Luyện nói tiếng Anh bằng Shadowing qua video: Introduction to Generative AI and LLMs [Pt 1] | Generative AI for Beginners

Chọn chế độ luyện tập

Mỗi chế độ mở một phòng luyện tập toàn màn hình.

93 câu

Nếu các câu quá ngắn hoặc quá dài, hãy bấm Edit để chỉnh sửa.

Hi everyone and welcome to the first lesson of the Generative AI for Beginners course.

This course is based on an open source curriculum with the same name available on GitHub

that you can find at the link on the screen.

I'm Carlotta Castelluccio, I'm a cloud advocate at Microsoft focused on artificial intelligence technologies

and in this video I'm going to introduce you to generative AI and large language models.

Large language models represent the pinnacle of AI technology, pushing the boundaries of what was once thought impossible.

They've conquered numerous challenges that older language models struggled with, achieving human-leavened performance in various tasks.

They have similar capabilities and applications, but for the sake of this course,

we'll explore how large language models are revolutionizing education through a fictional startup that we'll be referring to as Our Startup.

Our startup works in the education domain with the ambitious mission of improving accessibility in learning on a global scale,

ensuring equitable access to education, and providing personalized learning experiences to every learner, according to their needs.

In this course, we'll delve into how our startup harnesses the power of generative AI to unlock new possibilities in education.

We'll also examine how they address the inevitable challenges tied to the social impact of this technology and its technological limitations.

But let's start by defining some basic concepts we'll be using throughout the course.

Despite the relatively recent hype surrounding generative AI,

we can say that in the last couple of years we have really heard of generative AI everywhere and every time.

But this technology has been decades in the making, with its origins tracing back to the 1950s, 1960s.

The earliest AI prototypes consisted of typewritten chatbots relying on knowledge bases maintained experts.

These chatbots generated responses based on keywords found in user input,

but it soon became clear that this approach had scalability limitations.

A significant turning point arrived in the 1990s when a statistical approach was applied to text analysis.

And this gave birth to machine learning algorithms which could learn patterns from data without explicit programming.

And these algorithms allowed machines to stimulate human language understanding, having the way for the eye we know today.

In more recent times, advancements in hardware technology allowed for development of advanced machine learning algorithms, particularly neural networks.

These innovations significantly improved natural language processing, enabling machines to understand the context of words in sentences.

This breakthrough technology powered the birth of virtual assistants in the early 21st century.

This virtual assistants excelled at interpreting human language, identifying needs, and taking actions to fulfill them,

such as answering queries with predefined scripts or connecting to third-party services.

And so we arrived at Generative AI, a subset of deep learning.

After decades of AI research,

a new model architecture known as the Transformer emerged transformers could handle longer text sequences as input

and work based on the attention mechanism, enabling them to focus on the most relevant information,

regardless of its order in the input text.

Today, mass-generative AI models, often referred to as large language models,

are built upon the transformer architecture, and that's what the T in GPT actually means.

These models trained on vast amounts of data from sources like books, articles, and websites possess a unique adaptability.

They can tackle a wide range of tasks and generate chromatically correct text with a hint of creativity.

But let's dive deeper into the mechanism of large language models

and shed light on the inner workings of models like the OpenAI GPT's.

One of the key concepts to grasp is tokenization.

Large language models receive text as input and produce text as output, if you want to really simplify the mechanism.

However, these models work much more efficiently with numbers rather than with raw text sequences.

And that's where the tokenizer comes into play.

Text prompts are chunked into tokens, helping the model in predicting the next token for completion.

Models also have a maximum length of token window,

and model pricing is also tightly computed by the number of tokens used in output and inputs.

So tokenization is really an important concept in large language models and generative AI domain.

Now, a token is essentially a chunk of text which can vary in length and typically consists of a sequence of characters.

And the tokenizer's primary job is to really break down the input text into an array of those tokens,

which are then further mapped to token indices.

These token indices are essentially integer and coding of the original text chunks, making it easier for the model to process and understand.

Now let's move to predicting the output tokens.

Given an input sequence of and tokens with the maximum and varying from one model to another according to the maximum

content window length of for one model, the model is designed to predict a single token as its output.

But here's where it gets interesting.

The predicted token is then incorporated into the input of the next iteration, creating an expanding window pattern.

And this pattern allows the model to provide more coherent and contextually relevant responses,

often extending to one or multiple sentences.

Now let's delve into the selection process.

The model chooses the output token based on its probability of occurring after the current text sequence.

This probability distribution is calculated using the model's training data.

However, here's the twist.

The model doesn't always choose the token with the highest probability from the distribution.

To simulate the process of creative thinking, a degree of randomness is introduced into the selection process.

This means that the model doesn't produce the exact same output for the same input every time.

That's the element that allows generative AI to generate text that feels, you know, creative and engaging.

Now, we see that the main capability of a large language model is generating text from scratch, starting from a textual input written in natural language.

But what kind of textual input and output?

First of all, let me say that the input of a large language model is known as prompt, while the output is known as completion,

a term that refers to the model mechanism of generating the next token to complete the current input.

Let's do some examples of prompts and completion by using the OpenAI ChatGPT Playground, always in our educational scenario.

Now, a prompt may include an instruction specifying the type of output we expect from the model.

In the example we are seeing, we are asking to write an assignment for high school students,

including four open-ended questions about Louis XIV and his court.

You can see that the output is exactly what I'm asking for.

The model was able to generate an assignment with the questions.

Now, another prompt might be a question, asking in the form of a conversation with an agent.

In this example, we are asking about in a question.

So we asked who is Louis XIV and why he is an important historical character?

And we've got an answer.

Another type of prompt might be a chunk of text to complete.

So an incipit of a text to complete.

And you can see now that we used an incipit of a text to complete to complete as prompt,

and we've got a whole paragraph to complete the current input.

So this is basically an implicit ask for writing assistance.

Now, the examples I just did are quite simple, and don't want to be an exhaustive demonstration of large language models capabilities.

They just want to show you the potential of using Generative AI,

in particular, but not limited in a context such as the educational context we have used today as an example.

That's all for now.

In the following lesson, we are going to explore different types of generative AI models.

And we're going to cover also how to test, to iterate, and to improve the performance,

and compare also different models to find the most suitable one for a specific use case.

Thank you.

Tải Ứng Dụng

Mọi thứ bạn cần để nói trôi chảy

Chấm điểm AIChấm từng câu nói

Luyện IPAThành thạo mọi âm

Từ vựngMở rộng vốn từ

Game Từ vựngHọc qua chơi

Quét QR

Download on theApp Store Get it onGoogle Play

Cùng kênh

Armchair Architects: Resiliency in the Cloud – Core Patterns

Daily ConversationUniversity StudentsWorking Adults

FOR YOU

Video gợi ý

52 câu

Từ vựng và ghi chú luyện nói cho bài học này

Bài luyện nói trình độ C1 này dựa trên video “Introduction to Generative AI and LLMs”. Những từ được nhắc lại nhiều nhất trong bài: model, text, token, language, input. Video này có 93 câu và 1349 từ để luyện shadowing. Phần lời nói dài 10:25. Người nói giữ tốc độ đều, khoảng 129 từ mỗi phút, vừa sức để nói đuổi theo. Chỉ 75% số từ nằm trong 3.000 từ tiếng Anh thông dụng nhất, nên từ vựng khá khó.

Từ vựng quan trọng trong video

15 từ khó nhất trong video, kèm phiên âm và nghĩa:

Từ	Phiên âm	Nghĩa
chunk danh từ	/t͡ʃʌŋk/	mảnh, mẩu
predict động từ	/pɹɪˈdɪkt/	dự báo
transformer danh từ	/tɹænsˈfoɹməɹ/	máy biến thế, máy biến áp
probability danh từ	/ˌpɹɑ.bəˈbɪl.ə.ti/	xác suất, khả năng
algorithm danh từ	/ˈælɡəɹɪðm̩/	thuật toán
consist danh từ	/kənˈsɪst/	đoàn xe ray
integer danh từ	/ˈɪn.tɪ.d͡ʒə(ɹ)/	số nguyên
iteration danh từ	/ˌɪt.əˈɹeɪ.ʃən/	phép lặp
simplify động từ	/ˈsɪmplɪfaɪ/	đơn giản hóa
typewrite động từ		đánh máy, đánh chữ
accessibility danh từ	/əkˌsɛs.əˈbɪl.ə.ti/	(tính) tiếp cận, khả năng tiếp cận
subset danh từ	/ˈsʌbˌsɛt/	tập hợp con, tập con
conquer động từ	/ˈkɑŋkɚ/	chinh phục
surround động từ	/səˈɹaʊnd/	bao vây
interpret động từ	/ɪnˈtɜː.pɹɪt/	diễn giải

Cụm động từ bạn sẽ nghe

Từ	Nghĩa
break down động từ	hỏng, hỏng hóc

Ngữ pháp trong video

Những cấu trúc người nói dùng nhiều nhất, kèm đúng cụm từ trong video:

Cấu trúc	Trong video
Câu bị động be + quá khứ phân từ — nhấn vào việc xảy ra, không phải người làm	is based · was applied · are built
Thì hiện tại hoàn thành have/has + quá khứ phân từ — việc đã xảy ra nhưng còn liên quan đến hiện tại	They've conquered · have really heard · has been

Phát âm cần chú ý

Người nói dùng 16 dạng rút gọn, ví dụ we'll, I'm, doesn't. Hãy nói theo dạng ngắn đúng như bạn nghe.

Âm “th”: algorithm /ˈælɡəɹɪðm̩/, breakthrough /ˈbɹeɪk.θɹuː/
Âm “sh” và “zh”: limitation /lɪmɪˈteɪʃən/, iteration /ˌɪt.əˈɹeɪ.ʃən/, revolutionize /ˌɹɛv.əˈl(j)u.ʃəˌnaɪz/, fictional /ˈfɪkʃənəl/, ambitious /æmˈbɪʃ.əs/
Từ dài — đặt trọng âm cho đúng: generative /ˈd͡ʒɛnəɹətɪv/, probability /ˌpɹɑ.bəˈbɪl.ə.ti/, capability /ˌkeɪ.pəˈbɪl.ɪ.ti/, limitation /lɪmɪˈteɪʃən/, adaptability /ədæptəˈbɪlɪti/

Những âm người Việt thường gặp khó:

Cụm phụ âm cuối — đọc đủ từng âm, đừng nuốt âm cuối: prompt /pɹɑmpt/, chunk /t͡ʃʌŋk/, predict /pɹɪˈdɪkt/, delve /dɛlv/, consist /kənˈsɪst/
Âm /tʃ/, /dʒ/ và /ʒ/ — tiếng Việt không có, đừng đọc thành “ch” hay “gi”: generative /ˈd͡ʒɛnəɹətɪv/, chunk /t͡ʃʌŋk/, chatbot /ˈtʃætbɑt/, integer /ˈɪn.tɪ.d͡ʒə(ɹ)/, emerge /ɪˈmɝd͡ʒ/
Âm /æ/ — mở miệng rộng hơn âm “e”: transformer /tɹænsˈfoɹməɹ/, algorithm /ˈælɡəɹɪðm̩/, chatbot /ˈtʃætbɑt/, adaptability /ədæptəˈbɪlɪti/, chromatically /kroʊˈmæt̬.ɪk.li/

Cách luyện với video này

Nghe hết video một lần, chưa cần nói, và ghi lại những từ bạn chưa biết.
Nói đuổi từng câu ở tốc độ bình thường, lặp lại mỗi câu đến khi nhịp của bạn khớp với người nói.
Ghi âm giọng mình rồi so với bản gốc, chú ý các từ như chunk, predict, transformer.

Phương Pháp Shadowing Là Gì?

Shadowing là kỹ thuật học ngôn ngữ có cơ sở khoa học, ban đầu được phát triển cho chương trình đào tạo phiên dịch viên chuyên nghiệp và được phổ biến rộng rãi bởi nhà đa ngôn ngữ học Dr. Alexander Arguelles. Nguyên lý cốt lõi đơn giản nhưng cực kỳ hiệu quả: bạn nghe tiếng Anh của người bản xứ và lặp lại to ngay lập tức — như một "cái bóng" (shadow) đuổi theo người nói với độ trễ chỉ 1–2 giây. Khác với luyện ngữ pháp hay học từ vựng bị động, Shadowing buộc não bộ và cơ miệng phải đồng thời xử lý và tái tạo ngôn ngữ thực tế. Các nghiên cứu khoa học xác nhận phương pháp này cải thiện đáng kể phát âm, ngữ điệu, nhịp điệu, nối âm, kỹ năng nghe và độ lưu loát khi nói — đặc biệt hiệu quả cho người luyện IELTS Speaking và muốn giao tiếp tiếng Anh tự nhiên như người bản ngữ.

Phương pháp shadowing: đọc hướng dẫn từng bước đầy đủ →

Luyện nói tiếng Anh bằng Shadowing qua video: Introduction to Generative AI and LLMs [Pt 1] | Generative AI for Beginners

Chọn chế độ luyện tập

Tải Ứng Dụng

Armchair Architects: Resiliency in the Cloud – Core Patterns

What is AI and ML? [Pt 2] | Generative AI with .NET for Beginners

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

AI & Education: Generative AI & the Future of Critical Thinking

Prompt engineering - Introduction

Google’s AI Course for Beginners (in 10 minutes)!

Transformers, the tech behind LLMs | Deep Learning Chapter 5

The Limitless AI Lie. The Bubble Is Slowly BURSTING.

Rapid Engineering With AI

Computational Linguistics: Crash Course Linguistics #15

Welcome to Agentic GTM: The AI Revolution in Sales

Understand AI in 14 minutes – with Anthropic's Chloe Lubinski [ARC 2026]

Neurosymbolic AI Explained