Name: 在 13 分鐘內學會 80% 的 NotebookLM！ (Learn 80% of NotebookLM in Under 13 Minutes!)
Uploaded: 2025-06-02T11:03:28.000Z
Duration: 12 min 36 s

Here's a rule of thumb for using Notebook LM.

以下是使用筆記本 LM 的經驗法則。

If your use case matches the following three criteria, Notebook LM will perform better than other AI tools.

如果您的使用案例符合以下三個標準，Notebook LM 的性能將優於其他人工智能工具。

程度副詞

First, you have a very low tolerance for hallucination.

首先，你對幻覺的容忍度很低。

Second, you're working with information scattered across different locations, different formats like documents and slides, and or across different mediums, text, video, and audio.

其次，你需要處理分散在不同地點、不同格式（如文檔和幻燈片）或不同媒介（文本、視頻和音頻）的資訊。

And third, you want a quick and reliable way to transform all that fragment information into a cohesive and meaningful output.

第三，你需要一種快速可靠的方法，將所有碎片資訊轉化為有內涵、有意義的輸出。

In the next 15 minutes, I'll go over key features, real-world use cases, and pro tips very few people know about.

在接下來的 15 分鐘裡，我將介紹一些關鍵功能、實際用例和很少有人知道的專業技巧。

Right off the bat, it's a bit overwhelming for most users to see this when creating their first notebook.

對於大多數用戶來說，在創建第一本筆記本時看到這些內容會有點不知所措。

So I recommend pressing escape, clicking the logo in the top left corner to go to the Notebook LM home page.

是以，我建議按下 escape 鍵，點擊左上角的徽標，進入 Notebook LM 主頁。

And now that we're oriented, we wanna bookmark this for easy reference in the future, change to list view, that's just a personal preference of mine, and sort by title.

現在，我們已經確定了方向，我們要將其添加到書籤中，以便將來參考，然後切換到列表視圖（這只是我的個人偏好），並按標題排序。

Now let's create a new notebook, and here I'm first gonna press escape again because I wanna first name this notebook Health Reports 2.

現在，讓我們創建一個新筆記本，在這裡，我首先要再次按下 escape 鍵，因為我想首先將這個筆記本命名為 "健康報告 2"。

And click the plus icon here to start uploading sources.

然後點擊這裡的加號圖標，開始上傳信息源。

Here, I'm just gonna upload my three most recent annual health checkup reports along with a PDF version of Tools of Titans by Tim Ferriss.

在這裡，我要上傳我最近的三份年度健康檢查報告，以及蒂姆-費里斯（Tim Ferriss）所著《泰坦工具》（Tools of Titans）的 PDF 版本。

And while all that's loading, I'm gonna add another source, YouTube video.

在加載這些內容的同時，我還要添加另一個來源--YouTube 視頻。

And I am first going to add a video on the topic of uric acid.

我首先要添加一段關於尿酸的視頻。

I promise this will make sense in a little bit.

One more source, YouTube video, and this is gonna be a video by Andrew Huberman on the topic of fasting.

還有一個來源，YouTube 視頻，這將是安德魯-休伯曼（Andrew Huberman）關於斷食主題的視頻。

Once all sources have been uploaded and processed, we can now click into individual sources.

上傳並處理完所有數據源後，我們就可以點擊進入各個數據源了。

I'll choose my most recent health report.

And I'm gonna blur this to not overshare, but ladies just know that I'm at peak physical health.

為了不過多透露，我想模糊一下，但女士們只需知道，我的身體正處於巔峰狀態。

And under source guide, we see that Notebook LM has produced a concise summary of a dense medical report I would definitely not have read word for word.

而在資料來源指南中，我們看到《筆記本 LM》對一份我肯定不會逐字閱讀的密密麻麻的醫學報告進行了簡明扼要的總結。

On the right, clicking into one of the key topics like abnormal results here, actually prompts Notebook LM to expand on that topic based on all the selected sources on the left-hand side, even though the key topic was just from one source, right?

在右側，單擊其中一個關鍵主題（如這裡的異常結果），實際上會提示筆記本 LM 根據左側的所有選定來源擴展該主題，即使關鍵主題只是來自一個來源，對嗎？

So that's the first important thing to keep in mind.

是以，這是需要牢記的第一件大事。

Everything in this chat interface takes into account all selected sources.

該哈拉界面中的所有內容都會考慮到所有選定的來源。

Meaning if we want Notebook LM to ignore a source, we need to first deselect it from the source list.

也就是說，如果我們想讓 Notebook LM 忽略某個來源，首先需要從來源列表中取消選擇該來源。

The only abnormal result from my health reports is my absolutely huge capacity to make dad jokes.

我的健康報告中唯一不正常的結果就是我開爸爸玩笑的能力絕對超強。

The Notebook guide feature down here is like a quick start guide for beginners.

下面的筆記本指南功能就像是初學者的快速入門指南。

There's a summary of all the sources added to the Notebook, pre-created templates like FAQs and briefing docs that are very situational, I'll give examples later, and suggested questions here to help users get started.

這裡有添加到筆記本中的所有資料來源的摘要、預創建的模板（如常見問題解答和簡報文檔），這些模板非常適用於各種情況，我稍後會舉例說明，這裡還有建議的問題，以幫助用戶開始使用。

And don't worry, we'll also go over audio overviews today.

別擔心，我們今天還會介紹音頻概述。

All right, we're gonna start interacting with the Notebook, but since the answers take a while to generate, I'll switch over to the actual health reports Notebook I've been using.

好了，我們開始與筆記本互動，但由於生成答案需要一些時間，我將切換到我一直在使用的實際健康報告筆記本。

First, I asked for the top 10 health trends based on my last three reports, a pretty time-consuming task even for doctors, right?

首先，我詢問了根據我最近三份報告得出的十大健康趨勢，即使對醫生來說，這也是一項相當耗時的任務，不是嗎？

But after just a few seconds, Notebook LM just gives me a list of 10 observations, one of which is the fact that I've had elevated uric acid levels over the last three years, which is unfortunately true because I eat a lot of red meat.

但僅僅過了幾秒鐘，Notebook LM 就給我列出了 10 條觀察結果，其中一條是我在過去三年裡尿酸水準升高，這很不幸是真的，因為我吃了很多紅肉。

And because I added a video on uric acid as a source, I can now ask what are the top three things I can do to lower my uric acid levels?

因為我添加了一個關於尿酸的視頻作為資料來源，所以我現在可以問，我能做的降低尿酸水準的前三件事是什麼？

I'm told I can do these three things, okay, but just to be safe, what exactly did the video say?

我被告知可以做這三件事，好吧，但為了安全起見，視頻裡到底說了什麼？

Clicking the inline citation brings up the video transcript and Dr. Berg says potassium citrate can knock out uric acid pretty fast.

點擊內聯引文可看到視頻記錄，伯格博士說檸檬酸鉀能快速消除尿酸。

Now, pay attention to this next part because I got burned by this.

現在，請注意接下來的部分，因為我被這部分燒傷了。

Whenever you see a good output you want to refer back to, click save to note.

每當您看到想要參考的優秀成果時，請單擊 "保存到備註"。

If you don't do this, the output disappears the next time you reload the notebook.

如果不這樣做，下次重新加載筆記本時，輸出就會消失。

According to Google, this happens because Notebook LM is not trained on any of the data that we upload, including our conversations, meaning if we close a chat without saving the note, all that data disappears.

根據谷歌的說法，出現這種情況是因為筆記本 LM 沒有對我們上傳的任何數據（包括我們的對話）進行訓練，這意味著如果我們在沒有保存筆記的情況下關閉哈拉，所有數據都會消失。

Next, I fast for 36 hours every week and since both the Hubren video and Tools of Titans talk about fasting, I can ask, hey, does anything from my health reports suggest I shouldn't fast for 36 hours every week?

接下來，我每週都要禁食 36 個小時，既然《Hubren》視頻和《Tools of Titans》都談到了禁食，我可以問，嘿，我的健康報告中有什麼建議我不應該每週禁食 36 個小時嗎？

And again, Notebook LM does a great job sharing context, telling me my blood work is normal and I can continue fasting with no issues.

同樣，Notebook LM 很好地分享了背景情況，告訴我血液檢查結果正常，我可以繼續禁食，不會有任何問題。

Without Notebook LM, yes, I can obviously go through the exact same information and draw my own conclusions, but that's very manual, very time consuming and I might miss key information.

如果沒有筆記本 LM，是的，我顯然可以查看完全相同的資訊並得出自己的結論，但這非常人工，非常耗時，而且我可能會錯過關鍵資訊。

In contrast, Notebook LM is able to quickly and efficiently reference multiple sources, connect the relevant dots and produce a good enough output in significantly less time.

相比之下，Notebook LM 能夠快速有效地參考多個資料來源，連接相關的點，並在更短的時間內完成足夠好的輸出。

Finally, I'm gonna throw a curve ball and prompt this notebook with, what do the sources say about incorporating deload weeks into my workout routine?

最後，我要拋出一個小問題，提示這本筆記本：關於將離職周納入我的鍛鍊計劃，資料來源是怎麼說的？

And as expected, Notebook LM says, none of the sources say anything about deload weeks, which is true, but the output does mention related topics.

不出所料，Notebook LM 說，所有資料中都沒有提到減負周，這是事實，但產出確實提到了相關主題。

This actually illustrates a very important point.

這實際上說明了一個非常重要的問題。

Even though Notebook LM and Google Gemini might use the same underlying model, Notebook LM is fine-tuned to hallucinate less, but as a result is also less creative.

儘管 "筆記本電腦 LM "和 "谷歌雙子座 "可能使用相同的底層模型，但 "筆記本電腦 LM "經過微調，幻覺較少，是以創造性也較差。

Whereas Google Gemini, while prone to hallucination, is optimized for speed and creativity.

而谷歌雙子座雖然容易產生幻覺，但卻能優化速度和創造力。

Wrapping up this example, not only can we manually add a note, but we can also select multiple notes or just simply select all and choose to convert all these notes to a standalone source.

總結這個例子，我們不僅可以手動添加一個筆記，還可以選擇多個筆記，或者直接全選，然後選擇將所有這些筆記轉換為獨立源。

Pro tip, once that new source is created, we can click into it, select all the text here, copy and paste to use somewhere else.

提示：創建新源後，我們可以點擊進入，選中此處的所有文本，然後複製並粘貼到其他地方使用。

By the way, if you wanna cut through all the hype and master essential AI skills, you might wanna check out my free AI toolkit.

順便說一句，如果你想拋開所有炒作，掌握基本的人工智能技能，不妨看看我的免費人工智能工具包。

Use case number one is something I call focus knowledge retrieval.

第一種情況我稱之為重點知識檢索。

And starting off with a simple example, I have a notebook titled Equipment Manuals where I've added all the user manuals for all my filming equipment.

從一個簡單的例子開始，我有一個名為 "設備手冊 "的筆記本，我把所有拍攝設備的用戶手冊都放在裡面。

This allows me to ask questions like, hey, how do I update the firmware for this monitor?

這樣我就可以問一些問題，比如：嘿，我怎樣才能更新這個顯示器的固件？

Or how do I enable this one specific setting in my camera?

或者，如何啟用相機中的這一特定設置？

And Notebook LM is able to retrieve that relevant information from my sources.

而筆記本 LM 可以從我的信息源中獲取相關資訊。

To replicate this, you can just Google the product you have followed by user manual, type PDF.

要複製這個功能，您只需在 Google 上搜索您擁有的產品，然後輸入用戶手冊和 PDF。

Side note, this is also how I found the PDF version of Tools of Titans.

題外話，我也是這樣找到 PDF 版本的《泰坦工具》的。

And even if you can't find a PDF version of the user manual, remember you can add the website directly as a source.

即使找不到 PDF 版本的用戶手冊，也要記住可以直接將網站添加為來源。

Pro tip, there are some websites that actively block Notebook LM from adding them as sources, but we can easily get around this by adding another source and just copy and pasting the text from that website right here.

提示：有些網站會主動阻止 Notebook LM 將其添加為來源，但我們可以通過添加另一個來源，然後將該網站的文本複製並粘貼到這裡，就能輕鬆解決這個問題。

Moving on to another example, I have a tax and accounting notebook for my business where I've added documentations like tax codes from the government and audit reports from my accountants.

再舉一個例子，我有一本企業稅務和會計筆記本，我在上面添加了政府提供的稅號和會計師提供的審計報告等文件。

In preparation for tax season, I can ask this notebook questions like, what are my tax obligations last year?

在準備報稅季時，我可以向這本筆記本提問，比如去年我的納稅義務是什麼？

What are some notable trends in my financial statements?

我的財務報表中有哪些值得注意的趨勢？

And very personalized questions like, hey, do I qualify for offshore tax exemption since I travel a lot?

還有一些非常個性化的問題，比如，我經常出差，是否有資格享受離岸免稅？

Last example for this use case, since I interview candidates as part of my full-time job, I have a recruiting notebook, this is just an example, where I add sources like guidelines from HR, performance rubrics, question banks, candidate resumes, and interview notes.

這個用例的最後一個例子是，由於面試應聘者是我全職工作的一部分，所以我有一個招聘筆記本，這只是一個例子，我在裡面添加了人力資源部門的指南、績效評分標準、問題庫、應聘者履歷和麵試筆記等資料。

I can now prepare for these interviews more effectively by asking questions like, hey, what are the key achievements and relevant skills of this candidate based on their submitted documents?

現在，我可以更有效地準備這些面試，提出這樣的問題：嘿，根據他們提交的文件，這位候選人的主要成就和相關技能是什麼？

Or based on what we look for in product marketing managers at this level, give me 10 questions to ask this candidate.

或者根據我們對這個級別的產品營銷經理的要求，給我 10 個問題來詢問這位候選人。

And what are the key strengths and areas for improvement for this candidate based on the interview notes?

根據面試記錄，該候選人的主要優勢和需要改進的地方是什麼？

Pro tip, if you try this yourself, remember to only select the documents from the candidate you're currently interviewing, or else NotebookLM might incorporate information from other candidates as well.

提示：如果您自己嘗試這樣做，請記住只選擇您正在面試的候選人的文件，否則 NotebookLM 可能會將其他候選人的資訊也納入其中。

Next up, we have the project context engine use case.

接下來是項目上下文引擎用例。

Put simply, I have a notebook for each project I'm responsible for at work, and I add meeting notes, project plans, and documents from similar projects as sources.

簡單地說，我為工作中負責的每個項目都準備了一個筆記本，並添加了會議記錄、項目計劃和類似項目的文件作為資料來源。

Side note, project and program managers benefit massively from NotebookLM, because by definition, their job requires them to one, work with information scattered across different locations, and two, synthesize that information in an easy to digest format.

題外話：項目和計劃經理從 NotebookLM 中獲益匪淺，因為顧名思義，他們的工作要求他們：第一，處理分散在不同地點的資訊；第二，以易於消化的格式綜合這些資訊。

And NotebookLM is designed to do exactly that.

Remember the suggested templates found under notebook guide?

還記得筆記本指南中的建議模板嗎？

Well, here we can take that a step further to create perhaps a high-level briefing document for senior leaders, a campaign timeline to make it easy for us to create a slide to visualize those key milestones, and even an FAQ document for colleagues who are unfamiliar with the project.

那麼，在這裡我們可以更進一步，為高層領導創建一份高級簡報文件，創建一個活動時間表，方便我們創建幻燈片來直觀展示這些關鍵的里程碑，甚至為不熟悉項目的同事創建一份常見問題文件。

Pro tip, uploading meeting transcripts from Zoom or Google Meet unlocks highly accurate answers to questions like, hey, what are my outstanding tasks?

專業小貼士：從 Zoom 或 Google Meet 上傳會議記錄，就能為諸如 "嘿，我有哪些未完成的任務？

Or write a meeting recap email based on this one specific meeting.

或者根據這一次特定的會議撰寫一封會議總結電子郵件。

And since I've shared recap documents from previous projects, I can ask NotebookLM to identify learnings and strategies I can incorporate in my next campaign.

由於我已經分享了以前項目的總結文件，我可以要求 NotebookLM 找出我可以在下一次活動中採用的經驗和策略。

Pro tip, if you're struggling to get started with NotebookLM, I recommend uploading files you know are related in some way, and then trying the suggested questions down here.

專業建議，如果你在使用 NotebookLM 的過程中遇到困難，我建議你先上傳你知道以某種方式相關的文件，然後嘗試下面建議的問題。

Also, if you just happen to be a Google Workspace user, you might wanna join my weekly newsletter to receive an insanely actionable tip every week.

此外，如果你恰好是 Google Workspace 用戶，不妨加入我的每週時事通訊，每週都能收到非常實用的小貼士。

Next up, I work in tech, and I'm obviously interested in AI, but staying current is tough.

接下來，我在科技領域工作，顯然對人工智能很感興趣，但與時俱進很難。

There's a lot to read, and honestly, it's hard to connect the dots sometimes.

要讀的東西很多，老實說，有時很難把它們聯繫起來。

Like for example, what are the implications of this big meta announcement for the rest of the industry?

比如，這個大型元公告對行業的其他部分有什麼影響？

My solution was to create an earnings analysis notebook with earnings reports from tech companies, along with articles from tech analysts that I've compiled in a Google Docs format.

我的解決方案是創建一個收益分析筆記本，將科技公司的收益報告以及科技分析師的文章以 Google Docs 的格式彙編在一起。

You'll see why that's important in a bit.

稍後你就會明白這一點的重要性。

Now, with NotebookLM doing the heavy lifting, I can ask very targeted questions such as, what is Google's monetization strategy with regards to AI?

現在，有了 NotebookLM 的大力支持，我可以提出非常有針對性的問題，例如：谷歌在人工智能方面的貨幣化戰略是什麼？

然後我就得到了這個結構化的列表。

And I can also ask broader questions like, how do AI strategies differ for Google, Meta, Amazon, and Apple?

我還可以提出更廣泛的問題，比如谷歌、Meta、亞馬遜和蘋果的人工智能戰略有何不同？

And it's actually amazing how NotebookLM first shares a one-sentence catchy summary.

實際上，NotebookLM 首先分享的是一句朗朗上口的摘要，這一點令人驚歎。

Meta, AI for everything, everywhere, before expanding on their respective strategies.

Meta"、"AI for everything"、"AI everywhere"，然後再闡述各自的戰略。

And because I enjoy listening to podcasts during commutes and workouts, I can ask NotebookLM to generate a personalized podcast episode by clicking Customize Audio Overview and providing specific instructions like, focus on how earnings from one company affects its competitors, and assume the listener has zero technical background.

因為我喜歡在通勤和鍛鍊時收聽播客，所以我可以要求 NotebookLM 生成一集個性化播客，只需點擊 "自定義音頻概述 "並提供具體說明即可，例如，重點關注一家公司的盈利如何影響其競爭對手，並假設聽眾沒有任何技術背景。

It's like they're taking a page from Meta's book, right?

他們好像在借鏡 Meta 的做法，對吧？