OpenAI AI Updates: June 25, 2026

1. OpenAI and Broadcom Unveil Jalapeno, a Custom LLM Inference Chip

OpenAI and Broadcom unveiled Jalapeno, OpenAI’s first custom AI accelerator chip, purpose-built for LLM inference. The chip was co-developed in just nine months and is optimized around the memory movement, networking, and serving patterns that matter most for frontier models, with early testing showing substantially better performance per watt than current state-of-the-art alternatives. OpenAI said engineering samples are already running ML workloads including GPT-5.3-Codex-Spark at production target frequency, with initial deployment targeted by the end of 2026 and gigawatt-scale data center buildouts planned with Microsoft and other partners in the years ahead. Source