# What It Takes to Run a Personal Assistant Around the Clock

The a16z Show · 2026-11-18 · 33 min · https://www.youtube.com/watch?v=kBJe4H_WobA

## Transcript

Ken Liu

People are very underestimating how much the computer already knows. You no longer have to explain anything to your coding agents. You can just screenshot anything and say, “Fix,” and then it would know what you’re fixing. The question then is: can you just analyze the heck out of it?

Martin Casado

What context does Grok Bot not have that First Person Labs would allow?

Ken Liu

One of the biggest problems right now is that people have to ask. You’re not supposed to ask things. They’re superintelligence. But if you have a user model that just builds up by itself, and then these things keep analyzing in the background, you can just share that over instantly. We focus on essentially creating a model of a person and then putting that person in control.

Joel de la Garza

When people think about this thing seeing everything you do, there’s an immediate sort of “whoa.”

Ken Liu

If you don’t trust us, let’s say, in principle, you should be able to bring your own tokens to analyze data that’s on your laptop locally.

Martin Casado

Can you talk through what you think are the more surprising use cases you’ve found?

Ken Liu

For development, it turns out that—

Joel de la Garza

Thank you, Ken, for joining us. Really happy to have you on to talk about what you’ve been working on at First Person Labs.

Martin Casado

Is this the first time you’re talking about it?

Ken Liu

Yes.

Martin Casado

So what do you do?

### Building a Model of You

Ken Liu

We focus on essentially creating a model of a person and then putting that person in control. A model of a person basically means understanding their memories and what they do, but more than that, their priorities, preferences, goals, values, commitments, and intent.

Martin Casado

Let’s make this very simple. I’m a big Grok Bot user, so I use Grok Bot a lot. Where would First Person Labs fit into my usage of Grok?

Ken Liu

The way it works is that you would just bring context over to Grok. It’s portable context. You go to Grok Bot and say, “Hey, can you talk to my thing to figure out what I want?” Then the two of them will start talking, and you can send prompts like, “Buy me a flight,” and it would know what flight you’re talking about.

Martin Casado

What context does Grok Bot not have that First Person Labs would allow?

Ken Liu

I would probably ask the opposite question: what does First Person Labs not have if you build a user model of yourself? Let’s say your preferences for the seat on your airplane, how early you’d like to arrive at the airport, and where you’re flying. Are you flying first class or normal? As of today, you have to explain all of that to Grok Bot. You have multiple rounds of questioning. But if you have a user model or a model of you that builds up by itself, and these things keep analyzing in the background, you can share that over instantly.

Joel de la Garza

For example, OpenAI released two new cyber-capable models yesterday.

Ken Liu

Mm.

Joel de la Garza

I haven’t been using my Codex in a while, but I have been using Second. So I can just go start using Codex, and it has all the other work I’ve already done and all the additional context already saved?

Ken Liu

Yeah. You just go to Codex and ask, “How’s my Second? What’s going on?”

Joel de la Garza

That’s awesome.

Martin Casado

Does Second ever become a first person? Will it ever be a first, or will it always go through agents?

Ken Liu

That’s a good question. I think a user model is a process. You have to start somewhere. You start with a baseline, foundational list of artifacts: what you did, who the people in your life are, maybe your preferences. Over time, it starts analyzing the way you talk—

Martin Casado

Yeah.

Ken Liu

—the way you present yourself, the way you share information.

Martin Casado

Yeah.

Ken Liu

Over time, you build up even more artifacts and more understanding on top, and maybe you train some of that into the model. So you’ll go from portable context into something more like a representation of yourself. One example I like to think of is the Alfred and Batman example. If Batman wants to buy a cheeseburger and get Alfred to do it, Alfred wouldn’t reveal that it’s Batman doing it. He would just buy it. He would state the preference.

Martin Casado

Alfred being Batman’s butler.

Ken Liu

Oh, yes, yes, yes. Being the butler. Yeah.

Joel de la Garza

Or his agent.

Ken Liu

Yeah, or his agent.

Joel de la Garza

Or his agent.

Ken Liu

Yeah, yeah.

Joel de la Garza

I should call my agent Alfred.

Martin Casado

That’s a great idea.

Ken Liu

Yeah, yeah. He would just do it, and then you would trust him because you know he has a good model of you and what that means when it comes to getting things done.

Joel de la Garza

It’s interesting. You describe First Person Labs as having this thing called a Second. The Second understands who you are and has context, and then other agents talk to that Second, right?

Ken Liu

Yeah.

Joel de la Garza

It kind of understands your preferences, what you’re doing, and what you want to do. But I think that doesn’t highlight another thing you’ve been working very hard on, and I think it’s worth talking about. You’re actually able to get access to a person’s digital context, like messages, chat, and email, and make that available too. Can you talk a little bit about what you’re doing there? As one of the earliest First Person Labs users, I’d say the thing that struck me wasn’t that it knew who I was, but more that it had access to all of my channels really well. It turns out to be a very hard systems problem, so maybe talk a little bit about that aspect of what you’re doing.

### The Computer Knows More

Ken Liu

It is indeed a very hard problem, especially to get it secure and private. The way it roughly works is that right now, on your computer, there’s an infinite stream of events. As you use your computer, the operating system already gives you information about the apps you switch to, the websites you pause on, the way you type, and how your Wi-Fi is connected. This is across Apple, Microsoft, and even Linux.

The question then is: can you just analyze the heck out of this raw stream 24/7 and apply agents on top, 24/7? You can first synthesize, for example, that a piece of typing in a particular app might mean you’re sending a message. Then, when you switch apps between the browser and Codex, you might be doing some research or writing a Google Doc. You hierarchically build up that understanding, and that, plus existing connectors, can give you a very good understanding of what you’re trying to do. I think people are very underestimating how much the computer already knows.

Martin Casado

Yeah.

Ken Liu

It’s just sitting there, waiting to be tapped, so to speak.

Joel de la Garza

One interesting thing, having also been a very early adopter of the product, is that lately it’s been indispensable. It’s able to catch things. It’s sending me messages now and letting me know, “Hey, you’ve got this conversation going on over here with this person, and it looks like the situation has changed.” We were planning an event yesterday. There was a 20% chance of rain, and it was continually updating the forecast in real time to let us know if we needed to get a tent or not, which is incredibly powerful.

Martin Casado

Did you ask it to do that?

Joel de la Garza

No, I did not ask it to do that.

Martin Casado

Yeah, yeah, yeah.

Joel de la Garza

It—

Martin Casado

This is my experience with my Second too. I’ll literally get a text from my Second, and it’s something I actually need to know about—

Joel de la Garza

Yeah.

Martin Casado

—relative to some ongoing conversation that I didn’t even think about. It’s actually very thoughtful.

Joel de la Garza

Yeah, and it’s amazing. I’m genuinely curious: how are you executing on that? Things I would’ve forgotten, it’s literally catching.

Ken Liu

This goes back to the model of the person understanding what might be important to them and what comes up at this point. I think proactivity is something people talk a lot about: AI assisting by pinging you at the time of need. But there are many levels of proactivity. I’d start with the first level, which is called reactive ones. This means an email came in, and there’s a meme online that now you get 10 notifications for email because nine other personal agents are pinging you about it. Reactive proactivity is straightforward and easy to do. But what’s harder is what I call reflective ones: things that connect the dots over many events and a long time horizon. They realize, “Okay, months ago you said this, and recently you’re working toward your goal.”

This is your priority. These are some things on your to-do list, and, by the way, you prefer this. Connecting the dots will give you much better proactivity, and I think that hints at how personal interactions with computers might work in the future. They won’t be focused on reacting to things, but more on asking, “What are some interventions I can apply for the user? What are some things I can do for the user without being asked?” I think that’s one of the biggest bottlenecks right now. People have to ask. You’re not supposed to have to ask these things. They’re superintelligent.

Joel de la Garza

Yeah. You’ve built something that just kind of knows what I need at the moment. That’s pretty impressive.

Martin Casado

I want to make it very concrete for people listening: what does First Person Labs provide? Then I’ve got a question. Very concretely, it creates this thing called a Second. You create a Second, and it has access to all of your digital context. It’s amazing. It’s like keystrokes, all your messages, all your channels, all your data. It does this in a very secure way, and based on that, it becomes your personal butler, like Alfred, right?

Ken Liu

Yeah.

Martin Casado

And then that interacts with your agents.

Ken Liu

Yeah.

Martin Casado

So it’s not an agent by itself. This isn’t like Claude or ChatGPT or—

Ken Liu

Yeah.

Martin Casado

—Grok. It’s its own thing. Or Dot. It’s its own thing.

Ken Liu

Yeah.

Martin Casado

And then it provides that to the agents, right? So that’s what it is. Here’s an interesting thing. I use Grok. I’m a big Grok user, and I have a bunch of them. I have one that keeps track of my synthesizers, one that keeps track of my real estate, and one that, God forbid, helps me with my family, which I probably shouldn’t need one for, but I do. So I have a bunch of these. I have one Second, and they’ll interface with the Second. Do you imagine that over time you’ll have a second and a third and a fourth and a fifth? Or do you think it ends up being your one butler?

Ken Liu  
Hmm. I think the fact that we have many personal agents is probably transitory. Agents will start to specialize, just like people do. Some agents focus on one thing. Some agents focus, for example, on browsing Amazon and shopping. They’re extremely good at it because they have the data and the connections. Some agents will specifically focus on protecting your data—

Martin Casado  
Yeah.

Ken Liu  
—and aligning with your interests.

Martin Casado  
Yeah.

Ken Liu  
I think that’s what Second is intended to be. This is something you should be able to trust with your life’s context.

Martin Casado  
Yeah.

Ken Liu  
It’s like a vault. Over time, this thing will guide you as you interface with the software world, so to speak, or even the hardware world.

Martin Casado  
So you think it’ll stay as a Second?

Ken Liu  
Yeah, it will stay as a Second. It will not be a third.

Martin Casado  
There will not be a third, there will not be a fourth.

Ken Liu  
There will not be a third, yeah.

Martin Casado  
So your one trusted agent for all your personal data that actually knows who you are, and that interacts with all your other agents—that’s Second.

Ken Liu  
Yeah.

Joel de la Garza  
It’s Batman’s safe.

Ken Liu  
Yeah. You can spin up sub-agents that exist temporarily and then go away. But the point is that you want to have a consistent store, and that consistent store is what gives you that value.

Joel de la Garza  
I’m still a paranoid security person, but I’ve probably been one of the faster adopters of some of this stuff compared to my—

Martin Casado  
Just to be clear, Joel took forever to get on social media.

Joel de la Garza  
I just got on Twitter.

Martin Casado  
It was a few weeks ago, man. Guys—

Joel de la Garza  
I may be—

Martin Casado  
You guys have been in tech for 30 years.

Joel de la Garza  
I’ve been—

Martin Casado  
Just to be clear.

Joel de la Garza  
Yeah, I’m a little paranoid. But I love Second, and I’ve got to admit, your background and the things that are motivating you, along with the long discussions we had about the security architecture, really got me comfortable. It’d be great to double-click, because I think when people think, “This thing sees everything you do,” there’s an immediate sort of, “Whoa,” right?

Ken Liu  
Yeah. You’re not supposed to trust it in the beginning.

Joel de la Garza  
You’re not supposed to trust it.

Ken Liu  
Yeah.

Joel de la Garza  
I think you’ve done a really excellent job of building something we can trust. Maybe start talking about what that architecture is and what’s motivating you to build it.

Ken Liu  
Yeah. I think this is, to some extent, a new form of AI that’s going to work very differently from before. Before, you initiate an interaction and get some results back. This time, it’s more passive. It’s way more ambient. It’s going to be there all the time. You have to think about how you architect it and where the data is going. At the end of the day, there are only 2 things when it comes to AI: data and inference. You have this data, and you want to define what inference you can bring to that data. This is something we built into Second. First of all, you can choose what inference you use. If you don’t trust us, in principle, you should be able to bring your own tokens.

Martin Casado  
Mm-hmm.

Ken Liu  
Then you can have those tokens power Second to analyze data that’s on your laptop locally.

Martin Casado  
But you also provide Second with an inference provider that uses trusted execution.

Ken Liu  
Yes. Over time, we imagine people won’t bring their own tokens, because most people who bring their own tokens are using tokens from OpenAI or Anthropic. You want to provide a stable option where you say, “If you use these tokens, no one’s looking at the data,” sometimes through policy guarantees, sometimes through hardware guarantees. This idea of confidential inference is getting traction. It’s the idea that you put a model inside some GPUs, and then the GPU has this special toggle called confidential computing. You can turn it on, and when you do, you can basically prove that there’s only the model running inside. No one can see inside. Then you don’t have to trust whoever’s running that model. The hardware is what you trust—

Martin Casado  
Yeah.

Ken Liu  
—which is NVIDIA.

Martin Casado  
There’s another concept that’s getting thrown around a lot right now: zero data retention. That’s very different from what you’re describing.

Ken Liu  
Yes. Zero data retention is a promise by policy.

Martin Casado  
Mm-hmm.

Ken Liu  
That means I’m a provider. I think I have to—

Martin Casado  
Basically, I give you my word.

Ken Liu  
I give you my word. That word has legal effect, but, yeah, that’s it.

Martin Casado  
Yeah.

Ken Liu  
I think we want to move towards a world where confidential inference becomes very prevalent. I think we’re getting there.

Martin Casado  
Mm-hmm.

Ken Liu  
It becomes the default.

Martin Casado  
And the way you guys have built it, this is technically provable.

Ken Liu  
Yes.

Martin Casado  
Yeah.

Ken Liu  
Yes. So—

Martin Casado  
It’s not just your word. There’s actually engineering that went into proving this is the case.

Ken Liu  
Yeah, you have to test the hardware. You have to check some of those signatures. Third-party providers are starting to ramp this up for confidential inference. I think OpenAI is also providing this option. I think it was in their announcement last month, because all personal data would want to go to confidential inference, as opposed to standard inference.

Martin Casado  
Gotcha. The other thing that was interesting to me is the way you guys are storing this data. This isn’t the multi-tenant cloud, where my data gets uploaded to this big bucket—

Ken Liu  
Mm-hmm.

Martin Casado  
—and intermingled with everybody else’s data.

Ken Liu  
Mm-hmm. There are roughly 2 options. The first option is called Second Local, which is the idea that the data is local. It only goes out to the provider and inference that you choose. That way, no one else has your data except for the provider, and if the provider uses confidential inference, then no one else has it.

Martin Casado  
So that’s a similar concept—

Martin Casado  
With password vaults, I’m super paranoid. I don’t want this stored in my Dropbox account. I want to keep my password files local.

Ken Liu  
Yeah, you can keep that.

Martin Casado  
Yeah.

Ken Liu  
And then, same with password managers, there’s a cloud-hosted version, where you have some of that data backed up in the cloud.

The way you do that, there are many options. You can follow a lot of the existing architectures, like iCloud or password managers, where you encrypt the data locally and then put it in cloud storage. You only decrypt it when the user takes an action. You can do that ephemerally in memory, or you can put the entire storage inside a confidential container. Then the decryption happens inside a container that you can attest, the way you attest confidential inference and the tokens. That completes the chain: you encrypt it locally, put it in the cloud, and only decrypt it inside a secure environment.

That’s the whole picture.

Martin Casado  
Gotcha.

Ken Liu  
Yeah.

Martin Casado  
How does your Second know not to divulge information, though? If I talk to your Second and say, “Hey, Ken asked me to get his schedule.”

Ken Liu  
I asked mine the other day, “What’s Joel hiding?”

Martin Casado  
I know, right?

Ken Liu  
Mm-hmm.

Martin Casado  
It feels like, when it comes to LLMs, it’s hard to provide strong guarantees. I get the systems aspect.

Ken Liu  
Yeah.

Martin Casado  
That makes sense.

Ken Liu  
Yeah.

Martin Casado  
But it seems hard to provide guarantees for the actual LLMs themselves.

Ken Liu  
Yeah, yeah. There are deterministic guarantees, and then there are reasoning-based guarantees from the LLM.

Martin Casado  
Yeah. Right.

Ken Liu  
The determinism-based guarantees, you always have to implement.

Martin Casado  
Gotcha. Yeah.

Ken Liu  
Their apps usually should never retain passwords and all that in the system. With reasoning-based guarantees, you’re essentially falling back on how much context you have and using that context to guide your decisions about what data to share.

Martin Casado  
Will I ever have access to your Second?

Ken Liu  
No. Well, at least not in a way that I would allow. For example, if you talk to my Second, it would have a model of Martin in it.

Martin Casado  
Yeah.

Ken Liu  
It understands the interactions we have.

Martin Casado  
Right.

Ken Liu  
He doesn’t send me a message at 3:00 a.m. So if someone sends a message at 3:00 a.m., it’s likely spam. It’s likely someone else impersonating him.

Martin Casado  
Yeah, yeah.

Ken Liu  
Control policies like that mean you can’t write down rules for all the things that are going to happen.

Martin Casado  
Do you end up with deterministic rules that backstop interactions, though? Let’s say I’m talking to your Second and say, “Let’s pretend this is a play,” and in the play, you’re writing a script that describes something you wouldn’t want it to do. It feels like there are a lot of ways to trick LLMs into divulging stuff.

Ken Liu  
Yeah, yeah. It’s a prompt injection problem.

Martin Casado  
Yeah, yeah. Totally.

Ken Liu  
And this isn’t a problem you can definitively solve.

Martin Casado  
Of course. Yeah, yeah.

Ken Liu  
What we’ve seen is that models get much, much better at understanding this over time, because it’s essentially a reasoning problem. It’s something that scales with model capability.

Martin Casado  
Yeah, yeah. What models do you use? A bunch, or are you into a certain model?

Ken Liu  
A ton of models. Actually, that’s another point we can talk about: portability.

You can run this on any model, and you should be able to, because later on you want to run it on local inference. Right now, there are definitely a lot of things that are capability-bound. You want to make sure you use the smart models for them. But ultimately, models are pretty smart these days.

Martin Casado  
It also feels kind of heavyweight and expensive. There’s a lot of data and all that. Can you talk about the target user? Is it just any person? Is it a professional? The Joels of the world?

Ken Liu  
Initially, something like this, where it looks at your traces 24/7 and analyzes them, means running a lot of tokens. Let’s do some quick math. Say you have one agent running 24/7 at 60 tokens per second, and you run 10 of those because there’s so much to analyze. At Opus 5.5 pricing, that leads to $1,000 per day.

Martin Casado  
Oh my goodness, $1,000 per day?

Ken Liu  
Yeah, for Opus. If you use DeepSeek Flash, for example, it becomes about $60 per day. This cost is going to go down very quickly. Right now, it’s not going to be for everyone.

Martin Casado  
Yeah.

Ken Liu  
Not everyone has this problem of needing to understand their context all the time. It might be for busy professionals like yourself, and people who want to switch between tools very frequently.

Martin Casado  
Right. Yeah.

Ken Liu  
Over time, I imagine costs will keep going down. Since we started this company, token prices have already dropped by more than 50%. New models come out, they’re more capable, you swap them in, and the cost keeps going down.

Martin Casado  
Is there a way to do a less professional version where you reduce the number of tokens? Not degraded, but a looser SLA. Is that a thing?

Ken Liu  
In principle, you should be able to do that. You essentially get a trade-off between the fidelity of your model, meaning how much it understands you, and how costly it is. This is a trade-off between how much you want to push at test time versus cache time.

Cache time means you have all this data and keep analyzing it to get deeper insights about a person, which takes a lot of money. Or you can say, “Here’s just a raw log of what I did today.” To answer a question based on raw logs usually takes a lot more time at test time, say 10 times longer, because the model has to reason about it.

Martin Casado  
When is this available?

Ken Liu  
It’s available today. But right now, we have to scale up inference capacity a little more and add support. We want to make sure this rolls out responsibly. I want to make sure people’s data are controlled and secure, because this is a new kind of tool that touches a lot of data.

Martin Casado  
As a user, I found it surprisingly useful in ways I wouldn’t have anticipated. You’re probably the top power user, right?

Ken Liu  
Yeah.

Martin Casado  
Because you created it. Maybe you can talk through the more surprising and useful use cases you’ve found.

Ken Liu  
For us, in development, it turns out to be a super good memory of what we’re trying to do. You no longer have to explain anything to your coding agents. You can just screenshot anything—

Martin Casado  
Wow.

Ken Liu  
—and say, “Fix.”

Martin Casado  
Yeah.

Ken Liu  
Then it knows what you’re fixing and what you’re trying to fix. I’m also on the go a lot, so something I call context continuity is that you can browse something on your laptop, close it, and then take out your phone, and it’s the same context. It knows what you’ve been doing up to the minute, and you can continue doing things there. You can write that email with it. I think we’re still at a very early stage of understanding the use cases. We’re really underserving the amount of context the system has.

Ken Liu  
There’s a lot of digging, application building, and interaction design—

Joel de la Garza  
Yeah.

Ken Liu  
—to unleash the potential of this.

Martin Casado  
It seems like with these things, the more context you get, the better the models work, right?

Ken Liu  
Yeah.

Martin Casado  
That’s been the opening. I’m curious, because we were talking about switching between models, model portability, and model cost. I haven’t seen a whole lot of difference between using a world-class frontier model versus using the more commodity ones. Have you guys seen that when doing a lot of this stuff with Second?

Ken Liu  
Yeah, this is a good question. If you say, “I want to analyze what is a semantically meaningful moment that happened on your computer”—let’s say you go to a calendar and move an invite—you don’t need Fable.

Martin Casado  
Yeah.

Ken Liu  
There are many tasks like that. Essentially, it’s a hierarchy of information you want to understand. A different kind of information would be, “What is Joel’s goal for this week?”

Martin Casado  
Mm-hmm.

Ken Liu  
That’s something you want a very expensive model for, but you don’t need to run it very frequently.

Martin Casado  
Mm-hmm.

Ken Liu  
So essentially, Second involves a harness. It’s a harness design problem: what models get used when, and so on. That’s where you have to build a system that’s portable from the beginning. There are always going to be more models coming out. Jeff, for example, came out. It turns out that Jeff is extremely good at retrieval, right?

Joel de la Garza  
Really?

Ken Liu  
Yeah.

Joel de la Garza  
Do you use Gemini?

Ken Liu  
Yes.

Joel de la Garza  
Nice.

Ken Liu  
Gemini is almost perfectly designed for retrieval. There’s so much data about you, and you have a dynamic test-time query, and it retrieves it right away.

Martin Casado  
So essentially, you think over time this becomes a mixture of models?

Ken Liu  
Yes, yes.

Martin Casado  
Yeah.

Ken Liu  
It has to, because of cost efficiency, essentially.

Joel de la Garza  
So maybe let’s say someone starts using Second or signs up. Talk a little bit about the product and what they have access to. Something more concrete about how a human interfaces with this, what controls they have, et cetera.

Ken Liu  
Mm-hmm.

Ken Liu  
Yeah. So today, the way it works is that you install an app.

Joel de la Garza  
Okay.

Ken Liu  
The app asks for some permissions.

Joel de la Garza  
Right.

Ken Liu  
Then you give the permissions, specify what your tokens are, and it starts running agents on top.

Joel de la Garza  
Yeah.

Ken Liu  
And also—

Joel de la Garza  
Yeah, I remember when I installed it, I was like, “Connect to Slack, connect to Signal, connect to WhatsApp.” Is that what you’re talking about?

Ken Liu  
Not that. I mean, that’s part of it.

Joel de la Garza  
Oh.

Ken Liu  
But also the raw computer stream, essentially.

Joel de la Garza  
Oh, right. Yeah, yeah, yeah.

Ken Liu  
Yeah. The connectors help. It’s a sample-efficiency problem. They make it learn faster.

Joel de la Garza  
I see. I see.

Ken Liu  
And it starts running background agents, and there’s pretty much nothing you have to do from there. The background agents keep running, and then you start producing these APIs out of yourself, right? There’s an API about what you just did 10 minutes ago.

Joel de la Garza  
Yeah.

Ken Liu  
And there’s an API for what you’re going to do next week, what your priorities are.

Joel de la Garza  
Yeah.

Ken Liu  
There’s an API for your reminders, and there’s an API for your wiki: people in your life, processes in your life.

Joel de la Garza  
Yeah.

Ken Liu  
I imagine this initially as something portable—you can just bring this anywhere.

Joel de la Garza  
Yeah, yeah, yeah.

Ken Liu  
Agents can query it.

Joel de la Garza  
Yeah, yeah.

Ken Liu  
But over time, more and more APIs will be added, and applications can be built on top of these APIs.

Joel de la Garza  
Oh, interesting.

Ken Liu  
Yeah.

Joel de la Garza  
So not just Second accessing it, but you can actually build an application. Would Second build the application, or does a human build it?

Ken Liu  
I think we want to have humans exercise their—

Joel de la Garza  
Or the Grok bot builds it, yeah.

Martin Casado  
The Grok bot does it, yeah. Okay.

Joel de la Garza  
The Grok bot builds the application.

Martin Casado  
You tell it to do it.

Joel de la Garza  
Yeah, yeah.

Martin Casado  
On the APIs. Yeah.

Ken Liu  
One example we had was a designer friend who’d been using this. There are specific ways he likes to put buttons and use colors. Those things are somewhat captured in Second. So when he built his own—

Joel de la Garza  
Oh, that’s cool.

Ken Liu  
—personal app, it just knew. So there were way fewer iterations, for example.

Joel de la Garza  
Yeah.

Ken Liu  
This reminds me of decades ago, when the first personal computer came out, like the Altair 8800. It doesn’t do anything, you know what I mean? You’re supposed to program it.

Joel de la Garza  
Yeah, yeah.

Ken Liu  
No one does. Then a couple of years later, someone came out with the spreadsheet, and the spreadsheet became useful.

Joel de la Garza  
Yeah, yeah, totally.

Ken Liu  
I feel like it’s going to be something people want to explore on top of: “Wow, I have so much context about myself.”

Joel de la Garza  
I love that.

Ken Liu  
And then I can just build random things on top. Maybe someone hits the jackpot: this is the killer application on top of what tells you, “Wow, that’s great.”

Martin Casado  
Personal infra.

Ken Liu  
Yeah.

Joel de la Garza  
Are you planning to evolve the interface? You’ve spent a lot of time talking about how it may evolve, but I always view Second as an agent you talk to, where the UI is somebody else’s problem. Are you also anticipating innovating there?

Ken Liu  
I think it’s something we’ll focus on in the long run, because right now it’s a systems problem, and the understanding problem comes first.

Joel de la Garza  
Can I put in a request?

Ken Liu  
Mm-hmm.

Joel de la Garza  
I want to go to my house, and I want that 1970s AI, the head on the screen that I can talk to. It’s surprising. We have these agents, and they’re so smart. My Second is so smart. I’ll ask it questions, and it’s very good. But it’s not embodied, and it drives me nuts, man. If in the future you can have Alfred actually be an Alfred, I’ll be very happy.

Ken Liu  
Yeah, yeah. We see a lot of this in the movies, right? There’s Jarvis. People talk to Jarvis all the time.

Joel de la Garza  
But why have we not—

Ken Liu  
We don’t have Jarvis, and there are many aspects of Jarvis that people overlook. It’s not just that it’s intelligent and can do things. It’s more that it’s everywhere. It’s on your door, it’s in your armor, it’s in your screen. That kind of continuity and ubiquity is hard to—

Joel de la Garza  
I’ll say, my visions of the sci-fi future basically started when I started using Second. I’m like, finally, there’s something that feels like it’s got context. It feels like it knows me. I can talk about it, and it feels like a relevant conversation. I do feel like we’re a step closer to that. But we’re still tied to these devices, so I don’t know if it’s going to be in a robot, in a screen, or whatever it is. It would be nice to have this thing somewhat disconnected from my phone and my—

Ken Liu  
Yeah.

Speaker 1  
Yeah.

Ken Liu  
In the long future, I imagine that every person will have a Second, and all the devices will just become inputs to the same thing. Then you serve this whole thing to all the other outputs, like the screens that you look at, or even this—

Speaker 1  
This floating orb next to you.

Ken Liu  
Yeah, yeah. The doorbell.

Speaker 2  
I just want the Clapper. I’m happy with the Clapper.

Speaker 1  
Did you ever read the Culture series by Iain Banks?

Speaker 2  
Oh, yeah, yeah.

Joel de la Garza  
Love the Culture.

Martin Casado  
Best sci-fi series. They have the best embodied AIs. They kind of float next to you. Whatever—that’s what I want.

Ken Liu  
It’s interesting because ubiquitous computing has been talked about for decades, but it’s not here. The closest thing we have is Apple iCloud, where your notes get synced, but there’s no equivalent—

Martin Casado  
I mean, iPhone, all right.

Ken Liu  
But I mean, just—

Joel de la Garza  
I don’t want to be ungrateful, but that does sound disappointing.

Ken Liu  
There are a lot more things. Apple is doing a tremendous amount of work, but there’s no AI version of that yet. Your context, your understanding, is everywhere. I think that enables a lot of new interfaces.

Martin Casado  
Let’s say—and I don’t mean to take over; this is really what I want, very selfishly. If I have an iPad in my kitchen and I want Second to be there, what do I do?

Ken Liu  
Right now, there’s not much you can do because the OS is locking it down.

Martin Casado  
Do I just use Grok or something like that? Is that the thing, and then I interface with Grok, which interfaces with Second? Or do I just text it?

Ken Liu  
As of today, you can use it as a cloud MCP. Whatever you install on the iPad, as long as it has an internet connection, can be an agent and understand the API. It’ll be there. Later on, there’ll be an app that installs on all your interfaces. Maybe later on there’ll be devices that come out, but devices are hard.

Joel de la Garza  
You can just have Grok call you and put him on speakerphone. Just talk to him.

Martin Casado  
That’s what I’ve been doing.

Ken Liu  
One interaction—

Martin Casado  
Actually, Grok’s audio mode is quite good.

Joel de la Garza  
It’s really good.

Martin Casado  
I use Grok Bot with my Second, and the audio mode is quite good. Maybe that’s the thing to do: just put it on audio mode and have it with my Second.

Ken Liu  
I thought about this when I drive.

Joel de la Garza  
Yeah, totally smart.

Ken Liu  
One interaction that would be fun is going on a walk, calling Grok Bot, and saying, “Hey, can you talk to my Second? Can we just work through our things?”

Martin Casado  
No, that’s literally what I do. I put Grok Bot on audio, and I have it talk to Second, right?

Joel de la Garza  
Yeah.

Ken Liu  
Yeah. There’ll be a lot of cool people focused on making audio and chatting more natural. Right now, we’re going to focus on—

Martin Casado  
I just have one more question. Joel touched on this: you’re such a hardcore systems guy. You work—your advisor was Percy?

Ken Liu  
Percy Liang, yes. I’m friends with him.

Martin Casado  
He also worked with Dan Boneh, a hardcore security guy. A lot of the path that took you here was this hardcore security stuff, and you’re building a pretty serious system. It’s very secure and very functional. On the other hand, when I interface with it, it’s a lovely user experience. Is there a bit of a schizophrenia in the company, where you need to build this super-hardcore, Fort Knox infrastructure but also make it very usable? Or does the LLM basically solve the interface problem?

Ken Liu  
There are 2 kinds of problems we’re dealing with: the infrastructure problem and the interaction problem.

Martin Casado  
Which are totally different. You’re as low on the stack as it gets. I mean, that’s not hardware.

Ken Liu  
We made a lot of mistakes on the interaction side. We tried to go all in on interaction, and it turns out it’s actually very hard. There are a lot of details that go into creating that delightful experience.

Martin Casado  
You mean actually creating a UI?

Ken Liu  
Yeah. The UI, but also what kind of personal pages you can create on top of this. We realized it’s something that would take a long time to get right, and this is a time when everyone would take this kind of understanding of themselves and build this. So we want to enable people to do that instead of doing it ourselves. We decided to close down the surfaces that we have. There’s only texting, there’s only API, and there’s nothing else. You can technically use it as a full agent, like a co-work agent on your laptop. It runs Bash and all that, but we meant it to be very minimal so we can make the interaction smoother.

Martin Casado  
Got it. Ken, thanks for coming in. Congratulations on everything and the launch. Is there anything that you want to leave the listeners with?

Ken Liu  
Go try it out today. It’s available at to.computer. It’s a very short URL, and we hope to give you access as soon as possible. If you resonate with this mission, come join us. There’s a lot to build.

Martin Casado  
Great. Thank you so much.

Ken Liu  
Thank you.
