I'm talking organizing your notes.

我說的是整理筆記。

Gone.

走了

Formatting your notes.

設置筆記格式

No more.

沒有了

Searching your note stop and trying to find that one thing you know you saved but can't locate.

搜索你的便籤本，試圖找到那件你知道自己保存但卻找不到的東西。

That is going to be gone forever.

它將永遠消失。

It's a new platform that Google just released to the public called Notebook LM.

這是谷歌剛剛向公眾發佈的一個新平臺，名為 "Notebook LM"。

In this video, I'll show you what Notebook LM is, how it works, and how you can get started using what I believe is the best software ever created for leveraging AI in creative work.

在本視頻中，我將向你展示什麼是 Notebook LM、它是如何工作的，以及如何開始使用這款我認為是有史以來在創意工作中利用人工智能的最佳軟件。

Anything Google created in this arena would already be interesting and worth investigating because it's Google.

谷歌在這一領域創造的任何東西都很有趣，值得研究，因為它是谷歌。

They have some of our most valuable data, some of the most powerful AI models, such as the recently released Gemini, which Notebook LM uses, and quite a track record for, you know, completely reshaping our relationship to information.

他們擁有一些最有價值的數據、一些最強大的人工智能模型，比如最近發佈的雙子座（Notebook LM 使用的就是雙子座），而且在徹底重塑我們與資訊的關係方面也頗有建樹。

But there's another wrinkle.

但還有一個問題。

One of the leaders and creators of the project is Stephen Johnson, multiple-time best-selling author and the person who introduced me to tools for thought, the general category that includes second brains.

斯蒂芬-約翰遜（Stephen Johnson）是該項目的領導者和創建者之一，他是多部暢銷書的作者，也是他向我介紹了 "思想工具"（包括 "第二大腦 "在內的一般類別）。

Stephen joined a team at Google Labs to create a completely different kind of AI that we have not seen before.

斯蒂芬加入了谷歌實驗室的一個團隊，致力於創造一種我們從未見過的完全不同的人工智能。

And let me tell you, it's the closest one yet to the vision of a true second brain I've been pursuing for years.

讓我告訴你，這是最接近我多年來一直追求的 "真正的第二大腦 "願景的一個。

Let's begin with a little getting started guide.

讓我們先來看看入門指南。

Start by visiting notebooklm.google.com and either creating an account or you can sign in with one of your existing Gmail accounts.

首先訪問 notebooklm.google.com，然後創建一個賬戶，或者使用現有的 Gmail 賬戶登錄。

Sign up is limited to users in the U.S. who are 18 years or older at the time that I'm filming this video.

註冊僅限於在我拍攝本視頻時年滿 18 週歲的美國用戶。

Once you're inside, this is the interface you'll see.

進入後，您將看到這樣的界面。

Everything in Notebook LM is organized in notebooks, each of which is like a single contained space for all the information related to a specific project such as a piece of writing.

Notebook LM 中的所有內容都以筆記本的形式組織，每個筆記本就像一個單獨的空間，容納了與特定項目（如寫作）相關的所有資訊。

You can create a new notebook by clicking this plus button right here and give it a title such as personal ruggedization.

點擊這裡的 "加號 "按鈕，您就可以創建一個新的筆記本，並給它取一個標題，比如 "個人加固"。

This was an online course that I took recently that I'd like to organize and distill some of my takeaways.

這是我最近參加的一個在線課程，我想把它整理一下，提煉出一些我的收穫。

This is the main interface that you'll be using to interact with Notebook LM and there's three main things to pay attention to.

這是與 Notebook LM 交互的主界面，有三個主要事項需要注意。

The first one is the column on the left, which is the sources column.

第一個是左邊的一欄，也就是來源欄。

This is really the main feature that Notebook LM has, which is you can click that plus button and choose from different existing documents from which the AI will draw its knowledge.

這也是 Notebook LM 的主要功能，即您可以點擊加號按鈕，從不同的現有文檔中進行選擇，讓人工智能從中汲取知識。

And the three kinds of sources you can use are Google Drive documents stored in your own account.

您可以使用的三種來源是存儲在自己賬戶中的 Google Drive 文檔。

You can upload PDFs and you can copy and paste text directly from other places such as a note-taking app.

您可以上傳 PDF 文件，也可以直接從其他地方（如筆記應用程序）複製和粘貼文本。

For my example, I'll use my Google Drive.

在我的例子中，我將使用我的 Google Drive。

You can select up to 20 different documents in Drive and each one of those documents can have up to 200,000 words, which means you can interact with up to 4 million words of text.

你可以在 Drive 中選擇多達 20 個不同的文檔，每個文檔最多可包含 20 萬字，這意味著你可以與多達 400 萬字的文本進行交互。

That's a far larger context window than any other AI tool out there.

這比其他任何人工智能工具都要大得多。

I'll go ahead and select my notes on that personal ruggedization class that I took recently and say insert.

我會繼續選擇我最近上的個人加固課的筆記，然後說插入。

And I want to show you what happens.

我想讓你看看會發生什麼。

So first of all, that source appears here in the left.

是以，首先，該信息源出現在左側。

If I click the source, a couple things happen.

如果我點擊源文件，會出現幾種情況。

First of all, the AI creates kind of a, almost like a summary or an abstract of this source.

首先，人工智能會創建一個類似於摘要或摘要的信息源。

And these are some of the key topics.

這些就是其中的一些關鍵議題。

And then if I want to actually see the full contents of the source, I can just scroll down here.

如果我想查看源文件的全部內容，可以向下滾動。

I want to add a few more sources because the real power of Notebook LM is not working with one source.

我想多添加幾個信息源，因為筆記本 LM 的真正威力不在於只使用一個信息源。

It's working and drawing from multiple sources all at the same time and simultaneously.

它在同一時間同時從多個來源工作和取材。

So what I'm going to do is click add source and add a few more Drive documents.

所以，我要做的就是點擊添加源，然後再添加幾個 Drive 文檔。

And what I'm going to do is navigate to a folder where I have saved all the notes on every book and article I've read over the past few years.

我要做的就是瀏覽一個文件夾，在那裡我保存了過去幾年我讀過的每本書和每篇文章的所有筆記。

Later on in the video, I'll show you how I was able to generate all of these documents.

在視頻的稍後部分，我會向你展示我是如何生成所有這些文件的。

And what I want to ask myself is what have I already read in the past and even taken notes on that might contribute to and be a useful resource in what I'm working on today?

我想問自己的是，我過去讀過哪些書，甚至做了哪些筆記，可能會對我今天的工作有所幫助，成為有用的資源？

So I'm just going to go through this list briefly and select any other documents that kind of strike me as potentially relevant.

是以，我只想簡要地瀏覽一下這份清單，然後選擇任何其他我認為可能相關的文件。

Here's one about what the world might look like in 2312.

這裡有一個關於 2312 年的世界會是什麼樣子的故事。

This is a good book here about the power of constraints, climate change, which is the topic of the course that I took, even about what it might look like to terraform other planets, such as in the science fiction book, Blue Mars, some big picture perspective about our place in the universe, designing for behavior change, because we may need to have a lot of behavior change when it comes to preparing for climate change.

這是一本關於約束的力量、氣候變化（這也是我所選課程的主題），甚至關於其他星球的地球化可能是什麼樣子的好書，比如科幻小說《藍色火星》中的內容，一些關於我們在宇宙中的位置的大局觀、行為改變的設計，因為在為氣候變化做準備時，我們可能需要進行大量的行為改變。

I'm really just kind of noticing which books would jump out at me as in some way related to the topic at hand.

其實，我只是注意到哪些書會讓我眼前一亮，覺得與手頭的主題有某種關聯。

So it looks like I have 13.

看來我有 13 個。

I'm going to go ahead and click insert.

我要繼續點擊插入。

All of the sources that I chose are now being added to the sidebar.

我選擇的所有資料來源現在都已添加到側邊欄中。

So let's talk about the two other spaces that you're going to be working with.

讓我們來談談你將要使用的另外兩個空間。

And now that we have all of our sources loaded up, the main one is this little box down here, which is really like other chat based AI tools, such as chat GPT that we're used to.

現在，我們已經加載了所有的源代碼，最主要的就是下面這個小方框，它就像其他基於哈拉的人工智能工具一樣，比如我們常用的哈拉 GPT。

You're basically going to have a conversation with the AI, but drawing on the sources over there in the left.

基本上，你要與人工智能對話，但要利用左側的信息源。

So I could say something like create an outline of the main ideas related to personal preparation for climate change found in these sources.

是以，我可以說，就這些資料中與個人應對氣候變化的準備工作有關的主要觀點編寫一份提綱。

Hit enter.

按回車鍵。

You can see it takes a minute.

你可以看到這需要一分鐘。

And there we go.

我們走吧。

It's a hierarchical, highly structured outline with main points and then supporting points or evidence or expanding on those points underneath each one.

它是一個層次分明、結構嚴謹的提綱，有主要觀點，然後在每個觀點下面有支持觀點或證據或對這些觀點的擴展。

And they're kind of in order from early things that you'll need to think about to much later things.

它們的順序是，從你需要考慮的早期事情到更晚期的事情。

This is just the first step.

這只是第一步。

There's a few different directions that we could go from here.

從這裡開始，我們可以有幾個不同的方向。

The first thing is I could ask it one of these suggested questions that you see down here.

首先，我可以向它提出你在下面看到的這些建議問題中的一個。

You can see I can actually scroll right and left.

你可以看到我可以左右滾動。

And what's interesting is they're based on this particular text.

有趣的是，它們都是以這篇特殊的文字為基礎的。

So they're not just generic ones that appear the same way every time.

是以，它們並不是每次都以相同方式出現的通用產品。

So things like what are the three main things to consider?

那麼，需要考慮的三件主要事情是什麼？

So let's say I just want something really snappy, really succinct.

比方說，我只想寫一些非常簡潔明瞭的東西。

I could click that.

我可以點擊一下。

It will ask that question.

它會問這個問題。

And there you go.

這就對了。

It's kind of distilled it down to the three main things that I need to know.

它將我需要知道的三件主要事情提煉出來。

What are some ways that individuals can prepare for and respond to both the personal and societal changes that are likely to occur as a result of climate change?

個人可以通過哪些方式為氣候變化可能帶來的個人和社會變化做好準備並作出反應？

Let's try that one.

讓我們試試這個。

As it's working behind the scenes, I'm really having a conversation.

當它在幕後工作時，我真的在進行對話。

I can ask it to expand or to distill.

我可以讓它膨脹，也可以讓它蒸餾。

I can ask it to give me more information on one point, but not others.

我可以要求它就某一點提供更多資訊，但不能要求它提供其他資訊。

I can ask it to give me different formats, like write this as a poem, write it as a narrative, write it as a question and answer, FAQ format.

我可以讓它給我提供不同的格式，比如把它寫成一首詩、寫成一篇記敘文、寫成問答、常見問題等格式。

You can see in this case, it's sort of adapted the content to really be focused on personal preparation, which is the angle that I'm most interested in.

你可以看到，在這種情況下，它對內容進行了調整，真正把重點放在個人準備上，而這正是我最感興趣的角度。

There's one more, the third of the main three interfaces that you need to know about.

還有一個界面，也就是你需要了解的三個主要界面中的第三個。

If you get a response, let's say this one that you especially like, you don't want to lose it.

如果你得到了一個迴應，比方說這個你特別喜歡的迴應，你就不想失去它。

This is a free-flowing conversation.

這是一場自由的對話。

So you might think, well, if I keep going and keep conversing, I'm going to lose track of some of these great responses.

所以，你可能會想，如果我繼續說下去，繼續對話，我就會忘記這些精彩的回答了。

All you have to do is click this little pin icon and it saves to this big space up here, taking up the top of the screen.

你只需點擊這個小圖釘圖標，它就會保存到這個大空間裡，佔據螢幕的頂部。

You can think of this as a kind of pin board, where you are pinning these kind of little cards with interesting information that the AI has given you, just so that you keep them top of mind and easy to see and easy to reference.

你可以把它想象成一種圖釘板，把人工智能提供給你的有趣資訊用圖釘釘在這些小卡片上，這樣你就可以把它們放在最顯眼的位置，方便查看和參考。

One more cool detail here.

這裡還有一個很酷的細節。

Let's say in the midst of your work, you realize, oh, there's another source I'd like to add.

比方說，在你工作的過程中，你意識到，哦，我還想添加一個信息源。

You can always click right here where it says add note and either copy and paste from somewhere.

您可以隨時點擊這裡的 "添加備註"，然後從某個地方複製並粘貼。

For example, your note-taking app or something that you found online or something from an email, or you can just write directly into the note.

例如，你的筆記應用程序、網上找到的內容或電子郵件中的內容，或者你可以直接寫在筆記中。

For example, let's say I remember that the creator of that course that I took, his name is Alex Stephan, recently wrote a piece on Substack that is much more recent and much more timely.

比如說，我記得我選修的那門課程的主講人叫亞歷克斯-斯蒂芬，他最近在 Substack 上寫了一篇文章，這篇文章更新穎、更及時。

And I want to also incorporate that writing and that thinking into what I'm doing.

我還想把這種寫作和思考融入到我的工作中。

What I can do is head over to Evernote.

我能做的就是去 Evernote。

Here is the excerpts from his article.

以下是他的文章摘錄。

I'm going to do command A for select all.

我要執行全選命令 A。

I'm going to copy all that text and put it right into a new note.

我要複製所有文字，並將其直接放入一個新筆記中。

And now what it will do is allow me to check this box right here and incorporate what I've just added right into the conversation.

現在，它將允許我勾選這裡的複選框，並將我剛剛添加的內容直接納入對話。

That was a very basic tour of three of the main areas that you are going to need to pay attention to to use Notebook LM effectively.

以上只是對有效使用筆記本 LM 需要注意的三個主要方面的基本介紹。

What Google has done is basically redesigned a note-taking app from scratch with modern AI in mind.

谷歌所做的，基本上是以現代人工智能為理念，從零開始重新設計了一款筆記應用。

You still need to take notes, but you can just kind of dump them into one giant pile and use the AI to sort through and make sense of them rather than having to meticulously organize things in files and folders.

你仍然需要記筆記，但你可以把它們堆成一大堆，然後用人工智能來整理和理清它們，而不必一絲不苟地整理文件和文件夾。

Notebook LM is different from other AI tools such as ChatGPT because you can train it on a specific set of documents you know and trust.

Notebook LM 與其他人工智能工具（如 ChatGPT）不同，因為您可以在您熟悉和信任的特定文檔集上對其進行訓練。

That could be excerpts from books you've saved, notes you've taken in class, highlights from articles or web pages, or your own thoughts.

這些內容可以是你保存的書籍節選、課堂筆記、文章或網頁的重點內容，也可以是你自己的想法。

This is called source-grounded AI.

這就是所謂的源接地人工智能。

You point the AI at a specific set of documents, effectively giving it instant expertise in whatever knowledge they contain.

你可以將人工智能指向一組特定的文檔，這樣就能讓它立即掌握這些文檔所包含的知識。

So you always know it's only drawing on authoritative, private, trusted information.

是以，您始終知道它只使用權威、私密、可信的資訊。

Next, I want to take a look at some of my favorite use cases that I've been using Notebook LM for.

接下來，我想看看我最喜歡使用 Notebook LM 的一些用例。

Sometimes I'm reading a difficult, complex piece of writing such as an academic paper, and I just need some help understanding it.

有時，我在讀一篇艱深複雜的文章，比如學術論文，我需要一些幫助來理解它。

What you can do is upload a PDF of what you're reading.

您可以上傳您正在閱讀的 PDF 文件。

This is a paper about the role of forgetting and learning.

這是一篇關於遺忘和學習的作用的論文。

I'm going to go ahead and select it and say, what is the role of forgetting and learning?

我要繼續選擇它，並說，遺忘和學習的作用是什麼？

So you can see here it's basically summarized what is quite a long technical paper into something that I can understand.

是以，你可以看到，它基本上把一篇相當長的技術論文總結成了我可以理解的內容。

So I noticed one of the points here, which is that knowledge can sometimes have a negative value, kind of piques my interest.

是以，我注意到這裡的一個觀點，即知識有時可能具有負面價值，這引起了我的興趣。

And the amazing thing about this conversational interface is I can now ask, what are some examples of ways knowledge can have negative value?

這個對話界面的奇妙之處在於，我現在可以問，知識產生負面價值的方式有哪些？

That's kind of confusing to me.

這讓我有點困惑。

So you can see here, this is fantastic.

所以你可以看到，這真是太棒了。

Knowledge that's incorrect.

知識是不正確的。

Redundant knowledge.

冗餘知識。

Harmful knowledge.

有害的知識

So imagine if I'm working on a project where I'm trying to convince, let's say, an IT administrator to not save every file that's ever been created across the entire organization.

是以，想象一下，如果我正在做一個項目，試圖說服 IT 管理員不要保存整個組織創建的所有文件。

That's something that I could ask it to do for me.

這是我可以要求它為我做的事情。

I could say, please turn this information into a letter written to an IT admin, arguing that we don't need to preserve every document ever created by the organization.

我可以說，請把這些資訊變成一封寫給 IT 管理員的信，指出我們不需要保存組織創建的每一份文檔。

And there we go.

我們走吧。

Probably need some editing.

可能需要一些編輯。

I'll definitely want to go through it and add my own touch.

我一定要把它看一遍，然後加入自己的想法。

But what's so neat about this is what you see right here, which is the citations.

但最重要的是，你在這裡看到的是引文。

Let's say I send this letter to the IT admin and they want to know, well, where did this come from?

比方說，我把這封信寄給 IT 管理部門，他們想知道，這封信是從哪裡來的？

What is the source?

消息來源是什麼？

What is the evidence?

證據是什麼？

What's the proof?

證據是什麼？

By clicking here, I can see specifically where every piece of information or fact or argument in this conversation came from.

點擊這裡，我就能看到這次對話中的每一條資訊、每一個事實或每一個論點的具體出處。

So for example, let's click on number six here.

例如，讓我們點擊這裡的第六項。

And not only does it show you what is the original text that it's drawing from, but over here on the left, it will open up a window and highlight in purple that piece of text in context.

它不僅會向你顯示所繪製的原始文本，還會在左側打開一個窗口，用紫色高亮顯示該文本的上下文。

This is so important.

這一點非常重要。

To have value, citations need to be shown in context.

要使引文具有價值，就必須結合上下文進行說明。

What was being argued before that up here?

在此之前，大家都在爭論什麼？

What was being argued after that?

之後又在爭論什麼呢？

What is the holistic kind of situation in which this knowledge arose?

產生這種知識的整體情況是怎樣的？

Let's do another one, which is meeting notes.

我們再做一個會議記錄。

How often have you been a part of a meeting, let's say a long meeting, and you get the transcripts of everything that was said, but they're so long and convoluted.

你有多少次參加過會議，比方說參加過一個很長的會議，你拿到了所有發言的記錄，但它們又長又錯綜複雜。

You don't really want to spend the time to read through all those.

你不會真的想花時間讀完所有這些。

Even just the notes that you take yourself as part of a meeting that you're in.

即使只是你自己在會議中做的筆記。

This is a great use case for Notebook LM.

這是筆記本 LM 的絕佳用例。

Here is a Google Doc, which is the full transcription of a phone call that I had with a client of mine who's named Duck.

這裡有一份 Google 文檔，是我與一位名叫鴨子的客戶通話的完整記錄。

And you can see it's very detailed, very comprehensive, has who was speaking, when they spoke, what they said.

你可以看到它非常詳細，非常全面，有誰在發言，什麼時候發言，說了些什麼。

So there's definitely value here.

是以，這裡絕對有價值。

But when I start to scroll, you can see this is 26 full pages of very detailed text.

但當我開始滾動時，你可以看到這是整整 26 頁非常詳細的文字。

I really don't want to spend the time to find the one or two facts or opinions or whatever it is I'm looking for from so much text.

我真的不想花時間從這麼多文字中找出一兩個事實或觀點或任何我想要的東西。

So what I'm going to do is just copy the title of this Google Doc, go back to Notebook LM.

所以我要做的就是複製這個 Google 文檔的標題，回到筆記本 LM。

I've created a new notebook here called Meeting Notes.

我在這裡新建了一個名為 "會議筆記 "的筆記本。

Click Add Source.

單擊添加來源。

Let's go back to Google Drive.

讓我們回到 Google Drive。

I'm going to paste it in the search just to make it easy to find.

為了方便查找，我把它粘貼在搜索欄裡。

There it is.

就在那兒。

You can see one selected.

您可以看到其中一個被選中。

I'm going to hit Insert.

我要打 Insert。

And what I can do now is essentially have a conversation with that document, which, if we look here, has over 12,000 words.

而我現在能做的，基本上就是與這份文件進行對話，如果我們看這裡，這份文件有 12000 多字。

It's much, much bigger than can fit in Chat GPT, for example.

例如，它比 Chat GPT 能容納的要大得多。

So what I'm going to ask is, what are the main points of my conversation with Doug?

我想問的是，我和道格談話的要點是什麼？

So you can see here, Doug expressed interest in creating a training program.

所以你可以看到，道格對創建一個培訓計劃表示出了興趣。

What kind of training program?

什麼樣的培訓計劃？

Well, he believes a group workshop would be most effective.

那麼，他認為小組研討會將是最有效的。

What does he want to incorporate into that workshop?

他想把什麼納入研討會？