Report: OpenAI's 'Jalapeño' ASIC Could Outperform Nvidia Blackwell in TCO and Efficiency
ivan_bezdomny · x · 2026-08-26
SemiAnalysis reports that OpenAI is developing a custom in-house ASIC codenamed 'Jalapeño.' The analysis compares the chip's TCO and throughput per MW against Nvidia's Blackwell and upcoming Rubin architectures, suggesting significant potential advantages in performance and cost-efficiency. Nvidia stock rose following the news.
Related event: OpenAI's First Custom Inference Chip Jalapeño Beats Nvidia Flagships(41 posts)→
More from Companies & People
- VoidStateKate supports Thsottiaux against online bullying — VoidStateKate · 2026-08-26
- AI agents give you 10,000 brilliant employees tomorrow — PeterDiamandis · 2026-08-26
- OpenAI finishes >10T param pretrain 'Bel', claims AGI potential — scaling01 · 2026-08-26
- LangChain to Host 'The Learning Loop' Event in SF on Continual Learning — LangChain · 2026-08-26
- Why AI projects fail in 2026? Shift to infra, talent, and ROI — mikeflache · 2026-08-26
- Electric emerges from massive pivot with new AI IT platform — DenehyXXL · 2026-08-26