In this episode of The Cognitive Revolution, host Speaker A interviews Yohei Nakajima—a builder of AI agents, venture‑capitalist, and creator of BabyAGI—about the intersection of artificial intelligence, identity, and cultural perspectives. The conversation opens with a note about a copyright strike that limits the YouTube upload, directing listeners to the show’s website for the full audio and video. Yohei contrasts Western and Eastern notions of self: the West often equates identity with one’s thoughts, while the East treats the mind as a tool whose output (thoughts) can be harnessed through practices like meditation. He proposes using AI to convert the flood of digital communications (emails, tweets, web content) into structured knowledge graphs that map people, entities, and events, enabling more intuitive connections and introductions. Yohei explains his practical workflow for building AI tools such as BabyAGI—iteratively testing prompts, leveraging GPT‑based web browsing, and constructing retrieval pipelines. He describes an autonomous CRM prototype that ingests Game of Thrones episode summaries from Wikipedia, automatically generating a dynamic knowledge graph of characters, alliances, and conflicts that evolves over episodes and seasons. The discussion also touches on how language embeds philosophy, using the Japanese greeting “genki desu ka?” (root‑energy) as an example of how cultural concepts of identity are woven into everyday speech. Throughout, Yohei emphasizes that viewing identity as a place within a larger system, rather than an isolated self, can guide AI development toward more collaborative and hopeful futures.
Chapters
Hello and welcome back to The Cognitive Revolution. Today we have a special episode with returning guest Yohei Nakajima, builder of AI agents and VC investor. As you may recall, when Yohei appeared on the show back in October, he had just recorded a talk at the TED AI event. As of mid-January, that talk is now online for all to see. So Yohei and I sat down on the morning of his birthday to watch the talk in full. Along the way, we paused it to discuss And expand on some of the important themes that he raises regarding identity and how Eastern and Western cultures relate to the rise of large language models. This was a great conversation, and I had a lot of fun doing it. But unfortunately, when we came to upload the video to YouTube, we got a copyright strike, and we have not been able to resolve that. So to see this full episode after the upcoming few minutes of highlights, I really hope you'll go to our website, cognitiverevolution.ai, where you can get the audio-only version and also subscribe to our audio channel if you've not done that already, and also see the full video on our Substack page. So thank you to Yohei for suggesting this. It was a lot of fun, a great conversation, and I hope you'll go see the full thing at cognitiverevolution.ai.
I think Western identity tends to think of like, my thoughts are who I am, and so my mind and my thoughts are my identity. I do feel like Eastern cultures tend to treat the mind and the brain as more of a tool. to control, and your thoughts as an output of that tool. And so like meditation and enlightenment is really about harnessing how to leverage that tool. As I get emails, as I get texts, as I, you know, as I follow people on Twitter, as I read websites, if I could just convert all that into a structured knowledge graph of the people and entities and events, it should be easier to like identify potential people to reach out to, to connect with, introductions to make amongst people, right? I've seen a couple of early tools of like helping people understand each other that previously wouldn't. Or helping find commonalities between 2 groups of people that might not be intuitive. And I think if we can start to think about AI as a tool for that, new ideas will emerge that can hopefully create a future that's not as bleak as some people see the future.
Maybe for starters, take us a little bit more behind the scenes of literally how do you do that work procedurally?
When I'm thinking about building a next mod of BabyAG or any AI tool for that matter, after I built a first prototype, I will run it Over and over again with multiple different prompts and examples, and I'll watch it do things and I just watch it over and over and over again until something like clicks for me when I'm like, wait. And I mean, a lot of the stuff I would wanna retrieve is online, I guess, right? A lot of my work is I'm doing web research all the time. And so I did find that with GPTs or with assistants, you can actually just tell it to like do a web browse with like a site-specific search, for example. And you, it's kind of like you built a retrieval over a website. I have a prototype. Like autonomous CRM that I've been testing, which I'm testing it with Game of Thrones episode descriptions from Wikipedia. And so I'll like upload one episode description at a time. And the idea is that it's like on the backend building a knowledge graph of all the information.
Episode by episode, season by season. And, you know, you would perhaps want a history of like, this person is, you know, aligned with this person and then they're enemies, you know, and there's kind of a, you know, it's not just one fixed description.
I think the concept of identity in today's world, a lot of people think about like, who am I? And make it really like, you know, internal versus I wanted to get people to start thinking about identity as your place in a larger system, I guess. It was only after I grew up that I started to really appreciate how much philosophy is embedded into language, specifically Japanese language too, because you're using Chinese characters where the characters themselves have meanings. A good example is a common way to greet someone is genki desu ka? Like, are you genki? Is how Japanese people greet someone. But the characters for genki Gen is root and ki is energy. So it's like, how's your root energy? It's the most casual way in Japanese to ask someone how they're doing. And I think that's a very philosophical way to ask somebody how they're doing.
For me, and I think for most who have just kind of the traditional Western background, it is natural to think of ourselves primarily as individuals. And then this thing is like this kind of weird language model, and I've got to tell it what role to play, tell it what individual to be.
What I didn't get into the talk is that a lot of these studies, when they're looking at the interaction events, they're Also looking at the trails ants leave as part of the collective intelligence of like a communication. So if you look at a single ant, you would not consider the trail they leave as part of that ant. But when you think of the ant colony as an identity, then the trails they leave, the tools they use to communicate with each other, become part of that collective intelligence. So if you look at me individually, my computer is not part of my intelligence. But if you look at human society as a collective intelligence, then our computers, the technologies, the internet all become— Part of us. Part of that identity of that collective intelligence.
