# Industrializing AI: Engineering, Open Research, and Market Strategy

**Podcast:** Latent Space: The AI Engineer Podcast
**Published:** 2026-07-23

## Transcript

All right, we're here in the studio with Faisal Khan from Polesight together with Gibu.
Welcome.
Thanks.
Thanks for having me, guys.
Good to be.
Yeah, fresh on the plane.
You texted me.
You were like, hey, I'm on my way to SF.
I was like, you're on the plane right now, right?
Like, hey, you know.
After I texted you, I realized that probably coming in with major jet lag was going to offer some fun experiences today, but let's do it.
I mean, I think the thing I would tell guests is that they don't actually have to prepare that much because if you're...
truly working on this every single day, then even like what you hazily remember is going to be new for a lot of the audience that don't live in your world every day, right?
So 10 years ago, you did a talk at Google Slush talking about the democratization of AI.
And now here you are like open sourcing an incredible new model that we're going to talk about.
But I guess what got you into democratization of AI?
Like it's not obvious from your LinkedIn or something.
No, it's not at all.
Actually, I don't think it's obvious how I got in this space.
I owe getting into this space to Andre Karpathy.
In 2015, he wrote an article called The Unreasonable Effectiveness of Recurrent Mindfulness.
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 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.
And you can kind of read it and the text kind of makes sense, but it doesn't.
And there's an example of code a little bit further down.
Shakespeare.
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 intelligence and the ability to write code.
And so I started building Sourced, 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 2019.
And that sounds really cool today, but back then, no one cared.
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.
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 my 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 kept going.
We failed, ultimately, at the time, and it kind of was like the biggest failure of my career, right?
blew $12 million of investors' money, which was a lot back then.
You spent, still a lot, and you spent years with like a group of 40 people just obsessing over this problem.
And life took a different turn and family kind of became a focus.
And I kind of kept my heads down.
I'm really, frankly, didn't really look at language models for the following two years.
Kind of big mistake considering.
Following years, it'd be really interesting.
And then ChatGPT came out.
And it was kind of like a vindication.
It's like people started texting me.
I found like my old, you know, work decks and these old talks.
And throughout that whole journey, you know, 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 and open source.
When we started Poolside, that actually wasn't the case at all.
And I want to 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 going to 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 going to be the biggest driver for LLM capabilities.
Today, very obvious, three years ago was not an opinion held or direction held at either OpenAI or Google or Anthropic or others.
And so people kind of looked down on us a little bit.
They were like, you know, this is really going to 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 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 co-founder 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, we want to get to AGI, we want to support a world of abundance, and we want to 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 pick at us a little bit.
Like this didn't happen overnight.
It was like 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 kind of used as an analogy or things.
I said, kind of, well, if I go back to back in those days, kind of 2015, 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 I would have that first chapter where everyone's trying to figure things out.
You'd get the chapter of Chachapiti coming out.
And then you would get to the chapter where the world was at a fork in the road.
And 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.
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.
If we were at the frontier, I don't think we could have changed our mind.
And I don't mean this like it's on the moment there's too much capital involved, too much expectations.
You've built up things, right?
We're a small team, you know, just improving and improving.
And so 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, 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 want to release open source models because misuse of models has, you know, real potential risks associated with it?
How is the government going to 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 100 foundation model companies than a world that has five, even if I was one of the five.
And the smallest and most meaningful contribution we can make for 100 to exist is to open up our research and open up our weights right now and kind of figure out along the way how we can do more.
Yeah.
I think, if anything, over the past three years, that has become a bit more true.
You are one of a cohort of Neolabs that people are now calling that.
And, you know, we're doing this on the day that Thinkie launched their new model and you are our performance dev on some benchmarks that they released, right?
Like, they just don't have it yet.
It goes to show that I think, like, actually, this is one of those things where, like, there actually is room for multiple players and you are seeing a little bit more of the future.
Maybe more like 20, not 100, but, like, you are one of the 20.
I really hope so, right?
I think we are, I'm excited about their release.
I'm excited about everyone kind of releasing because, like, ultimately, like, choice competition is both going to drive progress in the right direction, but the fact that, like, you know, we create models.
And while we all drink out of the same well 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 going to 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.
I think more than just one of the 20 Neo labs, up until recently, you know, most of open source innovation was coming from the Chinese labs, right?
So there's the deep seek of the West.
Is it today?
Okay, maybe it's thinking machines, reflection, but there aren't many, right?
So one of the things you guys started sort of in France, Europe.
But very much now you're kind of taking that American standpoint.
And more than just that, the point is the Chinese models that we see, they're not super open research.
The work you put out is, I think, some of the best.
So every few months you get not only frontier models, but also here's a sort of breakdown, blog, paper, technical report of here's everything for state of whenever to build.
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 data sets, challenges around like at least certain things, but being able to share your research, like how do we do it?
What are the lessons we learned that we spent tens of thousands of experiments of compute on?
I think very much so.
One correction though, Vibu, and I say it's 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...
So the story once and for all is very simple.
We 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 going to hire any researchers in the Bay Area.
We're going to 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 Singapore and other places.
And it was because we kind of took a view that this was going to 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, like the most interesting, innovative ideas, were not just going to 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 and different places.
And we have a lot of the team in the US and a lot of the 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.
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 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 12 months.
There's a few that I think still haunt me and scare me.
We're going to talk about them later.
But it kind of created like 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.
When we first wrote our first training code base completely from scratch.
It wasn't a fork of any open source.
It was like, okay, let's build 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.
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 get to where we were.
And so there's this kind of notion of open source and talent and these things.
I think we just took different decisions from a different starting point.
And I think we are lucky.
I do want to definitely call it lucky.
There's a lot of hard work in the team that now that's starting to kind of show up in results.
Just because we probably won't revisit this again, but...
And this is a fun recruiting challenge if someone knows the answer.
What was the bug?
And then we won't tell the solution.
So the bug, this is, you're going to test my memory here.
So, but I think I can recall.
So if you, if you look at, so if you take like Adam as an optimizer, you have epsilon, which is like in the denominator.
Exactly, 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 know 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 a 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 I don't recall the exact bug, but what I remember is once we solved it, we no longer had to choose epsilon as much.
as like what's happening in the llama paper and other places uh 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 uh 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 going to get beaten up so hard.
It's such an experimental science that the things that seem obvious, you very quickly get to learn.
You were wrong, and hopefully you figure out why, and sometimes you don't even.
Yeah, so one of the reasons that when you released your new models, Vebo got really excited.
I mean, everyone got really excited, but Vebo led our paper club on it, and you guys saw it, obviously.
Maybe talk through some lessons learned in that, whatever you can sort of disclose.
We can focus on model factory stuff, whatever you think is a good starting point.
So I would say that 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 where every researcher is spending their time, they're spending their time writing code, right?
Looking at data 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 bases for training and like data pipelines that were kind of patched together.
And we kind of looked at this and said, well, ultimately model building is a process.
You're going from raw data, right?
Like pre-training, raw material, the web, et cetera.
You're doing a whole bunch of filtering, cleaning up transformations, analyzing these days that's far more complex than it was three years ago.
Then you're training a model, which is effectively a large distributed systems problem 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 you're post-training and then you're reinforcement learning.
And so we kind of 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 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 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 on a Foxconn today, no chance.
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 and other 35 engineers.
And we are running, I haven't checked the latest count, but far more than 10,000, maybe 10 to 20,000 experiments a month.
And so if you look at that scale of every model run that is, like it's ultimately, you need to be able to trust it.
It's 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 XS2 that we launched.
It was five weeks from the beginning of pre-training to launch.
The model that we're going to 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 moved 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.
It's another rocket coming 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, 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.
So I look at the screens when I walk, like when we come together in our monthly, we do monthly onsites, and I kind of 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 running 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 pipelines, in both pre and post 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 going to look like.
And that's frankly, so when we talk about, like to 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, as a matter of the pre-training like big run or if it's now a post-training, 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 90 days before, 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 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 someone to 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, et cetera.
So that's usually, there's a little bit of intervention, but that's always within like in-call periods, right?
Not on-call.
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 onto the next one.
And I think that's the way it should be.
I think I also just want to point out, so for context, this was like a month ago.
We found it actually in the tech report.
We just came in with, okay, new models dropped.
Haven't heard about it.
We're very much like, ah, okay, look, it's like, you know, on par with Kimmy, DeepSeek, whatnot, the small ones, Gemma level.
Oh, it's a very cool paper on what goes into building.
And then we hit this page, right?
Like literally the page two of Tech Report is this process allowed us to build the small model from scratch to delivery within five weeks, applying the lessons.
And then...
I'm like, oh, this paper is not about here's a tech report of benchmarks and here's how many tokens it was trained on.
Like for people that want to dive more from what we're not going to discuss on the podcast, it's all laid out here, right?
From custom software that agents can use to interface with training code, pre-training data.
Yeah, all that stuff, you know, read the paper here.
But I would like, I love principles.
I think that is a...
good starting point for maybe telling some stories.
Maybe we can go one by one past the principles.
I'll just call it a Dexter, just got bought by a prefect.
Yeah.
It's kind of fun.
But yes, I'm actually very familiar with Dexter.
Just anything where like they trigger some kind of story.
Well, I would say, well, experiments because 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 data sets, 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 like 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 set, you have to make a change, you have to fix something, et cetera, you've got all this time of like repackaging it, 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 and 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 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 second, right?
And it's actually not a lot, right?
From like a data, moving data perspective.
So we said, well, we have our training cluster and now we've got like our AWS kind of set up.
where we can build these amazing big data pipelines.
We can set things up.
We use Spark underneath the hood, like all of these things.
When you say AWS, it's not actual AWS.
It's your internal.
It's our internal, like just running like our infrastructure.
Site web services.
Exactly.
Our stuff running on like an AWS account or like any hardware, right?
Yeah, yeah.
And 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 data set to materialize.
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 have the search 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 what 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.
And it took us a while.
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.
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 had 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.
We also had some great hires, like our co-head of applied research, Nikolai, who joined us from Yundex.
We've been working on language models since like the early 2020s.
I think brought that into the company of like, hey, we want to have even more rigor.
And then once we kind of 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 I think we became much more scientifically rigorous in the last couple of years and the infra underneath enabled it.
And then there's just fun stuff like...
Yeah, a lot of it's fun.
Like even just the, one, you share all the ablations, two, picking the data sets, right?
There's like...
A random small paragraph in here where it's just like, oh, yeah, pre-training data, we have some, we have an auto mixer.
You know, it trains eight small models, scales them up, picks the pre-training data set.
We don't even need to look at it.
I'm like, wow, a lot of engineering rigor there.
And there's just, you know, there's just a lot.
Yeah, and look, we want to put out more.
Like, actually, we treat writing papers as something that we haven't earned the right for yet for a long time.
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 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 one that doesn't allow us to catch up.
But in this case, we said, okay, we're going to give ourselves, I think we gave the team like 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 want to talk about over time and we will definitely start doing.
And as we earn more of the right, but also now have like added to our mission that we want more foundation model companies to exist, you'll see us like be way more proactive and just trying to keep dropping some of those like things that we've learned along the way that can help others like speed up.
Which is the other cool side of this, right?
It's not like back to your point, it's not just here's the benchmarks of our training.
If you want to replicate, here's experiments of optimizers, data sets, post-training.
You lay out a lot of it here alongside here's your system for how to do it.
So it's really like promoting other people can do the same.
And by the way, I also want to make clear, we have been incredible.
We've taken a lot of advantage of the fact of all the open research that others have published.
And you mentioned the Chinese labs.
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 incredible Chinese lab has 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 in the receiving end of something coming to you, I think you also have kind of an obligation to give back.
Do you have a favorite or underrated Chinese lab?
that you want to shout out everyone shout out to EPC.
That's a good question.
Mouan obviously for...
Mouan, for kidding me.
Yeah, look, I think obviously everyone's been talking about Zifu lately with GLM 5.2.
I think what most people don't realize is when they started.
Yeah.
Right?
They started years before ChatGPT.
They're just rebranded.
And so I have 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 a sexy thing to do, when believing in LLMs, you know, was going to get you ridiculed.
I remember like back in 2016 when we were doing what we'd call machine learning on code with some of these models, you know, we would...
People will just frankly laugh at us, like, this makes no sense.
Why are you wasting all these, like, millions of dollars on trying to figure this out?
And so I would say they're probably the one that I think deserves a shout out, not just because their latest model is very good, but because they fought to get here.
And I think every foundation model company, it takes time to get here.
It took us three years to get to the model that we're now going to be releasing.
And now the time in between the models is counted in weeks.
It's no longer counted in months or years.
But this stuff's hard.
And if we can make it a little bit easier for the next person, we should all do so.
Because if we don't do so, 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 neolabs, or whatever we want to call them, to start.
And so one of my current mission is I want to encourage whoever is a researcher right now who thinks they can actually tackle this to go and leave and become my competitor.
Start another foundation of all companies.
I think we need it.
I think otherwise we're not going to be in the world where...
I don't want to just be the fifth or the sixth company that wins.
I want to look at a world where there's a massive choice.
What else do people not see in starting a foundation model?
You know, there's a lot of compute.
There's a lot of capital required, a lot of compute.
You lay out model factory and how to do the training, but there's a lot there, right?
Well, look, this is an oversimplification, and I always asterisk with that because it can land a little bit the wrong way in people's minds.
But I actually think you can sum down.
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.
That's a big part of foundation modeling.
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 allow for more model capabilities.
But at the limit, if you could train a large enough model, like you had infinite compute, if you had infinite compute, you'd be at AGI probably already tomorrow.
let me say that infinite compute with infinite ability of much faster networking because networking ends up being more of the bottleneck than compute.
But so I do think that 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 shape our intuitions.
And a lot more people could be highly capable researchers.
And I think that's, 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 agents is a legit reinforcement learning researcher now, making real progress.
And that happened in the span of like six months.
would have not been what I think most people assumed was possible, you know, a couple of years ago.
Yeah.
I think one of the interesting moments is when you can sort of self-host, like, you know, in a programming language, like, if you can compile the language in the language, the equivalent is, can you use your own tools, right?
You have the pool CLI, you have your own models.
Presumably, you're not only using your own models, there's no way.
But like, you know, what's that percentage over time?
This is the first model that we're releasing that is starting to meaningfully contribute to our own work.
It's not a state-of-the-art model yet, Fable, and other very capable models.
But Laguna S is really interesting.
I'm going to actually pull up the quote.
Peng Ming, one of our co-heads of applied research, said something last week as the model came out about 10 days ago, much better than, frankly, we had hoped for, 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 5th of July on a Sunday, and it's kind of been burned in my brain ever since because the Laguna S model, as you'll see it, and why it does so well in benchmarks and why it does so well in using it on a day-to-day basis is that it's just incredibly persistent.
It reasons a lot.
I do call that out.
We have work to do on making it more efficient.
We have work to do on offering different reasoning modes.
But this is the model that has been able to do things that I never thought it could do.
118 billion 8B active model, which is not that large.
It fits on a DGX Spark and still runs at 30, 40 tokens a second on a Spark.
is able to solve ERDOS 397 independently.
It's able to do complex programming tasks.
It's able to, I asked it this morning to make me a Wi-Fi 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 10 hours a day with this model for the last 10 days.
I'm not exaggerating.
I was on my 11-hour flight yesterday.
I spent 10 hours reading trajectories and traces of the model.
And what I take away from it is exactly what Pengling said.
We are going to 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.
No 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 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 today for knowledge work.
Represents 25% of the global economy, $25 trillion 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 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.
at least 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, extremely large model, and the cost of that model is going to be very expensive to run, we notice, right?
So larger model, ROI.
So I know that at the very limit, I'm not going to use the world's largest model one day, quadrillion parameter, whatever crazy skill we scale up.
to do a basic coding task.
Already today, I'm starting to size down for certain tasks.
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 trillion, five trillion, 10 trillion.
Maybe we can just 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 solve knowledge work, the accounting, the legal, the code that we write.
And so if that holds true, It is an argument for the commoditization of models.
It's an argument that open source can win and succeed in this world.
And now it's, of course, a self-serving argument and it's a hopeful argument.
But theoretically, at 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 want to 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 going to 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 want to 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?
Yes.
Right?
It's entirely post-training.
Are we done improving anything on pre-training?
Is pre-training done?
No.
Okay.
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've got to solve for.
Those are ultimately, you know, engineering challenges.
I have, I would say, a not commonly held opinion that reinforcement learning will move earlier and earlier into pre-training.
Yeah, mid-training.
Not even mid-training.
Like mid-training today, right, is, like if you look at, 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 was a year and a half ago, I think, if I recall correctly.
where you can very early on in a model, as it starts capable of being able to use language, et cetera, induce reasoning.
And so the question that I kind of have is like, we have the data set 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 pre-training 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 I've 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 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 and they make the models better and like we're all addicted to them and we'll use them, right?
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 pre-training 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.
I think the whole world knows how to do this now.
I think 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 not sure if the path to AGI is just more environments.
It seems like a never-ending...
Okay, I want instruction manual for this table, right?
Am I going to environment out building furniture?
Or are we just going to tail end, like, we need some general solution?
I think there's 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, it's 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 RL phase is where you don't learn as much new knowledge.
You reshift distribution and you can have it reasoned towards what you want.
On your point about mid-training, a lot of mid-training is still just continue pre-training in a domain, say medicine, then you do RL.
So still just pre-training.
It's just better data, right?
I mean, mid-training, I like how we invented this word.
It's effectively just like, you know.
It's a second phase.
It's a second phase of pre-training with like a really dumb way to do a curriculum.
Ultimately, what you'd want is a curriculum from token zero to token 30-whatever or 40-train tokens that really truly is the optimal curriculum for the model to learn.
But mid-training is essentially a two-stage curriculum on the web because we do not have to compute effectively 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 tour.
Because now we do this, right?
We talk stage two and stage three and stage four mid training.
But ultimately, all we're doing is we're trying to assign a curriculum to the web data that we have to allow the model to learn better.
I think at some point, as things get compute, as models get cheaper to run, as the 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?
This is, I think, 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 decide to focus on like a mid-training effort.
But what you really want is engineering and skill of experiments that allows for a much more continuous spectrum that you don't, you have infinite stages.
We're not there.
Our 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 think, oh my God, it was so cute that we did our pre-training data like this in such a naive way.
Like we barely ordered it.
We didn't really do a good job at like kind of building that curriculum.
We'll get into that in the industry.
And I'll confirm that, you know, when I talk to 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.
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.
Versus like your, I might clearly break through pure research and, and finding that balance and, and adjusting the percentage to it based on where you are in the race is really important.
I mean, so like, this is a nice way.
I was going to bring out auto research at some point.
That's another Andre invention.
A coinage.
Which is like, honestly, how many objective functions can there be?
Just try a thousand of them, set it running, whatever.
You know what you're looking for.
You're looking for lost curves like that.
It's also a thing people take bets on, right?
When you say more Neolabs, you're doing a version of we'll do foundation models, scale them up, next token predictors.
a lot of other Neolabs that we see want to take a completely different approach, right?
At some level, you're right.
It's all compute efficiency and that's the net objective.
But, you know, some are, okay, different architecture, like vastly different amounts of compute spend.
So some are different.
They're not just, they're like, you know, 99% not balancing.
Here's the vanilla and scale up there.
99% on here's novel research that'll change everything.
And I think, look, I think you, It depends when you started as well, right?
When we started, like, the novel thing we did was reinforcement learning on code.
That's no longer novel by far, but 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, this was like your original 2023 blog.
Yeah.
And like you do lay it all out here.
The bug 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 say here things like to push beyond current capabilities 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't fine tune your way to success, right?
Major capabilities emerge from training a base model made accurate and useful during fine tuning.
Which like for perspective at the time, you know, we knew, closed models, open-air Anthropic were huge.
The open models we had were like Mistral 7B, a 30B, a 70B.
When we actually, the date on this thing is wrong.
When we published this, it was April 2023.
I think this is just a habit on the migration.
On archive.org.
Mistral had started, we started on the same month, right?
So this wasn't even, there was only, I think, Lama out at the time.
And that's it, right?
And so, But I agree.
I think we want as many diversity of ideas.
And I do think if you're starting today, you want something that gives you an edge.
And what I do think we sometimes over, I think at the limit, every architecture works.
And RNN works.
It's just not compute efficient.
If you had infinite compute, you could probably just take a basic RNN from back in the day and you could get pretty far.
Now, there have been meaningful breakthroughs, attention to other things that are there.
But I think we're still very early in figuring these down.
The things I'm most excited about, I'm most excited about people doing extremely low precision training.
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 smaller model with higher precision by definition.
It's just how does that actually play out?
What's the actual size limit?
You now have companies that are trying to figure that out.
Those are the kind of things that can change our industry if they're done right.
Because ultimately, our bottleneck on compute is a Matmol bottleneck and a networking bottleneck.
And 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 FP8.
Only thing that in this run, I have to admit that wasn't FP8 was the all-to-all.
In the new run we just started yesterday, the FP8 was all-to-all.
That was just like cut off date.
Like, oh, we're not perfectly comfortable wanting to do it.
You've got amazing work by Nemetron and NVFP4 training.
Like, I think it's underrated what they've done there.
I'm excited to get to NVFP4 training.
Doesn't make sense yet because we're still training on hoppers.
We're like relatively small.
We're a 10K H200 cluster company right now.
We'll be scaling to a lot more soon.
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 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 size is.
So we have XS, which was 30B-ish.
Old medium was 200B, which is going to be deprecated, it seems.
So a new Laguna Small.
Laguna Small, 118, 1, 1, 8 billion total parameters, 8B active.
So very sparse.
It's a scale-up of the XS 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 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 pre-training run done, apply the latest post-training.
And, uh, And so this is, I think, a nice weight class.
It's one that also will fit on the DJX Spark, which I have a small soft spot for.
I love having that little thing run a good model.
Yeah, we covered it on this part of GTC last year.
Nice.
I think a GPT-LSS 120B was the first because it's a large single GPU, which was the H100, right?
Rent one H100.
Now you've got 128GB Macs, Mac Minis, Sparks.
It's 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 start using it, you'll realize that we are outperforming models two or three times their size.
Yeah, and they think, so for example, today's thinking model is like a trillion per amps.
So yeah, exactly.
And look, and by the way, I'm excited about, I have, it just came out.
So for those of you who are listening to this, like I saw it on my phone.
If you're humming in two seconds, I haven't even had a chance to read the post.
But somehow you are, not only you're better than Dinky, which is like one of those benchmarks, but also like on certain benchmarks, like the Tao Bench one, like you're actually state of the art.
We're, look, we're doing, I'm not sure if we're state of the art.
I mean, Tao 3 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 want to 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 interesting thing you mentioned earlier is you're starting to shift a lot of your actual usage to it, right?
Benchmarks are like, they're good to compare, but they're not super realistic.
They have to, right?
This is how they're going to dog food benchmarking.
No, you have to.
Like, you have to use your own models and you have to have your own internal evals and benchmarks.
And what the funny thing is, like, within...
first 30 minutes of a new checkpoint coming out that's you know the kind of first post train after a pre-train you yourself can feel in the first 30 minutes of where this model is going to be like you don't know exactly but like when this one came out we were like oh like this is different like uh and and i think that's i think that's the best example uh but it's a little bit like you know, like your kids.
I don't have kids, but you know, parents, like they see their kid and it's perfect and they love it.
And then like, you know, they don't see all the rough edges.
You always get that when you build your own models.
The most fun part is that you like, you love a little bit every model that you do.
We try to kind of 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 on to 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 want to 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 way now in the world is that you get a lot of feedback.
How do you think about building it with like working with a harness, right?
So open code, codex, you have your own pool CLI tool, basically getting people to use it, the co-design of model harness, training it in.
So you need to do some multi-harness training.
Like if you, especially at these smaller sizes, like you want to 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 it's just because of like, where are you putting your reinforcement learning compute, right?
You're putting your RL 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 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 want to trade it off by putting 10 harnesses in your RL runs because it's just complexity.
It's complexity of engineering because when you're trying to do good science, when you're trying to really understand what made my model improve, you want to 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.
They might have different sub-agents or different prompts.
If it's open source, you can look at the source.
Yeah, but it's time, right?
I really cannot trust it.
I know I'm a weird person on this because 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 generalize to other harnesses quickly.
And by the way, our model works well in other harnesses.
I really encourage people to do it.
It works well.
Like we've been testing in OpenCode and KiloCode and others and like, and ClonCode.
Which just got bought today.
I saw it in Honda.
Exactly.
Everything's getting bought.
Exactly.
And I think part of that is like, you know, and there's some amazing, I'm excited.
Like I think Hermes is actually a ridiculously cool harness.
Like, and so.
And, you know, part of the question was actually just like, How much effort is model versus model plus harness, right?
So new benchmarks like agents last exam, it's not wanting to just measure the model.
Same with models getting more and more agentic.
They need a harness to operate in, right?
I think for when you're asking that question to a model company, I think you can separate it in two parts, which is like 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 I 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, right?
It's not a deep research harness.
So I think we see incredible ability for complex harnesses that build 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, that 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 a harness is going to outcompete us as they should.
And that's just because the harness is the stopgap between what the model is capable of and what it needs as additional instructions and what it needs as access to data and tools.
And that's ultimately, I think, what a harness is.
It's like, is it able...
As you build more capable models, you're improving the instruction following the models.
And so additional harness is just saying, hey, if you encounter X, Y, or Z, 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 kind of like a person who's getting 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, 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 want to work with more harness-like creators to also make sure that if it needs some additional training, like publishing, that we will do it.
I mean, I think when you say it's a race, there's a question of what are you racing to?
Are you racing to be the best coding model company?
or the best coding model plus harness company.
I think that's a dozen different things.
Or fell in the blank.
Or neither.
So we, I erased 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 like software tasks is a path towards AGI.
because it forces us to solve the hard problems.
It forces us to solve the ability to do extremely long horizon, complex work that requires lots of reasoning, external tools, data, et cetera.
And one of the things I can show you, so 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 arts.
It was never trained for it.
It was never 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 LegalVenge.
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.
We've gone and 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 say that we won't publish it.
And so, I mean, the other way is just to give it to artificial analysis and let them run it.
Like third parties then.
Oh, 100%.
And we are going to be doing this as well.
And still it takes time and effort, right?
Because you're working with people to understand like, you know, the infra failures and like the tools they're using and like are they set up well.
But I agree.
You absolutely want to.
I'm a big fan of companies like Vals and AA and like others that are doing this stuff.
I thought of fairness.
You're the first to bring it up.
Yeah.
I think they're great.
And they've got like, I love 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.
It's an actual monopoly, kind of, I feel like.
Oh, and duopoly, maybe.
I think it can be broken.
Yeah.
I think it can 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.
Like, if an eval is well-constructed, everyone's celebrating it.
And everyone's willing to pay for it.
And everyone's willing to make the foundation market.
Yeah, yeah.
I think creating eval, yes.
But, like...
In terms of being like, we are the industry standard ones that will run T-Bench and make sure that you didn't cheat.
And I'll run it the same way that you run it versus your competitor ran it.
Yeah, that is very true.
And we need that.
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.
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-arising 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 SOTA 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 we're not as strong on, like it 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 seen less in their training data.
So, but yeah, are we an agent like model plus harness company?
No, we're a 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, understood.
Yeah, I think that is my minor pushback.
If you are truly identified as a model company, then make the best model for open code, right?
Instead of for pool or whatever.
I think that's minor compared to actually if the goal is AGI, I actually make the best model for Hermes, right?
Because that is the next stage after coding.
Look, and we're working actually very closely with them because I do think it's...
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 right that you want to kind of balance that out.
But ultimately, you just want general capabilities that everything works equally in every harness.
Just on the topic, do you guys do much with like Hermes, OpenClaw, NanoClaw, whatever?
Pi.
No, Pi is a different Pi.
It's more coding.
I'm a big fan of Pi, though, I have to say.
I think it's a really...
I forgot to mention Pi.
Pi, you sound closest to Pi, pool in Pi, in terms of the minimal surface.
It's because I don't...
Allow me for one more strong opinion.
I've been saying this now for two years.
I think MCP and tools are stupid.
Ooh, let's go.
Now, you support MCP.
I support MCP and we support tools and everything.
They make absolutely no sense to me.
And I'll explain a little bit why.
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, it doesn't matter if it's coding or something else, you are going to be interacting with data sources, right?
And you're going to 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 going to stuff 50 tools in the like system prompt to know 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 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.
EOS.
Yeah, exactly.
Like you already see this happening more in models because when you start training them in RL, the models want to be free.
They want to be able to do the thing they want to do in the most efficient possible way.
And it is not calling one of the 50 tools in their 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?
A model's code base that has access to the API keys and data sources and little libraries and documentation that it needs and just let it run free of the task.
And I think that is the way we're going.
I think we will, in 12 months, not see a single system prompt that is stuffed with 20 or 30 or 40 tools anymore.
No comment.
No pushback there.
I think it will be supported for a long time just because a lot of people are trained on that now.
But maybe you guys don't have to support it in your models going forward.
But yeah, I do think writing code is more generalist and it's a means to an end.
And we do support tools.
And this is actually the first model we're doing parallel tool calling in, which we needed to catch up on.
So that's there.
So it's there, but it's a personal...
nitpick.
I want the models to have as many degrees of freedom and just be free and do capable things.
Yeah, so that was on the path towards like, okay, how do you use poolside models and Laguna models for my Hermes or my OpenCloud, all those things.
And so typically what I look for is computer use or vision.
That's a very big one.
You guys have a blog post on that.
But then also the persistence, I think, is very strong value, as well as long context, which you guys have a million token context.
Anything else?
So for us, look, so for us, vision understanding is the next thing, right?
Like we don't have vision understanding.
Which I was going to say is we don't have vision understanding in these models yet.
Yeah.
And so this is something that we've started efforts on.
Like we think 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 the things I loved about the Thinky model.
two minutes I scrolled the blog post.
They're very committed to multimodal, including audio.
Their state-of-the-art audio, as much as it's a trillion parameter, state-of-the-art audio, but also all trained from scratch, right?
No encoder in the sense...
To me, that's one of the strongest reasons why you need to trade from scratch is you just have a different tokenizer.
I'm fully aligned.
Zero disagreement from me here.
Just add the modality and keep it simple.
I don't think we'll touch audio for a very long time.
It's kind of in the name too, you know, ink, ink, ink.
True.
Yeah, yeah.
What's so hard about audio?
It's not about what's, again, it all comes down to focus.
That's easy.
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 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.
But this is the point, right?
You want more diversity.
You want more different foundation model companies who focus on different things.
I think we are just kind of like a horse with blinders on.
Just like, yeah, you have a path.
We have a path.
We want to catch up to the frontier and we don't want to distract ourselves with anything else.
Yeah.
I will call out that one of the branches of research is DeepSeek OCR, which is, can you just throw away the text tokenizer and just only vision?
I find this, I look, the geek in me is like, looks at this stuff and it's like, okay, let's like, look at the number of bits in code.
I think it's super cool, right?
But I think, I think this is what we're going to come back down to.
probably works it's just is it compute efficient enough is it going 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 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 and i have been debating you know for years about like um should reasoning be in latent space should reasoning be in tokens But one thing that I think him and I really agree on, and all three of us, is that language is incredible because it's such an incredibly dense way to encode knowledge and information and intelligence.
If you think about what went into a physics paper, then there's 20 or 30 pages, the amount of intelligence and bot and whatnot to then generate that.
In that 20-page document, 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 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, 50 minutes on YouTube.
But if you treat that as video in data versus text data, right?
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.
OpenAI has a lot of vision, multimodality.
Anthropic kind of just didn't, right?
Fable is a big step up in image processing, but they're not known as the multimodal company, right?
They're the language model coding company that has multimodal capabilities that's never super flexed and goes pretty far.
Look, in this, 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 that's the first hurdle.
And once we get that, then we can improve a whole bunch of other things.
But at the same time, on the other end of the spectrum, it's really exciting to see people building these spatial models, the world models that are being built for very different use cases.
But I think ultimately it all comes together at some point.
Okay, so scaling models.
This is Laguna S for small.
You have good naming.
Extra small, small, medium, large.
Still scaling?
So the new medium started training and it's much bigger than the last medium started training yesterday.
So it's a 39-day pre-training run.
How do you know the days in advance?
Just the computer model factory.
Right, and at this point with the model factory, it's...
I thought it was interesting.
So in the Laguna medium and extra small, you even quoted number of GPU hours for how many days and whatever for different size.
And I'm like, oh, you can also work backwards to how much that costs, right?
What GPUs, how many hours.
And you realize it's not a lot.
No, it's not.
It's not a lot of money.
And, you know, you started with DeepSeek of the West.
And I think that's the DeepSeek moment, right, was a moment when people realized 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 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 and then the game is just a game.
I think that's a little bit like with model.
Yeah.
People had over indexed on deep sequence trained for $5 million 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 XL 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, He does make fun of people for saying small is 24B or something.
No, no, no.
Small for Mistral now is over 100B.
What?
Yeah, I can pull it out.
I mean, our small rate is 118, so I don't want to say anything else.
I mean, I think it's also...
Okay, your small is not...
We all know that the single hardest thing for any foundation model company is naming...
I don't want to say that we're good at it either.
I mean...
This is Laguna S 2.1.
But at least people understand medium is bigger than small.
Until you mess that up, you have a password.
We try hard.
While we're on the topic of naming, this is going to be at the end, but might as well.
Why poolside?
Why Laguna?
So when we started the company, it was going to 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, I 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.
You have to realize the company at this point is me, my co-founder, CEO of Margarita.
We know the first person is going to join us.
We haven't incorporated yet.
And we were discussing an OpenAI Microsoft-style deal with this big tech company.
They were going to provide us with a lot of compute.
We would give them 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 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, 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 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 of the known NAVs 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 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.
Yeah.
I mean.
That's a great story.
I know you've told it before, but I just wanted to let it on the record.
That's what I did the first time I met you.
You told me, you sat me down, we were in the hotel somewhere, and you were like, we're raising 500 million.
And then you gave me the whole vision, and then you actually did it.
And I was like, I don't have that much opportunities to ask, just how do you do that kind of raise to those kinds of VCs?
What are they looking for?
Yes, vaguely AGI.
But like, what do they want when you look at the world's definitely changed, right?
When we were raising that $500 million round, the majority of investor conversations were still trying to explain that these models were not just stochastic parrots and that they were going to keep going.
I've seen the world go from open AI is going to win it all and there's no one else who can build company, right?
I mean, Anthropic struggled, you know, to raise their $500 million round.
It'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 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 looked for people who shared that belief, which is like, this technology is going to fundamentally underpin everything that's economically valuable and scientifically interesting for the future, then the value function afterwards is easy to understand, which is like, hey, if you get there, you are 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 their product market fit?
Which really, a couple of years ago, was part of the question.
How big can these things be?
You tell people that you'd be at these amount of revenue numbers in our industry right now, people would still laugh you out the room.
Now I think it's a function of...
Who in the world believes that it's going to 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 is kind of self-selecting out foundation model companies because they're like, look, I can't make...
The money I put there 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, going to 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 going to be two players, I think is very short-sighted from investors.
I think that group who thought that was a lot bigger at the beginning of the year than now.
I think the last couple of months have woken up a lot of people and going, holy shit, like 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 beat it.
The restrictions that people put on models now, I think, is another area of this, right?
Like 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.
But it is insane.
It is wild that we are like okay with that.
Do you have more problem with Anthropics saying it or the White House saying it?
You're picking two different limitations and restrictions there.
Look, I think I'll put it this way.
I think we want to, as this technology gets more capable, for the better and worse, we do want to 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 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 where is there 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 are going to 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, that's kind of democracy always.
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 a 20-year time span, the world kind of directionally goes correct.
Democracy does work.
At least, what's the famous quote of it's the worst of all?
It's the best of all the worst systems or something like that.
It's the worst form of organization except for all the others that we've tried.
Exactly.
You can always count on me for a Churchill quote because I've studied Churchill a lot.
I love 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 want to share their opinion and be vocal, if that's with their representatives or just out on X, like do 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.
Is there a point at which you will change your opinion there?
Yes.
I mean, look, 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, egregious 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.
Right?
And 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 are restricted, I think that's totally okay because I don't think anyone should be irresponsible.
What I do want to call out is that people have been calling for the fear of misuse of these models since GPT-2.
Right?
And I still remember, like, we cannot release GPT-2 because the whole world will get missing.
I mean, that was Dario.
And so, like, this is not a commentary on Dario.
It's a commentary in general in the space.
And so, 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 probably the right direction.
Yeah.
I mean, I want to say something in defense of this.
It's better to err on the side of safety and then roll it back rather than the other way because the other way, it's a one-way decision.
I think that's true.
The caveat there is also the competition, right?
You don't have global err on the side of safety, right?
You're talking...
Yeah, exactly.
So you don't get to do unilateral safety because someone else will just be more unsafe than you.
Yeah, exactly.
You can pause innovation here.
It doesn't mean it's pausing.
They're complex parts, right?
And I think we are much better off talking about certain capabilities 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, 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 tobacco.
But it effectively established an oligopoly of cigarette companies because no one else could ever compete.
And it was probably the best moment to the tobacco industry that that ever happened.
And we don't want to do that right now.
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 happen 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.
What's the future we want to be excited about?
What do we want to have?
And I think that's a future where intelligence is a commodity.
Everyone can access it.
It becomes cheaper and cheaper.
And I think that's important.
It can impact more of the world.
And it's not one where a single company puts their thumb on their skill of both what it outputs to or turns it on or off.
I think the one entity that has more power than the US government here, is NVIDIA.
Because basically whoever gets the allocations gets the compute.
You can take it down to TSMC or...
TSMC below that.
But I just wanted to test provocative statements to see if you have any response.
I need to think on that one.
Which actually I think they are regulated, right?
Like you can see the government...
Can they ship to China?
Okay, but you know.
They're not trying to.
Look, I think this industry has existed because of what NVIDIA has done.
I know that people like it's easy to give them flack, but I also want to say, I remember when we started Sourced in 2015 post that Kapathi article, it was able for this progress to happen because we were able to put consumer GPUs in servers and they allowed us to do so and you kept going further.
And so this is something.
Like foundation models are so closely linked to their hardware and their systems.
Why do we see these stepwise progress happening?
We see them happening because of the next generation of networking and systems that come out, right?
The difference of a model you could train on hoppers versus GB300s is the difference in a trillion parameter model and a five or six trillion parameter model.
And so these things really coexist, I think, very closely to each other.
And I think 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 co-designing 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 NVIDIA allows for competition.
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 about model companies versus what we're seeing with chip companies.
The gap also seems to be the expertise in who regulates it, right?
Who at the government decides what's too safe, too smart, too dangerous?
But while we're throwing spicy questions out there, do you have anything that comes to top of mind that could be changed?
Should open AI anthropic open source models, is it open weights?
Is it what we do in RL that determines, you know, your safety barriers?
Is there anything that should be done there?
Yes.
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 you think about like, And we're seeing this in inference, right?
The pre-fill and decode just work better with a general purpose and a GPU and a more specialized chip, right?
Like the Grok chip at NVIDIA, the LPU and the GPU combined.
And there's different versions of that in the industry.
And RL is batch size constraint, right?
So like you are ultimately, and you're batch size constraint because you don't have infinite tasks.
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 going to 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 the 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 pre-fill and decode to different chips to come to reinforcement learning.
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 RL from all 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 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.
I had a tour of their data center and physically you can see how PD disaggregation is mapped out in the data center and you have to own your own hardware to do that.
Yeah.
No, look, I think it's...
I think more innovation in space is just like, is the coolest thing.
And, 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.
And it's just because I can scale it up further because I can't add more GPUs to it because of that 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.
What date is it today?
We're on July 15th, so this came out five days ago.
And I thought this was very cool.
I think lower precision RL while keeping it stable were...
We're still doing this in FP8.
And so I was excited to see them sharing this work and bringing it out.
It's definitely something that I'm excited to be doing once we move to Blackwell GPUs.
But yeah, cool.
Part of open research, you know, you take and you give.
Exactly.
I'll just quickly mention, there was a paper that did a vision on levels of quantization, and they roughly concluded that 4-bit was the sweet spot.
I remember this just a couple of years ago, right?
I think I remember this.
I think it went rear.
One year came out.
But I'm like, okay, maybe NVFP4 is it.
You can't really, the lowest you can go is ternary.
That's it.
There's not that many.
I mean, there's still quite a difference between NVFP4 and 4-bit, right, in terms of what's possible.
But I think NVFP4 is underrated in terms of what it is.
I'm quite excited that when it came out, it's just getting that extra.
Like that trade-off between range is very cool.
A couple of questions.
I have a quick one.
Okay, quick question back to technical side.
So any big takeaways from XS 2.1, medium, to training the new small, just general in terms of training models?
You mentioned a lot in the earlier discussion about, okay, in pre-training, there's a lot you can squeeze out, right?
You can learn a lot more from the web.
At the same time, you took, 30B and scaled it up to 120B, right?
Is there any gating on how small is too small?
So I'm just going to ramble for a bit.
I'll come to a question at the end.
But, you know, part of Carpathie's thesis was cognitive core, right?
We've seen VibeThinker, NANBEDS, 3B, 4Bs that reason a lot.
And then, you know, the idea is you offload to a different model for...
work, these are small reasoning models.
So have you found anything interesting in modal sizes like 20, 30 Bs on device, 100 Bs on single GPU?
Can you squeeze out more there?
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 excess size as well.
And I think we learned a lot during S training that will allow us to improve excess size even further.
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 our space to squeeze out of models much smaller.
I don't think that's an argument against scaling.
And one, by the way, I think this is a nice thing that it's not very helpful to have a post-training recipe for a smaller model and try to apply it to a bigger model.
In all cases, you're going to have to rethink most of the recipe.
But a recipe for post-training for a bigger model applied to a smaller model is almost always just a really good improvement and baseline.
You can still tweak it more, but I don't think that's necessarily obvious.
And so once you make your bigger models better, you often have 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 has 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.
And that's on all axes of...
There's like an axis of how long a model will reason.
So how long can it stay agentic?
And there's also efficiency, right?
You want to ideally push on both.
And the thing to clarify you guys aren't doing right now, which we do see at Frontier Labs, is the distillation, right?
You have a big, big model that you don't really ship to users.
And what you put out for inference is typically distilled from that, which gets you quite a bit, right?
Look, I think it's something we don't do right now because of like...
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 engineering component of like a bigger model and every kind of order of magnitude size, you'll 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 a progress for us to way 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 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 model, wait six months, train another bigger model.
You would be compounding so many changes of improvements.
that 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 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 deep learning for large language models.
But we are all, I think, 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.
Amazing.
I was going to end off with a little bit more history.
You spent some time looking at metrics for engineering team productivity.
How do you think about engineering team productivity today?
I mean, it's wild, right?
I mean, 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.
I don't know, to me...
Like, how do you measure, you know, because literally in a...
Yeah, you're doing this.
Look, I think it's a good question.
It's one I haven't thought about in a long time.
But, you know, you're pretty qualified to do it.
I'm going to...
No, it's a fair point.
Let me take a second to think about it.
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 delivering that value.
And I think what we're doing with these models becoming more capable is that we are massively 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 staying in the back walk 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-LM still apply.
And it's just a notion of cycle time.
In this case, it's lead time from The moment you have a valuable thing that you are 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 kinds 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.
potentially 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, you know, pre-LMH.
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.
Is there a way to eval that when you're interviewing somebody?
Oof.
Because that is, you know, the most compressed version.
I think the common answer to this is agency.
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 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 showed agency and your personal backstory shows a ridiculous amount of agency, right?
Like, I think that is ultimately it.
It's the...
The Silicon Valley, you know, quote of the of the last, you know, year and a half or so.
So you can just do things.
Right.
Yeah.
That's, I think, what you're looking for.
I think then aligning high agency people is very hard because they all want to go their own way.
That's the whole point.
Right.
Yeah.
But I think the the notion of 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 want to do with 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 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 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 it becomes political about gathering the resources.
So when you say, this is our common goal, and these are the boundaries that we've set, right?
We're not multimodal.
We focus on RL.
We do these things.
And you're upfront with people before they join the company.
You know, you get a lot of agency.
You can run where you want, but these are the places where we say, this is the lanes that make sense.
I think it actually gets the best out of people because like innovation comes from constraints.
We did this with relatively little computer and 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 access that might others might have not.
Right.
We, we purchase relatively little external data.
I was going to ask about that.
Exactly.
Right.
That was a constraint, but it's a constraint that pushed us to move on other areas to improve.
And like, and there's lots of versions of that.
So I think high agency people, you want to empower, you want to get them really excited what they're doing, but you also want to 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.
And maybe if you care about those places, go somewhere else.
Yeah.
Great.
Last call to action.
Who are you hiring?
We are hiring on every possible role in applied research and engineering in the company.
So from pre-training all the way to evals, to post-training architecture, like we are still in a world where, you know, individuals can have massive impact.
And I think our pitch to join us.
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.
Less than 70 people built this model, less than 115 in engineering and researchers together 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 source the model.
Yeah, look, all of those things are part of that.
But I think ultimately, you can today pick between joining a very large foundation model company, but you are one of many.
And not by any fault of them, but just by definition, the denominators 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 if today you heard about the mission and aligned and you're optimizing for impact, I think we're a really good place to join.
Okay.
I think we ended there.
That's the most fantastic.
Statement.
You did amazing on four hours of sleep.
Thank you, guys.
So, you know, podcast, Evel, definitely.
I literally did it.
My eyes are starting to go like this.
I'm like, well, let's go.
Let's go back.
It was good to see you guys.
Thank you for setting this up.
We wanted to get this in because we think it's a great model.
And I think it's a great story to tell.
Thank you.