{"id":151052,"date":"2026-08-25T19:54:15","date_gmt":"2026-08-25T19:54:15","guid":{"rendered":"https:\/\/www.europesays.com\/ai\/151052\/"},"modified":"2026-08-25T19:54:15","modified_gmt":"2026-08-25T19:54:15","slug":"nvidia-earnings-preview-apples-ai-macs-openais","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ai\/151052\/","title":{"rendered":"Nvidia Earnings Preview, Apple&#8217;s AI Macs &#038; OpenAI&#8217;s\u2026"},"content":{"rendered":"<p>OpenAI&#8217;s &#8216;Jalape\u00f1o&#8217; Chip and Custom Silicon Ambitions<\/p>\n<p>OpenAI has released performance results for its first custom inference chip, &#8216;Jalape\u00f1o,&#8217; claiming it outperforms Nvidia&#8217;s systems in speed and efficiency. Richard Ho, OpenAI&#8217;s Vice President of Hardware, highlights that Jalape\u00f1o achieves high throughput and low latency simultaneously, a first in the industry. This is crucial for serving more customers more cheaply and providing faster response times for AI agents. Ho clarifies that the benchmarks were conducted using open-source, neutral methods, and that while Nvidia&#8217;s latest systems weren&#8217;t used due to their recent release, the comparison was against the best available products on the market.<\/p>\n<p>Ho explains that the Jalape\u00f1o chip&#8217;s design focused on reducing data movement, a key bottleneck for large models. This novel architecture, different from GPUs and CPUs, allows for the ultra-low latency that matters for gigantic workloads. OpenAI&#8217;s focus on inference, rather than training, is strategic, as they partner with Nvidia for training chips and aim to increase their own compute capacity for inference to meet growing user demand at lower infrastructure costs.<\/p>\n","protected":false},"excerpt":{"rendered":"OpenAI&#8217;s &#8216;Jalape\u00f1o&#8217; Chip and Custom Silicon Ambitions OpenAI has released performance results for its first custom inference chip,&hellip;\n","protected":false},"author":2,"featured_media":151053,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[306,25,3326,157,5070,186],"class_list":["post-151052","post","type-post","status-publish","format-standard","has-post-thumbnail","category-openai","tag-ai-startups","tag-artificial-intelligence","tag-investors","tag-openai","tag-startup-funding","tag-tech-news"],"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/151052","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/comments?post=151052"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/151052\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media\/151053"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media?parent=151052"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/categories?post=151052"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/tags?post=151052"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}