<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>AI Applications on 梦兽编程</title><link>https://rexai.top/en/categories/ai-applications/</link><description>Recent content in AI Applications on 梦兽编程</description><generator>Hugo -- 0.163.3</generator><language>en</language><copyright>梦兽编程</copyright><lastBuildDate>Sat, 01 Aug 2026 10:00:00 +0800</lastBuildDate><atom:link href="https://rexai.top/en/categories/ai-applications/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Agents Go to Work: qm, YC's Open-Source Multiplayer Agent Harness</title><link>https://rexai.top/en/posts/2026-08-01-qm-multiplayer-agent/</link><pubDate>Sat, 01 Aug 2026 10:00:00 +0800</pubDate><guid>https://rexai.top/en/posts/2026-08-01-qm-multiplayer-agent/</guid><description>YC&amp;#39;s team open-sourced qm: a multiplayer agent harness where every employee gets an isolated workspace while agents also collaborate in Slack channels, groups, and projects. 465 HN points later, the real problem isn&amp;#39;t the agent loop — it&amp;#39;s scoping and trust governance. The first complete answer to taking agents from personal assistants to team employees.</description></item><item><title>AI Office Agents: Fast and Cheap, But Not Ready to Ship</title><link>https://rexai.top/en/posts/2026-07-30-ai-office-agent/</link><pubDate>Thu, 30 Jul 2026 12:00:00 +0800</pubDate><guid>https://rexai.top/en/posts/2026-07-30-ai-office-agent/</guid><description>Baidu&amp;#39;s OmegaUse-OfficeVal benchmark tested 6 frontier AI agents on 100 real office tasks. The best model scored only 64% of the human baseline, and 38% of tasks scored zero. AI is faster and cheaper — but it can&amp;#39;t sign off on the result yet.</description></item></channel></rss>