Google TPU
product on 19 shows · 11 statements across 10 episodes · said 528 times in 180 episodes since 2019
TBPN 56 
Invest Like the Best 36 
the a16z Podcast 33 
BG2 Pod 25 
Big Technology 24 
Latent Space 21 
20VC 16 
All-In 15 
the MAD Podcast 14 
Acquired 10 
No Priors 7 
Cheeky Pint 3 
Catalyst 3 
the Y Combinator Startup Podcast 2 
the Knowledge Project 1 
My First Million 1 
the Official SaaStr Podcast 1 
Sourcery 1 
David Senra
Mentions by year, every show
tap a year for its mentions
TBPN 56Invest Like the Best 36the a16z Podcast 33BG2 Pod 25Big Technology 24Latent Space 2120VC 16All-In 1510 more shows
2026 87 mentions in 41 episodes 2 per episode
- FULL INTERVIEW: Dylan Patel Says We’re Still Underestimating AI
- Why AI Demand Is Outrunning Compute Supply
- Cerebras CEO: Why GPUs Can't Do Fast Inference
- Dylan Patel: NVIDIA's New Moat & Why China is "Semiconductor Pilled”
- Apple’s Folding Phone "Duo" Is Here + OpenAI vs. Google vs. Anthropic Revisited — With M.G. Siegler
- AI-Designed Viruses, OpenAI’s First Device, The Mansion Section | Diet TBPN
- Inside Anthropic's $100 Billion Al Compute Commitment | CFO Krishna Rao · Invest Like The Best
- Jensen On The Ropes, Sam Altman’s Conflicts, Allbirds’ GPU Pivot
- 33 more episodes that year, every mention in 2026 →
2025 118 mentions in 42 episodes 3 per episode
- GPUs, TPUs, & The Economics of AI Explained | Gavin Baker Interview · Invest Like The Best
- Dylan Patel on GPT-5’s Router Moment, GPUs vs TPUs, Monetization
- Google Part III: The AI Company. Google is amazingly well-positioned... will they win in AI? (Audio) · Acquired
- No Priors Ep. 127 | With SemiAnalysis Founder and CEO Dylan Patel
- Dylan Patel on the AI Chip Race - NVIDIA, Intel & the US Government vs. China
- Will AWS Buy Google’s TPUs, Remembering Claude The Gator, Ricursive Raises $35M | Diet TBPN
- Building the Real-World Infrastructure for AI, with Google, Cisco & a16z
- Inside the Trillion-Dollar AI Buildout | Dylan Patel Interview · Invest Like The Best
- 34 more episodes that year, every mention in 2025 →
2024 41 mentions in 12 episodes 3 per episode
- AI Semiconductor Landscape feat. Dylan Patel | BG2 w/ Bill Gurley & Brad Gerstner · Bg2 Pod
- The 10,000x Yolo Researcher Metagame — with Yi Tay of Reka
- E165: Vision Pro: use or lose? Meta vs Snap, SaaS recovery, AI investing, rolling real estate crisis
- State of AI 2024: Frontier Models, AI Geopolitics, Robotics | Nathan Benaich, Air Street Capital
- Eiso Kant, CTO @Poolside: Raising $600M To Compete in the Race for AGI | E1211 · 20VC with Harry Stebbings
- Aidan Gomez: What No One Understands About Foundation Models | E1191 · 20VC with Harry Stebbings
- Anthropic's Co-Founder on AI Agents, General Intelligence, and Sentience — With Jack Clark
- Ep20. AI Scaling Laws, DOGE, FSD 13, Trump Markets | BG2 w/ Bill Gurley & Brad Gerstner · Bg2 Pod
- 4 more episodes that year, every mention in 2024 →
2023 18 mentions in 5 episodes 4 per episode
- The State of Silicon and the GPU Poors - with Dylan Patel of SemiAnalysis
- AI Hardware, Explained.
- Intel's CEO Shares His Plan To Win The AI Chip War — With Pat Gelsinger
- Ep 18: Petaflops to the People — with George Hotz of tinycorp
- E143: Nvidia smashes earnings, Arm walks the plank, M&A market, Vivek dominates GOP debate & more
- every mention in 2023, scene by scene →
2022 4 mentions in 1 episode
2019 1 mention in 1 episode
every mention on every show, scene by scene, with the transcript →
10 statements about Google TPU, every show
Ross: Porting AlphaGo to TPUs jumped its ELO by hundreds of points
“AlphaGo running on GPUs had an ELO score of about 3200. Lease it all was about 35, 35 50. And I might be getting the first digit wrong. It might be 2000 instead of 3000. But like, you know, it was more than 200. And then when put on on TPUs, it actually went t…”
Sacerdote: Celestica was the sole supplier for Google's TPU servers
“Celestica's heritage was IBM supercomputing, and they kept all that talent and skill, and then we noticed they were the sole supplier of the Google TPU server”
Harik: Current Nvidia and Google chips offer 5M times 1990s compute
“You look at today where the latest Google TPUs and where the Nvidia chipsets are at, we're talking five petaflops. That effectively is five million times more powerful from a compute perspective, what existed two to three decades ago.”
Pope: Google's decision to build TPUs specifically for neural nets paid off
“They at least had the option, like the opportunity to design the TPUs for neural nets at least rather than graphics applications like NVIDIA. And so the overall architecture starting with single core doing what was at the time reasonably large systolic arrays …”
Huang: Google TPUs will inevitably transition to customer-owned tooling at scale
“Where will TPUs go when they, when it becomes a large business? Customer-owned tooling. There's no question about it.”
Gomez: Google TPUs are now viable for super large-scale AI training
“You can definitely train big models on TPUs. Those are actually now a usable platform for super large scale model training, and I think Google has proven that quite convincingly.”
Clark: Anthropic builds on Amazon Trainium, Google TPU, and Nvidia chips
“I can't get too much into the specifics, but I can just say we've sort of publicly stated that we're Working on both Tranium chips and also TPU chips. We also work on NVIDIA chips as well.”
Hotz: Google TPUs are the only successful non-Nvidia training chips
“The only company, there's one other company aside from Nvidia who's succeeded at all at making training chips... Mid journey is trained on TPU, right? Like a lot of startups do actually train on TPUs, and they're the only other successful training chip aside f…”
Hotz: Systolic arrays are the wrong architectural choice for AI chips
“I think systolic arrays are the wrong choice. Systolic array, I think they have systolic arrays because that was the guy's PhD. And of course Amazon makes... They are very power efficient, but it becomes hard to schedule a lot of stuff. On them, if you're not …”