<?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/53ceb35aa8a04768aca64bff1a4362ae&quot; frameborder=&quot;0&quot; width=&quot;1662&quot; height=&quot;1246&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1246</height><width>1662</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1246</thumbnail_height><thumbnail_width>1662</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/53ceb35aa8a04768aca64bff1a4362ae-a667ee6d01a1fda9.gif</thumbnail_url><duration>156.054</duration><title>Introducing Loopism: A Self-Improving Music Generation Artist</title><description>In this video, I introduced Loopism, our self-improving musical generation artist that creates music based on user preferences, like summer vibes. We have a generation agent that produces music, a critiquing agent, and a finding agent to evaluate the quality of the music. I demonstrated how users can rate tracks, with a threshold of four stars or a confidence score of 75 to save the music in our system. We utilize Weave to trace decisions and Redis for fast pattern learning, ensuring the system continuously improves. I encourage you to explore the UI and provide feedback on your experience.</description></oembed>