<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Gpt5 on AI Agents News</title>
    <link>https://aiagentsnews.top/tags/gpt5/</link>
    <description>Recent content in Gpt5 on AI Agents News</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Sat, 25 Jul 2026 12:45:21 +0000</lastBuildDate>
    <atom:link href="https://aiagentsnews.top/tags/gpt5/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>GPT5.6 tool calling: Why the client-owned loop matters</title>
      <link>https://aiagentsnews.top/posts/gpt56-tool-calling-why-the-client-owned-loop-matters/</link>
      <pubDate>Wed, 22 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/gpt56-tool-calling-why-the-client-owned-loop-matters/</guid>
      <description>GPT5.6 returns tool names, not code. Learn why the client-owned function loop and strict schemas are non-negotiable for autonomous systems.</description>
    </item>
    <item>
      <title>Coding agents: Simon Willison&#39;s new llmcodingagent</title>
      <link>https://aiagentsnews.top/posts/coding-agents-simon-willisons-new-llmcodingagent/</link>
      <pubDate>Sat, 04 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/coding-agents-simon-willisons-new-llmcodingagent/</guid>
      <description>Simon Willison&#39;s llmcodingagent 0.1a0 enables local file edits via explicit tool calls, contrasting with the 83.4% TerminalBench scores seen elsewhere.</description>
    </item>
    <item>
      <title>TerminalBench 2.1 exposes agent wrapper gaps</title>
      <link>https://aiagentsnews.top/posts/terminalbench-21-exposes-agent-wrapper-gaps/</link>
      <pubDate>Sun, 28 Jun 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/terminalbench-21-exposes-agent-wrapper-gaps/</guid>
      <description>Codex CLI paired with GPT-5.5 sits at the top of the Terminal-Bench 2.1 leaderboard with an 83.4% pass rate.</description>
    </item>
  </channel>
</rss>
