CUDA Kernels

topic on 2 shows · 4 statements across 4 episodes

Latent Space the MAD Podcast

4 statements about CUDA Kernels, every show

MAD Assertion Supported
Socher: Recursive demonstrated its system can build new CUDA kernels
“We also showed that they can build new CUDA kernels, which is very useful for faster inference.”
Richard Socher Sep 10, 2026 ▶ 1:08:54 When AI Improves Itself | Richard Socher (Recursive)
LATENT SPACE Prediction Not checkable as stated
Brockman: AI models will soon get very good at CUDA kernels
“Things like Cuda kernels are a good example of a very self-contained problem that actually our models should get very good at very soon, but it's just difficult because it requires a lot of domain expertise, a lot of like real abstract thinking. But again, it'…”
Greg Brockman Aug 15, 2025 ▶ 52:14 Greg Brockman on OpenAI's Road to AGI
LATENT SPACE Disclosure
Tay discloses he does not know how to write CUDA kernels
“Should I know CUDA kernels? I don't know CUDA kernels.”
Yi Tay Jul 5, 2024 ▶ 39:56 The 10,000x Yolo Researcher Metagame — with Yi Tay of Reka
Chintala: Inference Moats from Fast CUDA Kernels Last Only Months
“I think, like, Together and Fireworks and all these people are trying to build some faster CUDA kernels and faster, like, you know, hardware kernels in general. But those modes only last for a month or two. Like, these ideas quickly propagate.”
Soumith Chintala Mar 6, 2024 ▶ 28:36 Open Source AI is AI we can Trust — with Soumith Chintala of Meta AI

← every entity, every show

Made with StarZero

Turn any episode into a week of clips.

This entire site, thousands of episodes across every show transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.