video1.0<iframe src="https://www.loom.com/embed/1b7dc48bbef245eab4e1244e28290bae" frameborder="0" width="1112" height="834" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>8341112Loomhttps://www.loom.com8341112https://cdn.loom.com/sessions/thumbnails/1b7dc48bbef245eab4e1244e28290bae-5f61e0e8f9d832c0.gif170.9865In this video, I demonstrate our project that aggregates political bias and manipulation in Twitter feeds using the Chrome AI model and Gemma 2.5 flashlight. I show how the model assesses my feed, revealing a bias score of R0.20, and how it reacts to different threads, like Trump's, which skews right. We also have a manipulation slider that measures tweet manipulation on a scale of zero to one, and I've tested various methods to define manipulation. I encourage you to explore how the model understands context and biases in real-time as we continue to refine its performance. Please let me know your thoughts on the findings!