{"id":19426,"date":"2024-10-18T16:38:07","date_gmt":"2024-10-18T16:38:07","guid":{"rendered":"http:\/\/scannn.com\/google\/how-to-get-started-with-googles-notebooklm\/"},"modified":"2024-10-18T16:38:07","modified_gmt":"2024-10-18T16:38:07","slug":"how-to-get-started-with-googles-notebooklm","status":"publish","type":"post","link":"https:\/\/scannn.com\/lv\/how-to-get-started-with-googles-notebooklm\/","title":{"rendered":"How to get started with Google\u2019s NotebookLM"},"content":{"rendered":"<p> <br \/>\n<\/p>\n<div>\n<p data-block-key=\"nuyqe\">You might know Steven Johnson as an author. He\u2019s written a number of books, many focused on the science of how we think and the history of innovation. But he\u2019s also a Googler who has worked on the NotebookLM team from the beginning of the project two years ago. \u201cSimply put, NotebookLM is a tool for understanding things,\u201d Steven says. Think of it as your virtual note-taking and research assistant: NotebookLM takes information, digests and analyzes it so that you can glean more from it. It\u2019s designed for that \u201cdeeper dive\u201d you may need to take into a topic \u2014 or multiple topics at once.<\/p>\n<p data-block-key=\"53ic9\">With NotebookLM, you create individual notebooks dedicated to a topic or project. You can upload up to 50 \u201csources\u201d with up to 25 million words \u2014 all from things like PDFs, Google Docs, websites and YouTube videos. Then, NotebookLM uses Gemini 1.5\u2019s multimodal capabilities to assess and make connections between the sources you\u2019ve added. You can ask questions about the content or ask NotebookLM to format it in a specific way \u2014 it will even provide citations that link back to the most relevant original passages in your sources. And along the way, your private information is never shared or used to train the model.<\/p>\n<p data-block-key=\"9b64u\">If you\u2019re just getting started, try these eight tips from Steven to get the most out of NotebookLM.<\/p>\n<h2 data-block-key=\"7qq81\">1. Experiment with your recent documents \u2014 even if they\u2019re random<\/h2>\n<p data-block-key=\"b5obi\">One of the first things Steven suggests new NotebookLM users do is upload their 10 most recent documents into one notebook and start experimenting by asking questions. Even if your most recent documents are unrelated and totally random, it\u2019s a great way to test run what NotebookLM can do. Whether you know the material in the documents down to the letter, or it\u2019s all pretty new to you, NotebookLM will help you uncover some interesting insights.<\/p>\n<h2 data-block-key=\"7g1vf\">2. Create one main notebook and then identify topic-based notebooks from there<\/h2>\n<p data-block-key=\"4dgja\">Steven suggests keeping what he calls an \u201ceverything notebook,\u201d which you load up with sources that include the general knowledge you work with most days. The sources might be inspirational quotes from books you read, or the core documents that describe the company you work for, or all your brainstorming ideas that you\u2019ve captured over the years. \u201cI do a lot of open-ended thinking and exploring of ideas in my \u2018everything\u2019 notebook,\u201d Steven says. But it\u2019s equally important to create topic- or project-based notebooks as well. \u201cI\u2019ve got a notebook devoted exclusively to the work we do building NotebookLM,\u201d Steven explains. \u201cIt\u2019s got all the press releases, new feature descriptions and important internal docs we write as a team.\u201d By keeping all those related sources in a single notebook, Steven effectively has a personalized AI that\u2019s almost like having another member of the team. \u201cI can go in there and type something like, \u2018Draft the outline of a blog post for that feature we were discussing last week,\u2019 and Notebook knows exactly what to do.\u201d<\/p>\n<h2 data-block-key=\"k6vh\">3. Use NotebookLM to connect the dots from different materials<\/h2>\n<p data-block-key=\"8leki\">NotebookLM is extremely useful for situations where you need to manage, connect and synthesize information from multiple sources. \u201cWe all have this problem where we\u2019re working on something, and the information we need is scattered across desktop folders, tabs and wherever else,\u201d Steven says. This is what NotebookLM is made for, he explains: connecting all those scattered dots.<\/p>\n<p data-block-key=\"a0jm0\">It can be especially helpful as a next step after using Gemini and Gems. After you brainstorm or have other open-ended conversations in those tools, NotebookLM can take the results and turn them into something easy to follow. Steven offers the example of working on a slide deck. Maybe you start the process by brainstorming with Gemini, which leads you to open a few tabs of articles, save some design inspo images and put some notes in a Google doc. You can then feed all of that into NotebookLM, which will synthesize the information into an easy-to-digest format so you can reference everything in one place when you get to the stage of building your presentation in Google Slides.<\/p>\n<h2 data-block-key=\"8n2bp\">4. Start with the suggested questions<\/h2>\n<p data-block-key=\"9ug9j\">Once you\u2019ve added content to NotebookLM, it\u2019s time to start asking questions \u2014 which might leave you stumped. Similarly to tips we shared about using the Gemini-powered side panel in Workspace tools, Steven says NotebookLM\u2019s suggested questions are a great resource. \u201cThe model will actually help you ask questions that guide you through the material for a while until you think of something you want to ask,\u201d he explains. You can find some starter questions in the &#8220;Notebook Guide&#8221; that appears after you upload your first sources. Plus, when you start asking questions, NotebookLM will suggest follow-up queries, too, based on what you\u2019ve already asked and what you uploaded.<\/p>\n<h2 data-block-key=\"aj1gi\">5. Ask NotebookLM to deliver info in different ways<\/h2>\n<p data-block-key=\"680h\">Something that came out of early testing, Steven says, was the need for NotebookLM to show information in various formats. \u201cEveryone processes information differently, or even just prefers to see information presented in different ways,\u201d he explains. Using the Notebook Guide feature, NotebookLM can turn your uploaded content into an FAQ, a briefing document, a timeline, a table of contents, a study guide \u2014 or the popular new Audio Overview, which actually transforms your information into an engaging conversation between two AI \u201chosts.\u201d Try different options both to see what works best for your own learning purposes as well as for presenting information to others.<\/p>\n<h2 data-block-key=\"8jfgv\">6. Don\u2019t shy away from creative uses<\/h2>\n<p data-block-key=\"glt5\">NotebookLM is an amazing resource for work and school projects (the team actually just launched a pilot program for NotebookLM Business for collaborating within a workplace). But it\u2019s also a great tool for lots of creative uses outside the office or classroom. \u201cWe\u2019re seeing a lot of people using it for assistance with writing fantasy and sci-fi novels or developing games where they\u2019re working on world building and intricate backstories,\u201d Steven says. Maybe for your screenplay, you jotted down some notes in a doc, saved various webpages and took photos and videos as inspiration. \u201cThere\u2019s all of this information that can be hard to keep straight,\u201d Steven says. \u201cYou can put all of that stuff into a single notebook and ask things like, \u2018What was the deal with that one character?\u2019 Or \u2018Remind me which characters live where?\u2019\u201d<\/p>\n<p data-block-key=\"94u4u\">Steven particularly likes that you can ask NotebookLM for creative input with questions like, \u201cWhich characters do you think are most compelling?\u201d or, \u201cWhat are your favorite parts?\u201d \u201cIt\u2019s like being able to control F for \u2018interestingness\u2019!\u201d he says.<\/p>\n<h2 data-block-key=\"du39f\">7. Turn your sources into Audio Overviews<\/h2>\n<p data-block-key=\"8i6nm\">You should definitely turn each of those 10 documents you start with, or whatever else you upload, into an Audio Overview, Steven says. \u201cAfter waiting a few minutes for it to generate, you will have a very entertaining, kind of mind-blowing audio conversation about whatever you uploaded!\u201d Steven says. And the team has just released a new feature in Audio Overviews that allows you to adjust the format of the conversation. Just hit \u201cCustomize\u201d in the Audio Overviews panel and enter a short description of what you want the hosts to focus on from your sources. \u201cYou can also steer them in terms of the approach of the level of sophistication you want from the Overview,\u201d Steven explains. \u201cI\u2019ve been uploading my own writing and asking them to give me constructive criticism about my work.\u201d<\/p>\n<\/div>\n<p><br \/>\n<br \/><a href=\"https:\/\/blog.google\/technology\/ai\/notebooklm-beginner-tips\/\">Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>You might know Steven Johnson as an author. He\u2019s written a number of books, many focused on the science of how we think and the history of innovation. But he\u2019s also a Googler who has worked on the NotebookLM team from the beginning of the project two years ago. \u201cSimply put, NotebookLM is a tool [&hellip;]<\/p>\n","protected":false},"author":16,"featured_media":19427,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[100],"tags":[],"class_list":["post-19426","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-google"],"_links":{"self":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/posts\/19426","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/users\/16"}],"replies":[{"embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/comments?post=19426"}],"version-history":[{"count":0,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/posts\/19426\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/media\/19427"}],"wp:attachment":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/media?parent=19426"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/categories?post=19426"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/tags?post=19426"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}