OpenAI says its Jalapeño chip can power faster AI responses than the competition
Covered by 4 sources
Read the full article
OpenAI introduced its Jalapeño AI chip, designed with Broadcom, which delivers faster AI inference and greater efficiency than Nvidia's top superchips. Benchmarks show Jalapeño offers 1.5-1.9x more AI work per watt and 1.7-3.6x lower latency across multiple models. OpenAI plans limited deployment by end of 2026 and increased production in 2027, continuing development of future chip generations.
Covered by 4 sources
- The full stack behind abundant intelligence· 2 sources
