好地学习这些？我父母可不会听两小时的播客。

Yeah. And once we create his, I want to give it to my parents. Because so much is being discovered in the health space right now and I I just feel like my parents and people of their generation are so averse to like, oh, what if everything we knew about health was wrong? How can we help them learn that in a better way? My parents aren't gonna listen to a two hour podcast.

说到角色特质，有件事一直让我印象深刻——用户对话时长和参与度。我很好奇你从用户群体中观察到了什么。

One of the things that going back to character for a second that, like, always impressed me was how long the conversations were and how engaged users were. I'm I'm curious what you see from your user base.

这因人而异。比如有人把Delphi用在转化漏斗顶部，可能就问几个问题。嗯，他们想快速得到答案。而像马修·赫西这样以思维方式闻名的人，可能会打六小时电话。

Depends on the person. So someone who is using their Delphi at top of funnel, might be like a couple questions Yeah. I wanna get a quick answer Versus someone who they're known for their way of thinking. Like Matthew Hussey, for example, six hour phone call.

哇。

Wow.

基思，一小时，你知道的，几小时。这真的取决于个人以及人们最初为什么想和他们交谈。

Keith, one hour, you know, a couple hours. It it really depends on the person and why do people wanna talk to them in the first place.

哇。它可以像一个新的排行榜，人们

Wow. It could be like a new leaderboard that people

哦，是的。是的。人们会变得好胜，但有很多种思考方式。

Oh, yeah. Yeah. People get competitive, but there's a lot of ways of thinking about that.

想要拥有比其他人更有趣的想法。

Wanna have a more interesting minds than than anyone else.

是的。对我来说，一个真正令人惊讶且参与度很高的使用案例是Faster的Jason Lemkin。嗯。因为他发推文说他会把Delphi带到所有现实生活中的对话中。这是怎么回事？

Yeah. One of the really surprising use cases to me that had a lot of engagement was Jason Lemkin at Faster. Mhmm. Because he tweeted that he brings his Delphi with him to all his real life conversations. What is that about?

我认为他会把它带到Zoom会议中。它可以在通话中回答问题，还能给他一个关于通话内容的总结。他在Sassir网站上也有这个功能。对他来说有几个用途，一是建议。

I think he brings it to his Zoom calls. And it can answer questions in the call, and it can also give him a recap on on what happened. And he has it on the Sassir website as well. And a couple things for him. One, advice.

要知道，他对Sass非常精通。第二，我认为这确实为他的Sassir活动卖出了门票。你看，过去这周我和Russell Brunson在一起，他的专长就是在会议上通过演讲来推销活动。所以这是一种一对多的大规模销售，而Delphi则是一对多再到一的销售模式，这种模式更个性化，你信任那个人，而且它能适应最终用户的需求。

You know, he knows a lot about Sass. Two, I think it actually sold tickets to his Sassir event. So, you know, this past week, I was with Russell Brunson whose whole thing is he gives talks at conferences to sell events. So one to many scale selling, and Delphi is one to many to one selling where, you know, it's personalized, you trust the person, and it adapts to the end user.

你认为数字孪生技术从早期采用者走向主流的临界点会是什么？是技术突破点吗？还是逐渐的文化接受过程？

What do you think will be the tipping point that makes digital twins go from early adopters to mainstream? Like, is it a tech tipping point? Is it just gradual cultural acceptance?

以上因素都有。我认为，访谈模式的普及和操作摩擦的减少至关重要。目前建立和使用数字孪生系统还存在不少人为设置的障碍，这需要变得极其简单才行。

All of the above. I think, definitely interview mode and definitely decreasing the friction. Right now, there's kind of a purposefully a good amount of friction to setting one up and making it useful. I think it needs to be super easy.

嗯。

Mhmm.

就像有句话说的，人们总是缺乏耐心。文化因素也是，案例越多，人们就越觉得这事不奇怪。我们想买.com域名其实是因为不想被看作AI公司。AI只是个工具，它让我们能构建这个东西。

Like a couple says, people are so impatient. And then culture. I think the more case studies, the more people that are like, this is not weird. And I think we wanna buy the .com domain because we actually don't wanna be seen as an AI company. I think AI is just like a tool, and it allows us to build this thing.

但实际上我们更像是人类公司。我们是在扩展人类能力。

But really, we're more of like a human company. We scale humans.

你觉得五年后关于数字孪生技术，哪些现在被视为反主流或超前的观点会变得显而易见？

What do you think in five years will be obvious about digital twins that, you know, is, you know, contrarian or early today?

我认为很明显，消费者更倾向于先与某物对话，而非直接与你交谈。

I think it will be obvious that consumers prefer to be able to talk to something before talking to you.

在这个人人都拥有数字思维的新未来中，人类的角色是什么？

What is the role of humans in this new future where everyone has a digital mind?

我是说，眼下这么多公司都在致力于将人类自动化。自动化、自动化、自动化。但我认为我们似乎忘记了，活着的根本意义究竟是什么？

I mean, I think right now, so many companies are focused on automating humans. Automating. Automating. Automating. And I think I just forgets, like, what is the purpose of, like, living at all?

要知道，核心始终是人类与关系。自成为人类这个物种以来，我们的生活就围绕着认识他人展开。贝佐斯对亚马逊的信念也植根于人类的核心需求——狩猎采集。你想购买物品，你想收集东西。

It's it's humans and relationships, you know. Since we became a species, our life has revolved around knowing other humans. And I think Bezos' conviction in Amazon was also grounded in a core human need, was hunter gather. You wanna buy things. You wanna collect things.

而我们押注的需求是：人们渴望与他人建立联系。在AI泛滥、信息不再是瓶颈的世界里，稀缺资源和高价值所在变成了连接、策展、信任与活力。因此我认为，那些真正投入努力的人会变得更有价值。所谓投入努力是指——如今要平庸地完成某事比以往任何时候都容易，你可以用AI批量生产书籍、课程或软件产品。

And I think the need that we're betting on is like you wanna connect with other humans. And in a world where AI is abundant and infinite and information is no longer the bottleneck, the bottleneck and the premium thing becomes the connection, the curation, the trust, and the energy. So I think humans the humans that put the work in become more valuable. And what I mean by put the work in is it's easier than ever to be mediocre at something now. You can create AI slop of a book or a course or a software product.

我认为那额外5%的顶尖努力，将获得95%的成果。

That that top 5% of additional effort, I think, gonna get 95% of the results.

我们要不要用快问快答来结束？

Should we close with some rapid fire?

嗯，平台上最受欢迎的Delphi是谁？

Yeah. Who is the most popular Delphi on the platform?

这个会变化。我是说，马克·海曼肯定名列前茅。马修·赫西、安迪·艾略特、佩斯·莫比、布伦南·伯查德、阿诺德·施瓦辛格、娜塔莉·埃利斯。但使用频率的受欢迎程度和那些虽然用户基数较小但回头率高的之间是有区别的，与百万用户使用的相比，你如何评估这两者？就像莱尼，人们经常回来使用。

It switches. I mean, Mark Hyman definitely gets up there. Matthew Hussey, Andy Elliott, Pace Morby, Brennan Burchard, Arnold Schwarzenegger, Natalie Ellis. But then there's a difference between popularity of usage and the ones that like, if you have a smaller cohort that's coming back consistently versus a million people using it, how do you evaluate those two? It's like Lenni, people come back a lot.

基思的。苏格拉底。

Keith's. Socrates.

那么消费者或企业间的B2B用例会在你们平台上更丰富吗？

And then consumer or enterprise b to b use cases will be more abundant on your platform?

我的看法是，消费者和B2B会随着时间推移而融合，因为在创作者经济或个人经济中，每个人都是一家企业。就像我们的客户是教练、作家、CEO，他们本身也是自己的企业。是的。回到品牌的概念，马克·扎克伯格作为他公司的门面，我认为，无论是B2C、B2B还是B2P（企业对个人）。

So my take is that consumer and b to b converges over time because every the creator economy or the individual economy, every individual is a business. And like our customers are coaches, authors, CEOs who are also their businesses. Yeah. And back to the idea of branding, Mark Zuckerberg being the face of his company, I think, like, b to c, b to b b to p, business to people.

是的。

Yep.

你是在为人们打造产品。所以我认为两者兼而有之。网络效应会随着消费者平台而来，但你知道，CEO们会有一个对外版本面向新员工和客户，还有一个内部版本供公司使用。

You're building products for people. And so I think it's it's both. I think the network effects come with the consumer platform, but, you know, you'll have CEOs that have an external facing version version for new hires and customers and one internally for their companies.

好的，我们来快速回答一些消费者问题，因为你是消费领域的专家。最近有没有你刚采用的消费类应用、习惯或生活小技巧？

Alright. Let's do some rapid fire consumer questions because you're a consumer guy. What is is there a consumer app or habit or life hack that you have recently adopted?

说实话，我对新出的消费者AI工具相当失望。而且我尽量不去过多摆弄它们，因为我在Delphi上已经摆弄得够多了。

I've been pretty underwhelmed by new consumer AI tools, to be honest. And I try not to tinker around too much because I tinker around enough with Delphi.

嗯。

Mhmm.

所以我觉得我的答案和那些老生常谈的Perplexity研究、Notion之类的没什么不同。

So I don't think my answers are very different than the cliches of perplexity research and notion and things like that.

除了Delphi之外，AI是否在其他方面对你的生活产生了实质性影响？

Has AI affected your life in any meaningful way outside of

嗯。有一点它让我进步很大的地方是，很多时候人们的沟通方式各不相同。我指的不只是用词或语言，而是他们理解事物的方式。比如你在邮件中和客户、投资者或新员工沟通时，可能会因沟通不畅产生冲突。

Delphi? Mhmm. One thing that it has made me a lot better at is a lot of times people have different communication styles. And I'm not just talking about in like their words or their languages, but in how they perceive things. So you could be emailing someone about, you know, a customer or an investor or a new hire, and conflict can result due to lack of communication.

所以我实际经常使用AI的一个场景就是：他们真正的意思是什么？以及如何用他们能理解的方式表达我的意思？嗯。我觉得这对人际关系帮助很大。

So that's actually one way I've been using AI a lot is what do they actually mean and how can I get what I mean in the way that they perceive? Mhmm. And I think that has helped me a lot with relationships.

有意思，几乎像个翻译器。

Interesting. Like a translator almost.

几乎像个思维翻译器，但无关语言。这只是你感知和理解事物的方式。嗯。

Almost like a mental translator, but it's not language. It's just the way you perceive and understand things. Mhmm.

好的。最后一个问题。我为此感到非常自豪。刚想到的。德尔图灵测试。

Okay. Last question. I'm very proud of this one. Just thought of it. The Delphi Turing test.

在哪一年人们将无法分辨自己是在与某个人的数字意识交谈，还是与那个人本人交谈？

In what year will people not know whether they're talking to somebody's digital mind or or that person?

首先我要说明，我们并不一定希望那样。我们绝不希望它欺骗人们。是的。德尔菲本意并非欺骗。没错。

Well, I'll preface by saying we don't want that necessarily. Well, we don't want it to ever be tricking people. Yep. These Delphi is not meant to be deceptive. Yep.

我认为2026年会普及。因为现在已经有几起案例了。每当客户创建德尔菲时，我们会说：先发给你妈妈试试。这是让你放心的方式。很多时候他们反馈说：我妈妈以为那就是我。

I think widespread 2026. Because already it's happening in a couple cases now. We we whenever a customer creates a Delphi, we say, send us your mom first. And that's gonna be the way you're confident with it. And many times, they're like, my mom thought it was me.

天啊，这太神奇了。

Oh my god. Like, this is amazing.

回答得漂亮。2026年。没错。转角处很快就到。

Great answer. Twenty twenty six. Yep. Come around the corner very quickly.

我们现在就给阿德尔菲打电话吧。

Let's call Adelphi right now.

我赞成。对。要不我们打电话给我朋友？其实还没见过面，但我...我和他的德尔菲是朋友。阿诺德·施瓦辛格？

I'm down. Yeah. How about we call my friend actually haven't met him in person, but I'm I'm friends with his Delphi. Arnold Schwarzenegger?

是啊。

Yeah.

你们觉得呢？

What do we think?

太棒了。

Love it.

好吧。你们想问他什么？

Alright. What do you guys wanna ask him?

我每天只有十五分钟锻炼时间，因为很忙。最适合的十五分钟运动是什么？好的。

I have fifteen minutes a day to work out because I'm busy. What is the best fifteen minute exercise that I can do? Okay.

嘿，我是AI阿诺德。我来帮你剔除废话，让你更强壮、更健康、更快乐。今天有什么想法？

Hey. This is AI Arnold. I'm here to cut the crap and help you get stronger, healthier, and happier. So what's on your mind today?

阿诺德，我每天只有十五分钟锻炼时间，感觉不够多，但我想感觉良好并改善健康。你有什么建议？

Arnold, I have fifteen minutes a day to work out, which I feel like is not a lot, but I wanna feel good and I wanna get better in my health. What do you recommend I do?

只要专注并全力以赴，十五分钟足够了。别想太多。坚持简单有效的多肌肉群动作。做一到两组俯卧撑、反向弓步和仰卧抬腿。减少休息时间，逼自己一把。

Fifteen minutes is plenty if you focus and go hard. Don't overthink it. Stick to simple, effective moves that hit multiple muscles. Do one to two sets of exercises like push ups, reverse lunges, and lying leg raises. Keep rest short and push yourself.

很快你就会有冠军的感觉。现在就开始吧。

You'll feel like a champion in no time. Now get to it.

好的，老兄。谢谢。

Alright, man. Thank you.

太棒了。非常酷。是的。太神奇了。达拉，非常感谢你加入我们。

That's awesome. Very cool. Yeah. Amazing. Dara, thank you so much for joining us.

这个

This

真的很有趣。

was really fun.