Episode Categories:
Resources:
Join the discussion: Ask Jordan questions on NotebookLM
Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Connect with Jordan Wilson: LinkedIn Profile
Try Our Free AI Prompting Course: Register for our free Prime, Prompt, and Polish AI Course!
A Closer Look at NotebookLM
Artificial Intelligence (AI) has the capacity to completely revolutionize how businesses operate, particularly in relation to data management. Recently, an AI tool named 'NotebookLM', developed by Google, has made quite an impression amongst the tech community. NotebookLM integrates a generous amount of data, provides greater accuracy, and offers practicality that surpasses other similar models. However, it's likely that many decision makers, business owners, and LinkedIn's standard demographic have yet to be introduced to this transformative tool.
NotebookLM enables users to upload up to 50 sources, totaling a maximum of 25,000,000 words. These sources may come from a plethora of platforms such as YouTube videos, websites, and virtually any type of document. Furthermore, NotebookLM is an AI tool built on Google Gemini 1.5 Pro, marking it as highly powerful. Despite being free to use, one must have a Google account to access it. An interesting aspect about NotebookLM is that it doesn’t save chat history, ensuring user data is entirely private.
Why 'NotebookLM' Outshines Its Competition
While Google's Gemini model has its advantages, it fell short due to marketing discrepancies and limitations. NotebookLM is seen as a more impressive and practical choice, offering extensive features that cater to a user's every need. In fact, it's speculated that Google may even begin charging for NotebookLM due to its overwhelming popularity.
Exciting Updates Coming to 'NotebookLM'
NotebookLM users have something to look forward to: future updates are set to introduce bots that enable different notes to interact, boosting productivity through their agentic capabilities. Additionally, another upcoming update promises improved user experience and more exciting features. It serves to illustrate Google’s strategic commitment to enhancing user experience.
Key Considerations with 'NotebookLM'
With NotebookLM's recent popularity, there have been concerns about potential future charges and data privacy. These are valid considerations and users are advised to understand the terms of data privacy when uploading documents. Particular website restrictions may also prevent data scraping, so being aware of these limitations can help optimize NotebookLM's usage.
Bringing AI to Life with 'NotebookLM'
NotebookLM has been proven to be quite effective for handling large volumes of personal data, and it's also capable of editing coding projects including Python, CSS, and HTML. Its usage of a rag (Retrieval Augmented Generation) grounded approach, which connects AI outputs to real-world information or specific knowledge bases, helps to increase accuracy and relevance.
Conclusion
With its extensive functionalities, NotebookLM is an AI tool that is too good to be overlooked. Its potential to significantly improve workflow and data management could greatly benefit the business sector, making it a worthwhile investment. Keep an eye on this space for more developments on NotebookLM - the best AI tool you’ve probably never used, but definitely should.
Topics Covered in This Episode
1. Features of NotebookLM
2. NotebookLM vs Google Gemini
3. Benefits of NotebookLM
4. Use Cases for NotebookLM
Podcast Transcript
Jordan Wilson [00:00:17]:
NotebookLM from Google is the best AI tool that you've probably never used. Yeah. We've talked about it on the everyday AI show plenty, But I think some recent updates from Google's notebook l m makes it not just one of the most useful AI tools, but probably one of the best. Right? One of the things that we always, worry about when using large language models is number 1, how can it work off my company's data? And number 2, how can we get rid of hallucinations? Right? So whether you're using Microsoft Copilot, Google Gemini, chat gbt, and profit claw. Those are things that are you are constantly, kind of struggling with. Notebook l m kind of solves it. It's wild. Alright.
Jordan Wilson [00:01:16]:
We're gonna be talking about notebook l m, what you need to know, how to use it, the pros and the cons, everything today on everyday AI. What's going on y'all? My name is Jordan Wilson, and I'm the host of everyday AI. This is for you. It's for everyday people. How we can all learn and leverage generative AI through a daily livestream podcast and the free daily newsletter. If you're brand new here, maybe this notebook l m caught your eye and you wanna know more. Well, you are in the right place. Alright? So, if you haven't already, please make sure you go to your everyday a i.com.
Jordan Wilson [00:01:49]:
Sign up for our free daily newsletter where every single day we recap our podcast episode, but also it is literally a free generative AI university there. We have more than 360 different episodes, so go learn from the world's experts who are leading in AI, whatever you care about, marketing, advertising, education, nonprofits. There's a category there. You can learn everything. So make sure you go check that out. Alright. Before we get into notebook l m, and I am very excited for today's show, Let's first start as we do every single day by going over the AI news. So first of all, speaking of OpenAI, OpenAI has their dev day today in San Francisco.
Jordan Wilson [00:02:32]:
So OpenAI's dev day 2024 is set to kick off today in San Francisco. So while the in person event is invitation only, there could be a live stream available, but we're not really sure yet. This has been a kind of quiet, announcement from OpenAI. They've talked about having dev days, throughout the world really in different cities, but this is their 1st dev day in 2024. And like I said, there's very few details, but if we follow most of their patterns, there could be a live stream today around 11 AM CST. That's kind of how they've normally done it. And you can just kinda keep an eye on, OpenAI's, you know, social media accounts, but generally they will put out a live stream on YouTube. So we'll see if that actually happens.
Jordan Wilson [00:03:21]:
Last year at dev day, OpenAI announced a lot. The new model their new model of the time, GPT 4 Turbo, the assistance API, custom GPTs, so many new capabilities. So we'll see if this year they if they're announcing anything new. I don't necessarily think that we're gonna be seeing anything big, today. I think that it's mainly going to be developer tools and some API improvements, lower cost, etcetera. But we might get some news on the new o one model or some Sora or DALL E updates. Alright. Cerabras Systems has filed for an IPO amid growing AI chip competition.
Jordan Wilson [00:04:00]:
So, Cerebras Systems, an AI chip startup, has filed its prospectus for an initial public offering aiming to trade under the tickle the ticker symbol CBRS on the Nasdaq. So this move comes as the company seeks to establish itself in a competitive market dominated by giants like Nvidia. Yeah. When we talk about, generative AI, we have to talk about the GPU chips, that power it all and just the, immense needs for that power and energy. So the company's WSE 3 chip, which boasts more cores and memory than Nvidia's popular H100, positions itself as a strong contender in the AI chip market, which is increasingly crowded with competition from companies like AMD, Intel, and even Google. So, the technology IPO market has actually been kinda sparse, since in 2024, so not a lot of new, technology companies going public. But there's obviously rising interest rates pushing investors toward more profitable assets, making Cerebras IPO a significant event to watch. Major investors in Cerebras right now include Foundation Capital, Benchmark, and Eclipse Ventures with notable individual backers like OpenAI CEO Sam Ullman.
Jordan Wilson [00:05:19]:
Interesting there. Alright. Last but not least, Microsoft is slowly, maybe, quietly rolling out a Copilot 2.0 with new features and a fresh a fresh look, for web users using copilot@copilot.microsoft.com. So Microsoft is reportedly set to launch an updated version of its very popular copilot AI chatbot featuring a revamped interface and new functionalities aimed at enhancing user experience. So the new CoPilot 2.0 will showcase a post, pastel shaded user in their interface. That's hard to say in the morning. Pastel shaded user interface, replacing the previous, design, and it is reported to be faster and more intuitive and friendly similar to chat gbt. It's also rolling out a card based design that could be implemented encouraging users to explore various AI applications such as journaling or improving sleep.
Jordan Wilson [00:06:17]:
So So for the first time, Copilot will also include a voice mode allowing users to interact with the AI using spoken commands. So it has 4 new voices right now, Meadow, Grove, Wave, and Canyon. Also upon a first use, Copilot 2.0 will ask for the user's name and remember it for future sessions, creating a more personalized experience. Alright. Lot more on those stories and so much more. So make sure you go to, your everyday ai.com. Alright. Livestream audience, thanks for joining us.
Jordan Wilson [00:06:51]:
I know there's there's a bunch of LinkedIn problems, you know, happening with our livestream, but you can always catch up on the podcast or, you know, on on YouTube. So, yeah. Thanks for, sabbatical life who let everyone know, hey, frozen on YouTube, go over or sorry, frozen on LinkedIn, go over to YouTube. Yeah. Sorry about that y'all. But nonetheless, let's jump right into it. Notebooklm from Google is frigging amazing. Did did our first review of the tool probably, like, 4 or 5 months ago, but there's been some recent developments, that I think makes this a no brainer, for everyone to use.
Jordan Wilson [00:07:31]:
Companies, individuals, for fun use cases, for business use cases. There's no, honestly, it's probably one of my most used tools. Alright. So let's talk about some of those use cases, and we'll tell you what it is. But, you know, notebook l m, it's not technically its own model. It is an AI tool from Google based on their Google Gemini model. Some use cases for it that I love right off the bat just so you can kind of, set your mind to it. The ability to learn, having it, you know, having a learning assistant like this is it's wild.
Jordan Wilson [00:08:11]:
Right? So, we're gonna do some live demonstrations later, but, I love to use it for learning. I love it to use it as a personal large language model, and then also a fast company RAG model. Alright. We're gonna talk more about, you know, grounded models and retrieval augmented generation here in a minute. And also, I do wanna talk about this, and I I wanna talk about how significant this is. We always talk about these, you know, now it's just called the ChatGPT moment. Right? In technology, in AI. Right? But it's kinda like that moment.
Jordan Wilson [00:08:49]:
Right? It's it's when you there's almost kind of like a line in the sand, you know, like, wow. This is this is pretty big. This is pretty big. If I'm being honest, when ChatGPT came out in November 2022, I wasn't very impressed, which I'm always, like, curious. Right? Even NVIDIA CEO Jensen Huang, you know, talks about the ChatGPT moment. Right? Kind of this, shift toward traditional AI and traditional machine learning to this generative AI wave. You know, Jensen Wong and most others talk about the ChatGPT moment. When ChatGPT came out, I was not very impressed if I'm being honest.
Jordan Wilson [00:09:27]:
You know, at that time, our our company, we had been using different GPT tools for more than a year, right, since late 2020. So, almost 2 years. So ChatGPT, when it came out, I was not impressed. It wasn't even one of my 5 favorite GPT tools. So it's always funny when we talk about this ChatGPT moment in this kind of that you're like, oh, okay. This makes me think about AI a little differently. And I wanted to share some of mine. So for me, there were a couple, but it wasn't ChatGPT.
Jordan Wilson [00:10:02]:
I'd say one of my first ChatGPT moments or sorry. Yeah. Was when ChatGPT got plugins. Okay? Plugins are obviously gone now in lieu of GPTs, but the thing that really was an moment for me about ChatGPT plugins, well, you could run 3 of them at a same time, at the same time. And we almost had agentic AI at that point. Right? Now it's gone. But essentially, you could have 3 different plugins doing different tasks working with each other. So plugin a could go research something, pass that information off to plugin b, and then autonomously would do the work between the 3 plugins.
Jordan Wilson [00:10:43]:
That's gone. We have GPTs now, but you can only use 1 GPT at a time. But that was probably my first ChatGPT moment. Then Suno, the, kind of text to music and the AI music, platform. I don't know if any of our livestream audience has, used Suno. It's amazing. Right? And that's another one. When I heard Suno, I immediately reached out and had their CEO, Mikey, on the Everyday AI Show.
Jordan Wilson [00:11:09]:
And then probably one of my more recent ones was Claude artifacts. Right? The ability for a large language model to essentially deploy code, and and and to render code live in the browser, Huge. Right? A a huge step for large language models. Notebooklm has been my latest. It is at least for me, and I think for a lot of people, it is a ChatGPT moment. I know that's a weird thing to say. Right? Like, oh, notebook LM is a ChatGPT moment, but I think it is. Because I think it is slowly changing what is possible with large language models.
Jordan Wilson [00:11:47]:
So emphasis on the slowly, because with some of these other tools, it was almost like love at first sight or, you you know, the moment at first sight. It wasn't like that, at least for me with notebook l m, because like I said, we've we've reviewed it 4 months ago. And I was like, oh, this is great, but I think it's actually been some of these quiet updates over the last couple of months that have really turned this thing into a powerhouse. Alright. So let's go over the basics. Alright. Let's go over the basics of notebook l m. So it is based on Google Gemini's 1.5 pro.
Jordan Wilson [00:12:25]:
Alright. So, yes, this is from Google. It is not its own model. Right? NotebookLM is not a a frontier foundation model. It is an AI tool built on top of Gemini 1.5 pro, Google's, most powerful large language model right now. It is free to use. Let me repeat that. It is free to use.
Jordan Wilson [00:12:50]:
Okay? Wild. But you do need a Google account, FYI. Alright. Also, as always, a big, a big key, a big feature that sets notebook l m aside from, apart from others is the ability for it to handle large amounts of your data. Right? So before you run out there and dump everything, in Google's notebook l m, As always, be aware of what companies do with your data, read their privacy policy, etcetera. Okay? I gotta get that out of the way. Here's the other thing that you need to know. It's not a traditional chat interface.
Jordan Wilson [00:13:31]:
Alright. I'm gonna explain what that means a little bit more, but it doesn't save chat history. It works on this thing called notes, so notebook l m. Right? And I actually think that's a bad thing, or or sorry. I actually think that's a good thing. Even though it sounds like a bad thing, right, not saving your chat history, I actually think it's a good thing, and I'm gonna explain that to you later. The biggest thing here that sets everything else apart is being able to quickly and easily upload all of your documents. And when I say all, I mean, my gosh, it can handle a lot of your documents.
Jordan Wilson [00:14:06]:
Then the very popular Deep Dive AI podcast. Right? That's probably what has caused notebook l m to fall on your radar, and this was not an original feature. Right? This feature has only been out for a couple of weeks. We we reviewed it the day it was released and shared that in our newsletter. But I think that's really what has built this, into kind of an all encompassing tool, to learn. Right? And then it is a grounded rag approach. Retrieval, augmented generation, we're gonna talk about that more in a second. And it is y'all.
Jordan Wilson [00:14:43]:
It is stupid impressive. It's very impressive. Sabbatical life says, yeah. Free for now. Jackie Jackie joining from YouTube. Yeah. Our normal LinkedIn audience. All I had to leave.
Jordan Wilson [00:14:57]:
LinkedIn. What's wrong with you, LinkedIn? Says Jackie says when everyone uses it and it's like crack, Google will charge. Maybe. Or is this their Trojan horse? We'll see. Alright. So from a visual perspective, podcast audience, I'm gonna describe this to you. It's very simple. When you go into notebook l m, you essentially will click on new notebook.
Jordan Wilson [00:15:19]:
Think of notebooks as a chat where you upload all of your documents. Okay? And when I say all of your documents, I mean all of them. Because now as of this week, there are some new file formats that I think, like I said, it is kind of this slow rollout of multiple things that have made, this moment for notebook l m. So you can upload files from Google Drive. Right? So your Google Docs, Google Slides, etcetera. So it natively, reads your Google files. So if you are a Google Workspace user, whether personally with a Gmail address, your company, that's great. Then you can also upload links to websites and YouTube URLs.
Jordan Wilson [00:16:04]:
That part is huge. Right? That part is huge. YouTube URLs. That saves so much time. However, it is worth pointing out the video has to have captions enabled. Otherwise, it won't work. Similarly, with a website, if a website blocks certain, certain bots essentially. Right? So a lot of website publishers now are, putting something essentially in their robots dot t x t file that tells the rest of the Internet how it can and cannot access the information.
Jordan Wilson [00:16:36]:
So if certain, news art if if certain articles or websites block access to certain scrapers or crawlers, that won't be able to work. However, you can just paste the text in there. So that is the last kind of, option there at the bottom, but then you also have the ability to upload any files you've downloaded. So it's not just Google only. Right? It's not just, oh, I don't have Google Docs, so I can't use it. Well, you can copy and paste anything, website links, YouTube links, and also here's the other huge the other huge one. The ability now to upload MP threes. Yeah.
Jordan Wilson [00:17:12]:
Y'all think of all the all the use cases already. Right? Being able to record all your meetings. Right? Download the audio of those meetings or the transcripts, and you literally have a notebook that can handle everything, a large language model that can handle every single thing you're working on. And I can't emphasize enough the context that you can fit in. Alright. That is what makes notebook LM different immediately, is you can upload up to 50 sources. And you might be saying, okay, Jordan, that's that's not a lot. You know, I have more than 50 files on my computer.
Jordan Wilson [00:17:53]:
Okay. Well, you can combine them because each source can be up to 500,000 words. Okay. That is 25,000,000 words. 500,000 words per source, 50 sources. That is 25,000,000 words. Alright? There are very few aside from enterprise companies, but you can get 90% of the day to day data that you need right there. We have, for the first time, a business, rag, large language model that is so easy to use.
Jordan Wilson [00:18:33]:
That's one of the things that makes notebookLM different. And, hey, livestream audience, thank you all for for jumping over to, to to YouTube. Sorry that, LinkedIn is not working, but if you have questions, please get them in now. Alright. Another things that makes this different, well, it's a grounded model via a rag approach. Alright. Let me quickly explain what that is, and I'm going to oversimplify it. So if you're a, even nerdier than I am, you know, you don't have to say, oh, Jordan, you're wrong on these definitions.
Jordan Wilson [00:19:04]:
I'm simplifying here. I wanna talk about what it means for a model to be grounded. Okay. So grounding is a broad concept in AI that essentially refers to connecting an AI systems understanding in its outputs to real world information or a a specific knowledge base like your company's knowledge or something specifically that you're trying to learn. Alright. So grounding aims to make AI responses more accurate, more hallucination free, relevant, and aligned with certain facts or scenarios. Okay. So that is the concept of a grounded model.
Jordan Wilson [00:19:38]:
One of the ways that you achieve a grounded model, one of the ones that's most probably, relevant to people here is retrieval augmented generation or RAG. It is a process to ground a model. So most of you all have heard about RAG, but RAG is essentially a technique that enhances AI models by retrieving relevant information from external sources to help augment the model's knowledge when a user asks for something. Right? So, you know, we talk about a RAG layer. Okay? So think, when you send a query to a large language model, it goes straight to that model. So a rag layer or the process of retrieval augmentative generation, think of it as a layer between your question and the and the model itself. Okay? That is a rag layer. For all intent purposes, we're simplifying here.
Jordan Wilson [00:20:33]:
Okay? And you put your mod all your information in this kind of retrieval augmentive generation layer. And that is one of the ways you can ground a model to make it more factual, to make it more hallucination free. Right? Because that's one of the biggest problems right now with any model is fighting fighting against hallucinations and also bringing your data in there. So, essentially, having RAG inside of a model combines the best of a large language model with that retrieval system, so you can get up to date information and domain specific knowledge. Okay? Here's the thing I love about notebook l m. It is rag or grounded by default. You cannot go in, click new notebook, and just start chatting. That's not how it works.
Jordan Wilson [00:21:24]:
Right? If, let's say you work at a shipping company, and you're in marketing at a shipping company. Right? You're gonna upload all your documents, all your meetings, etcetera. You aren't going to use that model to write a haiku, about, advertising at a marketing company. Right? It is grounded in the data. So for the most part, although you can always kind of, you know, quote unquote jailbreak it, or kind of make it go in a different direction. It is only going to work in the data that you provide it. Right? If you ask it to do something else that is not really in its knowledge base, it's gonna nicely tell you, hey, that's not really what I'm here for. So one one kind of, phrase that I like to tell people when working with a grounded model, is it's grounded.
Jordan Wilson [00:22:15]:
Think of it like that. Right? Little Jordan in the corner got in trouble, got grounded. He's gotta stay there. Can't do anything else. He's gotta stay there and look in the corner. So the same thing when you set up a new notebook inside of notebook l m. It is grounded. Right? You have to start by putting it in the corner, and you say, hey, model.
Jordan Wilson [00:22:33]:
This is literally all you can look at and all you can work on. So it's very different than a traditional model that you can it's not grounded. You can do literally anything and everything. And even when you upload your documents right into ChatGPTs. Right? You can build a custom GPT inside of Claude's projects. Right? Inside of Google's gems. Right? So all of these kind of versions of the big models that you can personalize with your data. Right? So those are kind of the 3 comparisons.
Jordan Wilson [00:23:05]:
Custom GPTs from ChatGPT, Claude Projects and Google Gems. And then also, Microsoft Copilot has, GPTs as well. Although they got rid of that on the pro plan, which I'm sad about. Anyways, so all the other model makers, you can do something similar. Right? Upload all your data, give it some custom instructions, But here's the thing, those models aren't grounded even after you do that. Right? And that's can be actually frustrating sometimes, because you kinda want the best of both worlds. You want a model that can openly do anything and everything, and you you know, it has all these crazy capabilities, but you're like, no no no no. Be grounded.
Jordan Wilson [00:23:40]:
Only use my data. Well, it can actually be difficult when using those other systems even if you're trying to build a smaller version via GPTs, via projects, via gems inside of Google because those models aren't grounded, and they're still maybe going to go in other directions that you might not want them to. And it might use either its own internal training base, its own internal data, or it might browse the web and bring in information that you do not want. That is not an option with notebook l m, which some people might say, oh, that's a huge downer. I think that is the biggest benefit. Like, everyone wants to get rid of hallucinations and they want to work with their data. Well, there you go. The best and most accurate and secure way to do that is by using a grounded approach, like notebook l m and bringing in rag data.
Jordan Wilson [00:24:37]:
Alright. So let's keep it going. It doesn't save your chat history. Okay? That's a little new approach, but I'm going to show you, how you can still save all of that information. Okay. So when you are chatting in one session inside of notebook l m, all of that information will stay there in the chat. However, once you close out, refresh the page, etcetera, you lose access to that chat history. However, you can save it at any time.
Jordan Wilson [00:25:07]:
There's essentially a save as note button, and then what that does is it adds that to your notebook's knowledge. Alright? So like I said, you do have to change the way that you work a little bit to get the most out of notebook l m. The other big thing, and this is huge. I shouldn't have waited 25 minutes to tell you this part. It's it cites its sources. Alright? And if I'm being honest, before notebook l m, there was really no model that did this. The only model that I think did this fairly well was, Adobe's AI assistant. Right? Acrobat AI assistant, which I've I've I've been using a lot, and I've really loved it.
Jordan Wilson [00:25:48]:
But before that, there was no model that could literally cite. Right? Even on your own document, external. So, yes, ChatGPT has improved that, especially when it goes and and uses the web. You do you have to do a little fancy prompt engineering to try to get it to cite more things. Perplexity, you know, kind of an answers engine, not technically a large language model, does a very good job with citing. However, sometimes it hallucinates and it makes things up with these sources. So that is what is huge here with notebook l m, is it cites the sources it gives you for almost every single thing it pulls out, and then you can go click on that and read about it. Right? And if you're like, wait, Did I really say that on that meeting a year and a half ago? Oh, wait.
Jordan Wilson [00:26:34]:
I can click. Oh, there's the transcript. There's literally exactly what I said. Right? So think of the concept how you can search for anything on Google, and you can scroll through and click obviously a page and go read that page. Same thing. Right? You essentially are creating your own search engine, right, of all all of your data, all of your documents, all of your transcripts, whatever it is that you are uploading. All your YouTube videos, all your m p three recordings of of important calls. It's all in there, and it is cited, and you can click and investigate.
Jordan Wilson [00:27:05]:
That is huge because like I said, normally models only do that with external sources of knowledge, mainly when they are fetching information off the Internet. Like I said, there are some ways with some fancy prompt engineering you can kind of get them to do otherwise, but for the most part, aside from Adobe, AI Adobe the Acrobat AI assistant, no other system or tool has been able to do that until notebook l m. And also the deep dive podcast. Alright? And this was one of those, I think viral, moments that has now gotten a lot of people paying attention to notebook l m, which is kind of funny because I'm like, I've been telling people to use notebook l m since it came out. Many months ago, in 2023, I've been telling people, like, hey. Use notebook l m. It's amazing. But it was this kind of ability to do these deep dive podcasts.
Jordan Wilson [00:27:55]:
So what this is, you can upload all of your information. In full disclosure, I do it for almost every everyday AI episode. I first make myself a personalized podcast. When I'm doing all my research, I now do all all of my, I guess, last leg research for every single show inside of notebook l m. So, yes, I'll use ChatGPT and perplexity and other sources to bring in information quickly, but then I'll take the best of that and I'll put it into notebook l m. So I'll have a bunch of sources, and then I will use the, audio overview, which is essentially a deep dive podcast. Right? So think. And this is great for students.
Jordan Wilson [00:28:36]:
Right? Think if you're maybe taping all your lap taping. Gosh. Did I make myself sound old there old there? Do people tape lectures? Audio recordings of your lectures, all the notes that you're taking, sources across the web. Right? Essentially being able to dump everything into a notebook, literally. I think that's why they called it notebook l m, because, you know, you're taking notes from all these various sources. But then this new audio, audio overview, which is called a deep dive conversation, and then what happens is you get 2 podcast hosts who have a conversation. And it's not just them reading. Right? It sounds like a real podcast, like 2 humans with very natural sounding voices.
Jordan Wilson [00:29:18]:
Okay. This isn't robotic voices. This isn't your traditional AI text to speech. These are neural voices. Right? They kind of laugh. They chuckle. They interact with each other. They they cut each other off like humans would.
Jordan Wilson [00:29:32]:
Right? If I had a co host, the co host would probably cut me off and we'd be doing something like this. We'd be bantering. Right? That is what this do. And again, that's what this feature is. This audio overview or deep dive feature, and y'all, I'm telling you, it changes learning. This is how I learn. This is how I've been learning since this, conversation came out. Previously, I would use 3rd party tools and do something the same.
Jordan Wilson [00:29:56]:
The way I retain information the best is I first do research, I take notes, and then I like to listen. Right? So I might go find a a YouTube video, maybe a podcast, or what I would do a lot of time is take my notes. I would have a a prompt or a GPT that would turn my notes into a podcast transcript, and then I would use a text to speech platform, or I would use, you know, even, ChatGPT's built in voice mode or Google's built in voice mode and just have it read it to me. Now the deep dive podcast is better, because having one AI voice read something to you is, like, that's okay. The the deep dive podcast that you can create in this, a audio overview section in notebook l m is fantastic by itself. Just that one feature. Not even talking about, oh, how it bases it off off all your documents. That one feature is, I I think, is maybe what made made notebook l m this moment.
Jordan Wilson [00:30:54]:
Right? It brings a level of human to AI. Right? Which I know that sounds weird. But you have very even famous people. Right? Like, an OpenAI cofounder, Andrej Karpathy, just posted recently on Twitter about how this is one of his most used, kind of features. The the this deep dive podcast and how he even feels, you know, almost personally attached to these 2 hosts, because like like me, he's using it seemingly for everything. Right? This is my secret. This is how I learned so much, essentially since this new feature came out a couple of weeks ago. Alright.
Jordan Wilson [00:31:36]:
Also, this begs the question. What's Google strategy here? Okay. So they have this amazing free notebook l m tool, but it's based on Google Gemini 1.5 Pro, which is a paid product. So what gives here? Because you have the normal kind of Gemini chatbot, You have Google Gems, which are personalized versions of, Google Gemini. Then you have Google AI Studio, which is for developers, as well as Google Vertex AI. Then you also have Google's search generative experience, which is now called AI overviews, and now notebook LM. What's the strategy here? Because it looks like Google has its Gemini model working just about in every corner of the web. Can I be honest with y'all for a second? I know it's hot take Tuesday.
Jordan Wilson [00:32:35]:
Should I as I take a sip on the coffee here, should I bring in some hot takes? Should I be honest about Google's AI strategy and their different, kind of Gemini rollouts right now? Let me know. Alright. Well, I think I think I'm gonna do it. Google Gemini by itself. Alright. Michael gave me the permission. Michael, thank you. Google Gemini by itself, I think, is not good.
Jordan Wilson [00:33:16]:
The front end of Google Gemini for me, and I use large language models usually anywhere from 2 to 8 hours a day. And I've been using the GPT technology since 2020. I am probably a point one, right, 0.1% power user in the world. I can't use Google Gemini. The front end of Google Gemini, it stinks. I said it. I said it. Sorry.
Jordan Wilson [00:33:42]:
It's not good. It struggles using you it struggles using any data that you upload to it. It struggles searching Google. Right? So you kind of have the worst of both worlds. You upload your documents. It doesn't do a good job. It sometimes just randomly hallucinates. It pulls in its own knowledge from its internal database.
Jordan Wilson [00:34:01]:
When you want it to search the web, you know, Google, sometimes it doesn't, and it falls back on its own internal database. I've I've done, dozens of videos. Right? This isn't just some random hot take that I gave you, on a whim. I've done dozens of videos. Google Gemini on the front end is not good. So there goes my future sponsorship with Google. Right? But I wanna be honest with you, it's not good. Google AI Studio is amazing.
Jordan Wilson [00:34:29]:
Right? The back end way that you can, kind of finesse and finagle, Google Gemini, the back end is great. Google Vertex, great. Right? Front end Google Gemini, not good at all. Right? There are certain use cases, don't get me wrong, if you want it, you know, it's great at creating copy from scratch or rewriting something in a certain tone of voice. That's not what I'm I'm talking about. I'm talking about pushing a large language model and using it for every single thing that it is supposed to be used for. Google Gemini is my least used model. Right? At least when we look at the 4 kind of major models, ChatGPT, for me, that's number 1.
Jordan Wilson [00:35:08]:
Microsoft Copilot, I would say, especially if you're Microsoft 365 Copa, Microsoft 365 copilot organization, that's probably your number 1. It uses the GPT, 4 o technology. So I'll say that's 1 a and 1 b. Right? Then you have Claude anthropic, Then you have, I think, a big drop off, and then you get to Google Gemini. But notebook LM, if I'm being honest, I'm using that more than everyone everyone else. I'm using it more than ChatGPT For that for these exact reasons that I talked about. Having these audio overviews, amazing. Being able to add sources from anywhere across them, anywhere across the web changes how you interact with inform, information.
Jordan Wilson [00:35:54]:
It changes how you learn. It changes what your company can do. Having a grounded model that rarely hallucinates and always gives you cited sources. I'm speechless, and I'm never speechless, but I don't understand Google's strategy. Because like I said, this uses Gemini 1.5 pro. When you use Gemini 1.5 pro, 1.5 pro on the front end in the chat, I can't stand it, but I can't get enough of notebook So what is their strategy? I don't know. Hopefully, they don't kill it. Please don't kill notebook Google.
Jordan Wilson [00:36:31]:
If I'm being honest, here's another hot take. This is Google's best product since the search engine that they built. Right? So many things they acquired. Right? Like, yeah, they acquired YouTube. They acquired so many of these other companies and turned it into other products. NotebookLM, and I've been using, right, Gmail and, you know, Google Workspace. Our businesses run on Google Workspace since the beginning. Notebooklm is Google's best product that they've built since the search engine, and I will go ahead and say, I don't think it's close.
Jordan Wilson [00:37:08]:
I don't think it's close. In terms of utility, and how the world can use this, I don't think it's close. This is probably the most useful and best tool that Google has built since the search engine, and I don't think it's close. Yeah. The transformer, Michael, good point. So the, the transformer as part of the GPT technology was developed originally by Google. I still think this is better. Right? Because what is the transformer, if you don't have a way to properly and accurately use it.
Jordan Wilson [00:37:47]:
Otherwise, it's just yes. It's, it's a piece of technology, but it doesn't do anything by itself. Right? Everyone else, OpenAI, Microsoft, everyone else is running with the transformer technology. Yes. And it has led the way. Right? So, yes, the transformer paved the path to get to notebook l m. Right? But the the transformer is not a tool per se. It is a a technical part of a recipe that has to be used with other pieces.
Jordan Wilson [00:38:15]:
I'm talking about the end product. Notebook LM. Amazing. Alright. Let's do this. Let's look live, shall we? We're gonna we're gonna make this quick. Alright? Because I know I'm already, over on time, so to speak. Alright.
Jordan Wilson [00:38:31]:
So let's go ahead, look live. Livestream audiences, we're having problems. Can you let me know if you're finding this? Alright. I'm gonna walk our pod podcast audience through. Okay. So when you go into notebook LM, like I said, you have to sign in with a Google account. It is free to use for right now. The source amount is is wild.
Jordan Wilson [00:38:49]:
Right? So I'm gonna click new notebook. Okay. So when you click new notebook, it automatically so when I talk about a grounded model, this is important. It doesn't take you to start chatting. Okay? Because I'm gonna I'm gonna put something in here. Alright? I can't start chatting. So if I x out of this, I literally cannot go click. I I I I literally cannot start chatting.
Jordan Wilson [00:39:13]:
Right? So let me go back and I'll show you. That's what it means for a model to be grounded. It literally does not work unless you upload some information in there. So I'm gonna go into, paste copied text. Alright. And I'm just gonna put in, this is a test. Because I want you to see and understand how this model works. So one thing you'll see is it instantly gives a kind of different, user interface, which I'm gonna talk a little bit about here.
Jordan Wilson [00:39:42]:
But now I can now start typing or start talking with my data. Right? And I can say as an example, you know, tell me about large language models. Here's what I mean when I say something is grounded. So it says the response back says, the sources do not provide any information about large language models. Therefore, I cannot answer your question. The only information provided in the sources is, quote, this is a test. Alright. So pretty amazing.
Jordan Wilson [00:40:15]:
Right? And this is what it means for a model to be grounded. It's in the corner. It can only look at the corner. It can only look at what we tell it to look at. Its features and functions are still driven by Gemini 1.5 Pro. However, it can only work on the data that we give it. Alright? But its features and functionalities, its skill sets are still backed. So you might think of that and say, like, oh, well, this is useless.
Jordan Wilson [00:40:44]:
No. It's absolutely not. This makes it amazing. Alright. So now let me give you an example here. So I'm opening up, another chat here. Okay. And I I finished building this one, yesterday.
Jordan Wilson [00:40:58]:
So every single Monday, we do a segment on everyday AI called the AI news that matters. That's a roughly, you know, 35 to 45 minute podcast where we talk about the most important AI news of the week. We do it every Monday. So if you can only join us once, maybe that's the day that you do it to keep up with AI. But so I took the transcript for all of these, and it's a lot of words. Alright. So right now, I have 35 different sources. Okay? And all of my sources are on the left hand side.
Jordan Wilson [00:41:30]:
So this if you're used to using large language models in chat view, normally, you look at the left hand side to find your chats. That's not what this is. On the left hand side is your sources. And like I said, there is only one chat. Alright? And let me just go ahead and do, an example of this. Well, let's actually do the notebook guide. Alright? So this is a huge piece, so this creates notes. Okay? So I'm gonna go ahead and do this live, and it actually might take a while.
Jordan Wilson [00:41:59]:
Because like I said, I have 35 different sources. All of those sources have about 10,000 words. Okay? It's complete transcripts from these podcasts. So I'm not great at math. Right? But that's 350,000 words. So for all intent purposes, that's about 300,000 tokens. Alright. So out of the box, most large language models could not even handle this much information.
Jordan Wilson [00:42:26]:
That's a point that I'm trying to show you right off the bat. The amount of information that notebook l m can handle is wild. Okay? So now there's these little notes. Okay? So at the top it says notebook guide, and I can either click add note or I can click plus to add a new source. Right? So for all of these, you see my source limit. Right now I'm using 35 out of 50. So you can click copy text, just paste the text in there, click, like I said, website, put the URL in, click YouTube, put a YouTube URL. It does have to have it has to be a public YouTube video, and it has to have captions enabled, or I can upload Google Slides, and it's gonna bring in my Google Drive, etcetera.
Jordan Wilson [00:43:09]:
Okay. So now there's these little notebook guides. Okay. I'm gonna click FAQ. Alright. And you'll see now this is the note view. Okay. And it's actually gonna probably take a super long time, because there's 350,000 words.
Jordan Wilson [00:43:23]:
Alright? And then I'm gonna click study guide. I'm gonna click table of contents. I'm gonna click timeline. Okay? I'm gonna click, let's see. Did I get timeline? I'm gonna click briefing talk. So these are some kind of think of these as like default prompts. Okay? So you can upload all your information, whatever it is, and then you can click those. Right? So it can create an FAQ on all your information, a study guide, a table of contents, etcetera, timeline briefing doc.
Jordan Wilson [00:43:53]:
So like I said, think of those as prompts. Alright. So those are going in the background here. Alright. And now they're done. Alright. They're they're finishing 1 by 1. So this is a lot of information.
Jordan Wilson [00:44:05]:
Alright. They're popping up as they're done. So now I have my FAQ, my briefing doc, my study guide, my timeline of main events. So this one's gonna be interesting. Right? 8 months of AI news, and it's instantly giving me a timeline of main events. So one thing I wish I wish I could make these notes a little larger. So they're a little small on my screen, but if I yeah. Even when I zoom in.
Jordan Wilson [00:44:31]:
Alright. So here's the timeline of events. This is a lot of information y'all. And this is actually if you wanna learn about AI, let me know. I'll send you this timeline of events. You know, leave me a comment somewhere that says timeline or DM me timeline. If, hey, if if you wanna catch up in, 9 months of AI news, by reading that, go ahead. Alright.
Jordan Wilson [00:44:52]:
And then it also creates these FAQs. Okay. Cool. So you might be wondering, alright. So how do I actually use this? Right? So I can now type and say, give me a timeline of LLM developments. Alright. Now if I put that into an ungrounded model, like even Google Gemini, like ChatGPT, it's going to do 2 things. It's going to first see, okay, do I have this, information in my knowledge base? Which for the most part it will, but normally, a model's knowledge base is up to a year or more out of date.
Jordan Wilson [00:45:29]:
That is mistake number 1. Right? When you are using a large language model that does not have RAG, it refers to its own internal database, its own internal training data, which is generally very old, And then it will make a choice on its own whether it wants to connect to the web to bring in more information, which sometimes will give you great things, sometimes it will give you bad things. Right. So there we go. Now we have a timeline of large language models based on the sources provided. Okay. So for our livestream audience, you'll see here, but it now has 21 different citations. Okay.
Jordan Wilson [00:46:04]:
So like I said, if you are querying the web with perplexity or with ChatGPT when it uses browse with Bing, this looks similar. But most models will not do this by default when you are working with your own internal documents that you upload. So like I said, GPTs, Claude Projects, or Google Gems. Alright. So now when I click one of these things so it says, okay. July 2024, meta releases llama 3.1. Alright. So now I can click that.
Jordan Wilson [00:46:36]:
That is citation 4. And so it brings me to my source guide on the left hand side. So I can still read that information on the right hand side of my screen, and then on the left hand side of my screen, it takes me straight to that point. So I can see it gives me the file name or the what I gave my, the name for this one is just July 29, 2024. So I just gave it the name of the date for my transcript, and then it is highlighted. So this information is highlighted, so I can instantly go back and remind myself of that information. Alright. So this is fantastic.
Jordan Wilson [00:47:11]:
Alright. So now I'm gonna go in. This is gonna take a while. I'm going to generate. Alright. I'm going to generate a podcast conversation. So think of all the different use cases. Alright.
Jordan Wilson [00:47:23]:
Think you are I mean, for students, this is a no brainer. This is a great way to actually learn something. Okay? Think of for everyone else. So like I said, let's say you work at, you know, at a big logistics company, you work in marketing. You have a lot of public documents. Right? Your own company's website, you know, white papers for your industry, information on your competitors, your next big presentation that you're working on, you know, all meeting transcripts with your team, your your KPIs that were handed down by you from your boss. Right? You can put all of this information in there. Again, you know, always follow your company's AI policy, You know, understand what, you know, Google and everyone else is doing with your data.
Jordan Wilson [00:48:11]:
Gotta get all that out of the way. Right? But then when you go in there, then you can still talk to this like you would normally a large language model. And say, hey. Here's all the information I gave you. Here's what I want you to help help me with in this chat. You know, go back and first always look at my data. Well, you don't even have to tell it to. Right? It's almost like I'm dropping good habits because that's what I'm used to doing when I'm uploading documents into custom GPTs, into chats inside of other large language models is reminding them, hey, stay grounded.
Jordan Wilson [00:48:38]:
You don't have to do that. It does it by default here in notebook l m. But think, now all of a sudden, your job as a marketing executive at this logistics company is a whole lot easier. You could say, hey. Please help me forecast, you know, findings, or or help me for, forecast revenue for next quarter based on my, revenue that I've shared for the last 4 years. Right? It can do anything that a large language model can do. Right? Analyze data, can can help you, summarize long things, make them shorter. You can give it bullet points, and it can make that information longer.
Jordan Wilson [00:49:15]:
Right? Anything that you can do in a text to text model. Right? So right now, you know, notebook l m, you can't create, videos. You can't create, you know, spreadsheets. So there's certain things that you cannot do. So this isn't a an end all be all replacement. But if you are thinking of text to text, if you are thinking of, hey, I need hallucination free outputs from a large language model, to me, yeah. Yeah. You have to use notebook l m.
Jordan Wilson [00:49:45]:
Alright. So this is taking a little minute. We can go back and it should it should be done. Alright. So let's go back into the chat. Okay? So like I said, you have to you have to save these things as a note, because if I refresh this, it is going to be gone. Right? And this is probably some information. Right? When I said, you know, please give me a timeline of LLM developments.
Jordan Wilson [00:50:06]:
So I can click this save to note. So when I click that save to note, you'll see it is now in the upper left hand corner, it says saved response. So I can click on this, and then I can even from there, click help me understand, critique, suggest related ideas. Right? So even when you click on OneNote, you get some, some new information. Alright. That's important to know. I can also, change the name of it as well. So now it is one of my saved sources on the left hand side, so I can go in, rename it, etcetera.
Jordan Wilson [00:50:42]:
Alright. Another thing that you can do, and I'm not going to do it now because I'm in the middle of generating this conversation. Yeah. I figured this conversation is gonna take a while. And I'm gonna end by talking about, the future of this product, and a couple of other things. But on the left hand side, when you upload all your sources, you might not wanna use them all at once. So you can quickly click the select all sources to deselect all. So maybe as an example, you wanna use, notebook LM for different purposes, but all within your data.
Jordan Wilson [00:51:14]:
So you can quickly toggle sources on and off. So maybe first, you wanna go through your meeting transcripts. Right? So you can toggle everything off aside from those meeting transcripts. I hope, FYI, because I know, people from notebook l m are, reading this, and I know that they're putting out now tons of great updates. We need folders, FYI. Right? I need to be able to have a folder with all my meeting transcripts, and then to quickly be able to toggle that on and off. I need something that says, you know, competitor information with all the competitor information in there. I need all my internal information, you you know, goals.
Jordan Wilson [00:51:46]:
I like, we need folder structures because 50 sources is a lot. It's great, but we need folders. Anyways, you can toggle sources on or off, so that when you ask notebook l m something, you can make sure it's only looking at certain sources. That's like, I don't know, super grounding. Right? Like, hey, don't don't look at all my competitor information. Don't look at all the, you know, information that I brought in from, the web. Only look at these certain info, sources that I have toggled on or off. So I have 35.
Jordan Wilson [00:52:15]:
Right now I'm having a conversation and I'm generating an AI overview, the deep dive AI podcast of all 35 of those, pieces of information, which is why it took a while to get done and it's finally done here. Alright. So now, let's go ahead and listen. Alright. Let's go ahead and listen. Hopefully, livestream audience, let me know if you can hear this. I'm not gonna play the whole thing, but I do want you all to hear what this sounds like. Alright.
Jordan Wilson [00:52:40]:
So let me know if you can hear this. This is the audio overview, the AI podcast deep dive that was generated based off of my content. Alright. Let's listen to maybe 30 seconds.
NotebookLM [00:52:51]:
It's incredible, isn't it? The speed at which AI is evolving. One minute we're trying to grasp the concept of AI generated art and the next, bam, we're talking about AI that can create entire video sequences from a simple text prompt. It's a lot to keep up with even for those of us who live and breathe this stuff. And let's be honest, who has the time to wade through endless articles and podcasts? That's why we do these deep dives to cut through the noise and bring you the most impactful AI developments.
Jordan Wilson [00:53:18]:
I agree. It's crucial to discern the hype from the truly transformative. Not everything labeled AI is created equal.
NotebookLM [00:53:25]:
Exactly. Speaking of transformative, let's talk about OpenAI's Sora. This new AI model is causing quite a stir. Imagine typing in a detailed scene description, let's say. A cat in a detective hat chases a robot.
Jordan Wilson [00:53:39]:
Alright. So, hopefully, y'all could hear that AI overview. I know we're having some technical issues for the livestream, but if you couldn't, it was 2 hosts that sounded fairly human. Right? That didn't sound like a normal text to speech voice. Those are the words that we've heard you say. Yeah. It's it's because it's all my data. Right? A couple things to know about these, the AI overview.
Jordan Wilson [00:54:03]:
It will always be there now. You don't have to save it. It's not like chat history where it's gonna go away. The thing I like is it has play by, playback speed. So I always listen to it at 1 8 or 2 o, so you can hear that. I actually think it sounds better at, like, 15. So listen to how it sounds in 15.
NotebookLM [00:54:20]:
Butt mouse through a bustling marketplace. And then boom. Sora generates a full minute of high definition video complete with realistic textures, lighting. It's
Jordan Wilson [00:54:27]:
I think that's just how I always talk, just like excited and fast. You know, I generally listen on 15 or 18. So it has built in speed control, which is which is huge, and then you can also download, that podcast as well. So again, a great thing to do if if you have a trip, you're gonna be on the plane, you're in the car, you wanna learn about things. I mean number 1, I hope you just continue to tune into everyday AI and learn about it here with us, but this is another great option. Maybe you need to learn about something very specific. Maybe you have a big meeting coming up and you wanna prep for it. Yo.
Jordan Wilson [00:54:59]:
I cannot think of any way that you should not be using this. That's why, like, when I talked about, Andrei Kapathy, right, OpenAI cofounder largely, but, largely referred to as one of the smartest people in the history of artificial intelligence, he's talking about this. Like, he is using this all the time. I am using it all the time. You should be using it all the time. I'm not sponsored by Google. They're not, you know, advertising on the everyday AI podcast anytime soon after I, you know, said, hey, Gemini's front end stinks. But notebook l m is probably one of the best tools I've ever used in my life.
Jordan Wilson [00:55:36]:
And I've used 1,000 with an s of AI tools. It is one of the best. Alright. So that is a quick overview of inside the platform. Like I said, all of your notebooks are on the left. You can upload up to 50 sources that have 50,000 words. 25,000,000 words. My gosh.
Jordan Wilson [00:55:55]:
So dumping information of all kinds. YouTube videos, if there's captions, websites, copy text that you can just copy and paste anything in there. Google Slides, Google Docs, wild. Absolutely wild. Alright. So let's wrap this up. This turned into a long one. So well, what's next? What's next for this tool? Is it gonna go away? Is Google gonna charge for it? I don't know.
Jordan Wilson [00:56:15]:
I don't think it's gonna go away because I think this thing is wildly popular. If I'm being honest, I think this has been better received than their Gemini model. Right? We remember when Google first announced, Gemini, they did some, I'd say, some not so great marketing. They kind of lied a little bit. Right? And they showed us that these marketing videos with Gemini, showing it could do all these things that in actuality it couldn't. Right? It showed us as an example responding to the paper rock scissors game live. It couldn't do that. In the research paper it said, oh we actually took a ton of pictures of that video of paper, rock, scissors, and then we did a bunch of prompt engineering, and then we got the output that we needed, and then we used that.
Jordan Wilson [00:56:57]:
So, yeah, we you know, they they kind of said, okay. Maybe Gemini can't do all these things, and we had to do a bunch of, you know, duct tape under the hood. NotebookLM is not like that. NotebookLM is freaking impressive. It is great. I am using this nonstop. Alright. So what's next for it? Are they gonna start charging for it? Probably.
Jordan Wilson [00:57:17]:
If I'm being honest, I'm using Google Gemini on the front end. I don't know. 10 minutes a week, because I don't think it's very good. I'm using notebook l m, sometimes more than an hour a day, and I think that's gonna become the norm. A free tool with all of this, information you can upload I mean, they're gonna have to start charging for it. They're gonna have to. Right? So what's next? Okay. So shout out here to testing catalog.
Jordan Wilson [00:57:48]:
Alright. So this is a a Twitter account. They also have a website. Good stuff. Go check them out. Testing catalog. So they just shared something yesterday. You you know, kind of some some leaks or some behind the scenes, that they're going to notebook l m is going to be creating bots.
Jordan Wilson [00:58:07]:
Okay. So what I hope this means ultimately is that your notebooks will be able to talk to each other, or your different notes within notebook l m can be able to talk to each other. Alright. So that's a pretty, pretty good feature that I think is coming, and hopefully, like I said, hopefully what that means is your notebooks will be able to talk to each other. That will be huge. Alright. Because there we have essentially agentic rag. Alright.
Jordan Wilson [00:58:35]:
Not to throw out a bunch of buzzwords, but, you know, a grounded, bot. Right? So it's grounded in rag, retrieval augmented generation, your data only, and then they can talk to each other. So this agentic nature, that would be amazing. Right? Also, Reza Martin, you know, trying to get Reza. Let's get you on the show. So she's the product lead at notebooklm, and she did share something, in response to this, this testing catalog, kind of blog post slash tweet yesterday. And she did say this, custom chat bots. I have a lot to say.
Jordan Wilson [00:59:13]:
This is pretty widely used internally at Google, and literally every day someone pings me to say, this has 10 x our team's productivity. Not joking. In the hacks, you're still looking at the old version. So she's saying, essentially we're all looking at the old version. There's a newer version with more capabilities. And so she says, not joking. In the hacks, you're still looking at the old version. So I'm excited for what you all think when the new version launches.
Jordan Wilson [00:59:42]:
So, yeah, apparently, there is going to be a sizable update coming to notebook l m pretty quickly. Alright. That was a lot. We were all over the place. I did see a couple of questions, so I'm gonna try to answer them quickly. Marie asking, do the podcast host voices change every time you use it? No. It is the exact same. 2 hosts every time.
Jordan Wilson [01:00:02]:
I believe they only speak English, and you can't really get them to say anything. So people have found out there are ways you can kind of hack it. Right? So in the notes that you upload or in the sources, you can kind of tell it, oh, talk about this. Right? And people did this, you know, existential, you know, oh, these 2 AI hosts are trapped. Right? So you can just put in information in your source document that kind of steers them, but they're still going to take their own spin on it. So you can't just give them a script or, you know, anything like that, but you can steer them in certain directions like you can you can steer any model with proper prompt engineering. So no. The host, you cannot change, their voices.
Jordan Wilson [01:00:39]:
It generates once. That's what you get. You can download it, play it, speed it up. Alright. Cecilia asking, so once it has your rag or data and has chewed on it, will it extrapolate and go outside the Internet, to the Internet for comparisons, or it is only internal digestion? As of now, it is grounded. So it does not look on the Internet. As far as I know, I've done testing. It cannot look on the Internet.
Jordan Wilson [01:01:07]:
Right? So which I think is generally, when I'm speaking about sending large language models to the Internet, it's something you need to do. It's because these models, even that offer some sort of quote unquote rag retrieval on minute generation. Right? So even when you can upload files into GPTs, you can upload files into Claude, you can upload files into Google Gems, you can upload files into Copilot GPTs. Sometimes they still struggle to stay grounded, and will instead refer to their own internal knowledge base or go off on the web. Right? So that's why even using these kind of, other options that I just talked about, sometimes you still need web access. I don't think you need web access with notebook l m, because you can literally just bring in those 10 or 20 different websites, and there you go. Right? Amazing. The control that you have.
Jordan Wilson [01:01:59]:
Jason asking, can you upload source code? If you're asking, can you upload, coding? Right? Can you upload your Python projects and CSS and HTML? Yes. I did some testing on it. I uploaded some code. You know, I said, hey, can you change this code for me? Yes. So most of the features and functionalities that Gemini 1.5 can do, most, it can do as well. So, yes, it can summarize long documents, make it shorter, take bullet points, make it longer. It can look at all your different documents even if those documents are coding. Yes.
Jordan Wilson [01:02:30]:
Gemini is actually even the front end Gemini chat is great at coding, FYI. So yes, it can notebook l m can work with your source code as well. Oh, that was a long one y'all. Here's the thing. I had a whole section that I knew I wasn't gonna have time to get to. I put together 7 additional helpful tips on how I'm using notebook l m. I wanted to give you all the basics, and I knew if I dorked out this would turn into a 3 hour like Lex podcast. I can't do this.
Jordan Wilson [01:03:00]:
This was an hour. So please always feel free to listen to this in 2 x. I ramble. It's unedited, unscripted. I wanna bring you what I like to say is the realest thing in artificial intelligence, but there was more I couldn't get to. I had all these great tips and tricks, so maybe I'll turn them into a podcast or a video in the future, but I have them ready to go. So please repost this, you know, on LinkedIn or retweet it, you know, on Twitter. If you do, I will send you that list.
Jordan Wilson [01:03:28]:
Right? So whether it's a list or a video, I have a bunch more information that I was gonna take me way longer to explain, and I knew this was already gonna be long enough. So if you're listening on the podcast, make sure to check out your show notes. I always leave a link to our LinkedIn livestream even though it wasn't working today. So go repost that, and I will share those 7 additional tips with you. Alright. So, some I'd say some tricky ones. Some ones that really take, many, many hours of using the tool to understand and to really get the most out of Notebook LMS, so make sure to share that. Also, make sure to go to your everyday ai.com.
Jordan Wilson [01:04:03]:
Sign up for the free daily newsletter, and join us back tomorrow and every day for more everyday AI. Thanks y'all.