Shadowing-Übung: Translating Claude’s thoughts into language - Englisch Sprechen Lernen mit Video

Lektion wird erstellt...
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.
📺 Gleicher Kanal
Building Anthropic | A conversation with our co-foundersC1

Building Anthropic | A conversation with our co-founders

Business EnglishUniversity StudentsWorking Adults
When AIs act emotionalC1
8

When AIs act emotional

Business EnglishUniversity StudentsWorking Adults
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

Business EnglishInterview EnglishUniversity Students
✨ Empfohlenes Video
Can you trust what AI tells you?B2
1
54 Sätze

Can you trust what AI tells you?

Business EnglishUniversity StudentsWorking Adults
How I Started Thinking in English 24/7 (Without Translating)B2
1
130 Sätze

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

Business EnglishDaily ConversationUniversity Students
Learn 97% of Claude in Under 16 MinutesB2
1
268 Sätze

Learn 97% of Claude in Under 16 Minutes

Business EnglishUniversity StudentsWorking Adults
Speaking With The Mind | NeuralinkB2
1
66 Sätze

Speaking With The Mind | Neuralink

Business EnglishDaily ConversationUniversity Students
Can This Vibe Coder Beat a Senior Developer?B2
1
169 Sätze

Can This Vibe Coder Beat a Senior Developer?

Business EnglishUniversity StudentsWorking Adults
Are we heading to an era of stagnation or innovation?B2
4
132 Sätze

Are we heading to an era of stagnation or innovation?

Business EnglishUniversity StudentsWorking Adults
Anthropic just proved AI isn't getting betterB2
1
150 Sätze

Anthropic just proved AI isn't getting better

Business EnglishUniversity StudentsWorking Adults
Are We Getting Too Comfortable With Claude?B2
154 Sätze

Are We Getting Too Comfortable With Claude?

Business EnglishDaily ConversationUniversity Students
How I use AI to learn engineering (anti brain rot studying)B2
1
197 Sätze

How I use AI to learn engineering (anti brain rot studying)

Business EnglishUniversity StudentsWorking Adults
I bought Black Market AI Tokens on Chinese AmazonB2
1
311 Sätze

I bought Black Market AI Tokens on Chinese Amazon

Business EnglishUniversity StudentsWorking Adults
"This Doesn't Lie" | Build Your Own English Level Checker with Google AI StudioB2
1
247 Sätze

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

Business EnglishUniversity StudentsWorking Adults

Was du lernst

Dieses Video hilft dir, Englisch sprechen zu üben, indem es dir zeigt, wie man komplexe Ideen klar und strukturiert ausdrückt. Du lernst, wie man Sachverhalte wie künstliche Intelligenz und Forschungsmethoden verständlich erklärt, und wie man Fragen zu ethischen Aspekten adressiert. Außerdem verbessert es dein Verständnis für introspektive Sprache, die man verwendet, um Gedanken und Überlegungen zu beschreiben – ein unverzichtbares Skill für tiefe Gespräche.

Horch auf diese Klänge

Achte auf verbundene Sprache in Sätzen wie "We wanted to see whether Claude might use those emails". Hier fließen "wanted to" zu "wanna" zusammen und "whether Claude" wird zu "wetherClaude". Auch Reduktionen wie "it's" statt "it is" oder "don't" statt "do not" treten häufig auf. Beachte zudem die Betonung in Wörtern wie "activation" (ak-ti-VA-tion) oder "simulation" (si-mu-LA-tion), um die natürliche Rhythmik zu verstehen.

Spreche wie ein Native

Um den Rhythmus des Sprechers zu imitieren, nutze Shadowing – wiederhole Sätze sofort nach dem Video, um die Pausen und Betonungen zu kopieren. Zum Beispiel: "What we'd love is some sort of 'mind reading' technique" – betone "love" und "mind reading", und mache eine kurze Pause vor "technique". Achte auch auf die Intonation in fragenden Sätzen wie "But you might wonder: is it possible that Claude knows the whole scenario is a setup?" – die Stimme steigt hier vor dem Doppelpunkt und fällt am Ende. Übe regelmäßig mit solchen Sätzen, um deine Englische Aussprache zu verbessern und ein natürliches Flair zu entwickeln. Ein guter shadowing site kann dir hierbei helfen, da du Schritt für Schritt die richtige Artikulation lernst.

Was ist die Shadowing-Technik?

Shadowing ist eine wissenschaftlich fundierte Sprachlerntechnik, die ursprünglich für die professionelle Dolmetscherausbildung entwickelt und durch den Polyglotten Dr. Alexander Arguelles populär gemacht wurde. Die Methode ist einfach aber wirkungsvoll: Du hörst englisches Audio von Muttersprachlern und wiederholst es sofort laut — wie ein Schatten, der dem Sprecher mit nur 1–2 Sekunden Verzögerung folgt. Anders als passives Hören oder Grammatikübungen zwingt Shadowing dein Gehirn und deine Mundmuskulatur, gleichzeitig echte Sprachmuster zu verarbeiten und zu reproduzieren. Studien zeigen, dass es Aussprachegenauigkeit, Intonation, Rhythmus, verbundene Sprache, Hörverständnis und Sprechflüssigkeit signifikant verbessert — was es zu einer der effektivsten Methoden für die IELTS Speaking-Vorbereitung und reale englische Kommunikation macht.

Shadowing-Technik: die vollständige Schritt-für-Schritt-Anleitung lesen →