
Daniel T. Hall
6.4K posts

Daniel T. Hall
@danielthall
Not here anymore. Find me on Bluesky: @danielthall.bsky.social Strategy + Design @Toyota. Previously AI @Google



Using NotebookLM to remember everything you've read. On Hard Fork I talked about my collection of 8K quotes. I have them in a single notebook which effectively gives me a personalized AI grounded in the most important ideas I've read. Here's how to build your own version... A lot of folks have asked how I get 8,000 quotes into a single notebook, when currently notebooks are limited to only 50 sources. The key thing is that each source can have up to 500,000 words in it, so if you can compile your quotes into giant documents, you can easily fit a quote collection of that size into a single notebook. (You could almost have 80,000 quotes in fact!) 1. Use e-readers to highlight passages in books you read. 2. Use the amazing service @ReadWise to collect and organize all your quotations in one place. (They can be web clippings as well.) 3. When you have your quotes imported into ReadWise, choose the ones you want to add to a notebook (or select them all) and use Readwise's Export to Docs feature, which will format each quote so that it works brilliantly inside of NotebookLM. (Author, title, and page number will be attached to each quote.) 4. Once those docs have been created, add them all as sources to your "reading history" notebook Once you have those sources loaded, you can ask questions, brainstorm, explore new ideas -- all with an AI that has effectively read everything significant that you've read. And of course, you can always click on citations to jump back directly to the original quotes themselves. In this thread I've posted a few screengrabs of the range of queries you can use in a notebook stocked with your reading history... youtu.be/VyQox7MMjG8?si…






With friends at @Google we announce 💜 Magic Insert 💜 - a generative AI method that allows you to drag-and-drop a subject into an image with a vastly different style achieving a style-harmonized and realistic insertion of the subject (Thread 🧵) web: magicinsert.github.io











