OpenAI's Custom Chip Embarrasses Nvidia, While Company Vows to Keep Buying From It
6 Articles
6 Articles
ChatGPT has achieved a significant breakthrough, announcing its success in developing its own AI chipset. This is the company's first, and it aims to reduce its current dependence on Nvidia.
OpenAI's Custom Chip Embarrasses Nvidia, While Company Vows to Keep Buying From It
The post OpenAI’s Custom Chip Embarrasses Nvidia, While Company Vows to Keep Buying From It appeared first on 24/7 Wall St.. OpenAI published a newsroom post on August 25, 2026, announcing its first custom inference chip, called Jalapeño. On a public benchmark, a 700-watt part from OpenAI outperformed Nvidia (NASDAQ:NVDA) accelerators rated at 1,200 and 1,400 watts. The obvious read is that OpenAI has begun replacing its largest supplier. The do…
OpenAI has created a chip that beats Nvidia's best products in selected benchmarks, but that advantage alone isn't Jensen Huang's biggest problem. Jalapeño undermines something far more valuable than a few performance records—and this on the eve of the largest manufacturer of AI pickaxes' financial statements.
OpenAI has designed its first AI chip, named Jalapeño, but does not manufacture it directly. This chip was developed to serve OpenAI's AI infrastructure, helping the company reduce costs and lessen its dependence on Nvidia GPUs.
OpenAI has released today the first performance results of Jalapeño, its first inference chip of its own, and the numbers are good enough for the industry to take them seriously. The chip, co-developed with Broadcom and manufactured in the TSMC N3P (3nm) process, delivered between 1.5 and 1.9 times more AI work per watt and between 1.7 and 3.6 times less latency than comparison systems — the NVIDIA GB200 and GB300 — in the benchmarks of the Infe…
OpenAI's Jalapeño AI Chip Shows Faster Inference Than Nvidia's Flagship GPUs GB200 and GB300
OpenAI's Jalapeño inference system has beaten Nvidia GB200 and GB300 on latency and throughput per rated kilowatt in company-run benchmark tests. The post OpenAI’s Jalapeño AI Chip Shows Faster Inference Than Nvidia’s Flagship GPUs GB200 and GB300 appeared first on WinBuzzer.
Coverage Details
Bias Distribution
- 50% of the sources are Center, 50% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
