Ep. 027 - OpenAI Jalapeño: Better Than Nvidia Blackwell (Accelerators) episode artwork

EPISODE · Aug 30, 2026 · 1H 3M

Ep. 027 - OpenAI Jalapeño: Better Than Nvidia Blackwell (Accelerators)

from SemiAnalysis Weekly · host Jordan Nanos, Doug O'Laughlin

This week Bryan, Myron and Jordan discuss our recent article on OpenAI Jalapeño. They cover the performance, architecture, programming model, implications for NVIDIA and more.1:05 Jalapeno Overview4:22 Tokens Per Megawatt9:15 Benchmark Caveats13:48 The CUDA Moat21:12 How OpenAI Did It32:13 Samsung HBM442:10 AI-Designed Silicon49:24 Architecture Deep Dive56:58 Doom and WrapFull Article: ⁠https://newsletter.semianalysis.com/p/openai-jalapeno-better-than-nvidia

Episode metadata supplied by the publisher feed · Published Aug 30, 2026

Embed this episode

Ready to play

Ep. 027 - OpenAI Jalapeño: Better Than Nvidia Blackwell (Accelerators)

0:00 1:03:12

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

Frequently Asked Questions

How long is this episode of SemiAnalysis Weekly?

This episode is 1 hour and 3 minutes long.

When was this SemiAnalysis Weekly episode published?

This episode was published on August 30, 2026.

Can I download this SemiAnalysis Weekly episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!