<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/55aadf1aa3cd4486b3d4e8ef67fbc68e&quot; frameborder=&quot;0&quot; width=&quot;1178&quot; height=&quot;883&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>883</height><width>1178</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>883</thumbnail_height><thumbnail_width>1178</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/55aadf1aa3cd4486b3d4e8ef67fbc68e-1715408329927.gif</thumbnail_url><duration>163.18</duration><title>PressText in 68 seconds</title><description>In this video, I explain how we are using a large language model and a raptor framework for retrieval to make journalism accessible through text message. I demonstrate how we can ask questions about news articles that we don&apos;t understand and get answers in a quick and convenient way. I also highlight the importance of large language models in providing summaries and better understanding of complex news topics. Watch the video to learn more about this innovative approach to accessing news and becoming more informed citizens.</description></oembed>