0:00My job is to make the tokens as cheap as humanly possible. I will achieve that and I will do it through every layer in the stack available to me. I love the supply side levers. I will use every chip. I'll use every source of power and I will use every piece of land in the United States that's, you know, suitable for this. We still treat the agent as a person that is expensive to consult and you should ask them when you have a hard question. That's not the way to think about intelligence. It's incredible that the machine can think and we should [music] try to get that into as many hands as as many people as possible.
0:32[music] [music] I think it's important early in these conversations to just say the thing like literally what you're building and what it does today. So maybe just orient us there with a with a brief description like literally what the system is that you're building and why it should exist.
0:51Sal research is a token factory. We have an API where anyone can send us requests where they can use large language models, open source large language models for any task they want. Um, we will serve those tokens to them at a price that is unbeatable in the market.
1:05We also support their ability to build agents on top of this. We host what we call sandboxes, which are longunning agent virtual machines hosted in the cloud that are designed for agents that run for hours, days, or weeks. And so you should think about you as a peer company to others that serve different kinds of inference. You're serving one specific kind of inference and your goal is to be the absolute cheapest provider and enabler of a certain kind of use of intelligence.
1:30Exactly. The theme of our company is abundance. We want to deliver this new commodity of intelligence to as many people as possible at a at a cost that is sustainable for almost every industry. We think that whenever you make something 10 times cheaper, it's a new product category and uh we aspire to do that for tokens. We think it's so profound that the machine can think and now our job is to make as many machines as possible in the world work towards thinking.
1:53So if you think about uh the theme of the day being token costs is token cost the right way to think about this like is there some other way you'd put it to start with? Absolutely. Token cost today my north star is I want to have the lowest cost per token in the industry and do that by a mile. I don't think tokens are the final unit of uh of work or intelligence but they are what we use today and so it's very straightforward. I think after tokens you start to move more towards um more outcomes which is like a vague direction. Uh you can imagine for example today when you consume tokens
2:22through an agent you don't actually control how many tokens the agent reasons for. It can reason for a certain amount of time or it can call a certain number of tools and increasingly I think we will have agents do some unit of work take as many shots on goal as they can and however many tokens they use to get there is going to be kind of a dependent variable depending on the task.
2:42So you think about like agents that selfadminister a token budget as opposed to a company setting a budget for how many tokens engineers can spend per month.
2:50Why is there an opportunity that you can tackle it? It seems like the entire world is oriented around more better faster cheaper tokens. Right now it seems like the world is trying to solve this problem very aggressively.
3:03What was the unique opening that that you saw that's maybe the market's not being efficient in its attempt to tackle this? So I think there's two things that are tailwinds for our company. One is got to be the rise of open source. I had to talk about that first. I think we are starting to see an increasing number of our customers and the broader market care about owning intelligence. They they want to have control sovereignty over the thing that they depend on. Uh and so that created a much more robust market for customized models or even just like these vanilla open source models that no one can ever take away from you. You always have the weights.
3:32You always have the right to deploy them however you like. uh in that world there's been a reasonably robust market for the past couple years uh serving these models at large scale. The challenge is all those companies, you could take your pick, base 10, fireworks together, they all focus on low latency inference, and they were pulled in that direction by one very important customer, uh, cursor. And [clears throat] I think that that was the right choice about a year ago, and as of six months ago, it started to look like maybe low latency wasn't the only thing you wanted
4:01from an agent. You wanted more persistence, more long horizon tasks. And now, it's to me very obvious that the future of agentic inference is long horizon tasks. You're going to run the machine for hours or days at a time. It doesn't matter if it spits out tokens at 100 tokens per second. Maybe 10 is just fine. That comes with corresponding advantages and efficiency.
4:22Why are you so confident in that? It's it like to me it seems like I want everything as fast as possible.
4:27When you're waiting on it, you absolutely deserve the fastest answer possible. My trick is I don't want you to be waiting on it. I want it to be proactive. I want it to be in the background. One way to say it is like the best latency is no latency at all.
4:37When you wake up in the morning, the work's already been done overnight. you didn't even have to ask for it. Uh that's the dream. We're not quite there yet. But more importantly, I think the more you're in the loop as you prompt agents and wait for a response, in fact, you're the bottleneck uh in helping the in having the agent do more or less work. What we'd like is the agent to operate on more human time scales. You don't manage your colleagues every 5 minutes. You ask them to do a high level task and you come back and check in maybe every day, but more likely once a week. And that to me is the future of human agent collaboration, more like
5:07human time skills. say more about the early indications that this is happening and therefore you should be building this company.
5:13Well, so the first and most important thing is the idea of test time compute scaling. Uh the idea that you can give an agent more time and it will give you a better answer. So that was theorized about 2 years ago now and uh but it wasn't really something that we could actually bet on until I would say late last year with Opus 45. Opus45 was the first agent that was at all suitable for longer horizon tasks and you know it was pretty mediocre and when it first came out but you look at the more recent models and what we've done on open source as well and you see that agents are capable of running for an hour at a
5:43time. I wouldn't say it's days but definitely an hour is quite suitable today. And so just seeing that like average turn or task length get longer and longer uh it doesn't take many points to have you kind of draw out the exponential and see that agents are worth running for longer periods. What what do you think will be the market share of longrunning agents in 3 years or something like this?
6:02You know, I love this market because it's unbounded. There's no human in the loop. So, you can consume as many tokens as you like in the background. Uh versus human attention span. If you tell me to consume 10x as many tokens at codeex or at cloud code, I'm actually not sure if I can anymore. I'm already in a loop and locked in coding for most of the the day that I'm at the laptop. What is undowned is how many tokens can be consumed in the background or proactively. So longterm, I think, you know, we're going to end this year at maybe 50/50 background and uh and real-time workloads, but I see this going to 9010
6:31in favor of background.
6:32What are the sorts of things like what are your favorite examples of something that gets accomplished much better as a background task than as a human in the lip task?
6:40Most deep research, most questions where you want to have a definitive answer over not 100 sources, not a thousand sources, but 10,000 sources or more. If you want to build an authoritative index of information like for example one of our customers parallel web systems seeks to do. They want to build an index over the whole internet and they want to monitor the internet in real time for changes. That is the kind of crazy exabyte scale task that you need a very different kind of intelligence or scale of intelligence to achieve. Deep research is a top category for us and
7:10then increasingly we see cyber security following this direction. If you think about, yes, there's so much code you can generate, but there's uh exponentially more ways to break that same code than it is to generate that code. And there are some great customers out there who are working very hard to uh find agents that can break any piece of software and proactively patch them. So when Fable first came out, for example, or Mythos first came out, basically there was this push in the cyber security community to run Fable against every line of code we've ever written and look for bugs in
7:3920 different ways. uh meaning you're looking for both memory errors, you're looking for business logic errors and looking for like network vulnerabilities, all these things. And these are all actually things that you would write specialized agents for. You wouldn't just have Fable look at the source code once, you'd have it actually set up environments where you can pen pentest these applications. And at some point, people started to make this joke that security has become proof of work.
8:01When you want secure software, it's really a question of how many dollars did you spend on anthropics APIs trying to break into your software. uh that is the best indication for how secure it is because that's the best tool in the world. And increasingly we found that the frontier of intelligence here is quite jagged. It's not the case that Fable finds a supererset of all bugs in software. You would find some bugs with a very small model that you don't find with the large model. Uh you'd find some bugs with Haiku that you would find with Fable and vice versa. So it encouraged this very diverse approach to sampling
8:30and trying to build cyber security agents that break software autonomously such that you can patch them. If you were to get sort of like speculative and imaginative about the sorts of things that longunning very cheap very longunning agents can enable. We talked about some very practical examples deep research um cyber security etc. But if you if you get a little bit dreamier about the use cases new product category that this sort of inference will unlock and I guess the question is just like so what like what if you're maximally
9:00successful dream a little bit about what that might enable.
9:03Yeah absolutely. So I think for individual users what I'm excited about most is this idea of proactive intelligent agents. Um you can imagine Siri that is running in the background all the time to understand what's all the emails you received in a day, all the text messages you receive in a day and and has a much more encyclopedic view of your life and how to be helpful in that life. Right now there's still point solutions and so you have to you end up doing a lot of prompting. Siri is not very proactive. That's something we can fix with abundant abundant inference. If you trust uh the machine enough that it's reliable and also
9:33trustworthy as in private um you might even imagine the machine can understand how you interact with it and proactively surface your next action whenever you open your phone. Can we build a good model of what you're going to do next?
9:44My estimation is yes, we totally can.
9:46And the key to that is incredibly cheap intelligence.
9:48You have to be willing to spend tokens without any promise of return. That's the unlock. The long lens view to take on this is that we have we have a form of intelligence that can tackle any verifiable problem. Any verifiable problem means most software. It means a lot of formal like math proofs and similar. And it could also mean scientific discovery. These are all relatively verifiable problems. And all those things currently have a dollar
10:17cost attached to them essentially.
10:18That's a hidden one. It's like how many tokens could you possibly harness to make this work? And we have actually started to bring it within view a dollar cost for these long horizon tasks that is reasonable. It's not millions, it's thousands and maybe it could be hundreds or even tens of dollars in the near future to have a definitive answer to any scientific question to any research problem. RAMP is the only platform built to make your finance team leaner, faster, and better, saving businesses 5% annually on average, so you can stay
10:48focused on growth. RAM customers grow revenue 3.2 two times faster than the average American business. Visa, Verscell, Kerser, Stripe, Notion, 11 Lab, Shopify, and 70,000 other businesses all now run on RAMP. Mine does too, and so should yours. Learn more at ramp.com/invest. OpenAI, Cursor, Anthropic, Perplexity, and Verscell all have something in common. They all use work OS. To achieve enterprise adoption at scale, you have to deliver on core capabilities like SSO, skim, arbback, and audit logs.
11:19Instead of spending months building these missionritical capabilities yourself, you can just use Work OS APIs to gain all of them on day zero. That's why so many of the top AI teams you hear about already run on Work OS. Work OS is the fastest way to become enterprise ready and stay focused on what matters most, your product. Visit works.com to get started. Felix by Rogo is a personal finance agent that turns a single prompt into [music] finished client ready work using your firm's own templates, context, and standards. Send Felix an email like, "Take [music] these comments
11:48and turn them for me." Or, "Udate my tracker with the context of these emails." And Felix sends back finished [music] PowerPoint decks, Excel models, and sourced research. Felix works the way your team already does, delivering [music] work quickly and accurately around the clock. Learn more at robo.ai/felix. [music] And so, if we dream about that future, we're we then become limited just by the questions that people can ask.
12:11Basically, pretty much the questions we can ask. uh the models are on the cusp of basically taking even a high level question and chasing it down every possible follow-up you can have the model essentially take that on its own and the question is what is your token budget and we will solve the token budget problem what about non-verifiable tasks I put basically the entire category of human taste into that category we have not solved human taste yet and I don't know that it fundamentally can be I'm excited to be surprised here but um we
12:40are focused on very quantitative uh problems we leave the quality of writing we the uh the beauty of art to to people.
12:47All right. Now, let's talk about the uh the very clever stack of solutions that you hope to build ultimately to have this giant token factory, extremely lowcost intelligence supplier of extremely lowcost intelligence.
12:59I think you think about this in terms of level software, hardware, uh and power.
13:03Talk through what your master plan is to approach this challenge that's so different from what others are thinking about doing.
13:09You know, we always have to start with software. you know where is the opportunity on today's chips with today's data centers to improve efficiency and the first thing we did was we tried to build the entire LM software stack around peak GPU efficiency meaning we're using Nvidia GPUs we wanted to squeeze out more tokens from the same chip than anyone else in the world and that starts with the lowest level of programming kernels it's actually my background I spent my whole life actually uh my whole professional life working on GPUs and kernels in Nvidia was my first job while
13:37I was in college and uh I got to see how the tensor cores got to earn their right to be on the chip. This is back in 2016.
13:44Just describe what that means for for the lay person.
13:47So, okay, tensor core is a specialized unit on the GPU that accelerates matrix multiplication.
13:52Simple as that. There's been a long history of how we evolved at tensor core over time that we'll get into.
13:56And why is matrix multiplication so important?
13:58That's a great question. I actually I cannot say that there is a divine truth of the inverse that explains why matrix multiplies seem to be the atomic unit of computation. But uh one way I've heard it described to me is well it's a really succinct way to mix two blocks of numbers together and have them interact in some interesting way. That's as much as I can say about it. It is really convenient that linear algebra turns out to be a very compact representation of arbitrary relationships in data. So Nvidia great graphics company obviously has had market share dominance in GPUs
14:26and and gaming graphics for quite some time. And then starting in like the mid2010s they started to actually start these like skunk works projects to make the graphics processor more suitable for machine learning tasks that they were tracking. I remember actually reading some of the like lab notebooks of some of my managers when I was at Nvidia.
14:43they would visit these small ML conferences like ICML or NURPS at the time and they would just take note of these papers like oh this deep learning thing seems to be catching on and what's really interesting is that these grad students are using gaming Nvidia GPUs in order to train their large models we should double click on this and figure out what's going on here and by 2015 2016 at least Jensen had the conviction to to kind of double down on hey this usage of our models is only of our chips is only going to grow let's start
15:12allocating more and more precious silicon die area to this capability that seems to be emerging. Let's put the first version of tensor cores on the chip. So, we're talking about, you know, taking this gaming chip which is designed for painting pixels on a screen and adapting it to do metric multiplies and it was early and you would be competing against the graphics teams essentially when you ask for more silicon area and any chip company.
15:36There's always competition for that. It is something that that the designers guard so carefully. you don't ever want to invest in the wrong technology because that's opportunity cost that you could have allocated to some other functionality. And so we we kind of like fought and tooth and nail and got just a tiny bit of diary maybe like 5 10% something like that for the first generation of these chips uh to get some some amount of acceleration for basic convolutions which were the fundamental operation for computer vision models in
16:04the day. Uh, and then we had a software team that was trying to squeeze all the performance we could out of the chip.
16:11And I think on that software team, which is where I work, that's what actually taught me the most about um, just the ethos that Nvidia has around they have this term called speed of light. They always chase the speed of light for any piece of hardware that they make. It is so ingrained in every engineer's mind that if the machine can do it, we're going to push the machine to the frontier until it does what we think is.
16:29And the speed of light is the edge of what's possible.
16:31The speed of light is the edge of what's possible. Exactly. uh if we think the chip can run at this frequency and produce this many multipliers per cycle, we're going to get there. We're going to break every bottleneck and get to that peak level of performance. And so to this day, I tell all my engineers like we're chasing 100% speed of light. I don't care about relative numbers versus the competition. I only care about absolute numbers. Uh what are we able to do on the chip and how do we achieve that?
16:51Before we leave that chapter of your time at NVIDIA, anything else beyond that cultural touch point that really like changed the way you think about things or that stood out the most about how the business ran back then or its culture? I have a ton of stories about Nvidia. We can I can tell you a few of them. Um, one of my favorites is that on the tenure side, a lot of people I worked with in Nvidia in 2015, 2016 are still there today. That company has incredible retention and these are the best engineers uh, frankly on the silicon side at least I've worked with in my whole career. They're extremely extremely motivated and passionate.
17:20They've believed in parallel computing as a concept through its various incarnations and have loved seeing the chip evolve. This is their life's work and they're extremely extremely competent in that direction. They're also a very frugal company. Nvidia and all, I guess all the Silicon Valley companies after 2008, they had some cutbacks and like perks. So, no free lunch. Uh, for example, Nvidia took it one step further. There was no free milk in the fridge. So, if you wanted to drink coffee at Nvidia and you wanted some milk, you actually had to chip in a dollar every month to the milk club and
17:49the milk club would stock Costco milk in the fridge. And I remember that distinctly. We don't do that at sale, but uh it's a it's a frugality that permeates the company. And so coming out of this time there, you get this experience of what it's like to develop more efficient usage of the underlying hardware through software.
18:06And so so link that to, you know, today's environment.
18:10Yeah, absolutely. So, so I think um the GPU is fundamentally a throughput machine. The GPU is happiest when you give it a lot of work to do and let it chew through that work at peak utilization of its compute units. But that's actually not the way that we've taken AI in the last couple years. We've really pushed AI to be an interactive chatbot tool is the most common form of AI usage today. And in that world, you care a lot about actually spitting answers out to the to the person at the keyboard as quickly as possible. To your point about don't make the user wait, I want things as fast as possible. And so
18:38that's actually quite interesting for the GPU. It's very difficult to put the GPU in its happy path of being fully compute utilized when you're trying to spit out tokens quickly. There's a fundamental trade-off on the GPU between being uh throughput oriented or latency optimized and everyone has chosen latency optimization because the shape of usage was chatbot oriented. I believe that's the most profound change we're going to see in the next year. We're going to move away from chatbots to more proactive or background agents. And in that world, it makes a lot more sense to
19:08build a stack around throughput.
19:10Can you explain technically why the trade-off between throughput and latency is unbreakable? Why can't we have both from the same hardware? It's quite foundational in almost every system that you could ever possibly look at. There's always a trade-off between getting a small amount of data through the system as quickly as possible and leaving a lot of buffer uh room for that or trying to run wide and slow like narrow and fast or wide and slow is like a classic trade-off in all computer science. But for GPU specifically, I think there's one thing to focus on which is there's this concept of like batching on the
19:39GPU. We want to group many users work together into a batch that we can uh run all at once on the GPU. That's the parallel processing of the GPU. We'd like to have a lot of parallel work to do. The thing is though, you're doing net more work when you run a large batch of compute together. And so you might be filling all the units, but every step along the way as you carry a a batch of work through the GPU, there's more work to be done. And so any individual token or any individual user's request in that
20:08batch, it's going to spend a longer time on the GPU being carried with other people's traffic. Maybe the way to say it is um you know, if you want to get downtown and SF, you can take the bus or you can take a private transit. And the private transit is going to have its own direct path as the crow flies or you know, using exactly the roads that you want from point A to point B. a bus, it's going to have to serve many more people and it it has to fundamentally uh do something that works for everyone and so it takes a slower path and it stops and and waits for other people to get on and off. I think the bus versus
20:37car analogy is pretty accurate and it's a great analogy and so step one for what you're trying to do is like create the best possible bus on top of Nvidia GPUs. Like that's step one of your optimization.
20:49That's exactly right. It means we explore things like different parallelism schemes. Maybe that's another example I can give you is um with Nvidia GPUs, one of the things that they've really innovated on and done a great job with is the NVLink uh interconnect between GPUs. And in fact, that NVLink system is so good that you can if you have a large matrix multiply that you want to perform faster. You can actually cut that matrix multiply in half and shard it [clears throat] across two or more up to eight, let's say, Nvidia GPUs and have them all work on
21:16pieces of that larger matrix multiply and have them connect their results together at the end. Reduce their results back together at the end. And this is a great great way to cut the minimum latency of of an operation.
21:29You're each GPU is now doing 1/8 as much work, let's say, uh, and therefore it can finish faster but not eight times faster. It's sublinear scaling. You'll use eight times more hardware, but you won't get eight times the speed. You might get like four to fivex the speed. You're not going to get strong scaling.
21:44And this is because of communication overhead. It's because every GPU is going to be a little bit less efficient working on a smaller tile of work than a larger tile of work. And so, it's the only way to speed up if you want the minimum latency possible. You can do that, but it is not the choice I would make. For example, I would prefer to use a different parallelism scheme like expert parallelism or pipeline parallelism. And we may do interesting things to overlap and hide the communication latency in a way that you would have less ability to do that for a low latency server.
22:12So is the right way to think about NVLink as a technology which improves latency performance? Yes.
22:16And only latency performance which will segue into the next segment of what we you know do differently as a company. But yes, NVLink is mandatory I would say for low latency inference.
22:26So Nvidia is excellent at low latency inference. And I'm telling you that we don't really care that much about low latency inference. So where does that leave us? Well, I think I'm not holding my breath for other companies broadly to figure out NVLink quickly. It's a challenging technology to figure out.
22:40It's hard to scale. It's hard to productionize. And so, if I do have some other vendors chip and it is good at the foundational compute components, it can still do metric multiplies really well.
22:49It just can't communicate those results across its peers quickly. Well, maybe there's a room for that other chip in my stack as a really really good compute per dollar option. And that's what I actually optimize for in most cases is how many flops does this chip have and how much is it going to cost me per hour to operate to own and operate. Uh and so there are other chips that definitely rank higher than Nvidia on flops per dollar, but they may not have as much interconnect. And so it's my job to figure out what parallelism scheme am I going to use that's going to make this
23:19chip suitable for inference. It's not going to be tensor parallelism. Nvidia is basically mandatory for that. But other techniques may work well for me.
23:27So before we leave the latency part of the story, can you comment on companies like Cerebras or others that can perform incredibly fast operations? I'm curious like what you think about those approaches, those companies, what might happen in the future. What is your prediction for the future of very low latency focused hardware? Cerebrus Grock uh and a couple others that are coming out of stealth now I think have made a very interesting bet on not just building another GPU but actually building a different kind of accelerator that focuses on a different memory
23:56hierarchy. Uh they want to maximize the amount of SRAMM on the chip and use that as very very fast memory for for weights and KV cache. So SRAM versus DRAM there's two ways to make memory for a chip. One is to integrate the memory on the logic die itself. Like meaning you tell TSMC, I want this many megabytes of of storage on my chip. Uh and there's a way to build that. TSMC has a standard cell library you can use and you can just print out a bunch of cells of SRAM.
24:23The problem with SRAMM is it takes a lot of area on the silicon die. Um, so if you want to build a large die like let's say the Nvidia Blackwell at 800 mm square. If you made that whole DS RAM, it would be in the maybe like singledigit gigabytes, it's not a crazy amount of of data storage. Compare that to if you're willing to take a different process technology entirely. So not TSMC anymore, but now Micron SKH Highix Samsung. They build DRAM, which is a whole different way to build memory
24:51that's more focused on capacitors than transistor cells. So, SRAM, the standard way to build SRAMM is what's called the 6T transistor cell. It's a stable transistor arrangement that allows you to write a bit to it and then it holds that state in that bit regardless of whether you keep applying. Well, you had to apply some power, but uh it it's holding that bit without any sort of like active management. It's static.
25:12Now, dynamic RAM, DRAM, it's dynamic because what you do to write some data is you write a charge onto a capacitor and as soon as you write that charge into that capacitor, the charge is dissipating. it's been leaking. And so the dynamic part of DRAM is that you must every 50 milliseconds or so refresh every bit you've written. So you're constantly juggling billions of balls in the air essentially billions of bits have to be managed by a memory controller which is reading and refreshing every bit on the DRM. Now the benefit of that is you can get much much higher density and it's a whole
25:42different process technology. There's a ton of different trade-offs. Hence why we split the DM manufacturing into an entirely different company like Micron SKX and Samsung. These are the best companies in the world to do this. They build DM. And if you take DM from those companies and you stack it uh into many layers and you kind of print them or or solder them around the main logic die that you get from Nvidia, you can now get hundreds of gigabytes uh like Blackwell has 288 GB of HPM capacity
26:09around the logic die. And the logic die itself maybe only has like 500 megabytes of of SRAM. So it's possibly multiple orders of magnitude, three orders of magnitude difference in density for DRAM versus SRAMM. Okay, so let's go back to Cerebras. What are they doing? Well, they see this problem, there's not really an obvious way to increase SRAM density on the chip. But thing with SRAMM is because it's so physically close to the logic gates that actually do the computation, the arithmetic logic units are right next to the SRAMM that
26:39they're going to pull from, the compute units that are doing the matrix multiplies can pull data from SRAMM at just mind-boggling speeds. You know, Serbis quits pabytes per second, 21 pabytes per second further away for scale engine 3. And so compare that to HBM on an Nvidia black wall is u you know 10 terabytes per second or so in that range. So once again, many orders of magnitude difference, more capacity, but proportionally less bandwidth essentially.
27:04And so what Cerebrus does is they say that we're going to take as many of these dies as we can. We're not going to limit ourselves to the 800 millimeter u reticle limit, the TSMC 800 square millimeter limit that TSMC imposes on us. We're going to take the entire wafer and have actually every die connect to every other die over scribe lines. And we're just going to try to get as much SRAM as we can on the whole wafer. and we can get to like let's say 50 gigabytes of SRAM per wafer and then we're going to stack many wafers
27:32together in a pipeline or similar and now we can have you know up to a terabyte of memory very very fast memory and you do all that work just to get to the ability to read data from SRAMM at yeah 21 pabytes per second per wafer therefore you can now serve these language models at extremely high tokens per second because you can move the entire parameter count of a large model like Kimmy uh you can move all that data in and off the chip or sorry in and off the logic cores in about a millisecond
28:02or something like that.
28:03So there you go you have a path to a thousand tokens per second and so what is your prediction for like that segment of the market? Okay. So I think what happens to them is some hybrid sort of outcome like we we had to pair the Cerebras chip where it's very strong. It's very very good at fast access to memory with something that has more capacity for memory because it's true that you can take a one trillion parameter model like Kimmy and fit it on a large number of cerebrus wafers. But
28:31you can't do something about the KB cache very easily. The KV cache is something that grows as people use the model more and that is always dynamic. You don't even know how much KV cache you're going to need. It depends on what your users how many users you have and how many users you want to serve.
28:45Can you explain KV cache just like in basic? Yeah. So KB cache whenever you use a language model every token you send through the language model actually uh stays in the context window of the language model for as long as you're having a conversation. So if I we talk for 100,000 tokens, the 100,000th and oneth token is still in the conversation uh behind us and the model is referencing all the past conversation history in order to make better predictions about what the next thing
29:13we're going to say is. And so that KV cache is a bunch of memory. Um you have to store a representation for every token that you send through the language model. And it frequently gets to be larger than the weights of the model themselves. You have this like crystallized knowledge in the model weights and you have the dynamic knowledge of the exact conversation we're having in the KB cache is the way I like to think about it.
29:35Yep. And and this is why sometimes people would observe like deep in a conversation things start to degrade because there's some sort of like technical problem.
29:42Yeah. So the KB cache is quite interesting in that regard. The KB cache is an exact representation of everything that came before. We we store all the information that we've seen in the conversation. However, during training, the model did not get trained primarily on very long context conversations. It got trained primarily on, let's say, 8,000 token conversations or 16,000 token conversations. So, if you take the model to 200,000 tokens, there was some training that happened at that context length, but it's not the model's like core strength. And so, there's there's
30:11always been a challenge for the Frontier Labs to figure out how do we make the model exactly as intelligent at 10,000 tokens as we expect them to be at 200,000 tokens. And it's going to be a perennial battle for us. We've had 1 million context windows as a concept for for years now. Enthropic was I think the first to hit the 1 million context window length. I still, you know, use /compact in my cloud code uh well before 1 million context length. I don't think it's actually great to hit the full length.
30:34And so these extremely fast, extremely low latency approaches ultimately are limited by by this factor.
30:40Yes, you can do whatever you want for the weights. It's very possible to have just unbeatable performance on weight storage. However, the KB cache is going to be a big thorn on your side. And so three years from now, five years from now, what role do you think these kinds of chips play? Like what sort of market share do they have in the heterogeneous chip market?
30:57Crisis and Grock and maybe a couple others, you should think of them as accelerators. What they are really good at is being used in conjunction with an more traditional GPU like device that critically has this offchip memory built in. You want offchip memory for capacity and onchip memory for speed. We want to hybridize these two things. So if you take uh transformers in the limit, you take a transformer to a million context length. What ends up happening is you have this you know computebound stage which is the actual matrix multiplies
31:26for the uh what we call the MLP which is where most of the model's knowledge world knowledge is encoded and then you have the attention layer which is where we're kind of dynamically adapting to the current conversation. Attention in the limit is usually memory bound and the MLP in the limit is computebound at large enough batch size. And I would say the original sin of transformers is that you've taken this extremely fundamentally memory bound layer and juxtaposed it right next to a computebound layer. It is very difficult
31:54to have a single chip that is good at both compute operations and memory operations. The GPU is quite balanced in this regard, but you have to choose one or the other. Cerebrus has a very fast memory access for something like a matrix multiply and it's really good to host the the MLP the the weights essentially on the Cerebrus chip but the GPU has the capacity to scale to really long context lengths and so you would like to put the uh attention possibly on the GPU and the MLP on the cerebrus chip and I believe this is what's happening
32:24with Nvidia and Grock. Can you riff for a minute just on transformers and uh yeah, you've been so good at explaining some of the core concepts just for people that again aren't aren't deeply familiar with what this innovation was in 2017 like what its strengths and weaknesses are and whether or not you think it will remain the dominant architecture or a dominant architecture for the future of AI. What it did was it it allowed us to learn an unsupervised data really effectively because transformers what they're all about at the end of the day
32:52is taking any sequence any arbitrary sequence of data and trying to find patterns in that data and they critically the attention operation which is the headline uh component of transformers. It allows the model to dynamically adapt to what it thinks is the most relevant component of the sequence. every step you take through a transformer, you are essentially like reweing the input that you looked at before and figuring out which is most relevant for your next prediction. And
33:22so it it's extremely amenable to uh learning arbitrary sequence data. And the most interesting sequences of data that we produce on a regular basis is language and that's how we got to dominance in the language regime. But uh to zoom out even further, I think what transformers really did well is that they scaled. Transformers make no such human prior.
33:41Transformers just say, "Well, there's going to be a pattern in the sequence of data, and if there is a pattern, I'm going to find it. I'm going to throw more and more parameters at this problem until it works."
33:50Uh, and transformers benefit from a lot of the computer vision work, too. For example, one of [clears throat] the challenges in computer vision was we had a hard time going from hundreds of thousands of parameters, which you get for like linear models like support vector machines or other legacy machine learning models. Those had, you know, on the thousands of parameters. Then we got to deep learning and got to tens of millions of parameters with computer vision. The biggest models were you know around like 150 million parameters was a huge model for computer vision. And now we routinely talk about trillions of parameters and transformers are the link
34:20to go from millions to trillions of parameters.
34:22And so if I think about the important units of scaling being data and compute does it stand a reason then that you think transformers will just stick around because that's the thing that we're good at getting more of those two things. Well, data is an open question, but comput. Yeah, transformers are so they're just such great sponges, you know, like you you you increase the compute available to a transformer by 10x and you'll get you'll get some log improvement somewhere. Uh and and so far the scaling laws really work. They're really quite beautiful. And to
34:51[clears throat] the point about I guess what do transformers do really well?
34:55They extend to almost any data set you can throw at them. They're extremely powerful general learners. And I think what's especially useful about transformers over other techniques that we've tried to replace attention is transformers represent any pair wise relationship that you want. Any token in the sequence can attend to any other token in the sequence. So if there's any relationship that's in the sequence at all, you're going to find it with transformer. Now it may be the case that you don't need all toall modeling. You don't need every token to look at every
35:22other token. But if you need to, transformers give you that option. And until we know a better way to kind of prune that space down uh a better way to kind of have information modeling be more selective attention is a very very good operation. This is another kind of trick that we learned in the computer vision days. Like one of the old Karpathy sayings is that you know if you have a new data set that you want to train a model for. Your first goal should be to overparameterize the the model and try to overfitit the data that
35:51you have to prove that there is a relationship that you can model or memorize that your learning algorithm works uh that you can instill knowledge into the model. Once you can overfit then you can compress and the compression is how you get generalization. You don't want to actually memorize the data that you have in front of you. you want to generalize and therefore once you overfit the data set then you can kind of work backwards and try to find the general patterns that fit into the smallest parameter count possible.
36:14What's your prediction for the future of data and riff on the importance of data in this whole story? I like the phrase that internet was a onetime subsidy on data. We got it for free. Uh it's extremely high quality about 30 trillion tokens of high quality text. Uh 300 trillion tokens if you take a wider view on what qualifies as good text and we've basically looked at it all already.
36:34Models have seen the entire internet many times over at this point. And there is not a whole lot more to be done on human data from the internet. The next phase of data in my mind is model self-improvement through RL environment gyms. Basically, in fact, we don't even benefit from getting more like random user interactions with AI. It used to be that, you know, the the new type of data that we cared about a lot was the interaction data from people using chatbt and giving TetBT signals on what they liked and didn't like. I like the
37:03argument now that the median model that we serve is so much more advanced than the kind of un than like a random human uh giving feedback that the signal you get from random human preference or I guess unconditioned human preference is not actually worth anything anymore. You want expert human preference at this point. The model has outgrown everyday generic Yeah. Everyday Joe. Exactly. So the feature of data to me is giving the model a hard verifiable task and letting it run in this gym where it's kind of
37:32isolated and it just has a a problem that it can make progress on and get measurement of whether it made progress on that problem or not. You can imagine coding problems are in this category.
37:40math problems are also in this category and um increasingly more and more we have we can just give the agent a computer essentially and have it act like it's a human worker and just give it feedback on whether it's making progress towards the target outcome that environment becomes the data. I think this is not a super differentiated take but uh it's been really really productive from what I've seen so far.
38:01And you think that just goes on for a really long period of time or is that another like if I think about the internet as this one big block like this is another big block that will have its you know day in the sun and we'll kind of get it all and and then we'll have to move on to something else.
38:16I think it's actually more profound than that. Basically the idea is that if you want artificial general intelligence the best way to get there is to just keep stacking specialized intelligences until you have no more gaps to fill. And the test here, the only thing you need to make sure you do to make this work is you must make sure that your task is verifiable. You need to give the model a self-grading system. If you have that, you have the recipe for self-improvement on any task you like. And I think you've seen this held up by the way frontier
38:44labs spend. They used to spend much that much on data. Now they spend a lot more on RL environments. And these environments absolutely capture that relationship of recursive self-improvement on a verifiable task.
38:55Okay. Okay. Now, so I like that we've veered off in different little side cars here, but coming back to your initial task of making existing hardware more efficient.
39:06By being more in control of what's going on at the hardware level through software.
39:10Um so, so yeah, just keep going on what you've done so far and what you want to do and then we're going to jump to hardware and then jump to energy finally.
39:18Sounds good. So, yeah, I mentioned kernels. It's surprising people think kernels are done. There are great people like Triau who write excellent kernels and they're they form the bedrock of all of our um modern deep learning is built on flash attention. Modern transformers are built on flash attention. But if you deviate from the happy path at all, if there's a new model that comes out that has a slightly different way to embed positional information like the change of the rope system. Suddenly the kernel that we had is not suitable for this new model and we may have to make a a patch
39:47to this kernel. I wouldn't say we're in the phase where we had to invent new kernels from scratch, but having the ability to quickly modify existing GPU kernel, sorry, a kernel, by the way, is a it's a general term for any program you run on the GPU. And so, historically, kernels tend to be put into a library where every kernel has a very very scoped purpose. Typically, you have a kernel for a matrix multiply. You have another kernel for even something as simple as addition. You want to add two tensors together, that's another kernel.
40:15[clears throat] And then increasingly we've started to fuse those kernels together. So if I do a matrix multiply and then I want to add it to another matrix that I've also multiplied maybe those two become one kernel and I just fuse the operations where instead of writing the data out to DRAM and then reading it back in just to do the addition maybe I can just do this uh easily.
40:33Why are humans still doing this? Like it seems like the sort of thing that AIs would be exceptionally good at engineering more efficient kernels. Maybe that's where we're going and we're just not quite there yet. But if if we aren't there yet, is that where we're going? If we're not there yet, why why humans still doing this? Why why is Tree out so wellknown? You know, it's a name I know.
40:51I don't want to speak for Tree, but what he taught me was uh you shouldn't write kernels by hand anymore necessarily. I like to say we write kernels in the whiteboard. We go to the whiteboard, we describe what we think the machine should be doing, then we succinctly describe that in in natural language to the a model. And then the model is able to do the execution of okay, here is my input and output. here is the strategy of how we want to dispatch this work onto the GPU. I'm gonna go implement this.
41:17So, we're doing the conceptual design.
41:18Exactly. And that I think I'm not sure exactly why models are not superb at doing this. I don't think this is like our remote or anything like that. I'm sure in 6 months time we'll have much better models uh on kernel engineering and I'm sure the labs would tell you that they already do a lot of their kernel engineering uh in a fully automated way. And so software as an edge, yeah, if I think about software as maximally near speed of light, efficient usage of of an underlying piece of hardware is is going to trend towards not being an advantage for a company like yours over time.
41:47That's right. The rising tide of something like Mythos or GBT 5.6 Soul that lifts all boats. It really does. Um I actually don't think there's a point in specializing to say we work on making the model better for just kernel engineering. I think that's actually not not the most meaningful subset of of like coding in general, uh, kernel engineering in particular.
42:08Maybe there's some like privilege information you inject into the prompt that's like a useful way to steer the model to be better at writing kernels, but broadly speaking, yes, we're all we're all downstream of the frontier in terms [clears throat] of this capability. I I always love this uh this from the history of energy there there's always this like pendulum between the raw source let's say coal and then if there's a certain amount of energy available inside of a chunk hunk of coal like what percent of it we can harness and use
42:36and a big part of the history of energy was getting that number from 10% to 95% or whatever right where are we in that's like if I just think about it at Blackwell or something and Blackwell is the piece of coal like what percent do you think we're at like How how efficiently can we use an existing piece today?
42:55There's a lot of different ways to analyze that. I think in some level we are really efficient at optimizing the performance when the GPU is doing the thing that it's most happy doing which is a large dimension matrix will apply that operation runs at you know 70 80% of peak utilization and it's limited not by software but by power. The way Nvidia quotes peak flops is a little optimistic. You never hit that because of power throttling but um because of heat.
43:20Yeah, exactly. thermals let's say 70 80% it's saturated it's pretty good but in practice you don't spend the majority of your time in a transformer in that happy path where you're doing a large batch m matrix multiply and so uh our job is to basically build the engine around the chip such that we are feeding the GPU these large batches of work at all times and one of the most profound transitions we've had in the GPU world in the last year has been this moving of you know you don't program one GPU at a time anymore you should think about the whole
43:49rack and maybe you should think about the whole cluster, the entire data center at a time. And with Nvidia again, they've started shipping not just a single GPU or a single motherboard, but actually the the whole rack system is something that they prescribe. They call it NVL 72. Uh their latest chip, the Grace Blackwell 300, um that ships as a rack of 72 units. And it is it's an open race to figure out who can program the whole rack scale computer as efficiently as possible. And my belief is that that shape of compute is the future of both
44:19efficiency and speed. In fact, Nvidia does a great job of if you want the lowest possible latency, you should be using that chip. And if you want the highest possible throughput, you should probably also be using that chip as of right now.
44:29And it's all comes down to like this is a very new paradigm of programming.
44:32One of the things you hear is that the market for the best chips, blackwells, let's say, is like a drug market or something right now. Like there's all sorts of fascinating things happening to get as many of them as possible because everyone's so short. Y I'd love you to react to that analogy like is that what it feels like but then also to talk about what the market is like for like not the bleeding edge chips like if I if I am willing to accept a slightly or or moderately inferior chip what's that market like let us into that world
45:00yeah okay a couple things number one uh yes basically has a long-term view on uh on all their chips they they see this immense demand for the black hole chips and they they can do what other suppliers have done in the past which is like just crank prices and made the market you know supply and demand curves will correct they'll intersect at some point and everyone will be technically happier but Nvidia sees the if they just let the most deep pockets buy all the chips that maybe hurts them in the long term if that customer ends up acrewing a lot of more power they understand that
45:30compute is power today and so uh they're quite strategic about how they allocate compute that's the first thought the second thought is that relationships matter a lot nobody wants to have a huge order of of a chip rental come in from this new startup that says, "Oh yeah, I'm going to rent 10,000 black wells for for three years or 5 years." The startup has only been operating for months typically. Who knows they're good for the money. The the way you convince someone to give you access to compute is is quite challenging uh these days and
46:00requires some pretty either great relationships or uh just incredible financial backing to make this happen on the Nvidia side. And it's all because the scarcity is so high and demand is just off the charts. Now, for other chips, I wouldn't even call them inferior. I I like to say there's no bad chips. There's really bad pricing. And uh I will make any chip work at the right price. That's like kind of one of the ethoses of the company. And let's talk about AMD. AMD, I think great chips overall. The challenge is that people don't um understand how to program them
46:29very well. So, you know, I've been talking to you about how we have such a great kernel team. We're so serious about squeezing the performance out of the hardware. Nvidia is pretty good at doing that for their own chips. Frankly, there's some alpha that we can squeeze out, but actually there's a lot more to be done on other chips because the vendor does a little bit less work than Nvidia does to make the best kernels out of the box or or even better for me there is alpha and just like other people have this perception that AMD is not as as good as Nvidia. That's music to my ears. I'm very happy for them to sleep on this chip and for me to buy as much as I can.
46:59Now, I think that that's not actually super true anymore. I think AMD is actually uh somewhat popular amongst the some large buyers. Um you know I think publicly Meta and OpenAI have bought a ton of AMD chips and so we're increasingly seeing that uh all the AMD supply is also being allocated but there's a long tale of other companies that are popping up yet net new companies are great uh such as etched or or senova or dmatrix all these companies are popping up and I think the main challenge for them is scale can they actually get enough wafer allocation
47:29from TSMC to pump out chips to make it into the market but certainly if there's a new chip on the I'd like to know about it as quickly as possible and evaluate whether we can buy a good fraction of that supply.
47:41And so it's fundamentally an arbitrage for you. Like if you can be much better at eking out performance from chips that have received less attention, you can then resell that at a margin and it could be a great business.
47:52Exactly. Exactly. And I think that it's not the case that everyone else is just, you know, has a skill issue that they can't uh, you know, make these chips work as well. I think we're quite competent in this. I think we're probably one of the best teams in the world to use multiple silicon architectures and and be quite aggressive in chasing down performance in unlikely places. But um yeah, I think it's the speed at which we we're willing to kind of build our stack around a new chip. We don't have a huge amount of incumbency around well our data center providers are only stuck with with this
48:20class of chip and it's going to be a huge pain for us to to deploy uh these net new chips. We have some very creative data center partners who are willing to move very quickly and there's a new class of those that we can talk about and most importantly we don't shy away from the challenge. Uh that's frankly a big part of this is just saying yes we love TPUs we're going to make TPUs work. Yes we love tranium we're going to make tranium work and if it doesn't work um easily we're going to find a way to fit it in with the heterogeneous serving system it will have a place every chip has a comparative advantage we have to find
48:50that advantage and then squeeze it in that direction. Ju just as an interlude before we get to hardware, data centers, energy, etc. which will be really fun part of the conversation. I'd love you to talk about your perception of the investor classes worry. Yeah.
49:05Like you look at memory stocks.
49:07Um or my current favorite is you look at the chart that plots the percent of the S&P 500 that's semiconductors.
49:13Historically it was like 2 3 4%. Now it's 19 20 21%. And it just sort of looks like if you're a student of market history, you get all these things through time that are sort of reached some crazy near-term peak and then and then collapsed back to long-term norms.
49:28Um, and I'm curious how that has all investors worried.
49:30Yeah. Uh so you know a lot of people made a lot of money in Micron and Skhinx and companies like this but everyone feels like ah these you know on the long term like compute's a commodity and uh it will not represent a quarter or fifth of the entire market capitalization of the world and and so they're scared and that's the setup. Um everyone acknowledges that like there's a huge shortage but everyone sort of feels like ah we'll figure it out and these things will revert back down to their their normal place in capital markets. I'm
49:59curious what you think about about that narrative.
50:02One thing, I'm less of a student of history as more of a member of history.
50:05I was I was born in 1997 and uh my mom worked at Intel in the 2000 in the run-up to the year 2000 and the the do boom and crash and you know I remember the time where Cisco was the most valuable company in the world and and Intel was close behind. I mean I mostly draw parallels to that period of history from 25 years ago to today. And I think the main difference is that a lot of the investment in networking equipment historically was speculative. We anticipated this future demand for users that never came. And I think what's
50:35interesting about token consumption or AI consumption broadly is that it's no longer speculative. People buy tokens because they're immediately valuable to them. You don't hoard tokens, you use them immediately. This is also even different from what we had 2 years ago where there was a supply crunch for hopper generation chips in 2023 2024. Uh in that period it was all training oriented spend and training is inherently speculative. Now it's everyone is instituting caps on how much you can spend on cloud code. It's a very very different world to be talking about inference spend and predicting inference
51:04spend to go up. I do think inference spend monotonically increases. Uh there's no speculation on inference spend. Vanta automates security and compliance for over 16,000 fast-moving companies like Ramp, Cursor, and Harvey, keeping them audit ready around the clock. It's the number one Agentic Trust platform, and it now helps companies like yours watch for the risks that show up between audits across your vendors, your AI tools, and your whole [music] environment. Every new tool your team signs up for, every vendor that turns on AI features, [music] is an opportunity
51:33for something to go wrong. And most security programs weren't built for AI's pace of growth. The Vant agent works like a 24/7 GRC engineer in the background, finding issues, drafting fixes for you, and cutting vendor assessment time by up to 50%. Whether you're a fast growing startup or a global enterprise, [music] Vanta helps you earn and prove trust. Invest like the best listeners. Get a special offer of $1,000 off Vanta at vanta.com/invest.
51:58Ridgeline is the first endto-end system of record with embedded AI for investment [music] management firms running portfolio accounting, reconciliation, reporting, trading, and compliance, all on one unified platform.
52:10Firms are moving off legacy technology and onto Ridgeline because of how far ahead Ridgeline's AI features are compared to anything else in investment [music] management software. I've been hearing from a lot of investment managers about AI, and they fall roughly into two camps, with some unsure where to even start, [music] and others convinced they can build their own order management system over just a weekend.
52:28The reality is that running an investment firm will always require governance, [music] controls, and a single source of truth for your data. And no amount of AI enthusiasm changes that requirement. If you're serious about your firm's AI strategy, Ridgeline [music] should be part of that conversation. And you can request a demo at ridgeline.ai.
52:44Coming back now to your take on hardware. And so the unit level is interesting to me like talked about chips, talked about racks, talked about, you know, clusters. I'd love to talk about data centers and you said you've had some interesting partners doing some cool things. Talk us about the the present and future of data centers as you see it.
53:04Y because this seems like you know obviously a critical thing for being able to serve all this inference is like lots of innovation in in this part of the world and obviously you're focused on it.
53:12I think one of the themes in our conversation has come back to what is training versus inference like what is the difference between these two?
53:17categories and you know what was different about two years ago being training oriented and today being inferenceoriented and I think the most conservative players in the entire AI stack have got to be the infra players whether that's data centers or even more conservative is TSMC the chip infra people uh and so data centers historically were built like AI data centers they were built for training uh and training is the superset workload over inference you can make any training cluster work for inference but maybe not vice versa and what the difference there is networking uh how much do you invest
53:47in bandwidth between chips and how large of a cluster do you need? There's actually a diseconomy of scale to to data centers in some way. Like it's way more expensive and difficult to build a um you know 100,000 GPUs in one data center than it is to build 10,000 than it is to build 1,000. And and we now we just talk about you know how many megawatts or gigawatts do you have? And basically there's no way to build a gigawatt data center in the United States easily anymore. Even 100 megawatts is is increasingly hard. It's basically impossible unless you're a
54:16very special set of customers. Uh 10 megawatts is probably on the edge of what's possible today and 1 megawatt I would argue is plentiful. So there's this incredible lore on the market where you can find lots of aggregate power but it will not be concentrated and that was not interesting to anyone who's building training uh data centers because you just assume all be in one spot for no one wants to deal with cross data center training.
54:40So the market has some lag in it. I think that the market still assumes that we have to go shake down those 100 megawatt and 10 megawatt data centers wherever we can find them is still the attitude I hear from a lot of data center developers but increasingly we're seeing a few new thinkers realize that inference is going to be suitable for these distributed 1 megawatt data centers and uh we're we're quite in agreement with that and we are very happy to buy small pools of compute across the United States and use that as our inference fleet. give us a sense of
55:09literal physical size of uh 1 megawatt versus 10.
55:12Yeah. Well, so this got really wonky with the advent of liquid cooling. Now you can pack insane levels of power density into a single physical rack. Like a megawatt of compute, you you'd imagine this like massive data hall, like a huge warehouse basically. And now you can actually pack that into Yeah.
55:29around like around like eight racks worth of compute. Each rack is about the size of a refrigerator. You can just imagine eight of them lined up. Um, yeah, that's a megawatt. And so your view would be that the future that you want to help build is a whole bunch of different chips that can be used together. Yes.
55:46That you can buy, you know, you're a buyer to ek out the most per chip.
55:52And that those chips can then be coupled in very small data centers to just do inference. And that those two steps of a whole bunch of random compute, some of which is cheaper than it should be, your ability to eat more out of it, and then small units of expression in a data center equals way cheaper intelligence. I certainly think so. Yes, there's a lot of ways to access cheaper flops if you're able to be creative with what you take. And so, one of the ways that I
56:19describe what we do is we will buy any chip anywhere in the world for any duration of time. That is a level of flexibility and liquidity that I think no one else has right now. Uh we're very aggressive about putting our money where our mouth is and we will we will really take any capacity uh and find a way to make it work in our fleet. And that is a big part of our advantage today and long term we had to create more of that advantage by investing in these data centers that other people are going to be skeptical of because you know what's going to happen when you set up these
56:48like this army of a thousand small data centers versus the one the one big gigawatt data center. Well, few things. You're not going to have power redundancy frank quite often. You're not going to have backup diesel generators on site. Those are all very expensive.
56:59We cut all that overhead. We're not even going to have redundant networking in a lot of cases. We're going to put these in facilities where we have good access to power, a single source of power and we're going to trench one line of fiber to these data centers, but we're not going to have like three lines of fiber with redundancy and failover and SLAs's.
57:14It's just going to go down sometimes. In fact, I won't be surprised if some of them get down to like 95% uptime, which is bad.
57:20Very bad. That's fatal, atrocious for anyone else. survive in a in a big a big gig you'd have basically zero buyers for a data center that has 95% up time I'm that first buyer I will buy 95% up time and the reason for that is because of this background engine thing that if there's things running in the background you don't care partially uh it's actually two things one is that we have a really robust control plane that is going to be fine handling any single failure in any single data center as long as it's not correlated with other data centers and I can just move the workload somewhere
57:48else I'm cool with that um the failures happen at some rate and I am basically linearly happy with a data center that's 95% uptime versus 98% versus 99%. It's just linearly good or bad for me.
58:01Now, you do need that async piece that I mentioned of, you know, we serve these long horizon agents because what happens when a request fails is that I'm going to have to go find a new GPU to put that request on. And that means that for that single turn of the agent's work, you know, it's working for an hour, but then it hits a roadblock because it's GPU got pulled away. At that moment in time, that agent is going to experience maybe like an extra minute or two or three, maybe even 10 of latency. But my argument is that my customers don't care
58:30because their agent was running for hours.
58:33Doesn't matter. [laughter] It doesn't matter if like a single turn occasionally becomes uh a little bit longer. Yeah. So we tell our customers, look, our average throughput is going to be very competitive, but our P99, our 99th percentile latency, it's not going to be controlled. It cannot be. And in return, I'll give you unbeatable economics.
58:51And I think that's the right fit for background agents.
58:52Talk about power as a category. What are you seeing that's interesting, innovative, where do you think this goes?
58:57Okay, so I said I want 95% uptime on my on my data centers. Could I even take 80% up time at the right price?
59:04Probably. Um, and what does that mean?
59:06Well, I'm a son of California. I love solar and wind. I think solar and wind power is way undertapped in the United States. And the challenge has always been this intermittency. You would even consider solar and wind unsuitable for data centers because you have a persistent base load and an intermittent power source. What are you going to do?
59:21Well, I think we're actually not that far from solving that problem. I am totally capable of tolerating a outage for my data center that's measured in in even days or weeks which is like the worst case nightmare scenario for a data center is that we're going to have a long-term outage because the wind is in blow and the clouds are in the sky fog is hanging over the valley for some time. That's the worst case scenario.
59:41It's in fact highly predictable and I can just call in capacity in some other place of the world whenever that happens. uh I'll just model the weather and figure out when my data center is going to be offline, move my data my workload somewhere else and it's fine.
59:54The trick is that it's going to give me better access to power that no one else is going to touch because it is so annoying to deal with that kind of outage.
1:00:01And if my chips are cheap enough, they're probably not going to be Nvidia racks. And if my chips are cheap enough, I don't mind the capital cost of having idle chips.
1:00:09Yeah. So I've heard you describe this entire system as like a scavenger strategy.
1:00:14Is is that Yeah. Unpack that analogy a little Well, first we scavenge chips and then we scavenge power for those chips.
1:00:21The idea is in both cases I do not want to be in bidding against Anthropic or Open AI for compute capacity. I'm not going to win against them and I don't want to. I want to be more creative and use the supply that they don't find legible today. And over time I amass enough aggregate supply. I'm never going to get concentrated supply. I will only get aggregate supply. And over time I build my aggregate factory that is unbeatable in economics.
1:00:43We are building a factory. We're trying to build the best steel factory in the world. Uh but it will come through mini mills not through large monolithic steel plants.
1:00:52And and if I imagine the different versions of this like how vertically integrated you can be.
1:00:57One version would be the extreme would be you own everything. So that it's a very capital inensive business. You own the power you know source. You build the data centers. You design your own chips. You control the software that eats the most out of those chips. And you sell the end finish token to your user like your user is me and you just own the whole stack.
1:01:20But you can imagine many other permutations of the business where you know you could whatever you draw the line anywhere you could be incredibly capital light own nothing and just be like the coordination plane across all this stuff the virtual scavenger right how do you think about that question of like which which type of these businesses to be you know there's actually two parts of me to receive that question. One is the CEO of a company that needs to work every day and and grow as sustainable and and as quickly as it possibly can.
1:01:49The other is the founder and the founder is much more imaginative and and just loves this stuff. The founder in me wants to do everything. This is my entire life. I spent my entire life thinking about chips, power, energy. Like all I care about is this stuff. So of course I want to be maximally ambitious. I don't want to stop ever. I will never stop until I have built the most efficient system from soup to nuts.
1:02:08You're doing real life factorial basically.
1:02:11very much so. So that's like the emotional from the hard answer. On the CEO side, I think we have to be more pragmatic. I think that the capital we're we're looking at for owning everything is like you said, it's insane. Yeah, software has high leverage, so we have to start with software, but ultimately, you know, do we own power generation or can we get great power purchase agreements with uh utilities? I'm more inclined to pursue like letting other people specialize in the things that they're historically good at and then see if we can get to the scale. I think of it as like I want
1:02:41to get to the scale where I earn the right to take this under our wing. I absolutely think that there's efficiencies to be gained everywhere in the stack. If you can break the assumption that people I would be buying from, they made assumptions about who their customers would be. And I maybe break those assumptions. It's a pretty optimistic view. Uh I think it's only possible because we're actually trying to underwrite the largest market for compute in the history of computing.
1:03:04we're actually going to build so many billions, trillions of dollars of investment into inference. Uh, and because of that focus, it makes sense to build a lot of things that are custom for inference. And it's my job to seek all the places where that's possible. And then as as they become obvious to me and my and my partners, I will get my partners to build custom things for me.
1:03:25And if they can't do it for me, I will do it myself.
1:03:27If you had to just zoom out on this entire system, software, hardware, energy, etc., and stackrank the places that you think that we are the most inefficient today at producing useful intelligent tokens.
1:03:40What does that list look like?
1:03:42I think compute scaling is actually like very efficient. Uh as in like you give me more flops and I will use more flops. And I would say we're actually fairly judicious already with our use of flops.
1:03:52Uh if you look at a modern model, there are very few models that are more than 10% dense, meaning 10% of the possible number of experts you can activate are activated. And I think the frontier models are closer to like 1%. So fairly sparse already. I don't think that we're wasting too much on the MOE side. People have been working with for quite some time. They're pretty good at squeezing.
1:04:12Where we are not good is attention and its use of memory. Specifically, the KV cache is quite uncompressed right now. I think if you look at the entropy in a KV cache, it's nowhere near it's not earning its keep. Like we're storing many kilobytes of data in the KV cache per token. Um, and that's probably off by an order of magnitude or two. And I I don't know what the Frontier Labs do, but Deep Seek certainly publishes really interesting work to compress that further and further. And they're making
1:04:42good progress. And I think the fact that they're able to make order magnitude progress here every year or so signals that there's a lot more room to go. I guess this all on the micro scale. If you zoom out further, I think that we actually don't marshall our compute effectively at all. Like we have all this compute in the world. Nvidia is pumping out 5 million Blackwell chips this year. Where are they all going? Are they all being used at all all the time?
1:05:01I certainly doubt it. I think that at some level we just need better orchestration of compute across the world. Uh this is very difficult to do because a lot of the comput disappears into private pools of compute that will never see the light of day and those GPUs sit very sadly idle. Uh it's actually it pains me physically to see that those GPUs are just you know silicon and power went into that and it's just sitting idle and I want to fix that. how we or organize and orchestrate the world's compute as a shared resource and and pack it more efficiently. I would estimate that, you know, we all
1:05:31make fun of XAI for having, you know, some challenges with total flop utilization on its clusters, but um the reality for the rest of the world is it's far far worse. A ton of GPUs just sit in warehouses or sit in private pools allocated to a specific customer um just don't get utilized.
1:05:47You're attacking the efficiency of that very directly.
1:05:49That's way more effective. Yeah. Um, what about fabs? Like what do you think is the future of fabs themselves? Like I think everyone is wondering will the memory companies will TSMC will Intel and others be able to how will they expand capacity basically?
1:06:07Will we do it here in the US?
1:06:09Um, yeah. Riffon fabrication of chips themselves. Like if we could just snap our fingers and have 100 times the chips, you know, in the stock today, uh, we'd probably have way cheaper way cheaper tokens. So yeah, that that seems like an important part of the universe to hear your view on.
1:06:25Yeah. Well, it's interesting. Everything grows in balance with each other, right?
1:06:28If we snap our fingers and double all those things, you might fix a TSMC bottleneck that there you're just going to run into another bottleneck. You make 20% more chips, then you have another bottleneck immediately. I will say though, it is interesting what they consider to be a mustd deliver. uh like what they consider to be like an invariant that their customers me are always going to want versus what I think of as like a more fluid relationship. I think that if a fab exposes more of their trade-offs to me, I'm able to make more intelligent decisions about what I
1:06:58think I can I can do.
1:07:00One of the most interesting examples here is that any fab has a lot of spread in their like worst chip that comes out of the production line and the best chip that comes out of the production line.
1:07:08There's a lot of variance in how chips are made. Uh and then the question is like you know if you have a company like TSMC they work very very hard to tighten what we call these process corners. We want to keep the worst chip as close in characterization to the best chip and they get a great lens to make that possible. But that means that they are adding a lot of controls in the process that maybe I don't need. Maybe I'm actually willing to find a place for that worst chip. You don't need to tighten the process control as much which takes more time and cost. Uh maybe
1:07:36I'm willing to take a lot more rejects.
1:07:38And I think for us it's like a more holistic optimization around there's you know cost of the dies, supply of the dies and then the cost of power and places we can put them. And my whole goal is to actually so dramatically expand the supply of of power uh across the United States that I have a home for a lot of chips that otherwise would not have earned earned their place in a data center.
1:07:59Can we talk about how you designed the system of your own business?
1:08:03What lessons have you learned? You talked about some of interesting Nvidia lessons. Yeah.
1:08:06But like bring me into the culture and how you structure a team and a business where this is the northstar.
1:08:12I think there's a lot of um you know in the limit thinking we don't worry about the immediate nature of like when we start working on a model the efficiency is not going to be very good. Uh but we we we think about like where we could end up in in like a month or or six months or a year's time. We don't accept the state of the of the machines we work on as fixed like even something like the blackwell chip if we think that there's some bottleneck that is holding us back from achieving this performance. I mean
1:08:41it's very important to me that we we understand and characterize that very well and write it down so we can both a tell Nvidia about it or friends and also to basically keep this in mind for future chips that we buy. We want to learn things that are what we think are um essentially like invariant for us or the company uh long term and and kind of fold that into future decisions that we make. We're very collaborative. I think one of the most important traits that we look for are people who either who are both good students and great teachers.
1:09:09Um a lot of our people on the team were TAs in college and and loved the experience of of sharing knowledge in this way. uh we we do whiteboard sessions all the time and I think the collegial environment where everyone has something to teach and something to learn is is extremely important for us.
1:09:25What are the attributes of people that you would want to hire that you think will be resilient to you know the work environment 3 years from now when more stuff is handled by machines?
1:09:35Curiosity. It's 100% curiosity. You know the one thing I cannot teach is love for performance, love for uh digging into every microscond that the machine is working and understanding what's happening on the machine at that time.
1:09:49That to me is the most important trait for a performance engineer and it's what I look for. I don't look for lots of AI experience. I don't look for, you know, CUDA experience at all. That's actually a huge red herring. I mean, CUDA as a concept or GP as a concept have evolved so much in the last 5 years. There's no point asking for 10 years of experience.
1:10:05I want to teach that, but I cannot teach the love for performance engineering. That is what I seek.
1:10:10Can you give your assessment of the major labs one by one, but also then the relationship of like closed source as a category to open source and like what you think is happening and will happen in a line. I would say the labs pay an immense premium to be 3 to 6 months ahead of of everything else. Uh and I think that's probably still worth it. I think it makes perfect sense for open and anthropic to do what they do. You know there's a sensitive topic around distillation which I think is part a very core piece of the relationship
1:10:38between closed and open frontier. And you know I'd like to offer an alternative view on that which is there is the sense that distillation is theft that you are taking something from the frontier models when you distill on their outputs. And in fact, even if that's not your intent, even if you don't ever try to, you know, scrape data from anthropic, one thing I'll offer is that an increasingly large percentage of the artifacts we put out on the internet are AI generated. Even if you just look at GitHub alone, you know, what percentage of repos created in the last year do we think were created by cloud
1:11:08code? Um, do we consider that to be distillation? Because that's probably all we need. I would not be surprised if you could train a fable glass model only on the outputs of code you consider good on GitHub that's open source. And certainly if we take the position that users own the outputs of their interaction with AI and they choose to put that up on GitHub, which a lot of them do, we're going to have latent distillation for a long time. It seems fundamentally impossible for me. Like I I don't think it's fundamentally possible to prevent the diffusion of of
1:11:37information or model capabilities. It will happen. The question is just how fast. And so then the question becomes, do scaling and improvement laws hold forever or for a really long period of time? And if they do, then there's value to being three and six months ahead and that will just last as long as it lasts and they can charge a huge premium for those tokens relative to a very cheap open source token. Is that the right way to think about it?
1:11:58I think it's possible. I don't know that the premium for being 3 to six months ahead is going to last that long. I mean, if you look at like enterprise deployments, uh, they don't move at 3 to six month speed. A lot of enterprises are probably still on like 46, Opus 46 or Opus 47. They don't they don't adopt the bleeding edge rapidly. There's a lot of questions that people have around rolling out any change at all. And I think we're just so early in scratching the surface that um I don't think there's any way to call a winner in this race and certainly I don't even think
1:12:27this is a race that can be decided ever. There's always it's a continual process and fundamentally I don't think open source ever goes away. If there's a vacuum because one leader steps out, a new leader will step in. There's too much incentive and too much there's a lot of tailwinds too. It's just it gets easier every day to treat to train a frontier class model.
1:12:44And so your hope of what the future looks like is what like what balance between closed and open, you know, what balance between model companies doing everything because they have the advantage of owning the stack or whatever. You know, Enthropic can do that, you know, is like the new Google could Google just do that or something.
1:12:59What do you hope the future looks like?
1:13:01I want abundant tokens and diverse harnesses. I want everyone to build their own harness and and every company every user even make the agent your your own. Uh I think we're we're very not that far away from that level of customization and capability. I want people to own their intelligence and I want that intelligence to be customized probably not through weight fine-tuning but probably through more in context learning. That's a more technical detail. But the underlying input to this abundance future is about
1:13:30is basically cheap tokens. My job is to make the tokens as cheap as humanly possible. I will achieve that and I will do it through every layer in the stack available to me. I love the supply side levers. I will use every chip. I'll use every source of power and I will use every piece of land in the United States that's you know suitable for this. And in return, people will have the incentive to explore what it's like to have abundant intelligence. We still treat the agent as a person that is expensive to consult and you should ask them when you have a hard question.
1:13:57That's not the way to think about intelligence. It's incredible that the machine can think and we should try to get that into as many hands as as many people as possible.
1:14:04You sit in such a unique seat and you have such a unique perspective on like what you're trying to do to make this feature a reality. What do you think are your most like divergent views of the world versus your friends who are really well informed and interested in this stuff? Like what what make your what ideas of yours make your friends look at you like you have three heads?
1:14:21Most of the ideas on chips, I would say. You know, when I talk about building custom chips and they ask me, "Oh, so what's different?" Basically, it's it's about sidestepping the HPM shortage and focusing on more extreme offload to other forms of memory such as flash. Um, I'm quite passionate about that idea.
1:14:38Everyone on my team knows that I keep banging the drum around like what would we have to change about the model architecture to make offloading KB cache to flash work at a much greater level.
1:14:47And um I'm whiteboarding that all the time. That's like in the community of like inference people. you know we have some divergent views on what you can do if you design a system around serving at you know one to 10 tokens per second which is our whole north star more broadly I think there is this like larger sense around you know what do you do how do people consume a trillion tokens per day like that's the world we want to create the capability for them to do that what's a trillion tokens like ground us in how much that is a trillion tokens well okay at openi
1:15:15pricing that's at least $5 million at the very least for 5.5 or 5.6 six. Yeah, I think the dollars was probably the most good metric. Yeah.
1:15:23Yeah. It's millions of dollars.
1:15:24Yeah. So, what's the world in which we consume what currently costs $5 million per person per day?
1:15:29Yeah. I mean, we were asking for at least at least um you know, three to six orders of magnitude improvement in cost per token. Uh get that into 5,000. You probably have some customers. And in fact, I would argue that we're for some size of model, we are approaching a trillion tokens being measured in, you know, tens of thousands of dollars. And that's something that you can imagine running for a single job.
1:15:51Are you at all worried that just like the average person just can't and won't do that like doesn't do that now with their own brain? Like there actually isn't that much demand for intelligence in the world.
1:16:01I never will believe in that. There is always demand for intelligence in the world. I think that the way in the on-ramps to that intelligence are our challenge as a product u you know community. I'm not a product person so I cannot say I had the best vision.
1:16:13You want to enable those people.
1:16:14I want to enable those people. I want them to never be held back by the sense that, oh, I my free tier users cannot use or I can't afford to give them this many tokens. And I hear that from my customers all the time. Um, we want to fix that.
1:16:25What about the inverse question? Not what you think is craziest, but like what consensus thing you think is wrong?
1:16:31One of the things I keep coming back to is this question of Nvidia. I am bullish on Nvidia in the short term. And you know, Nvidia, you should never bet against them. They're always going to reinvent themselves. But like fundamentally I think one thing that surprises people is when I tell them that hey if you look at you know Hopper to Blackwell to Reuben and you compare like for like like what is the performance per watt of Bloat 16 multiply it hasn't improved all that much or or even you take that one step further go to TSMC if you look at TSMC 5
1:16:59nanometer versus four versus three versus two the performance per watt on these chips doesn't change like a dramatic amount so the consequence of this is people lose their minds over geopolitics like what what happen if we lost access to DMC for any reason. And um my contrarian take is that it wouldn't be that bad.
1:17:17Supply would take a shock for sure, but the best processes that we have in the west uh like Intel not that far behind at worst like maybe 2x uh worse performance per watt and the gap is just far smaller than than you would make it out to be if you talk if you follow like the chipboard dialogue. What else is happening in the AI world that is not in your path? Meaning it's not like a component of this whole system that you would end up doing something in that interests you most.
1:17:42Well, we're fully downstream of models, right? So the model people get to decide how to design their their architectures and I have only like very light I mean I don't have any input to open AAI or anthropic but um I can only pray that they go in the direction that is a minimal to me and the ch like or I have to like do my best to predict where I think they're going to go and build my serving architecture accordingly. Both software and hardware choices they have.
1:18:06I think the most interesting game in some ways to play like once again this is going back to like the profoundity of the machine thinking and how consequential it is to decide to use something like sparse attention versus dense attention or um how consequential it is to like use a different data type like we were training in B16 but now we can train in FP8 or FP4 lower precision data types that is just an arbitrary choice it feels like but it has profound implications for what chips I can use and and you know how I should build my hardware think about the future of compute
1:18:35if you had a 100 entrepreneurs in a room, all of whom wanted to create some new compute startup.
1:18:40Y um and let's say they were specifically wanted to make hardware chips or systems or racks or whatever.
1:18:45What advice would you give them on like how to orient their companies or like the type of company, not the specific choice they're making on a tech tech bed or something like this because it seems like we're going to try everything and that will be great for the world. You know, some stuff will work. But if you had to give them advice on how to orient their business to be successful in this coming world, what advice would you give them? It's all about the bottlenecks on supply chain.
1:19:07So, you need to first convince me or convince an investor that you understand the like three to five bottlenecks that dictate modern chip supply. There's TSMC wafer capacity, there's HPM capacity, and there's um like advanced packaging, and maybe a fourth one would be power.
1:19:20Like, where will you get the power? How will you build these racks? Uh and I I want to hear like you should have a great answer to each of those four bottlenecks and how you're going to work around them because it's all arbitrage at the end of the day. You're building a chip because you think that Nvidia has made some choices that are difficult for them to change, which is true. Nvidia makes a lot of choices that are difficult for them to change. They're not perfect. They're just really well balanced. And so, you want to be spiky.
1:19:43You want to pick something and say, I think they've underpriced the impact of how short we're going to be on HBM. We're going to push really hard in this other direction instead. Which, you know, as a as an aside, I do think is probably the thing to attack most.
1:19:55Why? There's no easy way to bring on a lot more fabs of memory and those guys have been so it's going to be a while until we Yeah. Yeah. The boys in Boise don't uh don't love huge capex for for cyclical.
1:20:10They they've been burned on that many times.
1:20:12But conceivably like because of that shortage, the world is just going to route around it by making everything else in the system more efficient.
1:20:18I think they're gonna make everything else more expensive. Think that iPhones will cut their memory. iPhones are going to go up in price and um we're just going to deal with it. Why doesn't Nvidia go all the way to the end and sell tokens? Do you think Nvidia is really smart about this? They don't compete with their customers.
1:20:33Nvidia takes the long view on everything. Um, why don't they even start with the Neocloud? Why don't they just sell computer out the back door?
1:20:40Well, Nvidia is really good. Jensen is really good at making his friends billionaires. He's made Cororeweave a billion dollar company, many billion dollar company. And there's no need for him to kind of uh destroy that goodwill.
1:20:50like he wants to create a diverse community of NeoClouds and inference providers who are all jockeying to create demand for Nvidia such that if any one of them decides to I don't know vertically integrate or go with AMD or any other option he's got three more people ready to hungry to fill that position.
1:21:07It's great to have competition amongst his buyers.
1:21:09My favorite closing question for everyone is what is the kindest thing that anyone's ever done for you?
1:21:13The kindest thing I mean I my immediate first thought is like all the mentors that I've had over the years. It's a rare person who takes a lot of time out of their their schedule and um and you know makes it like their personal interest essentially to to make sure that you understand something that uh or teach you something or or like ingrain some value in you that they think that you're on the cusp of understanding but just push you over the line for understanding. uh a lot of the people in Nvidia that I mentioned earlier who instilled that like love of performance engineering in me but also my professors
1:21:41in college who I remember like my adviser in like sophomore year I was very impatient student so I show up at his office hours and say like I I want to build AI chips I know what I want to do why am I wasting time taking all these like other basic classes and networking and you know operating systems and he just looked at me and said like you know he laid out basically like the whole stack and showed me the depth of or the beauty of like understanding every piece in the puzzle like he he took my entire path of like trying to focus on one piece of the the system and said that you know it's so
1:22:11rare that someone can actually understand the entire stack from the gate level silicon all the way to building a great internet scale service and you know you should aspire to be someone who over the course of your lifetime achieves that level of understanding.
1:22:25It is such a rare rare trait and um you know it that level of expertise is so noble to chase and I think and that stays with me quite a bit. Not a common but an advisory. Neil, amazing conversation. Thanks so [music] much for your time.
1:22:37Thank you so much for having me.
1:22:42You know how small advantages compound over time? That's true in investing and just as true in how you run your company. [music] Your spending system is your capital allocation strategy. Ramp makes it smarter by default. Better data, better decisions, better economics over time. See how at ramp.com/invest.
1:22:59As your business grows, Vanta scales with you, automating compliance and giving you a single source of truth for security and risk. Learn more at vanta.com/invest. [music] The best AI and software companies from OpenAI to cursor to perplexity. Use work OS to become enterprise ready overnight, not in months. Visit works.com [music] to skip the unglamorous infrastructure work and focus on your product.
1:23:21Ridgeline is redefining asset management technology as a true partner, not just a software vendor. They've helped firms 5x and scale, enabling faster growth, smarter operations, and [music] a competitive edge. Visit ridgeland.ai to see what they can unlock for you.
