CUDA
4 statements across 4 episodes · 1 bullish · 1 bearish · 3 people on the record · first statement Apr 25, 2023 by Jensen Huang · said 29 times in 15 episodes since 2023 · across every show →
Mentions by year
brought up most by Jensen Huang (11), Sarah Guo (5), Elad Gil (5), Tuhin Srivastava (3), Cristobal Valenzuela (2), Satya Nadella (1), Lip-Bu Tan (1), Andrej Karpathy (1)
tap a year for its mentions
2026 5 mentions in 4 episodes 1 per episode
- Baseten CEO Tuhin Srivastava on Custom Models, and Building the Inference Cloud
- Re-engineering the Semiconductor Supply Chain with Intel CEO Lip Bu Tan
- We Need An Ecosystem in AI, And Every Company Can Win A Place In It
- Skill Issue: Andrej Karpathy on Code Agents, AutoResearch, and the Loopy Era of AI
- every mention in 2026, scene by scene →
2024 12 mentions in 6 episodes 2 per episode
- No Priors Ep. 89 | With NVIDIA CEO Jensen Huang
- No Priors Ep. 54 | With Sarah Guo & Elad Gil
- No Priors Ep. 95 | Best of 2024
- No Priors Ep. 81 | With Sarah Guo & Elad Gil
- No Priors Ep 56 | With Baseten CEO and Co-Founder Tuhin Srivastava
- No Priors Ep. 53 | With AMD CTO Mark Papermaster
- every mention in 2024, scene by scene →
2023 12 mentions in 5 episodes 2 per episode
- No Priors Ep. 13 | With Jensen Huang, Founder & CEO of NVIDIA
- No Priors Ep. 2 | With Runway ML’s Cristobal Valenzuela
- No Priors Ep. 44 | With Former Square CEO Alyssa Henry
- No Priors Ep. 32 | With NEAR’s Illia Polosukhin
- No Priors Ep. 30 | With Vercel CEO Guillermo Rauch
- every mention in 2023, scene by scene →
Everything said about CUDA, oldest first
Apr 25, 2023
Mar 21, 2024 bearish
Nov 7, 2024 positive
Huang: NVIDIA Improved Hopper Performance on LLaMA 5x in One Year
“CUDA made it possible for us to iterate so quickly, just in the last year, and then we just went back and benchmarked when Lama first came out, we've improved the performance of hopper by a factor of five without the layer on top ever changing.”
Mar 20, 2026 neutral
Karpathy: AutoResearch is limited strictly to domains with easily evaluatable objective metrics
“This is extremely well suited to anything that has objective metrics that are easy to evaluate. So for example, like writing kernels for more efficient CUDA, you know, code for various parts of a model, etc., are the perfect fit. Because you have inefficient c…”