DAPPCON 2025: AI Design Beyond Chatbots - Sydney Lai

Transcript

Hey everybody, my name is Sydney Lie. I know this is the last talk of the day, so I made sure to design the talk to be a little weird to, you know, have you guys have a little bit of fun. Um, so why am I even giving this talk? What is Gaia? What have I been working on? Just for a little bit of context, I have spent most of my career working specifically in infrastructure anywhere from IPFS storage to DEX infrastructure to key management solutions. So why am I giving a talk at DEPCON, right? And I think one of the most how do I I think one of the my biggest

motivations or biggest drivers as to understanding how do we provide web 3 rails to agentic workflows is probably one of my biggest drivers to even bring me to this place today. So again, because we talk a lot about DAPs, I was thinking, you know, one of the most important things I'm currently working on in my workflow right now is being able to securitize a lot of these agentic workflows, the data that goes into the agentic workflows and the people who provide that type of data. So when I'm thinking dabs, apps, apps, okay, what could that possibly look like? What are we currently building? I actually wanted to go through this

example with Minecraft as a UI. And so I'm going to use Minecraft as an example to showcase how we are currently using AVS's specifically to securitize our network. So this is going to be on a loop. You guys can kind of just visually follow along and I'm going to narrate what this is actually doing. So in this particular case, we at Gaia, we're building open- source infrastructure for you to be able to build DAPs or applications on web 3 rails. What that means is that you can build application layers that are agentic workflows. And so in this particular case, we decided to use Minecraft as a demo. And in this particular game, uh what we are

showcasing is that you can have autonomous agents in the game itself. Typically the game is driven by humans, kids, adults, doesn't matter. And in this particular case, what we are telling the agents to do is to accomplish certain tasks. We are telling them to get certain resources such as wood. Maybe they're going to go gather wood to build specific recipes, build a boat, build a house, weaponry, etc. And what we're seeing is that we are laying the foundations for MCPU or the ability to have this type of integration across different applications so that the autonomous workflow can make these decisions for you as a player because it

understands what your intention is. And so in this case what you're seeing is that um because we are running a model uh on this on top of this UI we are also providing the example that we're building in AVS to securitize this application so that it is actually wood or you are actually a good actor or the instructions which is you know come follow me go find this wood go me a boat that they're going to actually build you a boat and they're not delivering you like a house or something like that and in this particular case I wanted to further illustrate MCP um because I think oftent times we look at you know architecture through the lens of either

code or diagrams and in this specific analogy just think of it visually as let's say you're a MacBook you have your adapter and within the adapter you can have different dongles right and in these types of dongles it's really what kind of application or DAP layer you are plugging in and you're letting your automated workflow make the decision for you. If you want to go on collab land, make a a discussion in Discord, maybe unis swap, you need something traded automatically if a certain condition is met during Discord. Um or otherwise you need to once you swap it, you're going to sell it on MetaMask to gain an NFT, whatever the case may be. Um, at the end of the

day, what we've been working on on the upper right hand side is being able to provide that type of inferencing or context so that your agents can autonomously integrate and interact with the other uh applications that you so choose to integrate with. So, I'll give the example let's say you are using let's say chatbt and you say hey go pay my electricity bills. Uh, it's going to say hey I don't have context. What state do you live in? What is your authentication? How do I go and log in and pay your electricity bills as an example? So, how do we do this a how do we how do we know that this agent is running the AI model that we think it is, right? So, in the case of the example of Minecraft, you say, "Go build

me a boat." But do we know if that boat is actually a boat? Is it actually using wood or whatever the right resources are? And so one of our works that we've been really focused on at Gaia is being able to build a context network and index index context and data sets across both onchain and off-chain AI marketplaces. Um in this particular case you can see you know at the last time I took this picture we have about 700,000 nodes um about 8 trillion in throughput. So you do know that the node or the context network is not static it is live. And in this particular case, since we are in Germany, um we have about roughly 1/4th of our network being supported on a commercial enterprise

level through uh node providers here in Germany as well. And because we are an infrastructure tool and you know again we are at DVCON, we can look at the application layer on these types of infrastructure in many ways. The most common ones that we are aware of is going to be the chat application, right? the chat interface that most people know which is like hey how do I do this? What's the information for that? What is the context for this? We can then also stretch our imagination of our AI world from kind of a 2D chat application all the way to kind of a virtual environment. What does an AI environment or an AI world look like in the UI or the skin of Minecraft as an

example? But I think another thing to really understand is that when we are building these virtual worlds, the common question that we're always asked is what is real and what is reality? What is true identity of the other person? Is it a good actor? Is it a bad actor? Um is you know is this AI agent world uh valid as an example. So one of the things I really want to walk us through is just a really quick a quick quick taste of like what are the current solutions in securityizing AI that we see today. So one example is ZK proofs.

Um this is of of all the cryptography oriented types of security. I I do like this one. Um, as an example, for those who are new to this concept, ZK proofs, let's just say you are trying to buy alcohol in the US and you need to show your ID. When you're showing your ID, you're actually giving away a lot of private information because I see your home address. I see your date of birth, your height. We all lie about our heights. Um, but we also have the eye colors and all that stuff, right? And the this type of information not only becomes a privacy concern but it also becomes um a almost too much information, too much context and it also helps creates latency. And when you have a type of latency when you're

securitizing these data sets, then you as a user is going to have a bad DAP experience when you're interacting with it. Um you know another example could be is um using TE is another cryptography based or oriented type of security for securitizing AI. It is not my personal favorite. There are a lot of people who believe in this type of thesis which is totally fine and I think one of one of the main reasons for me is because uh there's two two reasons. one, it really requires um you know hardware a dependency and so as we've seen the advances of technology sometimes hardware can be outdated. Um and another reason is because for me it's it

requires too much binary decision-m yes or no if yes you know slash if no p etc. Right? And so I think that with the evolution of AI and how we've seen technology impact society and how society impacts technology, um it's going to need to really be able to handle nuance data and nuanced AI. So I'll give an example. You do something bad. Do you go to jail? Yes or no? Right? Um that can be nuance. Is this art nice? Is it a nice piece of art?

yes or no, right? So then these types of cryptography based um security solutions, it becomes harder to handle that type of information. And so in this case, going back to Minecraft, just to stay on theme is, you know, is the model wrong? If they're using a recipe book on the upper right hand side, you'll see, hey, look, we have this guide book, we have this data set, we've collected the materials that we need to make a boat in this particular case. And then you're looking at it technically it's a boat. Does the boat work? Does it even look like a boat? Do we know it's a boat? So one of the things that we've been really focused on um in this last year in our engineering is understanding how we build

statistical models into AVS's. So really being able to handle this type of dynamic data and this dynamic uh modeling for AI to be able to handle validity in this particular case. And so within this public research that you guys can see, um, one of the most important things that we're looking at is understanding how much the models deviate from each other. Um, how much do they statistically deviate from each other. So what you'll see here on this chart is that it really shows the distance between the model pairs and they're about 65 times larger than the highest scattered observed um you know plots uh within any of these models and

we're running a lot of these like like llama 3 base models. Um and so this larger separation between the inner model distances um really provides a variation that indicates that the guy nodes which ones are different which ones are the same which ones are true honest and at the end of the day um we're really looking at pattern matching as an example. So going back to the analogy of you know having a UI layer is what does a AVS look like or an agon layer AVS look like um with the with the image of Minecraft right so if we're looking at these AVS validation uh in the lens of Minecraft what we're seeing

is that these there's characters in this world the AVS's that acts as referees so as your AI agent is going around getting wood and all that stuff building a boat. What they're saying is, "Hey, we are a ref. Did you actually get the materials that you said you would? Is this an actual recipe that I said it is?" And and so this is can be thought of as almost like a visual representation of staking on an as the referees or the node the node providers being able to put down money and vouch for the agent.

Um, and then of course the bad referees uh will then get slashed or lose their stake um in that case if if they're caught cheating, right? Um here's another example of another visual of the AVS uh because you can also monitor and find backed actors and and invalidate if they are a creeper or if they have bad intention. Uh, one example and this is completely a tangent and I don't know if you can even see this which is I was using Gemini a few months ago and I was just walking around in the capital of the Philippines and I was just curious who is the president of uh the current the president of the Philippines and it said hey I cannot give you that information and then I started having an argument with my Gemini and I was saying

you know I'm asking for the current president of the Philippines this is not a controversial topic this is just a fact, right? And it says again, I can't give you that information because it cannot validate me as a paying customer. Cannot validate if I'm a bad actor or not in this particular case. And so, you know, this this last photo is a little bit larger. It's a little bit broader, but in this particular example is this is the architectural diagram to showcase how the AVS networks works with the indexing indexing infrastructure that we have at Gaia. So really, it's the back-end architecture that showcased what the Minecraft example was showcasing. But at the end of the day, what we're really trying to handle is

really problematic nodes and being able to have and handle subjective information and how do you do that both mathematically as well on an engineering scale? Because at the end of the day our you know I think our our biggest focus right now is being able to understand how do we scale validation on a AI network because if we look at what we're trying to do in the in the game of Minecraft is that we are playing this game we humans are building AI and what is the infrastructure that we are building so that we can not only create AI but set the guard rails to be able to

validate and really provide the guidelines so that it can be autonomous. And so today that's really my talk is just helping everyone understand what is an agon layer as how do you use it to securitize an AI network infrastructure and using it through the lens of Minecraft. Thank you everybody. [Applause] Um, oh, there's questions. Yes. Is there any questions this time around? Let's see for Sydney.

No. No. All right. Thank you so much. Thank you so much, Sydney.