OpenAI has unveiled Jalapeño, its first in-house AI chip, designed with Broadcom to run the models behind ChatGPT and Codex. Built for inference rather than training, the chip is pitched on efficiency, with OpenAI claiming far better performance per watt than off-the-shelf options. The move cuts its reliance on Nvidia and puts OpenAI alongside Google, Amazon, Microsoft and Meta in building custom silicon. First deployments are expected by year’s end, scaling through 2027.
Related Posts
3 students killed, 4 critical after train collides with school van in Murshidabad
A local train struck a school vehicle at an open level crossing, killing four people. The collision occurred Friday morning…
Russian strikes on Kyiv kill 14 overnight; warehouses damaged in fires
On Wednesday morning, Russian airstrikes tragically claimed the lives of fourteen individuals in Ukraine’s capital, Kyiv. The city was under…