<?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/d80c8bbeede3447889dc0e199869baac&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/d80c8bbeede3447889dc0e199869baac-f0a9e9355a93f985.gif</thumbnail_url><duration>134.701</duration><title>Game Lich AI Number Guessing Improvements 🎮</title><description>Hi, my name is Shana Genta, and I presented my Game Lich project, an interactive AI power and number guessing game built with Streamlit. The easy mode uses a 1 to 20 range, normal is 1 to 100 with 8 attempts, and hard is 1 to 500 with 8 guesses. I implemented an AI strategy that acts like an agent, analyzing prior guesses and using binary search to pick the next best move. During the demo, I showed sample inputs with too high and too low feedback, plus AI guidance on the remaining range. I did not ask the viewers to take any specific action.</description></oembed>