OpenAI's first custom chip Jalapeño: 9-month tape-out, AI-accelerated design
thehiphopswami · x · 2026-09-22
Richard Ho, VP of Hardware at OpenAI, details Jalapeño, the company's first custom AI accelerator, on The Data Exchange podcast.
Key points:
- Goal: control more of the hardware stack to lower inference costs and boost performance
- Unusual combination of high throughput and low latency; blank-slate architecture bringing memory and compute closer together
- The chip taped out in just nine months, with AI tools compressing parts of the development cycle and dramatically boosting expert team productivity
- Covers whether CUDA is still a moat, Triton, speculative decoding, RL, and agents driving inference demand
- Roadmap from gen one to gen three with HBM4 and new memory; power, not chips, is becoming the data center bottleneck
Related event: OpenAI Hardware VP Details Jalapeño, Its First In-House AI Chip(2 posts)→
More from Companies & People
- Apple vs Qualcomm: the 17-year war where Qualcomm took a cut of every iPhone — Aiden_Tech_Ai · 2026-09-22
- Tom Cruise warns Hollywood that AI is "coming and it's going to happen" — Polymarket · 2026-09-22
- OpenAI and Anthropic both shipped AI financial analysis tools for bankers this month — RichOliveira56 · 2026-09-22
- The Neo-Prime: Pairing Frontier AI Management with Performer Networks for Moonshots — davidfromkansas · 2026-09-22
- Runway launches DIFFUSE, a platform to hire AI-native creative talent — runwayml · 2026-09-22
- Commenters slam OpenAI for fumbling first-mover edge as Muse ships after acquihiring steipete — ChrisUniverse · 2026-09-22