{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/badb94ad47cf40b7828a5decc5fbd5a9\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/badb94ad47cf40b7828a5decc5fbd5a9-45219a45e9f55828.gif","duration":862.7892,"title":"CustomGPTs","description":"In this video, I delve into the evolution of my GPTs, starting from my first language model 8 years ago to the latest version, DSLmodels. I discuss the significance of sparse priming representations (SPR) in efficiently representing ideas and memories. I demonstrate the process of creating a custom metaprompt assistant and delve into the theory behind SPR techniques. Viewers are encouraged to follow along as we create a new custom GPT for decompression."}