OpenAI's VP of Hardware on Jalapeño: first custom AI chip taped out in 9 months
thehiphopswami · x · 2026-09-18
In The Data Exchange podcast, OpenAI VP of Hardware Richard Ho details Jalapeño, the company's first custom AI accelerator: a blank-slate architecture bringing memory and compute closer, breaking the throughput-latency trade-off, and targeting lower inference costs. AI tools compressed development so the chip taped out in just nine months. He also covers CUDA's moat, speculative decoding, the HBM4 roadmap, and argues power — not chips — is becoming the data center bottleneck.
Related event: OpenAI's first in-house AI chip Jalapeño taped out in 9 months(5 posts)→
More from Infra
- 421M-Parameter Laya Model Plays Flappy Bird on CPU via OpenVINO INT8 — simpleuserhere · 2026-09-23
- How to run Qwen3.8-27B with 160k context on a 16GB AMD card: full config — According_Study_162 · 2026-09-23
- MLX-Serve v26.9.5 lands with Qwen-Image 2.1 and 4-way MTP streams at up to 122 tok/s on M4 Max — TheMoonMidas · 2026-09-23
- DigitalOcean Managed Agents enters public preview: idle pausing, 75+ models, one bill — HeyAmit_ · 2026-09-23
- Swapping just the decision layer: Qwen + SGLang beats Jev by ~37% at same accuracy — VeryWellVersed · 2026-09-23
- Reka EdgeQ VLM Runs Natively on Snapdragon 8 Elite NPU With 0.73s First Token — RekaAILabs · 2026-09-23