Shadowing Practice: Introduction to Generative AI and LLMs [Pt 1] | Generative AI for Beginners - Learn English Speaking with Video

Choose a practice mode

Each mode opens a full-screen practice room.

93 sentences

If sentences are too short or too long, click Edit to adjust them.

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.

Download App

Everything you need to speak fluently

AI PronunciationScore every sentence

IPA PracticeMaster every sound

VocabularyBuild your word bank

Vocab GameLearn while playing

Scan QR

Download on theApp Store Get it onGoogle Play

Same Channel

Armchair Architects: Resiliency in the Cloud – Core Patterns

Daily ConversationUniversity StudentsWorking Adults

FOR YOU

Recommend Video

52 sentences

Vocabulary and speaking notes for this lesson

This C1 speaking lesson is built on the video “Introduction to Generative AI and LLMs”. The speaker keeps coming back to these words: model, text, token, language, input. This video has 93 sentences and 1349 words to shadow. The speech runs for 10:25. The speaker talks at a steady 129 words per minute, a comfortable pace for shadowing. Only 75% of the words are among the 3,000 most common in English, so the vocabulary is demanding.

Key vocabulary in this video

The 15 most advanced words in the video, with pronunciation and meaning:

Word	Pronunciation	Meaning
token noun	/ˈtoʊkən/	Something serving as an expression of something else.
generative adjective	/ˈd͡ʒɛnəɹətɪv/	Having the power of generating, propagating, originating, or producing.
prompt verb	/pɹɑmpt/	To lead (someone) toward what they should say or do.
chunk noun	/t͡ʃʌŋk/	A part of something that has been separated; a generally squat, thick, irregular piece of something, e.g. wood or stone.
startup noun	/ˈstɑɹtˌʌp/	The act or process of starting a process or machine.
predict verb	/pɹɪˈdɪkt/	To make a prediction: to forecast, foretell, or estimate a future event on the basis of knowledge and reasoning; to prophesy a future event on the basis of…
transformer noun	/tɹænsˈfoɹməɹ/	Something that transforms, changing its own or another thing's shape.
probability noun	/ˌpɹɑ.bəˈbɪl.ə.ti/	The state of being probable.
algorithm noun	/ˈælɡəɹɪðm̩/	A collection of ordered steps that solve a mathematical problem. A precise step-by-step plan for a computational procedure that possibly begins with an input…
capability noun	/ˌkeɪ.pəˈbɪl.ɪ.ti/	The power or ability to generate an outcome.
chatbot noun	/ˈtʃætbɑt/	A computer program that holds conversations through a chat room.
delve verb	/dɛlv/	To dig into the ground, especially with a shovel.
incipit noun	/ˈɪnsɪpɪt/	The first few words of a text, especially its first line.
textual adjective	/ˈtɛks.tju.əl/	Of or pertaining to textuality.
tokenization noun		The act or process of tokenizing.

Phrasal verbs you will hear

Word	Meaning
break down verb	To stop functioning.

Grammar in this video

The structures the speaker uses most, with the exact words from the video:

Structure	In the video
Passive voice be + past participle — the focus is on what happens, not who does it	is based · was applied · are built
Present perfect have/has + past participle — a past action that still matters now	They've conquered · have really heard · has been

Pronunciation to watch

The speaker uses 16 contractions and reduced forms, such as we'll, I'm, doesn't. Say them the short way, as you hear them.

The “th” sounds: algorithm /ˈælɡəɹɪðm̩/, breakthrough /ˈbɹeɪk.θɹuː/
The “sh” and “zh” sounds: limitation /lɪmɪˈteɪʃən/, iteration /ˌɪt.əˈɹeɪ.ʃən/, revolutionize /ˌɹɛv.əˈl(j)u.ʃəˌnaɪz/, fictional /ˈfɪkʃənəl/, ambitious /æmˈbɪʃ.əs/
Long words — get the stress right: generative /ˈd͡ʒɛnəɹətɪv/, probability /ˌpɹɑ.bəˈbɪl.ə.ti/, capability /ˌkeɪ.pəˈbɪl.ɪ.ti/, limitation /lɪmɪˈteɪʃən/, adaptability /ədæptəˈbɪlɪti/

How to practise with this video

Listen to the whole video once without speaking and note the words you do not know.
Shadow it sentence by sentence at normal speed, repeating each one until your rhythm matches the speaker.
Record yourself and compare with the original, paying attention to words like token, generative, prompt.

What is the Shadowing Technique?

Shadowing is a science-backed language learning technique originally developed for professional interpreter training and popularized by polyglot Dr. Alexander Arguelles. The method is simple but powerful: you listen to native English audio and immediately repeat it out loud — like a shadow following the speaker with just a 1–2 second delay. Unlike passive listening or grammar drills, shadowing forces your brain and mouth muscles to simultaneously process and reproduce real speech patterns. Research shows it significantly improves pronunciation accuracy, intonation, rhythm, connected speech, listening comprehension, and speaking fluency — making it one of the most effective methods for IELTS Speaking preparation and real-world English communication.

Shadowing technique: read the full step-by-step guide →

Shadowing Practice: Introduction to Generative AI and LLMs [Pt 1] | Generative AI for Beginners - Learn English Speaking with Video

Choose a practice mode

Download App

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

World Models explained in 10min..

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.

The Multi-Agent Architecture That Actually Ships — Luke Alvoeiro, Factory

Rapid Engineering With AI

Computational Linguistics: Crash Course Linguistics #15

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