跟讀練習: Prompt engineering - Introduction - 通過影片學習英語口語

選擇練習模式

每種模式都會開啟全屏練習室。

68 句

如果句子過短或過長，請點選 Edit 進行調整。

Welcome to this course on ChatGPT problem engineering for developers.

I'm thrilled to have with me Iza Fulford to teach this along with me.

She is a member of the technical staff of OpenAI and had built the popular ChatGPT retrieval plugin.

And a large part of work has been teaching people how to use OEM or large language model technology in products.

She's also contributed to the OpenAI cookbook that teaches people prompting.

So thrilled to have you with you.

And I'm thrilled to be here and share some prompting best practices with you all.

I'm not sure.

So there's been a lot of material on the internet for prompting,

with articles like "30 Prompts Everyone Has to Know" A lot of that has been focused on the ChatGPT web user interface,

which many people are using to do specific and often one -off tasks.

I think the power of LOM's large language models as a developer too, that is using API calls to LOMs to quickly build software applications.

I think that is still very underappreciated.

In fact, my team at AI Fund, which is a sister company to deep learning AI,

has been working with many startups on applying these technologies to many different applications.

It's been exciting to see what LOM APIs can enable developers to very quickly build.

So in this course, we'll share with you some of the possibilities for what you can do, as well as best practices for how you can do them.

There's a lot of material to cover.

First, you'll learn certain prompting best practices for software development.

Then we'll cover some common use cases, summarising, inferring, transforming, expanding.

And then you'll build a chatbot using an LLM.

Thank you.

We hope that this will spark your imagination about new applications that you can build.

So in the development of large language models or LLMs, there have been broadly two types of LLMs,

which I'm going to refer to as base LLMs and instruction -tuned LLMs.

So base LLM has been trained to predict the next word, based on text training data, often trained on large amount of data from the internet and other sources,

to figure out what's the next most likely word to follow.

So for example, if you were to prompt this, once upon a time there was a unicorn, it may complete this, that is, it may predict the next several words are,

that live in the magical forest of all unicorn friends.

But if you were to prompt us with what is the capital of France, then based on what articles on the internet might have,

it's quite possible that the base LM will complete this with, what is France's largest city, what is France's population and so on.

Because articles on the internet could quite plausibly be lists of quiz questions about the country of France.

Thank you.

In contrast, an instruction tuned LLM, which is where a lot of momentum of LLM research and practice has been going,

An instruction team has been trained to follow instructions.

So if you were to ask it, what is the capital of France is much more likely to output something like the capital of France is Paris

So the way that instruction -tuned OOMs are typically trained is, you start off with a base OOM that's been trained on a huge amount of text data,

and further train it, further fine tune it with inputs and outputs that are instructions and good attempts to follow those instructions.

And then often further refine using a technique called RLHF, reinforcement learning from human feedback,

to make the system better able to be helpful and follow instructions.

Because instruction TNLMs have been trained to be helpful, honest, and harmless.

So for example, they're less likely to output problematic texts, such as toxic outputs compared to base LLM.

a lot of the practical usage scenarios have been shifting toward instruction to,

you know, Some of the best practices you find on the internet may be more suited for a base LLM, but for most practical applications today,

we would recommend most people instead focus on instruction tuned LLMs, which are easier to use.

And also because of the work of OpenAI and other LLM companies becoming safer and more aligned.

So this course will focus on best practices for instruction to neural arms

which is what we recommend you use for most of your applications.

Before moving on, I just want to acknowledge the team from OpenAI

and DeepLearn .AI that had contributed to the materials that Ysia and I will be presenting.

I'm very grateful to Andrew Main, Joe Palermo, Boris Power, Ted Sanders, and Lillian Wang from OpenAI.

They were very involved with us brainstorming materials, vetting the materials to put together.

the curriculum for this short course.

And I'm also grateful on the deep learning side for the work of Jeff Lodwick, Eddie Hsu and Tommy Nelson.

So when you use an instruction tuned LLM, think of giving instructions to another person.

Say someone that's smart but doesn't know the specifics of your task.

So when an LM doesn't work, sometimes it's because the instructions weren't clear enough.

For example, if you were to say, "Please write me something about Alan Turing." Well, In addition to that, it can be helpful to be clear about whether you want

the text to focus on his scientific work or his personal life or his role in history or something else.

And if you specify what you want the tone of the text to be, should it take on the tone like a professional journalist would write?

Or is it more of a casual note

that you dash off to a friend that holds the OM generate what you want.

And of course, if you picture yourself asking, say a fresh college graduate to carry out this task for you,

if you can even specify what you want snippets of texts

they should read in advance to write this text about Alan Turing, then that even better sets up that fresh college grad for success to carry out this task for you.

So in the next video, you see examples of how to be clear and specific, which is an important principle of prompting LOMs.

And you also learn from Ezer a second principle of prompting, that is giving LDLM time to think.

So with that, let's go on to the next video.

下載應用

流利口語所需的一切

AI 發音評分逐句打分

音標練習掌握每個音

詞彙學習建立你的詞庫

詞彙遊戲邊玩邊學

掃碼

Download on theApp Store Get it onGoogle Play

同頻道

Prompt Engineering - Guidelines

Daily ConversationUniversity StudentsWorking Adults

FOR YOU

關於本課

在本課中，學習者將深入瞭解提示工程的基礎知識，特別是在大型語言模型（LLM）應用程式開發中的最佳實踐。通過本課程，您將學習到如何有效地使用指令調優的LLM，來快速構建軟體應用程式並促進您的學習程序。此外，本課程還提供關於如何構建聊天機器人的實踐經驗，激發您對新應用程式的構建想像。

關鍵詞彙與短語

提示工程 (Prompt Engineering) - 使用特定的提示來引導LLM產生期望的輸出。
大型語言模型 (Large Language Models) - 一種先進的演算法，專門用於文本生成和自然語言處理。
指令調優 (Instruction-Tuning) - 訓練模型以更好地遵循使用者指令的方法。
基礎模型 (Base LLM) - 訓練用於預測下一個詞的基本語言模型。
聊天機器人 (Chatbot) - 使用LLM技術構建的能夠進行對話的程式。
反饋學習 (Reinforcement Learning) - 一種通過人類反饋來改進模型效能的技術。
幫助性 (Helpfulness) - 指模型能夠提供準確和有用資訊的能力。
安全性 (Safety) - 指模型減少輸出有害內容的能力。

練習技巧

在練習英語影子跟讀時，推薦採用影子演講（shadow speech）的方法，專注於模仿講話者的語速和語調，尤其是本影片中提到的有關LLM的例項。您可以反覆播放影片，嘗試與講解者同頻率地跟讀。注意發音時，尤其要關注 提高英語發音 的細節，通過 shadowspeak 來提升你的流利度和表達能力。同時，選擇合適的 shadowing site 進行練習，將大大提高您的學習效果。此外，學習語句的節奏和重音也會幫助您更自然地說英語。通過不斷地練習，您將能夠更自信地使用這些語言技能。期待您在本課程中的收穫！

影片中的語法

說話人最常用的結構，並附上影片中的原話：

結構	影片中的用法
現在完成進行時 have/has been + -ing — 以前開始、現在仍在繼續的動作	has been teaching · has been working · has been going
現在完成時 have/has + 過去分詞 — 過去發生但與現在仍有關聯的事	there's been · has been · have been
被動語態 be + 過去分詞 — 強調發生了什麼，而不是誰做的	has been trained · been trained · have been trained
定語從句 who / which + 從句 — 補充說明人或事物	Fund, which is · LLM, which is · LLMs, which are

什麼是跟讀法？

跟讀法 (Shadowing) 是一種有科學依據的語言學習技巧，最初開發用於專業口譯員的培訓，並由多語言者Alexander Arguelles博士普及。這個方法簡單而強大：您在聽英語母語原聲的同時立即大聲重複——就像是一個延遲1-2秒緊跟說話者的影子。與被動聽力或語法練習不同，跟讀法強迫您的大腦和口腔肌肉同時處理並模模擬實的講話模式。研究表明它能顯著提高發音準確性，語調，節奏，連讀，聽力理解和口語流利度——使其成為雅思口語備考和真實英語交流最有效的方法之一。

影子跟讀法: 閱讀完整分步指南 →

跟讀練習: Prompt engineering - Introduction - 通過影片學習英語口語

選擇練習模式

下載應用

同頻道

Prompt Engineering - Guidelines

推薦影片

P1 机器学习的应用【2024公认最好的 | 吴恩达机器学习 | 教程 | Machine Learning Specialization(超爽中英!)】

Transformers, the tech behind LLMs | Deep Learning Chapter 5

Claude Code: The Advanced Guide (99% of Devs Skip These Features)

Easy Migration from Postgres to Databricks Lakebase

Rapid Engineering With AI

The 7 Skills You Need to Build AI Agents

New Skills! v1.1 brings /wayfinder, /research, /implement, /to-spec, /to-tickets

Most devs don't understand how LLM tokens work

What's new in Google Cloud in less than 1 minute

AI Concepts Every Product Manager Should Know in 25 Minutes | Crash Course

Improve Your English Listening & Speaking Fast | English Shadowing Practice B2 C1

關於本課

關鍵詞彙與短語

練習技巧

影片中的語法

什麼是跟讀法？