<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Inference on AI Agents News</title>
    <link>https://aiagentsnews.top/tags/inference/</link>
    <description>Recent content in Inference on AI Agents News</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Fri, 24 Jul 2026 12:09:21 +0000</lastBuildDate>
    <atom:link href="https://aiagentsnews.top/tags/inference/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Inference latency: Why 41B active beats 975B</title>
      <link>https://aiagentsnews.top/posts/inference-latency-why-41b-active-beats-975b/</link>
      <pubDate>Thu, 16 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/inference-latency-why-41b-active-beats-975b/</guid>
      <description>Learn why 41B active parameters matter more than total count for agent latency. Discover selection criteria for reliable, cost-effective systems.</description>
    </item>
    <item>
      <title>OpenAI Jalapeño chip cuts inference costs by half</title>
      <link>https://aiagentsnews.top/posts/openai-jalape%C3%B1o-chip-cuts-inference-costs-by-half/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/openai-jalape%C3%B1o-chip-cuts-inference-costs-by-half/</guid>
      <description>OpenAI&#39;s Jalapeño chip targets a 50% cost drop per token. We analyze the 3nm specs and what proprietary silicon means for your agent stack.</description>
    </item>
  </channel>
</rss>
