This one is for learning Japanese.

這本是用來學習日語的。

This one is for learning how to make better YouTube videos.

這本是用來學習如何製作更好的 YouTube 視頻的。

And last but not least, this one is for learning personal finances.

最後但並非最不重要的是，這本是用來學習個人理財的。

These are the four topics, the four study plans that I'm currently following.

這是我目前正在學習的四個主題、四個學習計劃。

They're all custom designed to fit my specific goals.

它們都是根據我的具體目標定製的。

Like for the Japanese one, I don't care about how to like speak Japanese or read Japanese.

至於日語，我並不關心如何說日語或讀日語。

I just want to learn how to understand Japanese so that I can watch anime without subtitles.

我只想學會如何理解日語，這樣我就可以看沒有字幕的卡通片了。

I know it's pretty specific.

我知道這很具體。

But yeah, they're all custom made at my study level, my skill set, my preferred resources, and my preferred study schedule.

但是，是的，它們都是根據我的學習水準、我的技能組合、我偏好的資源和我偏好的學習時間表定製的。

Before Chachipiti, each of these study plans would have taken me days, if not weeks, to get to this level.

在學習 Chachipiti 之前，每個學習計劃都要花上幾天甚至幾周的時間才能達到這個水準。

But with Chachipiti, I was able to do each of them in less than 10 minutes.

但有了 Chachipiti，我可以在 10 分鐘內完成每一個動作。

After I got the prompt right though, the prompt itself did take me weeks to actually figure out.

不過，在我弄懂了提示語之後，提示語本身確實花了我好幾周的時間才真正弄明白。

But luckily for you, in this video, I'm going to just show you guys this prompt to make a really optimized custom study plan using Chachipiti.

但幸運的是，在本視頻中，我將向你們展示如何使用 Chachipiti 製作真正優化的定製學習計劃。

That works for any subject.

這適用於任何主題。

Plus, I'm going to give you some bonus prompts and tips and tricks on how to use Chachipiti to make the actual studying process faster and also more fun.

此外，我還會給你一些額外的提示以及使用 Chachipiti 的技巧和竅門，讓你的實際學習過程更快、更有趣。

All right, let's have that start running while I explain the prompt.

好的，讓我們開始運行，同時我來解釋一下提示。

So for this example, I'm going to make a study plan for learning AI.

是以，在這個例子中，我要制定一個學習人工智能的學習計劃。

You can change that for any other topic that you want as well.

您也可以根據自己的需要，為任何其他主題更改。

All right, so the prompt.

好吧，那麼提示。

You are an expert learning tutor who is well versed in Scott Young's book, Ultra Learning.

您是一位精通斯科特-揚的《超級學習》一書的學習輔導專家。

So that is from this book over here.

這就是這本書裡的內容。

I have tried a lot of different frameworks from a lot of different books and resources, and by far the best one for how to create a good study plan using Chachipiti.

我從許多不同的書籍和資源中嘗試了許多不同的框架，而到目前為止，最好的框架是使用 Chachipiti 來制定良好的學習計劃。

This framework in this book works the best.

本書中的這個框架最有效。

So I actually covered this book in detail.

是以，我實際上詳細介紹了這本書。

You can check it out on this link over here.

您可以通過這個鏈接查看。

So I'm not going to go into much of it now, but just trust me on this one.

所以我現在不想多說，但請相信我。

OK, all right.

好吧

So moving on.

繼續前進。

So right now I want to make a study plan for ultra learning AI based on the principle of meta learning and the why, what, how framework.

是以，現在我想根據元學習原理和為什麼學、學什麼、怎麼學的框架，制定一個超學習人工智能的學習計劃。

So that is the framework from the book.

這就是書中的框架。

Why is why I want to learn it.

這就是我想學習它的原因。

What is what I will learn?

我將學到什麼？

This is divided into concepts, facts and procedures.

這分為概念、事實和程序。

How is how will I learn it?

如何學習？

This is based on techniques of benchmarking and emphasize, exclude.

這是以基準和強調技術為基礎的。

Benchmarking means to find common ways people learn it by doing research.

基準是指通過研究找到人們學習它的共同方法。

Emphasize, exclude means for making modifications to align with the goal.

強調、排除為與目標保持一致而進行修改的手段。

My why for learning AI is because I want to build simple web applications using LMS and other AI products.

我之所以學習人工智能，是因為我想使用 LMS 和其他人工智能產品構建簡單的網絡應用程序。

The why is extremely important.

為什麼是極其重要的。

Make sure to think carefully about why it is that you want to learn this topic and tell ChachiBT.

請務必認真思考為什麼要學習這個主題，並告訴 ChachiBT。

The more specific you are, the better.

越具體越好。

Like my Japanese one is specific for learning how to understand anime Japanese, so I don't have to read subtitles.

比如我的日文版就是專門用來學習如何理解動漫日語的，這樣我就不用看字幕了。

My personal finance one has specific goals about buying land and property.

我的個人理財計劃有關於購買土地和房產的具體目標。

And for making YouTube videos, I say specifically it's for making video essays to maximize for views.

至於製作 YouTube 視頻，我特別強調是製作視頻隨筆，以最大限度地提高瀏覽量。

I already know how to code in Python and know how to build a Python applications with Django.

我已經知道如何用 Python 編程，也知道如何用 Django 構建 Python 應用程序。

So I understand the components of a web application and how they work, etc.

是以，我瞭解網絡應用程序的組成部分及其工作原理等。

This is where you tell ChachiBT what you already know about that topic, so it's able to adjust its skill level for you.

在這裡，您可以告訴 ChachiBT 您對該主題的瞭解程度，這樣它就能為您調整技能水準。

So let's create a study plan using this framework.

那麼，讓我們利用這個框架來制定一個學習計劃吧。

Let's start with the what.

先說 "什麼"。

For the what in your study plan, we'll break it down into concepts, facts and procedures.

對於學習計劃中的內容，我們會將其分解為概念、事實和程序。

So it tells me the concepts that I need to learn, such as AI and machine learning basics, natural language processing, pre-trained models and APIs, web application architecture for AI apps and ethics and bias in AI.

是以，它告訴了我需要學習的概念，如人工智能和機器學習基礎知識、自然語言處理、預訓練模型和應用程序接口、人工智能應用程序的網絡應用架構以及人工智能中的道德和偏見。

And for facts, key libraries and frameworks, data formats, pre-trained model specs and performance metrics.

事實、關鍵庫和框架、數據格式、預訓練模型規格和性能指標。

And for procedures, the actual steps I need to take.

對於程序，我需要採取的實際步驟。

So all of this is very specific to my goal and looks very reasonable.

是以，所有這些都非常符合我的目標，而且看起來非常合理。

By the way, the reason why I didn't give you like one massive prompt and I said to start with the what is that this way it offers you flexibility.

順便說一下，我之所以沒有給你一個大規模的提示，而是讓你從 "什麼 "開始，是因為這樣可以給你提供靈活性。

Like, for example, maybe I don't care about ethics and bias.

比如說，也許我不在乎道德和偏見。

I should care about ethics and bias, but I could say something like, I don't care about ethics and bias.

我應該在乎道德和偏見，但我也可以說，我不在乎道德和偏見。

Please remove that.

請將其刪除。

But yeah, so yeah, this is how you can kind of iterate on top of it so that you get the concepts, facts and the procedures that you want to have.

是的，就是這樣，你可以在它的基礎上進行迭代，從而得到你想要的概念、事實和程序。

All right, let's actually add it back in.

好吧，讓我們把它加回去。

OK, so let's now move on to the how of the framework.

好了，現在讓我們來看看該框架是如何運作的。

All right, we asked ChachiBT to do benchmarking, which is to research common methods of learning.

好吧，我們請 ChachiBT 來做基準測試，也就是研究常見的學習方法。

So you and I are not the first people who want to learn how to use AI to build applications.

是以，你我並不是第一個想學習如何使用人工智能來構建應用程序的人。

So instead of trying to come up with something from scratch, we can actually ask ChachiBT to research the collective knowledge of people who have come before us and what they figured out is the best way to learn.

是以，與其從頭開始想辦法，我們其實可以請 ChachiBT 研究前人的集體知識，看看他們發現了什麼是最好的學習方法。

And based on that, we're doing emphasis slash exclude.

在此基礎上，我們正在進行重點斜線排除。

So we're emphasizing things that are targeted towards my goals and excluding things that are not useful towards my goal.

是以，我們要強調那些對我的目標有針對性的東西，而排除那些對我的目標無用的東西。

So in this case, from doing that research, we know that people use beginner friendly courses such as Anjanine's course on Coursera or Fast.ai.

是以，在這種情況下，通過研究，我們知道人們會使用初學者友好型課程，如 Coursera 上的 Anjanine 課程或 Fast.ai。

People use APIs and library documentation.

人們使用應用程序接口和庫文檔。

Project based learning is really important.

基於項目的學習非常重要。

Online communities and GitHub and for ethics and bias, looking at case studies and ethical guidelines.

在線社區和 GitHub，以及道德和偏見，研究案例和道德準則。

So we're emphasizing project based learning and API integration of web applications because we want to build a web app using LLMs and AI models through APIs.

是以，我們強調基於項目的學習和網絡應用程序的 API 集成，因為我們希望通過 API 使用 LLM 和人工智能模型構建網絡應用程序。

We need to have AI fundamentals with a focus on large language models specifically and for bias, identification and mitigation.

我們需要掌握人工智能基礎知識，重點關注大型語言模型，特別是偏差、識別和緩解。

What we're excluding is in-depth theoretical ML slash deep learning knowledge.

我們不包括深入的 ML 理論知識和深度學習知識。

Since I said that I wanted to be applied, I just want to build these applications, not like build my own models and deeply understand them.

既然我說要應用，我就只想建立這些應用，而不是建立自己的模型並深入理解它們。

That's why we're excluding this.

這就是為什麼我們要把這個排除在外。

And also we're excluding data set creation and fine tuning.

此外，我們還不包括數據集創建和微調。

These are things that we might want to do later on.

這些都是我們以後可能要做的事情。

But since I just want to build an application right now using the APIs, we can keep things simple and exclude that in this current study plan.

不過，由於我現在只想使用 API 構建一個應用程序，所以我們可以保持簡單，將其排除在當前的研究計劃之外。

All right.

好的

Now we want to combine together the why, when, how and come up with a comprehensive study plan that also has resources and timelines.

現在，我們要把 "為什麼"、"何時"、"如何 "結合起來，制定出一個全面的研究計劃，同時還要有資源和時間表。

So I said combine these things together and make a week by week study plan with specific deliverables.

所以我說，把這些東西結合起來，制定一個有具體成果的每週學習計劃。

For these deliverables, I said make specific assignments and projects with rubrics and specs that you can grade and provide feedback for.

對於這些可交付成果，我想說的是，制定具體的作業和項目，並附有評分標準和規範，你可以為其評分並提供反饋。

This is going to be really helpful so that it doesn't just tell you to like learn something very vague.

這將會非常有幫助，這樣它就不會只是告訴你學習一些非常模糊的東西。

We wanted to give you specific assignments that have objectives.

我們希望給你們佈置有目標的具體任務。

And later on, I'll talk about this as one of the later prompts.

稍後，我會把這作為後面的提示之一來談。

You also want ChatGBT to be able to provide you with feedback as you're completing the assignments and going through the study plan.

您還希望 ChatGBT 能夠在您完成作業和學習計劃的過程中為您提供反饋。

So we want to bake that in while we're making a study plan itself.

是以，在制定學習計劃時，我們要把這一點考慮進去。

And we want corresponding relevant resources.

我們需要相應的相關資源。

I said that I can study six hours a week with three hours on Monday and Wednesdays.

我說我可以每週學習六小時，其中週一和週三各學習三小時。

And I want resources that are primarily text or video courses because that's just how I learn best.

我想要的資源主要是文字或視頻課程，因為這是我最擅長的學習方式。

All right.

好吧

And here we go.

我們開始吧

Week one, introduction to AI, APIs and LLMs.

第一週，人工智能、API 和 LLM 簡介。

The objective is to understand AI basics and how pre-trained models and APIs works.

目的是瞭解人工智能基礎知識以及預訓練模型和應用程序接口的工作原理。

Concepts are going to be AI and machine learning basics and natural language processing and LLMs.

概念將是人工智能和機器學習基礎知識、自然語言處理和 LLM。

The facts.

事實

So it lists out what the facts are and what the procedure is going to be.

是以，它列出了事實和程序。

It has a deliverable.

它有一個交付成果。

So it says create a Python script that calls the OpenAI API to generate text based on the prompt.

也就是說，創建一個 Python 腳本，調用 OpenAI API 根據提示生成文本。

It was very specific about what it is that I actually need to accomplish.

我需要完成的任務非常具體。

And this rubric is helpful because it gives you an understanding of what should be included in the deliverable.

這個評分標準很有幫助，因為它能讓你瞭解交付成果中應該包括哪些內容。

And we have our little resources as well.

我們也有自己的小資源。

So week two is going to be integrating APIs into Django applications.

第二週的主題是將 API 集成到 Django 應用程序中。

So week three is working with image recognition models, so not just LLMs.

是以，第三週的內容是圖像識別模型，而不僅僅是 LLM。

And we have a deliverable to create a web app that accepts an image input of a plant and returns information about the species using a pre-trained image recognition API.

我們的交付成果是創建一個網絡應用程序，接受植物圖片輸入，並使用預先訓練好的圖像識別 API 返回有關物種的資訊。

Very interesting.

非常有趣。

I don't know why it's about a plant, but seems good.

我不知道為什麼是關於植物的，但看起來不錯。

Week four is your ethics and bias.

第四周是你的道德和偏見。

And week five is when we build our full stack AI application.

第五週是我們構建全棧人工智能應用程序的時間。

Very excited for that.

我對此感到非常興奮。

And week six is going to be for debugging, testing and refining.

第六週將進行調試、測試和完善。

Overall, it's going to be six weeks.

總的來說，這將是六個星期。

And by the end of it, it looks like we would have built a AI application just like how I want it to.

到最後，看起來我們就會按照我的想法建立一個人工智能應用程序。

It tells you exactly what it is that you need to learn.

它能準確地告訴你需要學習什麼。

And it has a project-based deliverables that you can apply to skills that you learn.

它還有一個基於項目的可交付成果，你可以將其應用到所學的技能中。

And it even has a rubric so you know what are the components that make up that project.

它甚至還有一個評分標準，讓你知道該項目由哪些部分組成。

And of course, the resources based upon what other people have used in the past and they found to be good.

當然，這些資源也是基於其他人過去使用過並認為不錯的資源。

Not to toot my own horn here, but I'm genuinely pretty proud of this prompting sequence to get to this point.

不是我自吹自擂，但我真的為這個提示序列能達到這一步感到非常自豪。

You have no idea how long it actually took me to get to this point.

你不知道我花了多長時間才走到這一步。

So, yes, just let me have this one, OK?

所以，是的，把這個給我，好嗎？

But we're actually not done.

但實際上，我們還沒完。

There is one more final step.

還有最後一步。

I hope this video has made you realize how useful ChatGPT is in terms of learning things.

希望這段視頻能讓你意識到 ChatGPT 在學習方面的作用。

But actually, that's just the beginning.

但實際上，這僅僅是個開始。

It's relevant to increasing your productivity across all aspects of your life.

它與提高你生活各個方面的工作效率息息相關。

HubSpot has a whole bundle of resources designed to help you understand and make the most out of ChatGPT.

HubSpot 提供了一整套資源，旨在幫助您瞭解並充分利用 ChatGPT。

It will make you super productive.

它會讓你的工作效率超高。

It's very well laid out and gives you lots of ideas on ways you can incorporate ChatGPT.

它佈局合理，為您提供了許多結合 ChatGPT 的方法。

For example, using ChatGPT to consolidate research materials like different articles, tutorials and resources.

例如，使用 ChatGPT 整合研究資料，如不同的文章、教程和資源。

So you can directly ask questions instead of having to flip through all of them yourself or keeping you up to date with industry news and updates.

這樣，您就可以直接提問，而不必親自翻閱所有問題，或隨時瞭解行業新聞和最新動態。

They also have this nice flowchart on when it's appropriate to use ChatGPT to solve a problem or streamline your workflow.

他們還提供了一張漂亮的流程圖，說明何時適合使用 ChatGPT 來解決問題或簡化工作流程。

My favorite part is that it has over 100 prompts to start playing around with, which is great since, as you can see, prompting is extremely important to getting the most out of ChatGPT.

我最喜歡的部分是，它有 100 多條提示可供開始玩轉，這一點非常好，因為正如你所看到的，提示對於充分發揮 ChatGPT 的作用極其重要。

The best part is that it's completely free.

最重要的是，它完全免費。

I highly recommend that you download it using this link over here, also linked in description.

我強烈建議您使用這裡的鏈接下載，鏈接也在說明中。

Thank you so much, HubSpot, for providing free resources to help us leverage the power of AI.

非常感謝 HubSpot 提供免費資源，幫助我們利用人工智能的力量。

And for sponsoring this portion of the video.

並贊助本部分視頻。

Now, back to the video.

現在，回到視頻上來。

Ideally, you want an expert, someone who already knows the content of your study plan, to look over your study plan and just sort of double check that things make sense.

理想情況下，你需要一位專家，一位已經瞭解你的學習計劃內容的人，來查看你的學習計劃，仔細檢查是否合理。

You can do this if you actually know someone who already knows AI or knows Japanese or is really good at personal finances and they can look over your plan.

如果您有認識的人懂人工智能、日語或精通個人財務，您就可以這樣做，讓他們看看您的計劃。

But assuming you don't know anybody, this final step is you're going to ask ChatGPT to now be an expert AI engineer that specializes in developing AI applications.

但假設你不認識任何人，最後一步就是讓 ChatGPT 成為專門開發人工智能應用程序的人工智能工程師專家。

And we're asking this AI engineer to look at the study plan above as if it's for the first time and to provide feedback on what they think and also what they think should be changed.

我們要求這位人工智能工程師把上面的研究計劃當作第一次看，並就他們的想法和認為應該修改的地方提供反饋意見。

So as an AI engineer, here are some strengths.

是以，作為一名人工智能工程師，這裡有一些優勢。

Project-based learning is good, balanced approach, API-centric, rubric for deliverables, ethics, and bias consideration.

項目式學習很好，方法均衡，以應用程序接口為中心，可交付成果的評分標準、道德規範和偏見考慮。

So some suggestions for improvement.

是以，我們提出了一些改進建議。

Maybe you want to have more emphasis on debugging and error handling because building AI applications often involves dealing with unforeseen edge cases, especially when integrating multiple APIs.

也許您希望更加重視調試和錯誤處理，因為構建人工智能應用程序往往需要處理不可預見的邊緣情況，尤其是在集成多個應用程序接口時。

And it gives you like specific changes, like increasing focus on error handling and then adding a mini project in week three where you intentionally introduce errors or unexpected inputs and learn to handle them.

它還會給你一些具體的改變，比如增加對錯誤處理的關注，然後在第三週增加一個小項目，讓你故意引入錯誤或意外輸入，並學習如何處理它們。

This is actually very common practice when you're debugging an application.

這其實是調試程序時非常常見的做法。

So a very good point here.

所以，這一點非常好。

Also introduce real world data earlier and more frequent iterations and refactoring.

同時，更早地引入真實世界的數據，更頻繁地進行迭代和重構。

So you can choose to incorporate some of this feedback or you can choose to ignore it.

是以，你可以選擇採納其中的一些反饋意見，也可以選擇置之不理。

So in this case, I'm going to choose to include some of this feedback.

是以，在這種情況下，我會選擇採納其中的一些反饋意見。

Thank you.

謝謝。

These include suggestions one and two into the study plan.

這些建議包括研究計劃中的建議一和建議二。

And voila, there you have it.

瞧，這就對了。

We have created a custom study plan for learning how to build AI applications.

我們為學習如何構建人工智能應用程序量身定製了學習計劃。

Don't worry if you didn't catch everything.

如果沒聽清，也不用擔心。

I'll leave a link in the description that has the prompt sequence in it.

我會在說明中留下一個鏈接，裡面有提示序列。

So now that we have the study plan, the next step is that we actually have to study.

現在我們有了學習計劃，下一步就是要真正去學習。

I also want to share with you guys some of the prompts and the little techniques that I use where I can get through the study plans so much faster and a lot more fun as well.

我還想和你們分享一些提示和我使用的小技巧，在這些技巧的幫助下，我可以更快、更有趣地完成學習計劃。

First, one of my favorite chat2BT study use cases is using chat2BT to create test questions.

首先，我最喜歡的哈拉 2BT 學習用例之一是使用哈拉 2BT 創建測試問題。

A couple of months back, I had to take the knowledge section of my driver's exam, but I didn't really feel like reading the hundreds of pages of rules related to driving.

幾個月前，我必須參加駕駛員考試的知識部分，但我實在不想看那幾百頁與駕駛有關的規則。

So instead, I just gave chat2BT those documents and told it to ask me questions.

是以，我把這些文件交給 chat2BT，讓它來問我問題。

If I don't know how to answer a question, I would just ask it to explain it to me.

如果我不知道如何回答一個問題，我會請它給我解釋。

And that was just a much more fun learning experience.

這樣的學習經歷更加有趣。

You can use this technique even if you're not actually studying for an exam.

即使你不是在為考試複習，也可以使用這種技巧。

But in this case, since I was studying for an exam, I also gave it samples of some of the exam questions from the test.