Ep. 027 - OpenAI Jalapeño: Better Than Nvidia Blackwell (Accelerators)
This week Bryan, Myron and Jordan (@JordanNanos) discuss our recent article on OpenAI Jalapeño. They cover the performance, architecture, programming model, implications for NVIDIA and more.
0:00 Cold Open
1:05 Jalapeno Overview
4:22 Tokens Per Megawatt
9:15 Benchmark Caveats
13:48 The CUDA Moat
21:12 How OpenAI Did It
32:13 Samsung HBM4
42:10 AI-Designed Silicon
49:24 Architecture Deep Dive
56:58 Doom and Wrap
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
Why it matters
inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → cost and model availability follow from who can build competitive silicon. A first-party breakdown of Jalapeño's performance per megawatt and programming model shows how much of Nvidia's CUDA lock-in actually binds.
postAMD's inference gap is a software and tooling problem, not a silicon one
articleMost Neoclouds Suck At Security OpenAI vs HuggingFace, Container Escapes,…
postSemiAnalysis on Jalapeno: OpenAI's chip, measured in tokens per megawatt
postGB300 NVL72 claimed at 7x perf-per-dollar over H200 for agentic inference
