[Analysis: OpenAI's 'Jalapeño' AI Chip Expansion May Face Samsung HBM4 Supply Constraints] BlockBeats News, August 26: Citrini analyst Jukan published an analysis stating that OpenAI's 'Jalapeño' AI chip may not achieve the scale of NVIDIA's Rubin platform in terms of expansion. Jukan believes that if OpenAI's HBM4 high-bandwidth memory relies entirely on Samsung's supply, production capacity ramp-up will face certain limitations. Jukan further pointed out that if OpenAI aims to further scale the deployment of 'Jalapeño,' it may need to lower specifications such as HBM4 transfer speeds to enable the use of HBM4 products from other suppliers, thereby alleviating supply chain constraints. Earlier today, BlockBeats reported that OpenAI announced the latest test results of its self-developed AI inference chip, Jalapeño (translated as: Jalapeño Pepper). According to the results, the chip outperformed NVIDIA's GB200 and GB300 superchips in the InferenceX benchmark test. On models such as GPT-OSS 120B, DeepSeek R1, and Kimi K2.5 1T, the AI workload per watt reached 1.5 to 1.9 times that of competing products, while end-to-end latency was reduced by 1.7 to 3.6 times. [Original Link]