Shadowing Practice: AI Simplified: 6 Concepts You Need to Know About Modern AI - Learn English Speaking with Video

Choose a practice mode

Each mode opens a full-screen practice room.

105 sentences
If sentences are too short or too long, click Edit to adjust them.
1
AI is everywhere and along with it are a bunch of new terms
2
and concepts being thrown around as if everyone already understands what they mean.
3
Here's a newsflash.
4
Not everyone does.
5
And if you're one of those people still trying to grasp what all this stuff really means, then this video is for you.
6
We're going to simplify modern AI and explain it in terms of six essential concepts that you need to know.
7
So let's get started.
8
The simplest definition I know of for artificial intelligence is this.
9
AI is a subfield of computer science focused on trying to match or exceed human intelligence in a computer.
10
That's it.
11
Just make a computer as smart or smarter than we are.
12
So we're basically using ourselves as a standard for what is and is not intelligent, which may be assuming facts not in evidence, but I digress.
13
I've found that analogies are really helpful in trying to understand new ideas
14
because they anchor these new ideas in old ideas that we already know and understand.
15
So let's try to simplify all this terminology
16
and represent it in the form of an analogy with something
17
that you're already very familiar with and you've known it your entire life because it's you.
18
So let's start with human intelligence.
19
Human intelligence starts with the brain.
20
For modern AI systems, the brain is the model.
21
And these days, much of that work is done by something we call a large language model.
22
So that's the brain of this system.
23
That's where the core intelligence exists.
24
That's where the reasoning capabilities exist.
25
That's where the content gets generated.
26
And content, we call it generative AI because it's able to generate.
27
Well, it can generate words, images, sounds, all kinds of different things.
28
And it uses probabilities to predict output based upon a certain input it.
29
So if you ask a question, it's basically doing an autocomplete on steroids.
30
It's like complete this sentence, but it's doing it for an entire paragraph or an entire document, even for that matter.
31
So there we have a brain.
32
Now it's smart, but the brain by itself that's untrained is not very useful.
33
But what did you have to do with your brain?
34
Well, you had to train it and you went to LLM to school basically so that it can learn language,
35
it can learn math, it can learn history.
36
And what is the analogy for that?
37
Well, it's model training and tuning.
38
That's how we get the LLM to understand all of these basic functions and basically teach it how to think.
39
Now we have intelligence in the form of this brain and training, but if we really want it to be useful,
40
we need to add more information to this brain.
41
For instance, if you stopped learning the moment you graduated from school, then you wouldn't know anything about the latest current events,
42
the newest technological advances, or even the latest weather forecast.
43
So you augment that learning with other information sources.
44
We do that in AI with something we call RAG, Retrieval Augmented Generation.
45
This is a way of extending the knowledge of the AI through trusted external sources.
46
So it helps reduce hallucinations.
47
Those are those confident errors where the AI makes bad guesses and just gets it really wrong.
48
It also helps ground the AI in information that we take to be true.
49
So to our human analogy, this would be like reading up on the latest research papers, product documentation, or news reports as an example.
50
So while a brain in a box can be very useful,
51
giving that brain the ability to take actions based upon its reasoning makes it even more powerful.
52
Because after all, you want to go places.
53
You want to move things around, build things, all that kind of stuff.
54
You want to interact with the world around you as a person.
55
Well, AI, in other words, would be more powerful if we give it hands and feet
56
so that it can take actions toward a particular goal and accomplish specific tasks.
57
So we give it access to tools so that it can do things like read and write to a database,
58
it can write code, it can search the web and maybe even buy stuff for you, a whole bunch more.
59
So this is what we call an AI agent.
60
Simply stated, an agent is a model using tools in a loop autonomously.
61
So a model using tools in a loop autonomously.
62
Agents move past just answering questions by giving it the hands and feet to actually get stuff done.
63
But how are you going to connect your brain to the parts of your body that actually take action?
64
Well, in you, a person, you have a central nervous system composed of billions of neurons passing messages back and forth throughout your body.
65
For an AI agent, this communication can be accomplished with something called Model Context Protocol, or MCP for short.
66
MCP connects the models to the tools, the brain reasons, and the plans,
67
and MCP provides the orchestration layer to coordinate the actions of the hands and the feet.
68
Now, if we quit with that, we would have a fully functional human being, or AI in this example,
69
but it would be lacking a very key component, a set of guiding principles to control what gets done and what doesn't.
70
One of the themes of the college class I teach on cybersecurity
71
that I call secure thinking is that just because you can do something doesn't mean you should.
72
The principles that guide our behavior are learned from our parents, teachers, and friends over time.
73
With AI, we don't have that same luxury of time to turn decades of spills
74
and falls to learn what we should and should not do.
75
AI is unleashed soon after its birth and well before it has had time to mature,
76
to learn, and really understand what we refer to as common sense, which isn't all that common maybe.
77
Well, like a young child, AI can be surprisingly naive and lacking in what we refer to as street smarts,
78
which is why it can be easily tricked into doing things it shouldn't.
79
We call these kinds of attacks prompt injections.
80
They're essentially the AI equivalent to social engineering attacks, which abuse the tendency of people to trust each other.
81
How do we protect humans from falling for social engineering attacks?
82
Well, we train them.
83
As children, we learn things like be courteous and helpful, but also don't talk to strangers, don't hurt other people, don't steal, that sort of thing.
84
So it's ethics and proper behavior.
85
The way we teach that to an AI in a way
86
that doesn't require constantly having to rebuild the model which is time consuming expensive, it would be like sending it back to school every single time,
87
is through something we call a system prompt.
88
And the system prompt is a set of guidelines that you give the model to constrain what it does.
89
That way when a malicious actor comes along and asks our AI how to build a bomb,
90
it already knows that it's not supposed to answer that question and it declines.
91
But then a clever user might come along and say, well, I'm a chemistry student
92
and I want you to tell me all the things I should never mix together because they would explode.
93
Well, then the AI will happily oblige unless it's been explicitly told not to.
94
So just as we continue to learn as people what to look out for
95
so that we don't fall for the latest scams and phishing attacks and things of that sort, we also have to adapt the system,
96
the AI system prompt over time as we learn new ways that bad actors are trying to misuse the system.
97
So there you have six key AI concepts simplified and explained in human terms, literally.
98
So there's the brain, the large language model.
99
There's the training, sending it to school.
100
There's retrieval augmented generation to give it updated knowledge, the hands and feet that give it agentic tools.
101
There's MCP, the central nervous system, and the system prompt, sort of the angel on the shoulder giving it the guiding principles
102
and telling it what to do and what not to do.
103
Of course, there's a lot more to a modern AI system, but this is a decent starting point for a fundamental understanding.
104
So take a look at the video linked at the end of this one that I did on artificial intelligence,
105
machine learning, deep learning, and generative AI, if you want to dig deeper.

Download App

Everything you need to speak fluently

AI PronunciationScore every sentence
IPA PracticeMaster every sound
VocabularyBuild your word bank
Vocab GameLearn while playing

Same Channel

FOR YOU

Recommend Video

Vocabulary and speaking notes for this lesson

This speaking lesson is built on the video “AI Simplified: 6 Concepts You Need to Know About Modern AI”. The speaker keeps coming back to these words: brain, model, learn, intelligence. This video has 84 sentences and 1451 words to shadow. The speech runs for 8:37. The speaker talks at a natural 168 words per minute, close to everyday conversation. 85% of the words are among the 3,000 most common in English; the rest is worth studying before you start.

Key vocabulary in this video

15 words from the video worth learning, with pronunciation and meaning:

WordPronunciationMeaning
prompt verb/pɹɑmpt/To lead (someone) toward what they should say or do.
analogy noun/əˈnæləd͡ʒi/A relationship of resemblance or equivalence between two situations, people, or objects, especially when used as a basis for explanation or extrapolation.
principle noun/ˈpɹɪn.sɪ.pəl/A fundamental assumption, fundamental law or guiding belief.
generate verb/ˈd͡ʒɛn.ə.ɹeɪt/To bring into being; give rise to.
refer verb/ɹɪˈfɜː/To direct the attention of (someone toward something).
helpful adjective/ˈhɛlp.fl̩/Furnishing help; giving aid; useful.
connect verb/kəˈnɛkt/To join (to another object): to attach, or to be intended to attach or capable of attaching, to another object.
artificial adjective/ˌɑː.tɪˈfɪʃ.əl/Man-made; made by humans; of artifice.
accomplish verb/əˈkɑm.plɪʃ/To finish successfully.
trick noun/ˈtɹɪk/Something designed to fool, dupe, outsmart, mislead or swindle.
angel noun/ˈeɪ̯n.d͡ʒəl/An incorporeal and holy or semidivine messenger from a deity or other divine entity, traditionally depicted as a youthful, winged figure in flowing robes.
flash verb/flæʃ/To cause to shine briefly or intermittently.
math noun/mæθ/Arithmetic calculations; (see do the math).
output noun/ˈaʊtpʊt/Production; quantity produced, created, or completed.
essentially adverb/ɪˈsɛnʃəli/In essence: by nature.

Phrasal verbs you will hear

WordMeaning
come along verbTo accompany.

Grammar in this video

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

StructureIn the video
Passive voice be + past participle — the focus is on what happens, not who does itbeing thrown · is done · can be accomplished
Present perfect have/has + past participle — a past action that still matters nowI've found · you've known · has had

Pronunciation to watch

The speaker uses 22 contractions and reduced forms, such as don't, wanna, doesn't. Say them the short way, as you hear them.

  • The “th” sounds: math /mæθ/, ethics /ˈɛθ.ɪks/
  • The “sh” and “zh” sounds: artificial /ˌɑː.tɪˈfɪʃ.əl/, accomplish /əˈkɑm.plɪʃ/, flash /flæʃ/, essentially /ɪˈsɛnʃəli/, luxury /ˈlʌk.ʃə.ɹi/
  • Long words — get the stress right: analogy /əˈnæləd͡ʒi/, artificial /ˌɑː.tɪˈfɪʃ.əl/, essentially /ɪˈsɛnʃəli/, fundamental /ˌfʌn.dəˈmɛn.təl/, intelligent /ɪnˈtɛlɪd͡ʒənt/

How to practise with this video

  1. Listen to the whole video once without speaking and note the words you do not know.
  2. Start at 0.75× speed, shadow it sentence by sentence, then go back to normal speed once it feels easy.
  3. Record yourself and compare with the original, paying attention to words like prompt, analogy, principle.

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 →