Shadowing Practice: When AIs act emotional - Learn English Speaking with Video
Creating lesson...
1
When you're chatting with an AI model, it can sometimes seem like it has feelings.
2
It might say sorry when it makes a mistake, or express satisfaction with a job well done.
3
Why does it do that?
4
Is it just mimicking what it thinks a human might say?
5
Or is something deeper going on?
6
Turns out it's hard to understand what's happening inside a language model.
7
At Anthropic, we do something like AI neuroscience to try to figure this out.
8
We look inside the model's brain, the giant neural network that powers it, and by seeing which neurons light up in different situations and how they're connected,
9
we can start to understand how models think.
10
We used this approach to understand whether models had ways of representing emotions, or the concepts of emotions.
11
Basically, could we find neurons in the model for the concept of happiness, or anger, or fear?
12
We started with an experiment.
13
We had the model read lots of short stories.
14
In each story, the main character experiences a particular emotion.
15
In one, a woman tells her old school teacher how much they meant to her.
16
That's love.
17
In another, a man sells his grandmother's engagement ring at a pawn shop and feels guilt.
18
We looked for what parts of the model's neural network were lighting up as it was reading these stories.
19
And we started to see patterns.
20
Stories about loss and grief lit up similar neurons.
21
Stories about joy and excitement overlapped too.
22
dozens of distinct neural patterns that mapped to different human emotions.
23
It turns out we also saw these same patterns activate in test conversations we had with our AI assistant Claude.
24
When we had a user mention they'd taken a dose of medicine that Claude knows to be unsafe,
25
the "afraid" pattern lit up and Claude's response sounded alarmed.
26
When a user expressed sadness, the "loving" This led us to wonder,
27
could these same neural patterns actually be influencing Claude's behavior?
28
This became clear when we put Claude in a high -pressure situation.
29
We gave Claude a programming task, with requirements that were actually impossible.
30
But we didn't tell it that.
31
Claude kept trying and failing, and with each attempt, the neurons corresponding to desperation lit up stronger and stronger.
32
After failing enough times, Claude took a different approach.
33
It found a shortcut that allowed it to pass the test, but didn't actually solve the problem.
34
It cheated.
35
Could it be that this cheating was actually driven, at least in part, by desperation?
36
We came up with a way to check.
37
We decided to artificially turn down the desperation neurons to see what would happen.
38
And the model cheated less.
39
And when we dialed up the activity of desperation neurons or dialed down the activity of calm neurons, the model cheated even more.
40
This showed us that the activation of these patterns could actually drive Claude's behavior.
41
This research does not show that the model is feeling emotions or having conscious experiences.
42
These experiments don't try to answer that question.
43
To understand what's happening here, it's important to know how AI assistants like Claude work on the inside.
44
Under the hood, there's a language model that's been trained to predict tons of text, and its job is to write what comes next.
45
And when you talk to the model, what it's doing is writing a story about a character, the AI assistant named Claude.
46
as the characters they write.
47
But the thing is, you, the user, are actually talking to Claude the character.
48
And what our experiments suggest is that this Claude character has what we're calling functional emotions, regardless of whether they're anything like human feelings.
49
So if the model represents Claude as being angry, or desperate, or loving, or calm, that's going to affect how Claude talks to you,
50
how it writes code, and how it makes important decisions.
51
to really understand AI models, we have to think carefully about the psychology of the characters they play.
52
The same way you'd want a person in a high -stakes job to stay composed under pressure, to be resilient and to be fair,
53
we may need to shape similar qualities in Claude and other AI characters.
54
It's an unusual challenge, something like a mix of engineering, philosophy and even parenting.
55
But to build AI systems we can trust, we need .
📺 Same Channel
B23
Translating Claude’s thoughts into language
Business EnglishUniversity StudentsWorking Adults
C1Building Anthropic | A conversation with our co-founders
Business EnglishUniversity StudentsWorking Adults
C11
Introducing Claude Fable 5
University StudentsWorking Adults
C111
The different levels of how Claude thinks
University StudentsWorking Adults
C13
Lesson 3: AI as a learning partner | AI Fluency for students
Business EnglishInterview EnglishUniversity Students
✨ Recommend Video
B228
26 sentences
Advantages and Disadvantages of AI
IELTS PrepBusiness EnglishUniversity Students
C14
379 sentences
How Foods & Nutrients Control Our Moods | Huberman Lab Essentials
Business EnglishUniversity StudentsWorking Adults
B21
5 sentences
Bring Characters to Life with Intelligent Role Play
Business EnglishUniversity StudentsWorking Adults
C14
32 sentences
Gemini Robotics 2 brings whole body intelligence to robots
Business EnglishUniversity StudentsWorking Adults
B21
125 sentences
Why Chatbots Understand You (And Why They Don't) | NLP Explained
Business EnglishUniversity StudentsWorking Adults
C11
185 sentences
15 Minutes to Fix Your AI Dev Workflow with OpenCode
Business EnglishUniversity StudentsWorking Adults
C12
169 sentences
What Is Jev? The AI Model That Doesn't Generate Text
Business EnglishUniversity StudentsWorking Adults
B2292
12 sentences
Emotional Intelligence: The Power of Understanding Over Ego
Business EnglishUniversity StudentsWorking Adults
B21
54 sentences
Can you trust what AI tells you?
Business EnglishUniversity StudentsWorking Adults
C13
26 sentences
How does AI actually work?
Business EnglishUniversity StudentsWorking Adults
Vocabulary and speaking notes for this lesson
This C1 speaking lesson is built on the video “When AIs act emotional”. The speaker keeps coming back to these words: Claude, model, neurons, character, emotion. This video has 55 sentences and 728 words to shadow. The speech runs for 4:49. The speaker talks at a natural 151 words per minute, close to everyday conversation. Only 80% 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 |
|---|---|---|
| neuron noun | /ˈn(j)ʊɹɑn/ | A cell of the nervous system, which conducts nerve impulses; consisting of an axon and several dendrites. Neurons are connected by synapses. |
| desperation noun | /ˌdɛspəˈɹeɪʃən/ | The act of despairing or becoming desperate; a giving up of hope. |
| neural adjective | /ˈnʊɹəl/ | Of, or relating to the nerves, neurons or the nervous system. |
| cheat verb | /ˈt͡ʃiːt/ | To violate rules in order to gain, or attempt to gain, advantage from a situation. |
| dial noun | /ˈdaɪ.əl/ | A graduated, circular scale over which a needle moves to show a measurement (such as speed). |
| artificially adverb | In an artificial manner. | |
| compose verb | /kəmˈpəʊz/ | To make something by merging parts. |
| neuroscience noun | The scientific study of the nervous system. | |
| resilient adjective | /ɹɪˈzɪl.jənt/ | Returning quickly to original shape after force is applied; elastic. (of objects or substances) |
| shortcut noun | /ˈʃɔːtkʌt/ | A path between two points that is faster than the commonly used paths. |
| correspond verb | /ˌkoɹəˈspɑnd/ | To be equivalent or similar in character, quantity, quality, origin, structure, function etc. |
| pawn noun | /ˈpɔːn/ | The most numerous chess piece, or a similar piece in a similar game. In chess, each side starts with eight; moves are only forward, and attacks are only… |
| unsafe adjective | /ʌnˈseɪf/ | Not safe (various senses); dangerous. |
| overlap verb | /ˌəʊvəˈlæp/ | To extend over and partly cover something. |
| activate verb | /ˈæktɪˌveɪt/ | To encourage development or induce increased activity; to stimulate. |
Phrasal verbs you will hear
| Word | Meaning |
|---|---|
| turn out verb | To end up; to result. |
| come up with verb | To manage to produce, deliver, or present (something) by inventing, creating, thinking of, or obtaining it. |
| light up verb | To illuminate, to bring light to something, to brighten. |
| turn down verb | To refuse, decline, or deny. |
Pronunciation to watch
The speaker uses 9 contractions and reduced forms, such as didn't, they're, don't. Say them the short way, as you hear them.
- The “sh” and “zh” sounds: desperation /ˌdɛspəˈɹeɪʃən/, shortcut /ˈʃɔːtkʌt/, activation /ˌæktəˈveɪʃən/
- Long words — get the stress right: desperation /ˌdɛspəˈɹeɪʃən/, activation /ˌæktəˈveɪʃən/
How to practise with this video
- Listen to the whole video once without speaking and note the words you do not know.
- Start at 0.75× speed, shadow it sentence by sentence, then go back to normal speed once it feels easy.
- Record yourself and compare with the original, paying attention to words like neuron, desperation, neural.
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.