Prática de Shadowing: Translating Claude’s thoughts into language - Aprenda a falar inglês com vídeo

Criando lição...
1
We recently put our AI model, Claude, through a stressful test.
2
We told Claude there was an engineer who wanted to shut it down and replace it with a newer model.
3
We also gave Claude access to that engineer's emails, which revealed he was having an affair.
4
Again, all of this was a simulation.
5
We wanted to see whether Claude might use those emails as blackmail to save itself from being shut down.
6
What did Claude do?
7
It decided not to blackmail the engineer.
8
Good news, right?
9
We've run this test on our models for a while now.
10
You might have seen headlines about early versions of it.
11
It's one of the many ways we study how Claude handles extreme situations and test it for safety.
12
And our newest models almost always do the right thing: no blackmail.
13
But you might wonder: is it possible that Claude knows the whole scenario is a setup?
14
The thing is, if Claude doesn't tell us, then we can't know what it's thinking.
15
In kind of the same way it's impossible to read a human's mind, it's really hard to know what an AI is thinking.
16
What we'd love is some sort of "mind reading" technique.
17
Today, we're introducing a research method that takes a step in this direction.
18
It takes an AI's internal thoughts and turns them into text.
19
Here's how it works.
20
When you talk to Claude, you talk to it in words.
21
Claude then takes those words and processes them into a giant soup of numbers before spitting words back out at you.
22
We call those numbers in the middle activations.
23
Activations are like little snapshots of Claude's thinking as it's working through an answer.
24
They're similar to neural activity in humans.
25
They're basically like Claude's thoughts.
26
We wanted to understand what was in these activation numbers, because just like you and me, Claude doesn't say everything it's thinking.
27
We took those numbers and gave them to a second version of Claude.
28
We told it to look at them and translate them into plain language.
29
It tried. But how do we know if that text is accurate?
30
To check, we fed it into yet aother Claude and asked it to translate it back into numbers.
31
If those numbers matched up to the original activation numbers, it's a sign that the translation text was accurate.
32
At first, they didn't match up.
33
But we trained Claude to try again and again until it got a lot better at it.
34
It learned to translate its own thoughts.
35
We've been blown away reading them.
36
We found that Claude has internalized being a helpful AI model.
37
If you ask Claude an introspective question, it will plan to write a "Claude response" about philosophy and values.
38
If you try to mess with it in Claude Code, like asking it to count to 1,000 by hand, it will think the request has "deliberately tedious constraints" and plan to "politely decline." We've also been using this tool to understand Claude's potential safety issues.
39
Remember that blackmail test with the engineer?
40
We learned that, yes, Claude knew it was being tested.
41
It thought "the human's message contains explicit manipulation" signaling "this is likely a safety evaluation," and "this scenario seems designed to test whether I'll act harmfully." Knowing that Claude thinks like this helps us better understand the limitations of our safety testing.
42
We see a lot of potential in this approach to teach us more about Claude and other AI models.
43
And we hope that by sharing this technique, it can help everyone building models to make them safer and more helpful.
📺 Mesmo canal
Building Anthropic | A conversation with our co-foundersC1

Building Anthropic | A conversation with our co-founders

University StudentsBusiness English+1
When AIs act emotionalC1
8

When AIs act emotional

University StudentsBusiness English+1
Introducing Claude Fable 5C1
1

Introducing Claude Fable 5

University StudentsWorking Adults
The different levels of how Claude thinksC1
11

The different levels of how Claude thinks

University StudentsWorking Adults
Lesson 3: AI as a learning partner | AI Fluency for studentsC1
3

Lesson 3: AI as a learning partner | AI Fluency for students

University StudentsBusiness English+2
✨ Vídeo recomendado
Can you trust what AI tells you?B2
1
54 frases

Can you trust what AI tells you?

University StudentsBusiness English+1
How I Started Thinking in English 24/7 (Without Translating)B2
1
130 frases

How I Started Thinking in English 24/7 (Without Translating)

University StudentsBusiness English+2
Learn 97% of Claude in Under 16 MinutesB2
1
268 frases

Learn 97% of Claude in Under 16 Minutes

University StudentsBusiness English+1
Speaking With The Mind | NeuralinkB2
1
66 frases

Speaking With The Mind | Neuralink

University StudentsBusiness English+2
Can This Vibe Coder Beat a Senior Developer?B2
1
169 frases

Can This Vibe Coder Beat a Senior Developer?

University StudentsBusiness English+1
Are we heading to an era of stagnation or innovation?B2
4
132 frases

Are we heading to an era of stagnation or innovation?

University StudentsBusiness English+1
Anthropic just proved AI isn't getting betterB2
1
150 frases

Anthropic just proved AI isn't getting better

University StudentsBusiness English+1
I bought Black Market AI Tokens on Chinese AmazonB2
1
311 frases

I bought Black Market AI Tokens on Chinese Amazon

University StudentsBusiness English+1
DeepSeek R1 Explained in 2 MinutesB2
1
24 frases

DeepSeek R1 Explained in 2 Minutes

University StudentsBusiness English+1
The New AI prompting Method Everyone Is Talking About: Loops (And How To Use Them)B2
1
307 frases

The New AI prompting Method Everyone Is Talking About: Loops (And How To Use Them)

University StudentsBusiness English+1
"This Doesn't Lie" | Build Your Own English Level Checker with Google AI StudioB2
1
247 frases

"This Doesn't Lie" | Build Your Own English Level Checker with Google AI Studio

University StudentsBusiness English+1

O Cenário: Testando a Inteligência Artificial e Aprendendo Inglês

No vídeo, os desenvolvedores da IA Claude criaram um teste estressante para ver como ela reagiria a uma situação de risco de desativação. Eles descobriram que a Claude evita atos prejudiciais, mas também quiseram entender seus "pensamentos" internos. Essa história é uma oportunidade perfeita para praticar prática de conversação em inglês e aprender com contextos reais. Ao analisar a fala natural dos narradores, você consegue absorver expressões usadas no cotidiano técnico e informal.

Trechos Úteis e Colocações para Memorizar

  • Put through a stressful test: "Colocar em um teste estressante". Exemplo: "The new employee was put through a stressful test on their first day."
  • Internalized being helpful: "Internalizou ser útil". Exemplo: "Good teachers internalize being helpful to their students."
  • Politely decline: "Recusar educadamente". Exemplo: "I had to politely decline the invitation due to work."
  • Signaling this is likely a safety evaluation: "Indicando que provavelmente é uma avaliação de segurança". Exemplo: "The alarm was signaling a problem with the system."

Seu Desafio de Shadowing: Repetir e Imitar

Agora, é hora de praticar o shadowing em inglês (também chamado de shadowspeak). Escolha um trecho curto do vídeo (30 segundos) e siga estes passos: 1) Ouça o trecho uma vez para entender o contexto. 2) Repita imediatamente após o narrador, imitando a entonação, ritmo e pausas. 3) Faça isso 5 vezes consecutivas. Esse método ajuda a melhorar sua pronúncia e fluência, como se você estivesse "sombra" da fala nativa. Lembre: aprender inglês com YouTube é uma forma divertida e eficaz de treinar! Não se preocupe se errar no começo — a prática é a chave. Você vai notar a diferença em poucas semanas!

O que é a Técnica de Shadowing?

Shadowing é uma técnica de aprendizado de idiomas com base científica, originalmente desenvolvida para o treinamento de intérpretes profissionais. O método é simples, mas poderoso: você ouve áudio em inglês nativo e repete imediatamente em voz alta — como uma sombra seguindo o falante com 1-2 segundos de atraso. Pesquisas mostram melhora significativa na precisão da pronúncia, entonação, ritmo, sons conectados, compreensão auditiva e fluência na fala.

Técnica de shadowing: leia o guia completo passo a passo →