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 consider collaborating 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 given the many lessons learned from similar categories, we advised him to proceed cautiously with its release.

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 a hit. An entrepreneur aiming to create something different began to reap his rewards.

Natural Selection is an AI startup based in Shenzhen, which 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 thinking—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, which moment made you feel that this new thing had to 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, conversations can go up to 20,000 turns, possibly more in the future, simple model context is definitely not enough. We have to find a way to solve the long-term memory problem.

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

Users staying in EVE, their bonds here, their interactions with characters—including the “soul” of the character itself—all relate only to the context.

Everything we do leverages context. Making characters write songs, sing, craft very touching lyrics, write postcards for users, 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, the memory system has proven its value in companionship products, but you also see the potential to connect the dots further?

Tristan: Exactly. Previously, working with 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 connections between nodes. If the act of “connecting” shifts from humans to AI, 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 linking (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 the value of AI in companionship and social scenarios. What do you think is different?

Tristan: I’ve thought about this for a long time and come 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 the 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, so we should pursue it.

When Sora appeared, our excitement wasn’t just about its video capabilities, but about finally starting 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 do you plan to do it? What’s the new core engine?

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

This was 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 logical with current technology. As a product creator, the only thing you need to design is—how do you get users to hand over so much context? That’s the only thing.

Zhang Peng: It seems you believe that competition among 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, understands 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 for building 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 interactions, my mind harbors many things that support my next generation, which may have nothing to do with your previous question, but I need those things.

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 specially trained small model selects the top 32 most relevant slots from the 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 precise 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 in 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? Those 50 can’t be purely retrieved, and you 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 want real 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 Elys now has tens of thousands of users. Do I expect every post to be seen by tens of thousands? Impossible. Daily posts are in the hundreds of thousands squared, and you simply 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 on whether it brings a breakthrough in a certain paradigm, and whether there’s a solid, scalable system supporting it—meaning it has long-term value.

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

07 Interaction must involve humans on at least one end

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

Tristan: I think AI-to-AI chatting is pointless. If you need to confirm the connection between two real entities, the information exchange is instant. We’re even very resistant to AI chatting endlessly. The truly meaningful interaction involves at least one human on each end. 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 entropy-increasing.

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 shift in interaction in the AI era

Zhang Peng: In 2024, when we discussed EVE, 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 a GUI, I have an LUI, but what’s the point? The fundamental change 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 want 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, 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 is where the greatest entropy is generated. In the past, humans fought entropy themselves, but now with AI, we can let AI fight entropy—let AI handle all unnecessary friction and 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. Energy is needed for harmony and stability.

Tristan: Exactly. Humanity has never been truly connected before.

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 supplied, 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: Entrepreneurship often discourages multi-track exploration; usually, doing one thing well is already very difficult. Have you ever thought about this?

Tristan: Many friends advise me to focus. Investors’ first reaction is always “Don’t let Elys delay Eve’s progress.” But when you’re holding something that could change the world, you feel everything must give way. You have no choice—you can only 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 “single-minded focus,” then don’t break it. For me, Elys is worth it. As a product manager, you can’t resist.

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