<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Tool-Use on Best of AI</title><link>https://bestofai.io/tags/tool-use/</link><description>Recent content in Tool-Use on Best of AI</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Mon, 31 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://bestofai.io/tags/tool-use/index.xml" rel="self" type="application/rss+xml"/><item><title>GLM-5.2 Turbo</title><link>https://bestofai.io/models/glm-5-2-turbo/</link><pubDate>Mon, 31 Aug 2026 00:00:00 +0000</pubDate><guid>https://bestofai.io/models/glm-5-2-turbo/</guid><description>&lt;p&gt;Zhipu AI released GLM-5.2 Turbo on August 17, 2026 as a faster sibling to GLM-5.2, built specifically for agent-driven workloads rather than general chat or one-off queries. It carries a smaller context window than the base model, about 200,000 tokens versus GLM-5.2&amp;rsquo;s full 1-million-token capacity, in exchange for lower latency on the long execution chains typical of coding agents and automation tools. Zhipu says it improved complex instruction decomposition and tool use, along with stability across scheduled and persistent tasks that run for extended periods without human supervision.&lt;/p&gt;</description></item></channel></rss>