High Signal Podcasts Evidence ledger
Method
Browse
How the evidence works
← All source episodes

Latent Space / episode intelligence

NVIDIA's AI Engineers: Agent Inference at Planetary Scale and "Speed of Light" — Nader Khalil (Brev), Kyle Kranen (Dynamo)

10 Mar 2026 25 published claims 3 attributable people
Open original episode ↗ Read the evidence

Speakers in the public record

Nader KhalilKyle KranenShawn Wang

Claim mix

belief 11prediction 3uncertainty 2commitment 2evaluation 2observation 2preference 2recommendation 1

Evidence policy

Every row below preserves an exact excerpt. Identified speakers are linked; unresolved voices are labeled and excluded from people counts.

Claim ledger

The useful parts, with receipts.

25 published records

02 / belief

Like they kind of occupy the same purposes and you call them, it does something on the system and, and that’s done. I think that in pre-training there’s just an enormous amount.

“Like they kind of occupy the same purposes and you call them, it does something on the system and, and that’s done. I think that in pre-training there’s just an enormous amount.”
Speaker
Kyle Kranen
Publisher
Latent Space

03 / uncertainty

Uh, sometimes I feel like the city believes in you more than you do. And even, uh, I don’t know if you remember, but I remember posting my first blog post and I had met you on Twitter and you gave me like an hour of your time super randomly, and you kind of coached me through, uh, writing content for developers.

“Uh, sometimes I feel like the city believes in you more than you do. And even, uh, I don’t know if you remember, but I remember posting my first blog post and I had met you on Twitter and you gave me like an hour of your time super randomly, and you kind of coached me through, uh, writing content for developers.”
Speaker
Nader Khalil
Publisher
Latent Space

05 / prediction

Is it just like, you know, people find an interest, you go in, you go deep on whatever, and that kind of feeds back into, you know, okay, we, we expect predictions.

“Is it just like, you know, people find an interest, you go in, you go deep on whatever, and that kind of feeds back into, you know, okay, we, we expect predictions.”
Speaker
Not verified from transcript
Publisher
Latent Space

06 / belief

Like, I think, um, you know, you talk to, you talk to Kyle, you talk to, like, every VP that I’ve met at Nvidia goes so close to the metal.

“Like, I think, um, you know, you talk to, you talk to Kyle, you talk to, like, every VP that I’ve met at Nvidia goes so close to the metal.”
Speaker
Nader Khalil
Publisher
Latent Space

07 / belief

I think at this point a lot of people are familiar with the term of inference. Like funnily enough, like I went from, you know, inference being like a really niche topic to being something that’s like discussed on like normal people’s Twitter feeds.

“I think at this point a lot of people are familiar with the term of inference. Like funnily enough, like I went from, you know, inference being like a really niche topic to being something that’s like discussed on like normal people’s Twitter feeds.”
Speaker
Kyle Kranen
Publisher
Latent Space

10 / belief

I think when it comes to how you’re serving inference, you know, you have a bunch of decisions to make and there you can always argue that you can take something and make it more optimal.

“I think when it comes to how you’re serving inference, you know, you have a bunch of decisions to make and there you can always argue that you can take something and make it more optimal.”
Speaker
Nader Khalil
Publisher
Latent Space

14 / uncertainty

Like you’re seeing these machines, they have like pedals to like move these saws and whatever. I don’t know what this machinery is, but I saw all three generations.

“Like you’re seeing these machines, they have like pedals to like move these saws and whatever. I don’t know what this machinery is, but I saw all three generations.”
Speaker
Nader Khalil
Publisher
Latent Space

15 / belief

Like, so like that, that, that chart that you see is them estimating what the human equivalent replacement is. Um, I think the, I think actually Enro release a more recent chart.

“Like, so like that, that, that chart that you see is them estimating what the human equivalent replacement is. Um, I think the, I think actually Enro release a more recent chart.”
Speaker
Shawn Wang
Publisher
Latent Space

16 / commitment

We will see before the end of the year an agent that is capable of running for longer than 24 hours with like self consistency the entire time.

“We will see before the end of the year an agent that is capable of running for longer than 24 hours with like self consistency the entire time.”
Speaker
Kyle Kranen
Publisher
Latent Space

17 / evaluation

Because there’s usually some, this is usually like a constant, you, you know, the SLA that you need to hit and then like you try and find the lowest cost version that hits all of these constraints.

“Because there’s usually some, this is usually like a constant, you, you know, the SLA that you need to hit and then like you try and find the lowest cost version that hits all of these constraints.”
Speaker
Kyle Kranen
Publisher
Latent Space

18 / prediction

On the decode side because you’re doing a full Passover, all the weights and the entire sequence, every time you do a decode step and you’re, you don’t have the quadratic computation of KV cache, it’s usually memory bound because you’re retrieving a linear amount of memory and you’re doing a linear amount of compute as opposed to prefill where you retrieve a linear amount of memory and then use a quadratic.

“On the decode side because you’re doing a full Passover, all the weights and the entire sequence, every time you do a decode step and you’re, you don’t have the quadratic computation of KV cache, it’s usually memory bound because you’re retrieving a linear amount of memory and you’re doing a linear amount of compute as opposed to prefill where you retrieve a linear amount of memory and then use a quadratic.”
Speaker
Kyle Kranen
Publisher
Latent Space

19 / commitment

We were like, on the risk of, of losing payroll, we’ve had to contract our team because we l ran outta money. And so like, um, because of that you’re really always forcing yourself to I to like understand the root cause of everything.

“We were like, on the risk of, of losing payroll, we’ve had to contract our team because we l ran outta money. And so like, um, because of that you’re really always forcing yourself to I to like understand the root cause of everything.”
Speaker
Nader Khalil
Publisher
Latent Space

20 / prediction

I think that, you know, when it comes to like an acquisition, I think the amount that the soul of the products align, I think is gonna be.

“I think that, you know, when it comes to like an acquisition, I think the amount that the soul of the products align, I think is gonna be.”
Speaker
Nader Khalil
Publisher
Latent Space

21 / observation

Uh, the common models like Deeplearning recommendation model, which came outta meta and the wide and deep model, which was used or was released by Google were very accelerated by GPUs using, you know, the fast HBM on the chips, especially to do, you know, vector lookups.

“Uh, the common models like Deeplearning recommendation model, which came outta meta and the wide and deep model, which was used or was released by Google were very accelerated by GPUs using, you know, the fast HBM on the chips, especially to do, you know, vector lookups.”
Speaker
Kyle Kranen
Publisher
Latent Space

22 / observation

Hey, you know, how do you program something in Cuda and run it? And then, and then we built, you know, like when Deep Learning was getting big, we built, we built Torch and, and, but so recently the amount of like layers that are added to that developer stack has just exploded because AI has become ubiquitous.

“Hey, you know, how do you program something in Cuda and run it? And then, and then we built, you know, like when Deep Learning was getting big, we built, we built Torch and, and, but so recently the amount of like layers that are added to that developer stack has just exploded because AI has become ubiquitous.”
Speaker
Kyle Kranen
Publisher
Latent Space

23 / preference

I feel like coding agents have been so much more effective than general purpose agents. And I think a large part of that is it just has access to the terminal, like you said, and that means it has access to everything that you’ve installed into your terminal.

“I feel like coding agents have been so much more effective than general purpose agents. And I think a large part of that is it just has access to the terminal, like you said, and that means it has access to everything that you’ve installed into your terminal.”
Speaker
Nader Khalil
Publisher
Latent Space

24 / preference

Yeah. And I’ll, I’ll go back and I have like a little crappy logging software I use and there’s just times where it wants to, like, I’m gonna go deep on research and it’ll, I eat up 80,000 tokens go on another go on another, yeah.

“Yeah. And I’ll, I’ll go back and I have like a little crappy logging software I use and there’s just times where it wants to, like, I’m gonna go deep on research and it’ll, I eat up 80,000 tokens go on another go on another, yeah.”
Speaker
Kyle Kranen
Publisher
Latent Space

25 / evaluation

Like, I don’t know if, I don’t know if I can say that, but like, you know, um, I think what my point kind of is, is that there’s, like, I look at slopes of the scaling laws and like, this slope is not working, man.

“Like, I don’t know if, I don’t know if I can say that, but like, you know, um, I think what my point kind of is, is that there’s, like, I look at slopes of the scaling laws and like, this slope is not working, man.”
Speaker
Shawn Wang
Publisher
Latent Space
Search evidence