Inside the Model Factory — Eiso Kant, Poolside AI

I owe getting into this space to Andrej Karpathy. In 2015, he wrote an article called the unreasonable effectiveness of recurrent role. Nice.

Yep. And that article, I read it, and I pivoted my startup at the time overnight to working on RNNs and later LSTMs and transformer models to be able to write code. If you go to this article and you scroll down, you can kind of start seeing, like, this was the the precursor to what ended up becoming language models.

So, at least what he was character level language models that were starting to actually predict letters. He has an example out here. There's a little Paul Graham generator.

You can kinda read it, and the text kinda makes sense, but it doesn't. And there's a little there's an example of code a little bit further down. It's Shakespeare.

And and for some reason, I read this, and I went down the rabbit hole of learning everything I could about RNNs and LSTMs. Right? This is pre transformer paper.

And I had built a completely unreasonable belief that neural nets should be able to generalize to anything and everything, and that language should be able to generalize, you know, to a lot of things that are intelligent and the ability to write code. And so I started building Source, which was a fully open source company trying to build what we used to call machine learning on code, language models on code. And we spent about four or five years on this till the end of twenty nineteen.

And that sounds really cool today, but back then, no one cared. Right? Like, no one cared.

We were in the dark. Like, we did things along the way. We tried applying convolutional neural nets to, like, the structure of code.

We were you know, when attention came out, we were applying it to LSTMs, and then the transformer paper came out. And it was it wasn't obvious and what we missed throughout that entire journey that we were on the right track, but we should have just kept scaling up. And today, to all of us, the scaling laws and scaling up seems like the most obvious thing.

But having spent four or five years of my life on working on language models on code, it wasn't obvious. I have a lot of respect to folks at Google and OpenAI and others who kind of took that confidence and and and kept going. We failed ultimately at the time, and it kinda was, like, biggest failure of my career.

Right? You blew $12,000,000 of investors' money, which was a lot back then. Yep.

You spent still a lot, but and you spent years with, like, a group of 40 people just obsessing over this problem. And life took a different turn, and and and and family kinda became a focus. And I kinda kept my head down.

I'm really, frankly, didn't really look at language models for the following two years. Kinda big mistake considering Following year is gonna be really interesting, and then ChatGPT came out. And it was kind of like a a vindication.

It's like people started texting me. I found, like, my old, you know, work decks and these old talks. And and throughout that whole journey, you know, we we kind of really had a strong point of view at the time that, like, as you're building more capable intelligence, it should be open, open source.

When we started Poolside, that actually wasn't the case at all, and I wanna be very open about it. When we started Poolside, we were like there was a premise of two things. One is this technology is not gonna stop compounding in capabilities.

I think to most people obvious today, but three plus years ago when we started, most people were still arguing if these were stochastic parrots or not. And the second was that reinforcement learning was gonna be the biggest driver for LLM capabilities. Today, obvious three years ago was not an opinion held or direction held at either OpenAI or or Google or Anthropic or others.

And so people kinda looked down on us a little bit. They were like, you know, this is really gonna work. And so we just started working the problem, and we never really thought about open source again.

We just kept our heads down and we and we built our, like, knowledge understanding from scratch. Right? We didn't roll out of an existing lab, so we picked up the papers and started writing code and figuring things out.

And it wasn't until the beginning of this year that me and my cofounder, Jason, picked up the open source conversation again. And if you go back to some of the early things on our website, it was very straightforward. It was wanna get to AGI.

We wanna support a world of abundance, and we wanna be the first company that gets there. But we started talking at the beginning of this year because it became kind of obvious that the world was going in a direction that was starting to kind of, like, kind of, like, pick at us a little bit. Like, it didn't this didn't happen overnight.

It was, a little bit we were seeing this, and we're like, okay. The world's going down a path. And throughout this journey, there was something that I kinda used as a as an analogy or things.

I said, kind of, well, if I go back to back in those days, kind of 2015 or 2016, we're working on this, and I picked up a sci fi book off the shelf, and I was reading the book about 2035. AGI is achieved, and the story would be over the following, you know, decades. And would have that first chapter where everyone's trying to figure things out.

You'd get the chapter of Chatuchu Picchu coming out, and then you would get to the chapter where the world was at a fork in the road, and the the one that it picked was one where three or four or a handful of companies were going to create all of intelligence moving forward. And when I thought about that story, it felt like a dystopian sci fi book, not a utopian sci fi book. And the reality is I'm a utopian sci fi guy.

Like, and so we kind of took a step back and said, hey. Can we play a role here? Now it was easy for us to do so because we were not at the frontier.

But we were at the frontier. I don't think we could have changed our mind. And I don't mean this like, it's when the moment there's too much capital involved, too much expectations, you've built up things.

Right? We're small team, you know, just improving and improving. And so we we knew that we could make that decision now, but it would be a lot harder to make as we got closer and closer to the frontier and caught up to others.

And a lot of soul searching, a lot of conversations, and said, no. This makes sense even if there's big unanswered questions. Like, how the hell do you build a business model with foundation models about open source?

Big open ended question that we do not fully have the answer to yet. Right? At what point do you no longer wanna release open source models because misuse of models has, you know, real potential risks associated with it?

How is the government gonna respond to open source? But I think it all just came down to one thing, and I'll stop the monologue, is the fact that I rather live in a world that has a 100 foundation model companies than a world that has five, even if I was one out of five. And the smallest and most meaningful contribution we can make for a 100 to exist is to open up our research and open up, like, our weights right now and kinda figure out along the way how we can, like, do more.

like, choice competition is is both gonna drive progress in the right direction, but the fact that, like, you know, we we create models, and while we all, you know, drink out of the same well of of data effectively, we do introduce very different behaviors and biases in our models. Some are intended biases. Some are completely unintended biases.

And if we shape up in an ecosystem in the world where open models are gonna be a part of the token economy, like, I don't think there's any question about it anymore, then we want to be able to live in a world where companies, countries, people can choose and say, hey. I am most aligned, and I trust most this provider for these kind of things. Yeah.

you know, frontier intelligence, and you're filling that gap too. Right? So not just only open weight, not just Western, but also pretty open research.

No. I appreciate it. Look.

I think it's I think it's actually the most meaningful contribution. Right? Weights are a binary.

Let's call them what they are. Yes. We can modify them.

We can change them, but, like, giving someone the weights does not allow them ultimately to recreate what you're doing. Right? And and so now there's challenges around releasing datasets, challenges around, like, release certain things, but being able to share your research, like, right, how do we do it?

What are the lessons we learned that we spent, you know, tens of thousands of experiments of compute on? I think very much so. One correction though, Vibhu, and I I say this because it's kind of been haunting us for quite a few years, we actually, from day zero, were an American company.

Yeah. They moved to We so the story once and for all is very started as an American company. We have always been an American company.

And early on, we made a very conscious decision. We said, we're not gonna hire any researchers in the Bay Area. We're gonna actually look for talent everywhere else in the world.

And that is everything from Middle America, Seattle to, you know, Serbia and to Taiwan and and and Singapore and other places. And it was because we kind of took a view that this was gonna become a talent war for this, and I think it has over the years. Now three years ago, that wasn't fully obvious yet.

I think today, that very much is. And we also realized that, like, some of the world's most capable people with, like, the most interesting, innovative ideas were not just gonna be here. And so it led us to create, like, a fully remote company.

And we ended up opening an office in Paris and London in different places, and and we have a lot of the team in The US and a lot of team outside. But we kind of always took this view of, like, we're an American company, but if we want the best of the best to work with us, we take a global view. Now we do also have people here in Silicon Valley, like the company's grown and others.

But I think one of the things that it slowed us down at the beginning, but it has sped us up now, and it's why you're seeing, like, the progress, I think, on our models and the cadence that which we release is because we didn't roll out of an existing lab. Right? We didn't we didn't actually have a lot of the information that's freely flowing around here at the time.

We just kind of took this point of view. It's like, okay. Well, let's just work the problem.

Let's just go and, like, read the few papers that are out there, and let's just figure this stuff out. And we made some hilarious mistakes in model training because of that over the years, like, especially in the first twelve months. There's a few that I think still haunt me and and scare me.

We can talk about them later. But it kinda created a, like, a a resiliency and persistency in the team, right, with extremely few people have left us over the years that, like, told us, okay. We can do this.

But when we first wrote our first training code base completely from scratch, it wasn't a fork of any open source. It was just like, okay. Let's pull it from scratch.

I remember we had this one moment where we spent three weeks working out an optimizer bug. Like, it was like training just couldn't get stable. We, like, obsessed over it.

And we thought, like, maybe we were wrong. Maybe we should have just forked this repo or shit on. But then when we solved it, I still remember at the time we were, like, five people in the company.

When we solved it, we're like, oh, we can do things. Like, if we're just willing to work hard. And I think that culture with a very strong engineering bias has kind of helped us, like, get to where we were.

And so there's this kind of notion of open source and talent and these things. I think we we just took different decisions from a different starting point, and I think we are lucky. I do wanna co definitely call it lucky.

I've also had a of hard work at the team that now, like, that's starting to kinda show up in results.

so if you take, like, Adam as an optimizer, you have epsilon Yeah. Which is, right, like, the denominator. And weight is up.

Exactly. In in in the denominator. And at the time, if I recall, you looked at, like, the early Lama papers and things like that.

People were juicing Epsilon, like, quite a bit. Like, they were, like, adding I don't if it was e minus four or whatever, like a high value for Epsilon. And if you think about this during training, it's kind of like bit weird and counterintuitive that we're adding noise to our optimizer by just adding effectively like a random number in the denominator, right, like, behind the decimal point.

And and I don't recall the exact bug, but it had to what I remember is once we solved it, we no longer had to choose Epsilon as much as, like, what's happening in the Lama paper and other places. And and it was, like, one of those fundamental moments where we had trusted this paper that was out there. And we're like, oh, no.

It has to be this way. It has to have this high value of Epsilon. But it made no sense to us intuitively.

Like, why do you have to have this so high? Like, if you're just trying to avoid division by zero, why can't the value be extremely small? And and and that was kind of like one of those moments where you realize, like, okay.

Finding things out from scratch yourself builds a better intuition. Because the one thing you learn very quickly with model building is that your intuitions that you start with are gonna get beaten up so hard. Right?

Like, it's such an experimental science that the things that seem obvious, you very quickly get to learn. Like, you were wrong, and hopefully, you figure out why, and sometimes you don't even.

our view from very early on in the company was that model building is ultimately 90% engineering. And I think we all know it in the industry because if you look at whereas every researcher is spending their time, they're spending their time writing code. Right?

Looking at data and and writing code. And so we kind of said, okay. The state at the moment, like three years ago, was Bash scripts and Slurm and Spaghetti Code basis for training and, like, data pipelines that were kind of patched together.

And we kinda looked at this and said, well, ultimately, model building's a process. You're going from raw data, right, like pretraining raw material, the web, etcetera. You're doing a whole bunch of filtering, cleaning up transformations, analyzing these days that's, you know, far more complex than it was three years ago.

Then you're training a model, which is effectively a large distributed systems problem, right, across hardware that has still it's become a lot more reliable, was extremely flaky back then, and now with every new generation, we get our new sets of challenges. And then you go into the next stages. Right?

There was no mid training back then, but, like, you go you know, you're post training and then and then you're reinforcement learning. And so we kinda looked at this and we said, well, this looks like an industrialized process. This looks like an end to end process that every single part of it kind of has its machinery.

Right? If it's your big data pipelines, if it's your crawling ingestion of the web, if it's your, you know, large scale distributed training, and then you've got your your reliability. And we said, well, why don't we take some of the world's smartest distributed systems engineers that we knew and make them part of the process of research from day zero?

Not retrofitting it later on, but like really from the beginning. And that became our model factory. And so our model factory started with a handful of components.

Today, it's thousands of components. And I kind of try to equate it to if you think about, like, someone who was at the very early days of Foxconn, if they had been there for the following, you know, decade, they would be able to rebuild Foxconn because they saw every decision that led to building that system and all the complexity. If you and I walk in a Foxconn today, no chance.

Mhmm. Right? Because we don't have the lineage and history of decisions that led to that.

And so we kind of built early on from the beginning with a team that really understood that, well, the metric that we are optimizing for is the speed of an idea from a researcher to an experimental result that we can trust to then being part of the next model training. And because it's such an experimental science, ultimately, in the beginning when it wasn't that complex, you could kind of patch your way around it. Right?

But now at any foundation model company, you are running I mean, we're a small team. Right? We're less than 70 researchers, another 35 engineers, and we are running well, I haven't checked the latest count, but far more than 10,000, maybe 10 to 20,000 experiments a month.

Don't wake up. And so if you look at that scale of every model run that is, like, it's ultimately it's it's you need to be able to trust it as an infra problem. And so what we have now done over the years has gotten really good at that.

And just by working it and improving it and obsessing over those kind of end to end decisions. So now what that means is that you looked up Laguna access two that we launched. It was five weeks from the beginning of pre training to launch.

The model that we're gonna talk about today was eight weeks from start of pre training, to launch. We started the next model literally yesterday because we now finished the post training required for the model we're launching, you know, next week or by the time this comes out today, and we move that compute to the much larger Laguna M model that we're now training. And so the model should be an artifact of someone's process.

It shouldn't be really a thing in itself. Like and we kind of treat this like the way you would look at, like, a SpaceX factory where, yes, the first rocket, really hard to build, but the much harder challenge was building the factory. And now they're rolling off, and no one is really thinking about the next launch anymore.

So it's just another launch. It's another launch. Another rocket comes off.

And that's what we're trying to do with model building. And what has been which was not planned from day zero, it was kind of in the back of our mind, like this will happen one day, is that when you build a really good end to end model factory with really good APIs and really good engineering systems, well, what is it perfect for? It's perfect for agents because agents are now starting to take over more and more work in our model factory.

Yeah. So I look at the screens when I walk, like, when we're we could come together in our monthly we do monthly on sites. I kinda walk behind people's screens, and I stop by and I talk to our researchers.

And the default is all of these different agents running on their screen that are writing the code. They're launching the jobs. They're evaluating the results that are coming back from the model runs.

They are, you know, making the changes. And we're still in the driver's seat. We're still coming up with the ideas.

We're still helping with the debugging. But more and more, and this is right now very profound on the data side of our of our pipelines in both pre and post and and and the synthetic data pipelines, it's starting to become more on the architecture side as well. You're starting to kind of see these twinklings of what RSI is gonna look like.

And that's frankly so when we talk about, like, your question about our models, I really talk about the model factory. And my coolest example of these things is always that when we kick off a new run, it's a matter of the pre training, like, big run or if it's now a poster, like, one of 10 post training versions we do for, like, pre release or many experiments, is that at any given moment, the changes that somebody made that they had experimental results on from the day before make it into that run. So there's not like a cutoff ninety days before or like, no, it's like literally from that moment because we can now trust the machine enough.

And then you also have to invest in a reliability. So one of my favorite metrics about like Laguna S is that there was no on call events. Right?

Like completely zero. And actually, we haven't had a meaningful on call event like some of the wake up for as far as I recall this entire year. Now there is one asterisk to that in usually the first six hours of launching a new model run.

Something breaks because you set a config wrong. You made a small mistake, etcetera. So that's usually there's a little bit of intervention, but that's always within, like, in call periods, right, not not on call.

And and I think that's starting to now compound. So the model we're releasing now, I love it. It's amazing, but we're already on to the next one.

And I think that's the way it should be.

Well, I would say well, experiments code is obvious, but I think one of my favorite things is I don't know where it is in here, but early on and I still think this is the case, actually, a lot of foundation model companies, people prepare their training datasets. They get packaged up, then they get copied over to a training cluster distributed across all of the nodes, and then training starts. And we looked at this three years ago, and we were like, that makes no sense.

You lose so much time because the moment you have to rematerialize the data, so you have to make a change, you have to fix something, etcetera, you've got all this time of, like, repackaging it, right, tokenizing it, repacking it, moving it over to a cluster, then distributing it across the nodes. The bigger your clusters are, you start using fancy, like, torrent like algorithms to, like, distribute your data. So why aren't we streaming data into training?

Right? Something that's very common in, like, just basic Like, just in time. Just in time, like, good computer science, like, principle.

And that was one of the first things that I think unlocked are the model factory. Because the moment you start thinking about, well, a training job, it doesn't matter if it's a big hero run or a small, like, you know, post training experiment, consumes a certain number of tokens per per second. Right?

And it's actually not a lot, right, from a, like, a data moving data perspective. So we said, well, we have our training cluster, and then we've got, our AWS kind of setup where we can build these amazing big data pipelines. We can set things up.

We use Spark underneath the hood, like, these things. But when you say AWS, it's not actual AWS. It's your internal It's our internal no.

It's our internal, like, just running, like, like, our Site web services. Exactly. Our stuff running running on, like, an AWS account or, any hardware.

Right? Yeah. Yeah.

So once we made that shift into, I can stream data into training, all of a sudden, you realize a lot of things unlock because now you don't have to wait for the whole dataset to materialize. You now all of a sudden when you're running data experiments about mixing data, it's a config because you've got these data sources that are coming in and you just set you we have the service called Blender that's in the report where we then say, okay. For this run, I want 20% of this source, 10% of this source.

I want this much so many epochs of repetition. I want this to be, you know, shuffled in a certain way, and your training job can start while the rest of the data is even still materializing. Also, it does is because all of this underneath so for us, we treated the data layer underneath as like an immutable data layer, and that was really important.

Like, experiments as code, immutable data later means that you can always go back and understand literally down to the single token at which cursor it went in on which version of the code. Yeah. And it took us a I have to admit, like, the first year of poolside, we understood that engineering had to get great, but we didn't understand yet that this is ultimately in support of, like, a good rigorous scientific progress.

We were quite a few we were a very small number of people, so a lot of it was YOLO ideas and YOLO runs. Yeah. And we built great infra for the YOLO runs.

But once we realized that we treated data as immutable and code as always version, and you could always track and trace every experiment end to end perfectly, you could repeat everything perfectly. Right? You have perfect reproducibility.

I can still reproduce runs from two years ago if I wanted to. Right? It actually enables the scientific progress, like the scientific process.

And I think that took us probably about a year, year and a half into the company to figure out. Those are some great hires, like our co head of applied research, Nikolai, who joined us from Yandex. We've been working on language models since, like, the the early twenty twenties.

I think brought that into the company of, like, hey. We wanna have even more rigor. And then once we kinda had the combination of, like, increasingly more capable platform that allowed people to do more but had this immutability, we were able to start actually, okay.

Every experiment is truly an ablation. We truly need to understand it. And and I think we became much more scientifically rigorous in the last couple of years, and the infra underneath enabled it.

And we wanna put out more, like actually we treat writing papers as something that we haven't earned the right for yet for a long time. So you earn the right to spend time, you know, publishing research once you're at the frontier because until then, you're catching up. And every minute and hour in this industry matters.

Like, I I obsess over it. Not just the wall clock time from idea to result, but just general, like, time every day that we, you know, waste is is one that doesn't allow us to catch up. But in this case, we said, okay, we're gonna give ourselves I think we gave the team, three or four days while still doing their work, like, give everything in there.

And to your point earlier, if you know your stuff, it's easy to, like, put it out. And so there's so many more things that we wanna talk about over time, and we will definitely start doing.

other people can do the same. And by the way, I also wanna make clear. We have been incredible like, we've taken a lot of advantage of the fact of all the open research that others have published.

Right? And and and you mentioned, you know, the the Chinese labs, and we I think it's important that there's, you know, from every country and every culture and background, including, like, Western companies like us, there's different models that come out that people can choose to trust. But I think we do have to give credit where credit's due.

Right? The the incredible Chinese lab have done an amazing job at sharing their research, and we have definitely, like, been on the receiving end of taking advantage of that. So when you're on the receiving end of something coming to you, I think it's you also have kind of an obligation to give back.

I think, obviously, everyone's been talking about Zifu lately with with GLM five point two. I think what most people don't realize is when they started. Yeah.

Right? They started years before ChatGPT. This is rebranded.

Yeah. And and and so I've like, I remember how hard it was to work on these things before the rest of the world got excited about it. And so I have an immense amount of respect for people who were working on improving models when it wasn't the sexy thing to do, when believing in LLMs, you know, was was gonna get you ridiculed.

I remember, like, back in 2016 when we were doing what we'd call a machine learning on code with with some of these models, you know, we would people would just frankly laugh at us, like, to be like, you know, this makes no sense. Like, why are you wasting all these, like, millions of dollars on trying to figure this out? And and so I would say they're probably the one that I think deserves a shout out, not just because their latest model was very good, but because they they fought to get here.

And I think I think every foundation model company, you it takes time to get here. Right? It took us three years to get to the model that we're that we're now gonna be releasing.

And now the the time in between the models is coming is counted in weeks. It's no longer counted in months or years, but this stuff's hard. And if we can make it little bit easier for the next person, like, we should all do so.

Because if we don't do so, we're we've got a small window before models are really impacting recursive self improvement to a level where catching up otherwise might become unfeasible. And we should try to, in that window, encourage as many neo labs or whatever we wanna call them, like, to start. And so one of my kind of current mission, but qualm is, like, I wanna encourage whoever is a researcher right now who thinks they can actually tackle this to go and leave and become my competitor.

Like, start another foundation of our company because I think we need it.

I I enter this is an oversimplification, and I and I I always asterisk it with that because it can land a little bit the wrong way in in people's minds, but I actually think you can sum down some and I saw 95% of model building to just doing you're just doing two things. You're improving data or you're improving compute efficiency. And I know that feels like an oversimplification for the incredible, like, gifted and skilled work people do, but if you really look at it, like, what are we doing?

We are looking at data. We're generating new data. We're improving data, and the only way to do that is to look at the data.

Right? That's a big part of foundation model building. And on the other hand, we come up with these incredible breakthroughs in inference, in architecture, and new attention mechanisms.

But what are they really doing? They're bringing compute efficiency. Now we have definitely had some breakthroughs over the years that that allow for more model capabilities.

But at the limit, if you could train a large enough model, right, like, you had infinite compute, we probably if you had infinite compute, you'd be at AGI probably already tomorrow. Right? Like, it it's not and so, and let me say that infinite compute with infinite ability of much faster networking because networking ends up being more of the bottleneck than than compute.

But, so I do think that that's those are the main things. And to just realize that this is engineering. I think it's become more obvious, but I think for quite a few years, people have held foundation model companies and researchers and others on this pedestal of, like, you're doing credible magic or rocket science or only, like, you know, Nobel laureate physicists can do this.

And don't get me wrong. There are some really hard problems that need to be solved, but a lot of the work that all of us are doing on a day to day is not sitting down trying to solve a math theorem. A lot of the work that we're doing is just really doing the basics right, writing good code, looking at data, improving it, running experiments, looking at plots, trying to see like, hey, trying to shape our intuitions.

And a lot more people could be highly capable researchers. And I think that's it it feels it feels far for people to do so. But I've seen in our own company, we've seen engineers become researchers because the model factory allowed them to be have a much lower hurdle of running experiments and trying things.

And one of the guys on our team who started as an engineer building our our agents is a legit reinforcement learning researcher now, making real progress. And that happened in the span of, like, six months. That would have not been what I think most people assumed was possible, you know, couple of years ago.

over time? This is the first model that we're releasing that is starting to meaningfully contribute to our own work. It's not as it's not state of the art model yet, Fable, and other other very capable models.

But Laguna S is really interesting. I'm gonna actually pull up the quote. Peng Ming, one of our coheads of applied research, said something last week as the as the model came out about ten days ago, much better than frankly we had hoped for or expected.

And he said, I have the feeling that a lot of the gains in Laguna S come not from more intelligence, but more from different behavior, more verification, less taking things for granted, not declaring victory early, and being way more persistent. And to be honest, those are more predictive than raw intelligence for success in human also to some degree. And this was he wrote me this on July 5 on Sunday, and it's kinda been burned in my brain ever since because the Laguna S model, as you'll see it, and and why it does so well in benchmarks and why it does so well in in using it on a to day basis is that it's just incredibly persistent.

But it reasons a lot. I do call that out. We have work to do on making it more efficient.

We have to work to do in on offering different reasoning modes. But this is the model that has been able to do things that I never thought it could do. A 118,000,000,008 b active model, which is not that large.

It fits on a DGX Spark and still runs at, you know, thirty, forty tokens a second on Spark is able to solve Erdos three ninety seven independently. It's able to do complex programming tasks. It's able to I asked it this morning to make me a WiFi scanner without using any external libraries on my Mac, and it's like figuring out like the core WLAN API by really persistently trying to understand it without access to the Internet.

And more and more, I love vibe checking. I've probably spent eight to ten hours a day with this model for the last ten days. I'm not exaggerating.

I was on my eleven hour flight yesterday. I spent ten hours reading trajectories and traces and like, of the model. And what I take away from it is exactly what Peng Ming said.

We are gonna be able to squeeze so much more out of smaller models than I think we had imagined in the industry because, yes, there's intelligence and larger models are more intelligent. Like, doubt about it. We should continue to scale up.

But the behaviors of being really persistent, of being able to backtrack when you're wrong, of, like, understanding how to interact with your environment show us that we can get a lot more out of it. And this for me has created a bit of a question in my mind the last couple of days. If you think about where we're using models today, right, we are using models say for knowledge work, represents 25% of the global economy, you know, $25,000,000,000,000 of work.

As we scale up models and they become more intelligent, we are excited about using them more and more for pushing the frontier of science. And if you look at the frontier of science, like true breakthroughs in science, they have been linked they they are linked to more intelligence in many places. Einstein figuring out general relativity is able to bring ideas together that other people would have not brought together.

And I think one of the many dimensions of intelligence is the ability to do that. And it's something we clearly see that as models get larger and more capable, they're able to pull more ideas and threads together that a smaller model wouldn't be able to. And we're starting to see examples of that in medicine and like in bio and other things.

But if you think about the majority of knowledge work that we do, and it includes building software. I'm a software developer at heart, first and foremost, probably, although I probably can't say it that much anymore because I don't write production code in years, is that what makes us good is actually our persistence. It's our ability to encounter a problem and backtrack and say, I need to go figure out this bug.

I need to go research this. I need to go look at the documentation. I need to, like, try different five different ways to see, like, if I can solve it.

But it is not necessarily bringing three ideas together from radically different fields. And so if we are now seeing, and I think Laguna S is an example, that we are able to make a relatively small model much more capable than I had definitely predicted or any previous, like, benchmarks had shown for any model remotely this size or even larger, based on coding tasks, that it's because of the behaviors. And so now the question I have, and I don't have an answer, is I know at the limit, so infinite model size, right, extremely large model, and the cost of that model is gonna be very expensive to run, we notice.

Right? So larger model ROI. So I know that at the very limit, I'm not gonna use the world's largest model one day, quadrillion parameter, whatever crazy like skill we scale up to do a basic coding task.

Already today, I'm starting to size down for certain So it means that there is an optimal. It means there's some curve that goes as we go up to model size for knowledge work. At some point, we're at the peak.

And after that, the return on investment of using a bigger model just doesn't make sense. Now I think the question is, before I would have thought that peak was extremely very far away, this model for me is the first sign that maybe that peak is at a 5,000,000,000,000, 10,000,000,000,000. Maybe we can squeeze way more out of these models.

I'm no longer thinking that we need two or three orders of magnitude on the largest models to be able to, you know, solve knowledge work, the accounting, the legal, the code that we write. And so if if that holds true, it is an argument for the commoditization of models. It's an argument that open source can win and, like, succeed in this world.

And that's, of course, a self serving argument, and it's a hopeful argument. But theoretically, the limit, it works. We just have to go discover in the next couple of years of how much more we can squeeze out.

Now I do wanna put a big asterisk. This does not mean I'm against scaling models. I think we ultimately only succeed if we scale our models as large as our competition.

I do not like I think we should not put our head in the sand and say we're gonna be king of open source small models. I think that's frankly, it's a cop out. It's trying to be king of your own kingdom, but not realizing what the rest of the world's doing.

All of us rather use a smarter, faster, you know, more model. But it's kind of a sign of hope. And so I don't wanna overly state this is a good model.

We have a long way to go to get to the state of the art. But what hopefully people take away when they use this model is that the behaviors inside of it are what push it to be far more capable, less than necessarily the number of parameters. Is that mostly post training?

Like Yes. Right? So It's entirely post training.

Are we done improving anything on pre training? Is, like, pre training done? No.

Okay. So I I just wanted to cover pre training and then we go post training. Pre training is not done.

I mean, look, there's a part of pre training of just dealing with skill. Right? Every new order of magnitude of model skill, you are going to get new things you gotta solve for.

That's those are ultimately, you know, engineering challenges. I have a, I would say, a not commonly held opinion that reinforcement learning will move earlier and earlier into pretrain. Yeah.

Is it midtraining? Not even mid training. Like like, mid training today, right, is like, if you look at the so we've been working on this for years already, and I think the best I think the first time we saw it out in public was the DeepSeek Zero paper.

This is a year and a half ago, think, if I recall correctly, where, you know, you can very early on in a model as it starts capable of being able to use language, etcetera, induce reasoning. And so the question that I kind of have is, like, we have this we have the dataset that's the web. And the web, I think we could arguably say, probably has the totality of humanity's knowledge somewhere encoded in different places.

It's a huge variance degree of quality from garbage data. And, like, once you look at pretraining data, you really get humbled of, like, what the web is to, like, you know, the most greatest scientific papers and best blog posts and, like, you know, best transcripts and whatnot. And so now what we are trying to figure out and have been doing a lot of work on, and it's a place where maybe not as open as we're on other things, but we will become more over time.

We've been spending a couple of years really doing research on how can we turn the web into not just next token prediction, but into a way to teach the model to think earlier in its training. And and I think there's a huge amount of gold to be found there. I think we are right now in you know, we've got some drugs in the industry.

One of the drugs is distillation. Another drug is, you know, more environments, like, and they're great, and they make us feel good, they make the models better, and, like, we're all addicted to them, and we'll use them, right, in in various different ways. And but, ultimately, I think we are still barely squeezing out of the web what we should be getting out of the web.

I think just next token prediction during pretraining is not enough. And so I think we'll see some very interesting things still happen, and that RL in post training to induce behaviors, to improve things. Like, I think the whole world knows how to do this now.

I think we're we're scaling it up. Everyone is. But I wonder if we need to go as far as we're going today with environments.

I'm not sure yet if You mean you're going too far? I'm I'm not sure if the path to AGI is just It's more environment. It's more environments.

an ability to generalize more from the web, but also I'm very encouraged. Like when I look at Laguna S, which is post training as as what is the big impact there. And I see like, oh, wait a second.

Just by making some of these behaviors much better, we're able to get so much more out of it. It just changes a little bit the way you think about intelligence. The analogy people draw often is the oral phase is where you don't learn as much new knowledge.

You reshift yeah. Yeah. So, you know, you reshift distribution and you can have it reason towards what you want.

still just pre training. It's just better data. Right?

Like, I mean, mid training, I like how we invented this word. Like, it's effectively just like, you know, The second phase. The second phase of pre training with, like, a really dumb way to do a curriculum.

But, like, ultimately, what you'd want is a curriculum from token zero to token 30 whatever or 40,000,000,000,000 tokens that really truly is the optimal curriculum for the model to learn. But mid training is essentially a a two stage curriculum on the web because we do not have to compute and effectively to to try to ablate the perfect curriculum. Right?

And so I'm pretty sure that you'll start to see people talking soon about some other terminus towards because now now we do this. Right? We talk stage two and stage three and stage four mid training and, like but ultimately, all we're doing is we're trying to assign a curriculum to the web data that we have to to allow the model to learn better.

I think at some point, as things get compute as as models get cheaper to run, as next generations of compute, this will become more of a continuous spectrum. I also think the reason, by the way, you have mid training and, like, stage two and stage three is organizational. Right?

It's this is, I think, a a thing where that we really try to avoid with the model factory is, like, mid training exists because there's a mid training team now. Right? There's people or, like, people in between decide to focus on, like, a mid training effort.

But what you really want is engineering and and skill of experiments that allows for a much more continuous spectrum that you don't you have infinite stages. Now we're not there. Compute's not there.

Organization design is not there for it yet, but I think we'll get there. We'll look back on a couple of years and become, my god, it was so cute that we did our pre training data like this in such a, like, naive way. Like, we barely ordered it.

We didn't really do a good job at, like, the the kind of building that curriculum. We'll get good at it the industry. And I'll confirm that, you know, when I talk with some researchers that this is a lot of the focus now is, like, how does pre training change and what is the next objective other than next token prediction?

I assume you don't have the answers, but you have some ideas. We have some ideas. We're not ready to talk about it yet.

Yes. We've been working on them for years, and I think that's the one thing that's also, like you asked earlier about, like, what's not obvious about building a financial model company is that you are constantly balancing the table stakes work, the recipe you know works Yeah.

like, the novel thing we did was reinforcement learning on code. No long that's no longer novel by far, but we would like we that's where we obsessed over when no one believed in RL. So you have to kind of when you start the company, you have to have your own idea.

You have to have something that's different that allows you to speed up. Right? For us, it was RL to LLMs that later became common, like, you know, knowledge, but in the beginning, it wasn't.

It's cool. You know?

Yeah. And, like, you do lay it all out here. The blog is pretty underrated.

Right? The whole RL on code was very, very early on. Very, very early.

And even we had to argue with people. Like, we we say here things like to push beyond current capability and to train your own foundation model. We had to argue with people that it mattered that you had your own, like, you know, base model.

You can fine tune your way to success. Right? Major capabilities emerge from training a base model made accurate and useful during fine tuning.

April twenty twenty three. I think this is just happened on the migration, probably filing on arc on on archive.org.

Mistral had started we started on the same month. Right? Yeah.

So this wasn't even there was only, I think, Lama out at the time. Mhmm. That's it.

Right? And so but I I agree. I think we want we want as many diversity of ideas.

And I do think if you're starting today, you you want something that gives you an edge. Right? And what I do think we sometimes over I think every arch like, at the limit, every architecture works.

An RNN works. It's just not compute efficient. Right?

Like, let's say, if you had infinite compute, you could probably just, you know, take a basic RNN from back in the day, and you could get pretty far. Now there have been, you know, meaningful breakthroughs, attention to other things that are there. But you I think we are we're still we're still very early in figuring these out.

The things I'm most excited about, I'm most excited about people doing extremely low precision training. Right? So like the ternary stuff that we're seeing and it was very cool.

The bonsai stuff yesterday was super cool to see. I think that if you can find tweets from me going back to 2023, which is like kind of the notion of like, well, it's an obvious trade off. Bigger model, lower precision equals, you know, smaller model with higher precision by definition.

Right? It's just what is like, how does that actually play out? Right?

What's the actual size limit? So you now have companies that are trying to figure that out. Like, those are the kind of things that can change our industry if they're done right.

Because ultimately, like, our bottleneck on compute is is is a MapMole bottleneck and and a networking bottleneck in the moment you start doing those things. So I'm excited about that. We're not doing any I mean, we're doing the usual, like, Laguna s was trained in FPH.

Only thing that in this run, have to admit that wasn't FPH was the all to all in the new run we just started yesterday. The FPH was all to all that was just, like, cut off day, like, oh, we're not perfectly comfortable wanting to do it. You've got amazing work by Nematron and NVF before training.

Like, I think it's underrated what they've done there. I'm excited to get to NVF before training. Doesn't make sense yet because we're still training on hoppers.

Right? We're, like, relatively small. We're 10 k h 200 cluster company right now.

We'll be scaling to a lot more soon, but and really a lot more. Someone is thinking about applying for a job. But, like, the yes.

I think it's there's so much more juice to squeeze out of this. And, hopefully, Laguna S shows people that a model of this size can get a lot more, and and we did this thing in eight weeks. We think there's a lot more juice to squeeze out at any model size.

We're now scaling up because it's the most optimal thing to do for us as a company. But if I had infinite time, I would love to push more the capabilities at other model sizes. I don't think we've properly announced what your new sizes.

So we have XS, which was thirty b ish. Yep. Old medium was 200 b, which is gonna be deprecated, it seems.

So new So Luna s, Luna small, 118, one one eight billion total parameters, eight b active. So very sparse. It's a scale up of the excess architecture.

It's the kind of classic, or quite classic these days, like three to one ratio of sliding window attention to global attention. It's just it's a nice size for a couple of reasons. One is just very cost efficient.

For us, it was a good way to do we wanted to get our progress out quickly. One of the things that we've seen is that it's a balance inside a foundation model company between focus on releasing and shipping and, like, your new novel research. But with the model factory, we are able to, like, treat the release of a model as less of a time investment from the team because it's just, oh, at this moment in time, you know, do the pretraining run done, apply the latest post training.

And and so this is, I think, a nice weight class. It's one that also will fit on the DGX Spark, which I have a small, like, soft spot for. I love having that little thing, like, you know, run a good model.

Yeah. We covered it on this part of GTC last year. Nice.

It's it's the home the home sweet spot. But I think what I'm most excited about is that this model hopefully shows people what is possible in this size. Because when you look at the benchmarks and and start using it, you'll realize that we are outperforming models two or three times their size.

So yeah. Exactly. And, Luke and by the way, I'm excited about I have it just came out.

So for those of you who listening to this, like, I saw it on my phone. If you're you're if humming in, like, two seconds, so I haven't even had a chance to read the post.

We're look. We're doing I'm not sure if we're state of the art on I mean, Taob three banking, I haven't checked where we sit on the leaderboard, but I think we are within our weight class, I feel very comfortable to say, and even in some weight classes twice larger that we are probably state of the art. I also wanna caveat this, like, you know, best model still in the world right now is definitely, you know, give me a fable, give me a 5.

6. To your point earlier, we also use other models. Yeah.

I think the so the the interesting thing you mentioned earlier is you're starting to shift a lot of your actual usage to it. Right? Benchmarks are like Yeah.

They're good to compare, but they're not super realistic. They they have to. Right?

This is how they're gonna dog food in benchmarking. No. You have to.

Like, you have to use your own models and and you have to have your own internal evals and benchmarks. And and what the funny thing is, like, within first thirty minutes of a new checkpoint coming out, that's, you know, the the kind of first post train after a pre train, you yourself can feel in the first thirty minutes of where this model is gonna be. Like, you don't know exactly, but, like, when this one came out, we were like, oh, like, this is different.

Like and and I think that's I think that's the best example. But it's a little bit like, you know, like your kids. I don't have kids by you know, parents, like, they see their kid and it's perfect and they love it, and then, like, know, they don't see all the rough edges.

You always get that when you bullet your model. It's the most fun part is that you, like, you love a little bit every model that you do. We try to kinda say this thing constantly.

It's like, it's the worst model we'll ever train. And so I know the team now is, like, already onto Yeah. The next one as it should be because this is a race.

And this model is a moment in time that hopefully shows people that we are serious about this race, that we wanna work really hard at it, that we want feedback. Right? Where is it good?

Where is it not? Like, one of the nice things about having your models out in open weight and out in the world is that you get a lot of feedback.

So you need to do some multi harness training. Like, if you especially at these smaller sizes, like, you wanna do a little bit of multi harness training for these models to just get the right, and it's very little. Like, you don't need a lot, but it's just, like, to get the right behaviors that you see in your harness transferring to the harness that, like, you other people might use it in.

We internally have been kind of just calling this polishing, which is like you've got your model, and you do a little bit of polishing so that, like, it's able to work well in other harnesses as it is in your own. No doubt it's going to be better in your own harness. And and it's just because of, like, where are you putting your reinforcement learning compute.

Right? You're putting your RL and and your synthetic data. You're putting it to your own harness because it's the one that you understand the best, and you're able to kind of push the most because that end to end control is what allows you to make it better.

Then transferring those capabilities is is more about just making sure the model, you know, induces the right amount of reasoning and, like, you know, understands some of the maybe more complex, weird tool call formats that might exist somewhere else. And so we do do some multi harness polishing as we call it. It's not really what drives capabilities, but it does create a better experience.

I think, frankly, I think everyone probably does these days, but it is totally fair to see why your own harness is going to still be better than others. And I think we see this with all the foundation model companies. And it's just that when you are pushing capabilities, you don't really wanna trade it off by putting 10 harnesses in your RL runs because it's just complexity.

It's complexity of engineering because these when you're trying to do good science, when you're trying to really understand what make my model improve, you wanna make one variable change to something you understand. And a harness from someone else, you don't know or understand in the same way as you understand your own. Right?

They might have different sub agents or different prompts, but in different If it's open source, you can look at the source. Yeah. But it's time.

Right? Like like, I really cannot stress it. Like, I know I'm, like, a weird person on this because, like, I have friends, like, can we meet up, or can we do this, or can we go I'm like, no.

Because ultimately, this is a race, and time is the only thing that matters. And if I look at our team and say, okay. What is complexity worth introducing on our general trajectory to building more capable models, which generalized to auto harnesses quickly?

And by way, our model works well on auto harnesses. I really encourage people to do it. It works well.

Like, we've been testing an OpenCode and KiloCode and others and like in ClotCode. Which just got bought today. Saw it.

Honda. Yeah. Exactly.

Everything's getting bought. Exactly. And I and I think part of that is, like, you know and there's some amazing I'm excited.

the harness like, we have a very slimmed down harness. When you look at it, it's like six tools. It's like shell and, like, shell kill, shell wait, write, fetch web, and, like, I don't know, bash.

Like, don't think I'm missing one, but like that's effectively all the tools. And it's very simple. It's very lightweight.

So it is not a harness that is designed to try to do well on a benchmark or try to do well on a certain subset of things. It's not a deep research harness. So I think we see incredible ability for complex harnesses that built lots of prompts around and extra data sources and other tools to really push capabilities of models forward.

But our model is still better than some other harnesses who do that in coding like tasks because it was RL'd with it. Now I do encourage people. I think our model, by the way, is perfectly fine and good in ours.

The the differences are probably maybe too small for anyone to notice, but we see it ultimately still on benchmarks by a little bit. So I think it's both are true. Foundation model companies with their harnesses will really push them because it's just operationally, frankly, the best way to have scientific rigor in improving your models, but also someone who takes our model and really does a lot of work on improving our harness is going to outcompete us as they should.

And that's just because the harness is the stop gap between what the model is capable of and what it needs as additional instructions and what it needs as access to data and tools. Right? And that's ultimately, I think, what a harness is.

It's like, is it able as you build more capable models, you know, you're improving the instruction following the models. And so additional harness is just saying, hey. If you encounter x, y, or zed, behave this way.

And so even if you would say that two models with two different harnesses can equally reach the same capability that you care about, a harness that is really tailored towards a capability will do it more efficiently. It's kinda like a person who's getting a a manual of how to do the task in the most efficient way with the right tools and the right data sources versus a really smart person who's like, go figure it out. They'll both solve the task, but one will do it a lot more efficient.

So I'm a big fan of all the harness development that's happening in the world. And we wanna work with more harness, like, creators to also make sure that, like, if it needs some additional training, like, that we will do it.

we I I I raised the AGI. Coding for us since day zero of our website has been and we've said this over and over again, we think focusing on coding and long horizon software tasks is a path towards AGI because it forces us to solve the hard problems. It's it forces us to solve the ability to do extremely long horizon complex work that requires lots of reasoning, external tools, data, etcetera.

And one of the things I can show you so we'll we'll have a web chat on with this model, and I've loved this model for deep research. Just using it in my coding harness. It was never trained for it.

It was never, like, looked at it, but it's great at it, in my opinion. Because ultimately, the skills transfer, they generalize. Now where we are not focused on today is to make sure that the world's greatest medical knowledge is encoded in this model or the world's greatest legal knowledge.

But it actually did we won't be publishing this benchmark because we didn't have time to really do proper, but it did really well on LegalBench. And at least on our first runs and we are very rigorous. When we publish evals, we have checked them for every little thing.

We have run them many times. We've passed. Like, we've gone and well, like, we try to be extremely honest with this.

So if we haven't spent enough time on a benchmark that we use internally that is public, we just said that we won't publish it.

I mean, the the other way is just to give it to artificial analysis and let them run it, Like, third party is done. Oh, 100%. And we are gonna be doing this as well.

And and still it takes time and effort. Right? Because you're working with people to understand, like, you know, the infra failures and and, like, the the tools they're using and, like, how they set up well.

But I agree. You absolutely want to. I'm a big fan of companies like Vowels and AA and, like, others that are doing this stuff.

I thought kindness. You're the first to bring it up. Yeah.

I think they're great. And they've got like, I I loved, like, a lot of the work they've done and put out. And so and there's, I think, many more.

And please create more eval companies. Like, create more evals. I think it's so valuable for the industry.

The actual monopoly kind of, I feel like, oh, and duopoly maybe. You know? I think it could be broken.

Yeah. Because and think it actually be broken really easily because creating an eval, for many people, isn't sexy work, but whoever does it, everyone is happy to get a good eval. You've never like, an eval is well constructed, everyone's celebrating it, and everyone's willing to pay for it, and everyone's willing, like, to fund your market.

Yeah. Yeah. Yes.

I I think creating eval, yes, but, like, in terms of being, like, we are the industry standard ones that will run TBench and make sure that you didn't you didn't cheat, and I'll run it the same way that you run it versus your competitor run it. Yeah. That is very true.

And we need that. And and it's actually nice that that's, like, a few standard places that we all have to, like, you know, adhere to. It keeps us all honest.

I think it's super important to do so. And but yeah. No.

I think our goal is to build the world's most capable models. And right now, we are focused on the coding agent capabilities, long horizon work, but what you see with that is that you get a lot for free. I've always said it's a lot easier for us as we get to, you know, SOTA and and Frontier on coding to then say, okay.

Now we're going to obsess in using the model factory to add more data for places that, you know, we're not as strong on, like, could be medical or legal or any other areas. And similarly, I think what we see, and we see this with reasoning models, a lot if you give models access to the right knowledge sources and they have capable ways of reasoning, they're able to go very well into domains that are less known to them or even seamless in their training data. So but yeah.

Are we agent, like, model plus harness company? We're model company, but I think models today cannot be trained without harnesses. It's not possible.

So it kind of is just like where before it was just the weights in the container. Well, now there's an agent harness that's attached to it. And but I think there's a big difference in being an agent harness as a model company than someone who's truly building an agent company.

I think they can do far more than we can. Yeah.

we're working actually, like, very closely with them because I do think, like, it's and you have to care. You have to invest in it. It's why we do the polishing, and we spend time on it.

And I think over time, yeah, you're you're right that you wanna kind of balance that out. But ultimately, you just want general capabilities that everything works equally in every in every harness.

Pi. No. Pi is a different.

Pi It's more coding. Yeah. I'm a big fan of Pi, though, I have to say.

I think it's a really forgot to mention Pi. Pi you sound closest to Pi in terms pool and Pi in terms of, like, the minimal surface In the minimal surface. Yeah.

Yeah. It's because I don't I have a allow me for one more strong opinion. I've been saying this now for two years.

I think MCP and tools are stupid. Oh, that's cool. Now you support MCP.

I support MCP and we support tools and everything. They make absolutely no sense to me. And, like and and I'll explain a little bit why, and and I think I can probably get people to come along on this one.

If you are looking for complex tasks, increasingly longer horizon, increasingly complex tasks, doesn't matter if it's coding or something else, you are gonna be interacting with data sources. Right? And you're gonna be interacting with things that are installed on some form of a virtual machine.

And what we are doing is that we're putting a layer in between those things. We're putting, like, MCP in between, we're putting tool calls in between, and this is even more about tool calls than MCP, where the model can just write the code and interact with the system. And we're starting to see that, like, Laguna S does this a lot, you'll see this as well in, like, frontier models.

They're increasingly no longer here. We're gonna stuff 50 tools in the, like, system prompt to no. Here's a virtual machine with these binaries installed.

This code base you can operate in. Here, a folder where you can write, you know, your memory if you want to, and the model is using code to do complex asks. And when it uses code, it is not one or two tool calls or three things that are chained together.

It actually starts, you know, using if statements and for loops and and making things conditional. And so I actually think we're moving from we already are moving from tool calls, you know, to effectively models writing code, little scripts. And you see this a lot when you get the Python, you know.

Code interpreter. Exactly. Like in just the arrow arrow in, you know, written code and the file.

I don't know what you call the EOF? Yeah. Yeah.

Exactly. Like, you already see this happening more in models, because when you start training them in RL, the models wanna be free. They wanna be able to do the thing they wanna do in the most efficient possible way, and it is not calling one of the 50 tools in there, like, system prompt.

And so I'm a very big fan of give the model a minimal harness, as minimal as possible, give it a container in which it has its own code base. Right? They've got a a model's code base that has access to the API keys and data sources and and little libraries and and documentation that it needs, and just let it run free at the task.

And I think that is the way we're going. I think we will, in twelve months, not see a single system prompt that is stuffed with 20 or 30 or 40 tools anymore.

but, yeah, I mean, if you can I I do think that's writing code is more generalist, and it's a it's a means to an end for And we do support tools, and we support and this is actually the first model we're doing parallel tool calling in, which we needed to catch up on? So, like, that's there, and, like so it's it's there, but I Yeah. It's a personal nitpick.

I, like, I want the models to have as many degrees of freedom and just, like, you know, be free and and and do capable things.

as well as long context, which you guys have a million token context. Anything else? So for us, Luke, so for us, vision understanding is is the next thing.

Right? Like, we don't have vision understanding. So I was gonna say is though We don't have vision understanding in these models yet.

Yeah. Too many. And so this is something that we've we've started efforts on.

Like, we think it's it's super important to have visual understanding. That's company vision. And so, no, we've got work to do there.

And this is actually one of things I loved about the thinking model, like from the two minutes I scrolled the blog post. Multi Right? The multi They're very committed to multi model including audio.

Yeah. Their state of the art audio, as much as it's a trillion parameters, state of the art audio, but also all trained from scratch. Right?

Yeah. No no encoder in the sense. To me, that's that's that's one of the strongest reasons why you need to trace from scratch is you would just have a different tokenizer.

You'd have different I'm fully aligned. Like, zero zero disagreement from me here. Like, just add the modality and and and don't put, you know, keep it keep it simple.

Where I don't think we'll touch audio for a very long time. It's kinda in the name too, you know, ink, ink, ink. True.

Yeah. Yeah. Maybe what what why so what's so hard about audio?

It's not about what's again, it all comes down to focus. That's easy. Right?

Like, saying no to things means that there's a researcher and compute that can go to making general progress. And our view is, like, general progress is going to come from the ability to push these models to far more capable reasoning, far more longer horizon tasks. I don't think audio adds to that.

I don't think it it pushes us close to AGI. I think it is a necessary modality as you get close to AGI. I think visual understanding sits in the middle of those things.

I think visual understanding can absolutely do so, but it also unlocks capabilities that are just valuable today. So but this is the point. Right?

You want more diversity. You want more different foundation model companies to focus on different things. I think we are just kinda like a horse with blinders on, just like Yeah.

You have a path. We have a path.

throw away the text organizer and just only vision? I I find this I look geek the geek in me is, like, looks at this stuff, and it's like, okay. Look at this.

Like, look at the number of bits in code on the app. They're right. I I think it's super cool.

Right? But I think I think this is what we're gonna come back down to. Like, probably works.

It's just is it compute efficient enough? Is it go like, I think so many of these things ultimately will work. It's just like, you know, what's the nice thing about text?

And and I I referenced earlier, Pengming and Nikolai are my two co heads of applied research who are just incredible. Like, we wouldn't have gotten here without them and the entire team. And and Nikolai have and I have been debating, you know, for years about, like, should reasoning be in latent space?

Should reasoning be in tokens? But one thing that I think him and I really agree on, and and all three of us and is that, like, language is incredible because it's such an incredibly dense way to encode knowledge and information and intelligence. Right?

If you think about, like, what went into a physics paper that then is in a 20 or 30 pages, like, the amount of intelligence and thought and whatnot to then generate that, like, in that 20 page document, like, those little amount of bits, there's so much encoded. And other modalities like video and images are amazing, but they don't have the same density of, like, knowledge or or reasoning or however, like, the things that we're trying to push for that are encoded in that modality. They're there in many cases.

You can watch an incredible lecture for, you know, fifty minutes on YouTube, but the and but if you treat that as video in data versus text data, right, the the bits to, like, signal to noise ratio, the compute efficiency of the modality is a lot, you know, a lot less. And so we kind of have this view. It's like with language, you can go really far, but also when you have limited compute, limited, you know, people, and they're very much linked to two, I think we can push language.

It's the more it's a better investment. But I want all the modalities. I find it super cool, and I love what DeepSeek and others are trying.

Like, I can retweet them all the time, but internally, we're just like, let's stay focused. Which I'll say, you know, you can see somewhat works looking at Anthropic.

in this, I think I I think Anthropic, I mean, they've done many things right, but I think this maniacal focus on just pushing capabilities, scaling up models is I couldn't agree more. I think it's it's that's the first hurdle. And once we get that, then we can improve a whole bunch of other things.

And but at the same time, on the other end of the spectrum, it's really exciting to see people, you know, building these spatial models, right, that are, and the world models that are being built, like, for very different, you know, use cases.

Still scaling? So the new medium started training, and it's much bigger than the last medium started training yesterday. So it's a thirty nine day pre training run.

And, you know, you started with deep seek of the west, and and and I think that's the deep seek moment, right, was a moment when people realized that you can train incredibly capable models for not a lot of money on the training run. But I think that's the falsehood. Right?

Like, the training run is not the expensive part. The training run is a very anticlimactic event. Right?

Like, we just had a Slack message come up yesterday saying, hey. The new model is training, and here are the links, you know, so you can can follow along the evals and, like, that's it. All the work that goes into that moment, it's kind of like how people talk I know nothing about sports, but how, like, athletes talk about, like, you know, it's all the preparation.

It's all the going to the gym, then the game is just a game. I think that's a little bit like with models. Yeah.

People had over indexed on deep sequence trained for $5,000,000 or whatever it was. Right? It's like there's the amount of r and d before that.

The infrastructure is built up. All the things, the data. But no.

So Laguna m is training, and, yes, there'll be an l, and there will be an x l. And and what you'll see what you'll see with m's, right, m is much larger than the last m. Right?

So these monikers are a little bit our version of the the AI He was making fun of people for saying small is 24 b or something. No. Don't know.

Small small for Mistral now is over a 100 b. What? Yeah.

I can pull it up. I mean, our small, right, is a 118, so I I don't wanna say anything else. Like, it's I mean, I think it's also okay.

Yeah. Your small is not We we all know that the single hardest thing for any foundation model company is naming I I don't wanna say that we're good at it either. I mean, it's this is Laguna, you know, Laguna s two point one.

It's it's By at least people understand, you know, medium is bigger than small. Until you mess that up, like, you have a passion. We we try we try hard.

when we started the company, it was gonna be called Snowball Labs. It was after the snowball effect because we expected this company to become a snowball effect, and it definitely has been a snowball effect for us. Turns out it's an Amazon trademark.

I kid you not that my co founder's next suggestion of a name was let's call it Bedrock. And so at this point, was like, okay. No.

You are amazing at naming things if you were at Amazon. And so early on in the company, before we were incorporated, we were at an annual conference of a very big major tech company, and we had been discussing with them. And you have to realize the company at this point is me, my cofounder, COO, Margarita.

We know the first person who's gonna join us. We haven't, like, incorporated yet. And we were discussing an OpenAI Microsoft style deal with this big tech company.

Like, they were going to provide us with a lot of compute. We would give them, you know, perpetual access, a whole bunch of kind of things. And we found out the name was trademarked, Snowball Labs, while we were at that conference and having this discussion that we had no right to have.

Right? We were a couple of guys who had nothing yet, but this big company was willing to entertain the fact that we might partner with them. And we were discussing this, and it was in the their annual conference in a public setting.

And the chief scientist of that company said, people can hear us here. Like, we should move somewhere else. Let's go to the restaurant poolside.

And for some reason, me and Jason looked at each other in that moment and said, oh. And then later that night, we the name stuck with us. The word stuck with us, and we said, let's call the company poolside.

And ever since, we never ended up doing that deal, and we used it as a reminder to never turn down our round down our ambitions because that would have been the easy path. And the hard path was what we did, which is start and try to raise exorbitant amounts of money when you're just a couple of guys who are not even building it in Silicon Valley, who don't come from any, you know, of the the known knobs and things like this. And so everyone assumes poolside because AGI, everyone sits poolside, and it was a playful name and we liked it and we it was a little bit different.

But actually, the name is like a reminder for us to never round down our ambitions. And whenever you're faced with those decisions, to just pick the harder path.

round, the majority of investor conversations were still trying to explain that these models were not just stochastic parrots and that they were gonna keep going. I've seen the world go from OpenAI is gonna win it all and there's no one else who can build company. Right?

I mean, Anthropic struggled, you know, to raise their $500,000,000 round. That's kind of like well reported. They pulled it off gladly.

And so I think when we raised that, it was about a year and a half ago at this point. The world was very different than it is today. I think the world today there's been there's been this function where the number of people who believe AGI is real is probably a super linear or definitely some form of an exponential function itself.

And I think this is important because if you hold the belief that we had three years ago and a year and a half ago, and we will look for people who shared that belief, which is like this technology is gonna fundamentally underpin everything that's economically interest or economically valuable and scientifically interesting for, like, the future, then the value function afterwards is easy to understand, which is, okay, if you get there, you are one of the commodity one of the players who can build this commodity. And over the years, building that commodity has become not just about building models, but also about building infrastructure and other things. And so I think today, because the number of people is bigger and the outcomes have been proven, I think the incredible financial success that Anthropic is having right now and the growth that OpenAI has had and others and Google no longer make this a question of is there a product market fit?

Which really, a couple of years ago, was, like, part of the question. Like, how big can these things when you tell people that, like, you know, you'd be at these amount of revenue numbers in our industry right now, people were still, like, would laugh you out the room. Now I think it's a function of who in the world believes that it's gonna be an oligopoly of intelligence, and who believes that oligopoly can be broken by other companies.

And I think that's what divides investors more than anything else. For the ones who believe in AGI, and then you've got a whole layer that, you know, is kind of self selecting out foundation model companies because they're like, look. I I can't make a the money I put there, you know, compared to what I can put in an application company is very different.

I think there's incredible application companies, and there should be many should be built. But I do think we are still in a world right now where this is the early innings of this can still be the early innings of who is going to, you know, be part of the set of people who win. This is intelligence is the most, in my view, gonna be the world's most demanded commodity.

It will more commoditize in margin and price, and the world wants choice and wants options. And so I think treating the world as like, oh, there's only gonna be two players, I think is very shortsighted from investors. I think that group who thought that was a lot bigger at the beginning of the year than now.

Mhmm. I think the last couple of months have woken up a lot of people and going, holy shit. Like, the the world both can use a lot more intelligence, but also, like, the world is far more complex.

We should have multiple choices, more options, things that can be turned off that can't be that the the restrictions that people put on models now, I think, is is another area of this. Right? Like, the the fact that we are entering into a world where model companies are saying, you're not allowed to use me for foundation model company development.

They should be allowed to do this. It's capitalism. It's their business.

It's their work product.

It is it is wild that we are, like, okay with that.

I I I'll I'll put it this way. I think we we wanna as this technology gets more capable, for the better and worse, we do wanna yield to democracy to figure this out more and more. I think any single company making unilateral decisions is is dangerous.

It's a concentration of power in a small number of people with very limited checks and balances, and that has never worked out well in history in any way, shape, or form. And this is not a criticism on the existing foundation model companies. This is just more commentary on, like, how I'd like the world to be.

I think in a world where the technology gets more capable, government needs to play an active role in determining, you know, where where's the real risks of misuse. Right? And I do think we need to separate safety between misuse and, you know, doomsday scenarios that, you know, I think are no one knows if gun are gonna happen or not.

And I think just like very practically, I think I'm glad to see there's a lot of conversation now starting to happen again at the government level of trying to figure this out. And now what the final decisions are, maybe I'm happy about them, maybe I don't, maybe I agree, maybe not, but ultimately, like, that's kind of democracy always. Right?

Like, at any given moment, I might not be perfectly happy with one or the other, but people chose to vote in someone to make those decisions. And so I think over the long run, over, you know, over a twenty year time span, the world kind of directionally goes correct, and democracy does work. At least what's the famous quote of, like, it's the, you know, the worst of all.

It's the best of all the worst systems or or something like that?

And so that's what I hope for. Now I do think we are in a critical moment of time. And so speaking up for anyone is important.

I think, you know, researchers who are thinking about starting their own foundation model companies start. You know, people who wanna share their opinion and be vocal if that's what their representatives are just out on x, like, so. And but concretely to your point, I think we are not at a level of capability right now that we should start restricting, you know, open models in any way, shape, or form.

I think it will hurt innovation if we do so.

I mean, look at and there has to be. Yeah. Right?

Like, you cannot if you sit with a straight face and say, this can be open forever in every way, shape, or form, it is just as I think a gracious as saying, you know, the opposite of it all needs to be closed down right now. Like, I think at any ends of extremes of spectrums is where we go wrong. Mhmm.

Right? And and in in society in any way, shape, or form. And so the answer is always more nuanced, and the answer is never black and white.

And so I think as we encounter, like, real world scenarios where we have to say, hey. We have to be more careful. We need to reevaluate.

If that means training a model differently and opening it up, having different versions, some things that, you know, that are restrict I think that's totally okay because I don't think anyone should be irresponsible. What I do wanna call out is that people have been calling for the fear of misuse of these models since GPT two. Right?

And I still remember, like, we cannot release GPT two because the whole world will get misused. I mean, that was Dario. And so, like, this is not a commentary on Dario.

It's a commentary just in general in the space. And so we have we have not been very good at this so far, and we need to get better at it. And I do think that the work that's happening with, like, safety institutes and better evals and things like that is is probably the right direction.

Yeah.

that we can, you know, commonly agree on and internationally agree on that we want to, you know, limit or not have available, then we should talk about it in black and white of models available. Yes or no. Like, the moment you start getting these big blanket statements, it's that's when you start getting at the risk of, like I always think back about when we banned advertising on cigarettes.

Good thing. I'm not saying I'm against that, but it effectively established an oligopoly of cigarette companies because no one else could ever compete. And it was the probably the best moment to this to the tobacco industry that that ever happened.

And we don't wanna do that right now. If we if we pull up, you know, walls behind innovation, and this is a self serving comment because I'm not at the frontier yet, but it's not just related to me. I think it's related to everyone in the space.

You are deciding right now in 2026 based on the current capabilities of models that this is something that only two or three companies can build. And that to me reads like chapter 14 of the most dystopian sci fi novel that I could read. Because from there, I think you can play out all the scenarios that happened in the world, and none of those are the ones that make me, you know, excited about the future.

And I think that's the thing we should all think about. Like, what's the future we wanna be excited about? What do we wanna have?

And I think that's a future where intelligence is a commodity. Everyone can access it. It becomes cheaper and cheaper.

Right? And I think that's important. It can like impact more of the world.

And it's not one where, you know, a single company puts their thumb on their skill of both what it outputs to or turns it on or off.

Look. I think this industry has existed because of what NVIDIA has done. Yeah.

Right? I know that we people like it's easy to give them flack, but I also wanna say, like, I remember when we started Source, right, in in in in in 2015 post that Kapathi article. It was able for this progress to happen because we're able to put consumer GPUs in servers, and they allowed us to do so.

And then, like and you kept going further. And so this is something like, foundation models are so closely linked to their hardware and their systems. Yep.

Why do we see these stepwise progress happening? We see them happening because of the next generation of networking and and systems that come out. Right?

The the difference of a model you could train on hoppers versus GB three hundreds is the difference in a trillion parameter model and a five or 6,000,000,000,000 parameter model. And so these things really coexist, I think, very closely to each other. And I think the the more interesting question, I think, for for the future is going to become of, like, how do we what can we unlock in terms of model capabilities, like, as we start codesigning these things even more?

And we're seeing that with, like, the next generation of systems. And I think the world the world, you know, abhors like, capitalism does a really good job at trying to, like, you know, push towards things that are that allow for more competition. Right?

And and NVIDIA allows for competition. It it's not you know? But if a government says no one else can build foundation models effectively through the regulation, that is very different.

Is it hard to go build an NVIDIA? Absolutely. Is it hard to build a foundation model?

I think it's very hard to build a foundation model. But we should, like, make the playing field one that where, you know, if someone wakes up tomorrow and wants to do so, they're, like, allowed to do so, and they're allowed to use the tools to do so. And I think there's still a big difference between what we're seeing in the discussions around model companies versus what we're seeing with chip companies.

One of the things that I'm excited about that I think we're more and more talking about, I don't think anyone is doing yet, is mix and match of hardware during RL training. Right? Like, the you think about, like, the notion and we're seeing this in inference.

Right? The the prefill and decode Yeah. Just work better with, you know, a general purpose in a GPU and and a more specialized, like, chip.

Right? Like, if the grok chip at at NVIDIA, the LPU, and the GPU combined, and there's different versions of that in the industry. And an RL is batch size constraint.

Right? So, like, you are ultimately and then your batch size constraint because you don't have infinite tasks. Right?

When you've got the entire web, you can be much more flexible in scaling up your batch size because you've got the entire web. But for RL, you have, you know, x millions of tasks that you are gonna be training on. And so you cannot blow up your batch size massively, which means that you actually can't scale compute to a certain extent with RL, same way you could scale compute with, like, pre training.

And so I'm very excited about anything that improves that. And I think one of the best ways to start improving that is the things that we're already starting to see in inference, which is the separation of the the prefill and decode to different chips to come to reinforcement learning. Right?

And I think we'll be there soon, and I think more people should be working on this because then all of a sudden, we're able to just be way more efficient in how we train our own from a ball clock time. Again, coming back down to the fact that it's a race. Right?

The race is measured not in how many GPUs, but the race is measured on on calendar time. And that's probably one of the biggest impacts we can have right now to speed up our industry. And so that's one, like, technically, I love geeking out about and talking to people.

Yeah. I would talk to Etched.

and so I'm I'm excited because that's frankly, like, all of us are, like, why why don't we finish, you know, post training this model, whatever, two weeks before release or not, sorry, between release between pre training, then, you know, mid training SFT, and then the time it takes for release. My biggest wall clock bottleneck right now is RL time. Right?

And it's just because I can't scale it up further because I can't add more GPUs to it because of that bad size constraint. There's a really cool blog post that just came out that was showing RL done in even lower precision than any of us are doing. I thought this was really cool.

So this what date is it today? We're on July 15, so this came out five days ago. And I thought this was very cool.

I think, you know, lower precision RL while keeping it stable, we're we're still doing this in FP eight. And so I was excited to see them sharing this work and and bringing it out. It's definitely something that I'm excited to be doing once we move to to Blackwell GPUs.

That's it. Like, there's not too many. Well, I mean, there's there's still quite a difference between n v f p four and four bit, right, in terms of what's what's possible.

But I think n v f p four is, you know, underrated in terms of of what it is. I'm I'm quite excited that it when it came out, it's, you know, just getting that extra like, that trade off between between range Yep. Is very cool.

There's a lot more to squeeze out. Like, I think not to make too many forward promises, but I think we can squeeze a lot more out of the XS size as well. And I think we learned a lot during s training that will allow us to improve excess, like, size even further.

And I think already since then, we have learned things that could have made s even better. I think there is a lot more still for, like, our our space to squeeze out of models much smaller. I don't think that's an argument against scaling.

It's just an and one, by the way, I think this is a nice thing that, you know, it's really it's not very helpful to have a post training recipe for a smaller model and try to apply it to a bigger model. Yeah. It just in all cases, you're gonna have to rethink most of the recipe.

But recipe for post training for a bigger model applied to a smaller model is almost always just a really good, like, improvement and and and baseline. You can still tweak it more, but I don't think that's necessarily, like, obvious. And and so you once you make your bigger models better, you often have a a a quick lever to quickly improve your smaller models again.

But will we be able to squeeze a lot more out of smaller models? Laguna S gave me a lot of confidence that I think we can. And I think it's around that discussion we had earlier about that it's about the behaviors, not necessarily the raw intelligence that you're trying to improve the models for.

why we're also, like, building these models. Right? These models are, for us, part of our research path.

So we've you know, Laguna Medium was much larger than the last two models that this one and last one that we've released, And we've trained even bigger models in the past. So there is the the engineering component of, like, a bigger model and and every kind of order of magnitude size, you learn new things in pre training about stability. But at smaller model sizes, you are able to just iterate a lot quicker, like, internally, right, on your research.

And so for us, distilling down to a smaller model doesn't actually serve the purpose. These models are kind of it's not the right term, but to us, they're dual purpose models. They are progress for us to wait to see, did we improve in the model factory and something to put out into the world.

And so that's why we don't do it. We've done distillation experiments, and there's, like, really cool things you can do. And I think if you have lots of user data, then you can go even further, right, in that.

But I think there's something to be said in having a a quick cadence of models trained end to end from scratch so that you as a research organization can learn the lessons and not wait. That was actually one of the big lessons we learned over the years when we used to have a much longer cadence between model trainings, like six months, and we would train just like a big big model, wait six months, train another bigger model, you would be compounding so many changes of improvements that at the by the time you're training your next model, it's a bit of a soup, and you don't really know what ingredients led to the outcomes. So when you are training far more frequently models, and this holds true for a post training and from pre training from scratch, you are much more able to get an understanding of what led to the improvements, and I think that's important.

Like, ultimately, we are all still there is no true science yet of, you know, deep learning for large language models, But we are all, I think, you know, trying to gain insights from our experiments because it's those insights that lead to scaling laws, that lead to the kind of improvements that allow us to be, again, more compute efficient and get more capabilities.

I mean, it's wild. Right? I mean, it's the it's like the golden age.

Like, it's the fact that you can just take an idea and build something by waiting overnight for an agent to do the work.

Look, ultimately, what is code? What is software? What is engineering?

Is to go from something that is valuable for an end user or sets of end users, like an idea, an extra bug fix, a feature to, like, delivering that value. And I think what we're doing with these models becoming more capable is that we are massively, like, both cutting out middlemen and compressing the time that it takes to deliver that value. And, ultimately, that iteration cycle for any startup or any company is what allows you to win.

Right? If you're able to solve a bug in two hours versus in staying in the backlog for three weeks, if you're able to, like, be on a customer call and learn, hey. If this feature existed, it would, like you know, they'll be willing to pay more and it's more valuable to them, and you ship it in a week instead of in a month.

And so I think ultimately, maybe the same things that we looked at years ago pre LLM still apply, and it's just a notion of cycle time. But in this case, it's lead time from the moment you have a valuable thing that you're looking to do for someone to the moment that is actually shipped to them. Every other metric is ultimately a leading indicator for that lagging indicator.

Right? It doesn't matter if you're looking at amounts of code, PR reviews, all of these kind of things. And so I think in this case, we are starting to move so quickly in some of these things that we can just sit back and look at what was traditionally the lagging indicator, which is the lead time from traditionally ticket to, like, you know, like an end result.

What I would look at in this new world that maybe we didn't think about before is how much can a single person do with that. Right? One of the most like, if you look at AI native companies, they're not designed like the engineering orgs of pre adult age.

They're actually designed with often just the builder. Right? And as close to the kind of customer to the ability to ship, there isn't necessarily a huge team in between that sits there.

And I think that is, I think, is exciting. Like organizations where a single IC can just, you know, get much closer to that. So I would look at from where the value sits that's identified to the moment it's shipped and how many people are involved in that.

And you want the amount of people involved in that to be less, and you want the time end to end to be shorter. Okay.

I think the the common answer to this is agency. Yeah. How much agency does a person have?

I think in the age of AI getting more capable, agency becomes probably one of the most important qualities for anyone. And I think agency is something you can look for in, you know, what people have done in the past because agency is something that if you have it, you are demonstrating it. Right?

No one has just agency and is is sitting back and not, like, exercising it. The whole definition of it is that it's exercised. And so understanding, like, what were things that people did in their lives and their professional and their personal projects that showed agency, and your personal backstory shows a ridiculous amount of agency.

Oh. Right? Like, I think that is ultimately it.

It's the, know, the Silicon Valley, you know, quality of the last, you know, year and a half or so. It's like you can just do things. Right?

That that that's I think what you're looking for. I think then aligning high agency people is very hard because they all wanna go their own way. That's the whole point.

Right? They yeah. But I think the the notion like, I think the notion of a good leader, right, in an organization is to be able to bring people together around, like, a common outcome.

And I think what you wanna do, anyone who's high agency I feel very lucky I've got an organization with incredibly high agency people. Like, I mean, I'm not the one who built the model. Right?

I I cannot stress this enough. Like, it's the team that, like, achieved this, and it's a team that is incredibly high agency. And so if you look at, like, what does it take to bring that together, it's it's ultimately a common goal and a common set of boundaries.

Because if you allow to just go you can do everything, you become an exploration algorithm. And this is what we see in big tech. Right?

In research and big tech, everything is an exploration algorithm. Everyone can do anything as long as you and then becomes political about gathering the resources. So when you say, hey.

This is our common goal, and these are the boundaries that we've set. Right? We're not multimodal.

We focus on RL. Like, we do these things, and you're upfront with people before they join the company. You know, like, you get a lot of agency.

You can run where you want, but these are these are the places where we say this is a miss this is the lanes that that makes sense. I think it actually gets the best out of people because, like, innovation comes from constraints. We did this with relatively little computing, relatively little money compared to some of, like, you know, the others that are out there.

And I've thought back on that quite a bit recently and thought, actually, it was a good thing because those constraints kind of forced us to become much better in certain other axis that might others might have not. Right? We we purchase relatively little external data.

I was gonna ask about that. Exactly. Right?

That was a constraint, but it's a constraint that pushed us to to move on other areas to improve. And, like and there's lots of versions of that. So I think high agency people, you wanna empower, you wanna get them really excited what they're doing, but you also wanna say, hey.

If you join this mission, this is the outcome I need you to achieve, but these are the places that we don't go.

We are hiring on every possible role in applied research and engineering in the company. From Yeah. Free training all the way to evals, to post training architecture, architecture.

Like, we are still in a world where, you know, individuals can have massive impact. And I think our pitch to join us, it's we spoke a lot about the mission, how we think about things, but I think we are one of the places where it's the highest ratio to individual to impact. Right?

Less than 70 people built this model, less than a 115 to engineering and researchers, like, did this effort. And that's a very broad definition because I put myself in the 115 list. And so being able to do this kind of work on a mission that you're aligned with, and you can have that in every individual still has a huge impact.

And being able to publish, being able to open open source the model. Yeah. Look, all of those things are are part of that, but I think ultimately, when you you can today pick between joining a very large foundation model company and but you are one of many.

And not by any fault of them, but just by definition, the denominator has become really big. And our denominator is quite small, and so the level of impact you get to have is really high. And I think ultimately, all of us, frankly, the most incredible high agency people I know, what are they optimizing for?

They're optimizing for impact. They're optimizing for impact, and am I aligned with the mission? And and if today you heard about the mission and aligned, and you're optimizing for impact, I think we're a really good place to try.