NVIDIA Hopper, every mention
69 scenes across 13 shows · ← back to NVIDIA Hopper
tap a year for its mentions
All-In 24
BG2 Pod 20
Invest Like the Best 16
Acquired 15
Latent Space 8
No Priors 7
TBPN 6
Big Technology 55 more shows
every year every show All-In 24 BG2 Pod 20 Invest Like the Best 16 Acquired 15 Latent Space 8 No Priors 7 TBPN 6 Big Technology 5 
the a16z Podcast 3 
Catalyst 2 
the MAD Podcast 2 
the Y Combinator Startup Podcast 1 
20VC 1
Verbatim, from the transcripts: passages where NVIDIA Hopper comes up on All-In, BG2 Pod, Invest Like the Best, Acquired, Latent Space
Ex-NVIDIA Engineer: Why AI Is About to Get 1000x Cheaper
- ▶ 50:46 Neil Movva This is also even different from what we had two years ago, where there was a supply crunch for hopper generation chips in 20, 23, 24.
- ▶ 1:16:40 Neil Movva 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 Rubin, and you compare like for like, like, what…
Next 100x in AI: Inference, Networking, & Self-Optimizing Models — Philip Kiely & Ali Taha, Baseten
- ▶ 37:12 Philip Kiely So like on GLM 5.2, um, if you want to get unquantized, uh, perhaps on hoppers even, um, and you're just using an off the shelf inference engine with no particular optimizations, no, no speculator, um, nothing, nothing extra around like KV…
Multi-GPU Kernels, Intelligence per Watt, Heterogeneous Inference, and More | YC Paper Club · Y Combinator
- ▶ 12:05 Stuart (Stu) On Hopper, you have one 32 SMs.
The AI Frontier: from open weights to open research — Eiso Kant, Poolside AI
Inside the AI power wars
- ▶ 3:20 Jeremy Eliahu-Ontiveros Uh, that's a Hopper H.
Big Technology AI Summit (full): Greg Brockman, Mike Krieger, Aaron Levie & Friends of The Podcast
- ▶ 3:37:27 Greg Brockman Hoppers are, you know, kind of, you know, not, not obsolete, right?
Perplexity CEO: Micron Will Be More Valuable Than Meta & How Export Controls Helped Not Hurt China · 20VC with Harry Stebbings
- ▶ 35:44 Aravind Srinivas And, um, the models that are, um, already in use today, these have been trained in the hopper generation.
Watts, Wafers, and the Future of AI Infra | Gavin Baker · Invest Like The Best
- ▶ 49:52 Gavin Baker Effectively in front of a hopper, or even an ampere, use that hopper and ampere for prefill, and extend the useful life of that GPU until it melts. 2 times in the scene
The Supply and Demand of AI Tokens | Dylan Patel Interview · Invest Like The Best
- ▶ 30:52 Patrick O'Shaughnessy Each 100 prices look like this. 3 times in the scene
Arm’s $15B Chip Bet, Sanders & AOC vs Datacenters, Meta & YouTube Lose Trial | Diet TBPN
- ▶ 1:35 Turner Novak NVIDIA is starting to sell their Grace CPU that goes with their hopper.
OpenAI Ends Side Quests, SF Housing Market is Back, Kalshi’s $1B Prize | Diet TBPN
- ▶ 15:59 unnamed speaker Like, you have to imagine that there will be models that only run on Rubin and need to be sort of re-architected to run on Hopper, I would imagine?
Who's Actually Funding the AI Buildout?
- ▶ 14:50 Neil Tiwari Um, and so for the, uh, hoppers, the H, uh, 100 or H 200 series of GPUs into the Blackwells, uh, there was a claim made that it could be 30 times more efficient.
Dylan Patel: NVIDIA's New Moat & Why China is "Semiconductor Pilled”
- ▶ 19:27 Dylan Patel It's not just Hopper, Blackwell, Rubin. 2 times in the scene
FULL INTERVIEW: Dylan Patel Says We’re Still Underestimating AI
- ▶ 4:48 Dylan Patel And, and over time, like, Hopper's now at five percent, but Blackwell's still 10 to 15%.
The Future of Everything: What CEOs of Circle, CrowdStrike & More See Coming in 2026
- ▶ 1:42:57 Chase Lochmiller Well, so we had started well before Hopper, uh, came out. 2 times in the scene
Artificial Analysis: The Independent LLM Analysis House — with George Cameron and Micah Hill-Smith
- ▶ 1:03:02 Micah Hill-Smith When you run all of that, for especially big sparse models, you can get a lot better than two or three eggs gain going from hopper to blackwell generation to video.
NVIDIA’s Jensen Huang on Reasoning Models, Robotics, and Refuting the “AI Bubble” Narrative
- ▶ 31:11 Jensen Huang Um, you know, and, and it wasn't, I think the first breakthroughs, none of it included Hopper. 2 times in the scene
Coreweave: AI Bubble Poster Child Or The Next Tech Giant? — With Michael Intrator and Brian Venturo
- ▶ 43:55 Brian Venturo They're going to do the things that they need the most, uh, firepower to do, and they're going to run their inference on hoppers, or they're going to run their inference on Ampere, the A 100, right? 2 times in the scene
Paramount’s Deal Playbook, Trump Opens Nvidia’s China Door, Saudis Loosen Drinking Laws | Diet TBPN
- ▶ 14:36 Jordi Hays It's Hopper.
GPUs, TPUs, & The Economics of AI Explained | Gavin Baker Interview · Invest Like The Best
- ▶ 6:33 Gavin Baker And the reason for that is, you know, after XAI figured out how to get, um, 200,000 hoppers coherent, 3 times in the scene
- ▶ 10:02 Gavin Baker Since Hopper came out of the scaling law for pre-training, and it held, and that's great, because all these scaling laws are multiplicative, so now we're going to apply these two new, um, reinforcement learning, verified rewards, and test…
- ▶ 10:31 Gavin Baker It's like, almost like imagine, like Hopper is like, you know, it's like a World War II era airplane, and it was by far the best World War II era airplane. 5 times in the scene
Ilya Sutskever on Dwarkesh Patel Reaction, NVIDIA vs Google, Trump Unveils Genesis | Diet TBPN
- ▶ 13:15 unnamed speaker All the magic from the, quote, god machines is pretty much still hopper-based.
After LLMs: Spatial Intelligence and World Models — Fei-Fei Li & Justin Johnson, World Labs
- ▶ 13:01 Justin Johnson Like, if you look at, if you look at the numbers, like, even going from Hopper to Blackwell, like, the performance per watt is about the same. 2 times in the scene
Google Part III: The AI Company. Google is amazingly well-positioned... will they win in AI? (Audio) · Acquired
- ▶ 3:38:36 Ben Gilbert He was talking about Blackwell, and he said something about Hopper, and he was like, eh, you don't want Hopper.
- ▶ 3:38:41 Ben Gilbert My sales guys are gonna hate me, but like, you really don't want Hopper at this point.
NVIDIA: OpenAI, Future of Compute, and the American Dream | BG2 w/ Bill Gurley and Brad Gerstner · Bg2 Pod
- ▶ 31:24 Brad Gerstner You then had a massive upgrade, which required, you know, significant data center overhaul with Grace Blackwell in 20, 25. 4 times in the scene
- ▶ 52:19 Jensen Huang Let's pretend Hopper, Hopper's an amazing chip, an amazing system. 3 times in the scene
Dylan Patel on the AI Chip Race - NVIDIA, Intel & the US Government vs. China
- ▶ 1:36:58 Dylan Patel It turned out that, um, multiple major neoclouds had sold out of hopper capacity. 3 times in the scene
⚡️Accelerators @ 3x NVIDIA H200 perf, Made in the USA - Thomas Sohmers + Mitesh Agrawal, Positron AI
- ▶ 14:53 Thomas Sohmers Percentage of theoretical memory bandwidth actually has gotten worse generation over generation, and we'll see exactly where Blackwell ends up, but all indications are, even though they, you know, more than doubled the theoretical memory…
Winning the AI Race Part 3: Jensen Huang, Lisa Su, James Litinsky, Chase Lochmiller
- ▶ 45:43 Jason Calacanis The H-one hundreds and whatever else you're selling them, and still have them all like you, because they must ask sometimes, hey, can I get extra? 2 times in the scene
- ▶ 48:35 Jensen Huang First, you know, first, in the old days with Hopper, it happened so fast. 5 times in the scene
Trump vs Powell, Solving the Debt Crisis, The $10T AGI Prize, GENIUS Act Becomes Law
- ▶ 1:00:56 David Sacks It's a less powerful version of the hopper chip.
Trump's First 100 Days, Tariffs Impact Trade, AI Agents, Amazon Backs Down
- ▶ 1:20:44 David Sacks So basically the leap from Hopper to Blackwell to Rubin, I guess, will be in next year.
Liberation Day, Tariffs, US v China Open Source, OpenAI, $CRWV, TikTok | BG2 · Bg2 Pod
- ▶ 57:11 Brad Gerstner The one thing I'd tell you about the depreciation argument as it relates to this company is, you know, a lot of people push on, you know, there's a statement by Jensen at GTC that, you know, hoppers may not have value because Grace…
The AI Cold War, Signalgate, CoreWeave IPO, Tariff Endgames, El Salvador Deportations
- ▶ 4:35 Gavin Baker Product transition in history in terms of Hopper. 3 times in the scene
- ▶ 12:21 Gavin Baker Hoppers are, you know, finely tuned.
NVDA GTC, M&A Wiz / Goog $32 B Deal, April 2 Tariff Uncertainty; Huawei Belt & Road; ChatGPT | BG2 · Bg2 Pod
- ▶ 48:34 Brad Gerstner Blackwell is 40 times more capable than Hopper was, and the, the demand is off the charts, and so, you know, notwithstanding that fact, I think the market's checking them at the gate, and they're saying, we'll believe it when we see it,… 5 times in the scene
DeepSeek, Open Source, Tariffs, DOGE, Market Impact | BG2 w/ Bill Gurley & Brad Gerstner · Bg2 Pod
- ▶ 12:23 Brad Gerstner They're not going to have access to Blackwell that is, you know, two to three X improvement on top of the Hopper series, which already exists.
AI Czar David Sacks Explains the DeepSeek Freak Out
- ▶ 7:11 David Sacks So Dylan Patel, who's leading semiconductor analyst has estimated that deep seek has about 50,000 hoppers. 2 times in the scene
The Future of Artificial Intelligence
- ▶ 2:20 unnamed speaker They spent over half a billion dollars on GPUs with estimates pointing to 50,000 hopper GPUs across variations.
DeepSeek Panic, US vs China, OpenAI $40B?, and Doge Delivers with Travis Kalanick and David Sacks
- ▶ 24:33 David Sacks So Dylan Patel, who's leading semiconductor analyst has estimated that deep seek has about 50,000 hoppers. 2 times in the scene
2024 Year in Review: The Big Scaling Debate, the Four Wars of AI, Top Themes and the Rise of Agents
- ▶ 1:11:22 Shawn Wang For him to make that statement, I think it's a, it's another indication that the transition from the H to the B series is going to go very well.
AI Semiconductor Landscape feat. Dylan Patel | BG2 w/ Bill Gurley & Brad Gerstner · Bg2 Pod
- ▶ 1:22:42 Dylan Patel Three-month, six-month deals at way better pricing than even the four-month or the four-year, three-year deals that you used to have for Hopper, right?
New SEC Chair, Bitcoin, xAI Supercomputer, UnitedHealth CEO murder, with Gavin Baker & Joe Lonsdale
- ▶ 50:00 Gavin Baker No one thought it was possible to make more than 25,000, maybe 30,032 thousand, pick a number, NVIDIA hoppers coherent. 3 times in the scene
- ▶ 57:16 Gavin Baker Grok three is the first new data point to support whether or not scaling laws are breaking or holding because no one else thought you could make a 100,000 hoppers coherent. 2 times in the scene
Ep20. AI Scaling Laws, DOGE, FSD 13, Trump Markets | BG2 w/ Bill Gurley & Brad Gerstner · Bg2 Pod
- ▶ 10:07 Brad Gerstner They called hopper demand exceptional. 2 times in the scene
No Priors Ep. 89 | With NVIDIA CEO Jensen Huang
- ▶ 6:44 Jensen Huang And so, so CUDA made it possible for us to iterate so quickly, just in the last year, and then we just went back and benchmarked, uh, when Lama first came out, we've improved the performance of hopper by a factor of five without the,…
- ▶ 21:16 Jensen Huang We can't, we couldn't build, we couldn't build Hopper without it.
Frontier Forum: An energy-first approach to data centers
- ▶ 20:18 Chase Lockmiller The Hopper, the current generation, the H-one hundred, H-two hundred, um, those are about 700 watts per chip.
Ep17. Welcome Jensen Huang | BG2 w/ Bill Gurley & Brad Gerstner · Bg2 Pod
- ▶ 17:41 Jensen Huang Now, we also put a lot of energy into continuously reinventing new algorithms so that when the time comes, the Hopper architecture is two, three, four times better than when they bought it, so that, that you, that infrastructure continues… 2 times in the scene
- ▶ 59:42 Jensen Huang Hopper wouldn't be possible.
NVIDIA's Artifical Intelligence Moat & Origins — With Bryan Catanzaro
- ▶ 17:15 Bryan Catanzaro Um, you know, improving the quality of our designs, you know, our hopper GPUs, for example, have a lot of circuits in them that were designed by AI that we built ourselves, uh, that have better, um, speed, um, and power and cost… 2 times in the scene
Holiday Special 2023 (Audio) · Acquired
- ▶ 55:54 David Rosenthal So, NVIDIA is one of their major partners, and Crusoe's data centers are filled with all the latest Hopper GPUs linked up with InfiniBand and optimized for the best
NVIDIA CEO Jensen Huang · Acquired
- ▶ 21:12 Jensen Huang Uh, we have, we have some great employees today that were there in the beginning, and I knew that they needed this amazing computer that we were building, and we're building the first version of the DGX, which, you know, today when you see…
- ▶ 30:32 Jensen Huang Bill Hopper.
- ▶ 30:38 Jensen Huang Uh, build Hopper, or somebody else is, uh, build a system for Hopper.
- ▶ 30:41 Jensen Huang Somebody is, uh, build CUDA for Hopper.
- ▶ 30:44 Jensen Huang Somebody's job is build CUDNN for CUDA for Hopper.
Nvidia Part III: The Dawn of the AI Era (2022-2023) (Audio) · Acquired
- ▶ 1:06:05 David Rosenthal Up until NVIDIA's current GPU generation, the hopper generation of GPUs for the data center, there was only one GPU architecture at NVIDIA, and that same architecture and those same chips from the same wafers made at TSMC, some of them…
- ▶ 1:06:42 David Rosenthal So there's the Hopper architecture, named after great computer scientist Grace Hopper, I think Rear Admiral in the U.S.
- ▶ 1:06:51 David Rosenthal Grace, CPU, Hopper, GPU, Grace Hopper, the H-one hundreds.
- ▶ 1:07:18 David Rosenthal This is a really big deal, because what they do with the Hopper architecture is they start using what's called chip-on-wafer-on-substrate.
- ▶ 1:10:55 David Rosenthal So, these three things that NVIDIA has been building, the dedicated hopper data center GPU architecture, the grace CPU platform, the Mellanox powered networking stack,
No Priors Ep. 18 | With Kevin Scott, CTO of Microsoft
- ▶ 19:52 Kevin Scott Um, yeah, like we're, we're deploying, uh, Hopper now at scale and, you know, like a bunch of the features of Hopper, like, you know, eight bit floating point, uh, you know, arithmetic and a bunch of other things are like things that, you… 2 times in the scene
Nvidia: The Machine Learning Company (2006-2022) · Acquired
- ▶ 1:18:36 David Rosenthal And indeed, this year, Nvidia announced they are making a data center CPU, an arm-based data center CPU called Grace to go with the new Hopper architecture for their latest GPU.
- ▶ 1:18:50 David Rosenthal So there's Grace and Hopper.