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
Black Sea attack: Merchant Navy officer’s family refuses cremation, seeks martyr status
Following a brutal attack in the Black Sea, the remains of Merchant Navy chief officer Sagar Gupta were brought back…
ITR filed under new regime, consultant’s mistake led to old regime & Rs 1.23L demand
A resident of Ali Asker Road, Bengaluru, Mr Shah filed his income tax return (ITR) under the new tax regime…
Watch: Boeing 777’s near-miss — wing skims inches from runway during risky manoeuvre
The widely shared footage has fuelled debate among aviation experts and pilots, many of whom questioned the unusually low altitude…