AGI: The Path Forward – Jason Warner & Eiso Kant, Poolside

How many people here know what poolside is and does? Anyone? Anyone? Yeah. So, let's talk about that real quickly. Poolside exists to close the gap between models and human intelligence. That's literally it. That's what we're here to go do. We're building our own models from scratch to do this. We're based on the idea 2 and a half years ago that we thought next token prediction was an amazing technological breakthrough, but it needed to be paired with reinforcement learning really to make that leap. So that's what we've been doing for the past 2 and a half years. So we're on our second generation of models now, Malibu agent. And instead of kind of like walking you through some slides and all that, we just thought maybe I don't know, let's kind of show you what we're doing here.

Jason Warner: So are you there? I got you, Jason. So as I said, you were supposed to see him today, but there's I don't know. Our airline system kind of works sometimes, maybe. So he's stuck in California, but we thought we'd just walk you through some demos here today. So what you're looking at here is a very modern programming language that the government uses to run all the world's critical infrastructure called ADA. Anyone familiar with ADA?

Audience: Yes. Yes.

Jason Warner: Okay. So everyone I saw put their hands up for ADA either has no hair or gray hair like me. So that should tell you what's going on here. So Eiso, why don't we figure out what's going on with this codebase here?

Eiso Kant: Well, let's start asking what the codebase is about.

Jason Warner: That's great. And what you're seeing here is obviously our assistant in Visual Studio Code backed by poolside agent, a model we train from scratch using our proprietary techniques. And you can see what's going on here. Kind of the stuff you expect from an agent. And obviously the form factors of all of these things are going to change a couple of times over the next couple of years, but you know people seem to like VS Code. So we're going to show you this demo here today.

You can see from this it kind of went through told you what this codebase is all about but you know these things run in our satellites and I don't know anything about ADA but I do know a lot about a couple of other programming languages. So Eiso what do we want to do here?

Eiso Kant: Why don't we see what this thing might look like in Rust?

Jason Warner: Let's do it. Let's ask it convert this database to rest.

So obviously you're going to see what's going on here. Again, if you guys have used other tools, you're not going to expect too much of the difference for what's happening here. Except that again, we're backed by our own model. We're not using Open AI. We're not using Anthropic. This is poolside. And poolside is a bottom and top stack that is right now if no one's touched it and I know no one in this room has touched this unless you work for a three-letter agency, a defense contractor, or you've sent missiles somewhere that we're not going to talk about in this session. Because that's where we're working. We're working in high consequence code environments for the last year inside the government and the defense sector. As you can see from this demo.

Um so what you see here is is kind of going through doing the conversions. What you see in the middle pane is something that we built to kind of show you as the streams come through all the different changes that are happening.

One of the tricky parts about working on inside the defense sector and things like that is you can't have an agent that's just going to run around and do stuff. I mean like I can't walk into half of these buildings. You can't give an agent access to these data source and just say, "Hey, go nuts." You need to have the right permissions. You got to actually really ratchet these things down to do things inside those environments that you know they feel comfortable with.

So, uh, where are we on this now? What is is it trying to fix itself yet?

Eiso Kant: Yes, it's it wrote about 1152 lines of code. Uh, and it just popped up a command start and tested, excuse me. Uh, so we see here all the files on the left hand side that it created. Uh this is essentially our live diff view that's available. Uh and as we see it's currently starting to actually test it out.

Jason Warner: So this is the part where we just sit here and watch this for 3 minutes and I see nothing.

Eiso Kant: No. What you see the good thing is that this is a very fast inference.

Jason Warner: Yes. So 1100 lines of code. Did it task completed? Do we know if this works yet?

Eiso Kant: Well, let's have a look. So it actually wrote some bell commands to test it. And when we check out the output of those, this actually looks pretty good. We ask can we verify that to run it?

Jason Warner: Let's go verify it. So of course our agent came back and gave a summary of what it did. But let's just ask how to run this.

Eiso Kant: Okay. So, I'm going to go open up now. So, it says this is how I can run the ADA version and this is how I can run the Rust version. Let's run the Rust version.

Jason Warner: Perfect. Let's have a look at We might be hitting an actual an actual demo bug. Let's have a look. Let's see what happens.

Eiso Kant: I know. No, no. Just warnings. Just warnings. Do we have an unwrap in there that we need to take care of? I heard that those things are dangerous.

Jason Warner: So, right now there's a ripple. Uh, let's hit help. See what we're able to do.

Eiso Kant: So, it looks like we have a set of commands. I'm going to be lazy. I'm going to copy paste these queries. So, create table users. Okay. So far so good. Let's insert a record. Okay. Well, let's find out if it actually did its job. Select start from users. Okay, we've got a record here. That's nice. Now, now I want to actually uh you see if I use the up arrow, it doesn't actually allow me to cycle through commands. Let's ask it to add a feature. Uh allows me to use the up arrow to cycle through. I think it will understand my center.

Jason Warner: The one thing we know about Eiso is he actually does know how to read and write but he can't type. So all those errors that you're seeing in there.

Eiso Kant: Yeah. So it looks like the agent's identified a package that we can use. Let's just quickly look here. Compare this to the Virgin one. And it looks like it's adding a library called rusty line and changing the files accordingly. It's currently built it and it looks like the build output is successful. There's some warnings. We'll ask it to clean those up later on. And it's now starting to test it.

Okay, apparently it works. It's going to It wrote itself a little bash script to test the history. It's wrote itself a little final demo script. So let it Okay. So, and it gave us the summary. Well, now how do I rerun this? I do kind of know that, though. So, let's just should know that. That was 30 seconds ago. Let's build it. And let's run it again.

Okay, let's do a help. And oh yeah, that's the up arrow. It works. Very nice. Now, our models aren't just capable coding agents. They're capable in lots of areas of knowledge work. They're also emotionally intelligent. They're fun. They're great to write bedtime stories with for the kids. So, I'm going to ask you to write me a poem about all these changes, but that's just more for fun.

Jason Warner: So, as Eiso was saying, this is just an interface into our platform. There's other interfaces into it if you're inside one of those organizations that has adopted poolside. So this is the coding interface into it but we also have other ways in which you you can interact with it web as well as an agent that you can download on your machine but yeah we don't really tout the poem writing or the songwriting though I did send this to my wife to see and I have been sending her love letters written by poolside so I kind of hope that she did not enter this session to know exactly how I've been doing that for the past 6 months but uh yeah so this is kind of poolside this is what we've been up to.

Um, so as I said, Malibu agent is as a second generation. We've got a ton more compute coming online and that's when we're training our next generation. That is be going to be the one that comes out publicly to everybody very early next year. We're going to have it behind our own API. It'll be on Amazon behind the bedrock API. Anybody in the world who's building out any sort of on a one side the engineering assistants like the cursors, windsurfs, cognitions, replets of the world, you can use ours. or if you use building out on any other side of the fence, the Harveys, the writers, the whatever applications of the world, there's going to be a fifth model out there that's going to be at that level that you can you can consume. But we're dead set on doing this and bringing this out to everybody in the world and kind of advancing that state-of-the-art and we're just going to keep pushing that out. So, that's kind of who we are.

Um, and uh you can find out very little more at our website since we don't put much out there. But Eiso, anything else you want to say before you uh try to go make your flight this time, please?

Eiso Kant: So, I would say that it's been a pretty incredible journey for the last 2 and 1/2 years of starting entirely from scratch and now building to a place where we see our models have grown up to become increasingly more intelligent. And the kind of missing ingredient that we had was compute. And now that it's unlocked for us and and with a large number of over 40,000 GB300s coming online, we see how we can start scaling up some of those models uh to get even further uh in in their level of capabilities and software development and other types of long horizon knowledge work.

What I think is exciting about this conference and this audience is of all the work that's happening of evolving the form factor. Right? Right now what we looked at was this asynchronous way of of operating with agents. You know, Jason, you and I, we have agents running that are doing tasks for for hours, and I think in the near future, we can see a world where they're able to start doing tasks in days in the coming years. And so, I think the interface will continue to change. Uh, we're really focused on the fundamentals, building intelligence, and being able to scale up and serve it. And it's why we go full vertical. It's why we go from our multi gigawatt campus in West Texas where we're building out data centers building out models.

And the interface that you saw today is just our version of an expression. But I think this audience is going to do an incredible job of building lots better versions of how to express using that intelligence uh into actually, you know, valuable, economically valuable work.

Jason Warner: Couldn't have said it better. Can't wait to see what you guys build on this uh in the future when it's publicly available. And if anyone really does want to build a data center campus, we are hiring for that. Um it is weird to be putting shovels in ground again like we did in the '9s and early 2000s, but that's what you got to do to scale intelligence these days.

Eiso Kant: So, I would make one other non-scheduled statement if you're going to be okay with this one, Jason. As as our models are are getting more capable, we'd love to also see who wants to build with them. Right now, the the vast majority of of you know, companies that are doing additional reinforcement learning and fine-tuning on top of models are are doing it on what I would consider right now the you know, best-in-class open source models, the the Quens and Fumies and Miniaxes of the world. And uh we'd like to start figuring out how we can you know partner with you with our our models anywhere from any checkpoint early on to where we are today for you to be building closer together with us on top of things. Uh we haven't really figured out the approach to it yet. Uh but I think since we have this audience it's uh it's not a bad place to put it out there and so definitely reach out to us. Uh we think the world till date was built by intelligence. The world in the future has been built on top of intelligence and so be a great way to partner.

Jason Warner: Well thanks Eiso. Thanks everybody here. And now we do have 5 minutes left. I don't know if we're supposed to take questions, but I'm happy to. So, if anyone does, but if not, I'm just going to go that way.

Audience: What was that?

Jason Warner: Sort of. I mean, I think of him that way. Here, here's a fun story. Here's how I met Eiso. I like to tell this story because Eiso is a fun fun dude. I met Eiso because started with a failed acquisition at GitHub. So back when I joined GitHub in 2017 as a CTO, I wanted to take GitHub from a kind of collaborative collaborative code host with open source bent and turn it into an endto-end software development platform infused by intelligence. And so you know the the products that we launched from 27 on or 17 on GitHub actions, packages, alerts, notifications, eventually code spaces, and then co-pilot was the last thing that the office of the CTO did before I left with Nat Friedman, Uga De Moore, and a couple of other folks inside there.

But Eiso in 2017 when I joined he had working code completion before the transform architecture had landed fully. He had on LSTMs and so I quickly tried to acquire his company and he just he just said no. So he just said no to me. Uh but we had that was a long drawn out process talking about what we thought neural networks were going to mean for the world. And so during that process, which was a lengthy one, we became really good friends and we'd stayed in close contact over the years. And then 22 rolled around, obviously Chat GPT comes out, Anthropics out, and we kind of saw the endgame at play and we said, "Do we jump back in or not?" And of course, yes, we jump back in. But I like to tell that story about how he just kept saying no to me and I just kept asking him questions and eventually he said, "Yes, we should found a company." Cuz by the way, when I asked him if we should do this, he said, "Oh, god damn no." That were his exact words. He's like, "No, we should just learn how to paint and sail." But here we are. So, yeah, it's it's been a great journey together.

Eiso Kant: Jason, I I think the reason we ended up doing this is because of our our opinionated view on what it was going to take to build more capable intelligence. And in the first 18 months of this company, you know, obsessing and focusing on reinforcement learning combined with LMS felt like one of the most contrarian opinions in the world, but I think today it's absolutely not. And it's super exciting to see the the progress that's continuing to make like we're in the coming years we're going to see the world that started in completions and went to chat and is now at a gentic increasingly approach more autonomous and we're all of it is stemming effectively from the combination of bringing highly capable models that are constantly evolving together with real world problems and and I think what we're starting to see now is we're entering these kind of awkward teenage years ahead of AGI where everybody in this room is building out incredible companies and applications is bridging this gap of what it really takes to make intelligence that in its raw form actually be valuable and we uh we want to be a small humble part of that.

We've got a lot of work still ahead of us. Uh the team is growing. Uh but hopefully what you've seen today uh is what our our customers and enterprises have been having access to and seeing for a while is that we're you know hard at work at uh at really pushing those capabilities. We also want to make sure we make them available to build together with others.

Jason Warner: Well, that's it. Thanks everybody.