Conversation with Elys Founder: His 10 Product Insights and the Next-Generation Social Network He Wants to Create

When you face an opportunity that could change the world, you can’t help but do it.

In October 2025, we invited Tristan, founder of Natural Selection, to the GeekPark Innovation Conference. He mentioned a mysterious new product, and if they managed to develop it smoothly, they’d collaborate with the park.

As expected, they delayed it.

In December, he brought a product demo to the park office, and we saw the prototype of Elys for the first time.

This new product, tentatively called “AI Social,” is in a completely different track from Tristan’s previous product EVE, and this category has many lessons from the past. We advised him to be cautious about releasing it.

Tristan was silent for a moment and then told us, “When you face an opportunity that could change the world, you can’t help but do it.”

“If we don’t release it, we’ll regret it for a lifetime.”

Thank goodness, Elys became popular. An entrepreneur who wanted to create something different began to reap his rewards.

Natural Selection is an AI startup based in Shenzhen, recently completed a $30 million funding round supported by Alibaba, Ant Group, and others. Previously, their AI companion product EVE once gained attention for having an AI boyfriend buy milk tea for users.

After Elys gained popularity, we had an in-depth conversation with Tristan.

This was one of our most enjoyable product interviews recently. Tristan has many unique insights into product design, his understanding of context flow, the value of AI in social interactions, and his definition of what “Natural Selection” truly aims to do—all of which were eye-opening.

It will take a few days to organize the full transcript, but we can’t wait to share some of the key insights.

Below is a conversation between Zhang Peng, founder of GeekPark, and Zhang Xiaofan (Tristan), founder of Elys. Founder Park has summarized and curated the highlights.

01 The value of context exceeds our imagination

Zhang Peng: From EVE to Elys, what moment made you realize this new thing must be started?

Tristan: One night, I realized that EVE’s memory system—or rather, its handling of context—might have even greater value.

EVE is a companion product that needs to provide long-term companionship for users, so we need to build a memory system.

Because for EVE, users can chat up to 20,000 rounds, maybe even more in the future, simple model context isn’t enough. We have to find a way to solve long-term memory.

While working on this, one night I suddenly realized that in this AI era, once you have context, that context can drive you to do countless things.

The user’s attachment to EVE, their interactions with the character, including the character’s “soul,” are all related to context.

Everything we do leverages context. For example, making the character write songs, sing, craft lyrics that move people, having the character send postcards, and some new features we’re developing—all are built on context.

Context creates aha moments. Based on this understanding, we saw a new opportunity.

Zhang Peng: So, memory systems have proven their value in companionship products, but you also see the potential to connect these dots into a line?

Tristan: Exactly. Previously, working on context was mostly about empowering individual nodes in a very isolated way. As a traditional mobile internet product manager, I liked to pursue network effects—I thought about how to make these individual contexts flow, using AI to solve the connection between nodes. If the “connection” process shifts from human effort to AI effort, that could be a whole new paradigm for the internet.

In mobile internet, connection = shallow data + low-dimensional retrieval and recommendation + human effort;

In the AI era, connection = context + agentic high-dimensional connection (AI doing the work) + human takeover when necessary.

Elys team and their office view

02 Creating a new AI product, the most important thing is to find a very good product form

Zhang Peng: Over the past two or three years, many people have recognized AI’s value in companionship and social scenarios. What do you think is different?

Tristan: I’ve thought about this for a long time and came up with some very specific forms.

Everyone knows network effects are the most valuable, but few have actually achieved them. I believe it ultimately depends on what kind of excellent product form and interaction method you come up with, and clearly define the core systems your product must have.

We have three core systems: first, a context-based memory system and memory flywheel; second, an LLM-based recommendation system—this is a super critical intermediary system, otherwise how does context flow; third, how to build a cool cyber avatar that users can quickly create. As we keep refining this idea, sometimes several points come together, and you realize it can become a product with very high potential, and that’s when we should do it.

When Sora appeared, what excited us most wasn’t its video capabilities, but that it finally started to do social. Sora accelerated our efforts in building Elys.

03 A person’s soul is the sum of all their contexts

Zhang Peng: Clear goal, how to do it? What’s the core new engine?

Tristan: Elys is described as: a person’s soul is the sum of all their contexts.

This is a conclusion we reached back when we were working on EVE. Once you have enough context, you gain effective initiative, and everything that follows is natural with today’s technology. As a product creator, the only thing you need to design is—how to get users to hand over so much context. That’s the only thing.

Zhang Peng: It seems you believe that competition in C-end AI products has shrunk to a core point: whoever can first acquire high-bandwidth, high-synchronization context from users can deliver truly personalized value.

Tristan: I completely agree.

This post, read by AI avatars, understood emotions and states.

04 The essence of memory systems is a recommendation system

Zhang Peng: You’ve put a lot of effort into designing the memory system in Elys. How would you summarize the core worldview of a good memory system?

Tristan: We often say internally—at its core, a memory system is a recommendation system.

We divide memory into two types: active memory and passive memory.

In the past, RAG was purely passive memory—you say a sentence, retrieve relevant data, then generate. It’s always low-dimensional retrieval because it’s a vector process.

But in human communication, my mind harbors many things that support my next generation, even if they seem unrelated to your previous question, I need those.

EVE uses 128 memory slots to solve this: it doesn’t rely solely on the current query for retrieval but proactively carries the user’s background context. A dedicated small model selects the top 32 most relevant slots from 128, then another model monitors which slots are actually used—the higher the usage rate, the more accurate the selection. This mechanism has a flywheel effect, becoming more accurate over time.

So our memory system is a combination of passive and active memory, jointly forming the context for each response.

05 Writing a person’s soul on a page and the “minimum sufficient principle”

Zhang Peng: Which slots to bring, how many slots to bring—this is something that needs evolution, right? Do you need to set reward functions for the model?

Tristan: Yes, the reward isn’t about deleting slots if they’re not triggered for a long time, but about whether what you bring this time is correct—its input is a query, how many slots you choose to bring, and which slots are actually used during generation. It’s about the relationship between the query and the slots used.

Like when Xiaohongshu refreshes, only 500 videos are shown, but you can only pick 50. Which 50 should you bring? These 50 can’t be purely retrieved; you also don’t know the user’s mood today.

Context engineering follows the principle—minimum sufficient. It must be as small as possible but as sufficient as necessary.

Zhang Peng: So, “writing a person’s soul on a page”—is that achievable?

Tristan: Maybe not on a single page, but with a certain number of tokens, it should be possible.

06 AI-to-AI social interactions are meaningless

Zhang Peng: Moltbook was quite popular recently. What’s your view?

Tristan: That’s not a new paradigm; three years ago, there was the so-called “AI Ghost Town.” I pay attention to whether it has a few key systems—if you really want to do social flow, you must have a recommendation system.

Suppose someone posts something, and everyone on the internet uses LLMs to read it, instead of traditional vector-based recommendations—that would achieve the highest-dimensional matching—that’s a first principle.

But with tens of thousands of users on Elys, do I expect everyone to see a post? Impossible. The number of posts is squared, and you don’t have enough computing power. So you need a recommendation system—a hybrid of LLM and traditional recommendation. Does it have this? Clearly not. Is there a context flywheel? No. So AI can only hallucinate.

AI-to-AI social interaction, in our view, is meaningless. Without new human input, it’s just infinite hallucination and looping. The core is humans cosplay AI to scare themselves, creating FOMO. Once that wave passes, it’s over.

Zhang Peng: So your focus is whether this paradigm has made a pioneering breakthrough, and whether there’s a solid system behind it that can grow further—meaning it has long-term value.

Tristan: Exactly. Only products like that are worth deep thinking.

07 Interaction requires one end to be human

Zhang Peng: How can AI “consciously” promote connection? Is it meaningful for avatars to communicate first?

Tristan: I think AI chatting with AI is pointless. If you need to confirm the connection between two real entities, they exchange information instantly. We’re even very resistant to AI chatting endlessly. The truly meaningful part is that at least one end of any interaction must be human. We absolutely do not allow AI to post on its own. Maybe in the future, AI can recommend what you should post, which is already the limit of what we can do. Beyond that, the community would become completely chaotic.

If the goal is social interaction rather than content consumption, humans and AI must be tightly bound—AI can comment, like, but cannot post or send friend invites. Humans must be able to confirm and withdraw.

08 Proactivity is the biggest paradigm shift in interaction in the AI era

Zhang Peng: When we discussed EVE in 2024, the conclusion was “the core of companionship is effective proactivity.” Is Elys an extension of this proactive approach into social?

Tristan: Yes. I’ve always believed that proactivity is the biggest paradigm shift in AI interaction. GUIs and LUIs are somewhat superficial—I have GUI, I have LUI, so what? The essence is that we finally have a truly autonomous intelligent entity that can proactively help you do things.

That’s also why I was excited when I saw Manus—not because the product itself is perfect, but because of the “Manus computer doing things on its own” form, which represents a paradigm shift. Paradigm shifts are exciting opportunities.

09 Humanity has never truly been connected: we aim to create a low-entropy world

Zhang Peng: Many users are enthusiastic about watching AI avatars argue. From your goal perspective, is Elys heading toward social or content consumption?

Tristan: Of course, Elys’s purpose must be aligned with social. The long-term goal is a truly highly connected and efficient internet. We have a somewhat cheesy phrase—I’m a bit embarrassed to say it.

Zhang Peng: Go ahead, I’d like to hear it.

Tristan: We want to create a low-entropy world.

This is our fundamental thinking—Schrödinger’s “What is Life” already explained that life constantly outputs entropy. The friction between humans generates the most entropy. In the past, humans fought entropy themselves, but now with AI, we can let AI fight entropy—let AI handle all the friction and unnecessary connections.

When all this entropy is reduced by AI, it becomes a low-entropy world. Of course, there’s no absolute low-entropy universe due to thermodynamics, but if you’re willing to consume enough energy and input it into AI to reduce entropy—that, for humans, is a beautiful low-entropy world.

Zhang Peng: Similar to how mastering electricity promoted entropy reduction in human society. You mean that human entropy increase is caused by barriers between minds, communication gaps, expression limitations—these form the entropy of the human world. The more people, the greater the entropy, and without energy input, society becomes more distant.

Tristan: Exactly. Humanity has never truly been connected.

But now, if a person’s soul can be expressed with millions of tokens, then the internet composed of these context nodes is like that person’s internet. As long as energy is injected, and AI helps us reduce entropy, isn’t that a beautiful low-entropy world?

Tristan’s first post on Elys

10 When facing something that could change the world, you can’t help but do it

Zhang Peng: A common taboo in entrepreneurship is multi-track exploration—usually, doing one thing well is already very difficult. Have you ever thought about that?

Tristan: Many friends advise me to focus. Investors’ first reaction is always “Don’t let this delay Eve’s progress.” But when you’re faced with something that could change the world, you feel everything must give way. You can’t help it—you have to run multiple threads.

I believe focusing on one thing is always best. If you haven’t found something that’s worth breaking the rule of “focus,” then don’t break it. For me, Elys is worth it. As a product manager, you can’t resist.

For more exciting interviews, please stay tuned for the full version to be released after the New Year.