Shadowing Practice: Introducing GPT-6 Astra for developers - Learn English Speaking with Video

Creating lesson...
1
GPT-6 Astra is here.
2
It's our latest frontier model and the best model in the world for tasks where raw intelligence matters.
3
For my own projects, Astra feels like working with an experienced collaborator.
4
I'm able to hand it bigger, less well-defined tasks with minimal handholding.
5
And whether you're coding, writing, designing, or just working on things that require a little bit more intellectual horsepower, you'll find that Astra delivers great results,
6
often on the first attempt.
7
So let's talk about the model's new capabilities, starting with computer use.
8
You might already be familiar with computer use.
9
It's a capability that lets a model use a computer or browser like you or I would.
10
With Astra, the model is more accurate and more efficient when using a computer.
11
It's easiest to show this in the ChatGPT app, but Astra's improved skills are also available in the API.
12
I'm going to have it illustrate where where I'm standing.
13
I'll take a photo, then send it to Codex to paint.
14
Use Krita to paint this picture in the style of Van Gogh and add the Golden Gate Bridge in the background.
15
Astra has to keep track of the picture I asked for while working through the app's controls.
16
It's using screenshots to see what's happening while keeping the app in the background, meaning I can stay focused on other work.
17
The model is able to paint a hopefully recognizable picture far faster and far better than I could have done.
18
The same ability can help with the workflows developers use every day, whether you're filling out forms for an API key or performing QA on a mobile app.
19
When it comes to creativity and knowledge work, we've also seen Astra produce significantly better outputs than previous models.
20
We took several prompts of demos, games, and tools we've built with previous models and rebuilt them at different reasoning levels.
21
Across the board, Astra has more attention to detail, better understanding of the user's prompt, and can build more sophisticated outputs.
22
In particular, it excels at building 3D models.
23
I've seen it make incredible renderings of gardens, shipyards, animals, cityscapes, even Dyson spheres.
24
In my own experience, I've found Astra's outputs, from slideshows to essays, significantly easier to read and work with than other models I've tried.
25
Its personality feels more natural to me, especially in the back and forth when I'm giving it feedback.
26
As you might expect, Astra excels at long-running tasks.
27
And as you give models longer, more involved pieces of work, you need better ways to work with them.
28
That's why we're bringing asynchronous tool calling and steering to the Responses API.
29
First, async tools.
30
With asynchronous tool calling, the model can keep working on other parts of a task while a tool call runs.
31
When the results are available, it can use that information to continue.
32
Steering lets you give the model new context or change its direction while a response is still in progress.
33
If you view steering in codecs, this should feel familiar.
34
Let's go ahead and give the model a task and then change what we're asking for while it's working.
35
You can see it pick up my new instruction and adjust its next steps while the tool it already started continues running.
36
I can change the direction without having to cancel the running tool or start the task over.
37
And I get the final result with the new context incorporated.
38
Astra is now available in ChatGPT, Codex, and the API.
39
Try it on your most challenging tasks and take a close look at the results.
40
Happy building.
📺 Same Channel
Introducing GPT-Image-2.5 in the APIB2
4

Introducing GPT-Image-2.5 in the API

Business EnglishUniversity StudentsWorking Adults
Introducing the Agents APIC1
12

Introducing the Agents API

Business EnglishUniversity StudentsWorking Adults
Introducing GPT-6 Astra: the most intelligent and aligned model in the world.B2
1

Introducing GPT-6 Astra: the most intelligent and aligned model in the world.

Business EnglishUniversity StudentsWorking Adults
Introducing dots, always-on agents built to handle everything.B1
4

Introducing dots, always-on agents built to handle everything.

Business EnglishWorking Adults
Reimagining IT with ChatGPTC1
2

Reimagining IT with ChatGPT

Business EnglishUniversity StudentsWorking Adults
Using Voice in ChatGPT WorkB2

Using Voice in ChatGPT Work

Business EnglishWorking Adults
✨ Recommend Video
I built the same game with Astra and Fable 5.1... only one was funC1
5
76 sentences

I built the same game with Astra and Fable 5.1... only one was fun

American AccentBusiness EnglishUniversity StudentsWorking Adults
How to Use Google Gemini Al (Full Tutorial)C1
1
227 sentences

How to Use Google Gemini Al (Full Tutorial)

Business EnglishUniversity StudentsWorking Adults
We Let $200 GPT-Pro Think for 7 Days on Unsolved MathC1
2
182 sentences

We Let $200 GPT-Pro Think for 7 Days on Unsolved Math

Business EnglishUniversity StudentsWorking Adults
Amazon Athena explained in 120 seconds💡C1
15
29 sentences

Amazon Athena explained in 120 seconds💡

Business EnglishUniversity StudentsWorking Adults
Gemma 4 Just Released - Whats In? In 2026!C1
1
28 sentences

Gemma 4 Just Released - Whats In? In 2026!

Business EnglishUniversity StudentsWorking Adults
Unreal Engine 5.8 - Experimental MCP Server Support Walkthrough | State of Unreal 2026C1
1
197 sentences

Unreal Engine 5.8 - Experimental MCP Server Support Walkthrough | State of Unreal 2026

Business EnglishUniversity StudentsWorking Adults
Rapid Engineering With AIC1
1
12 sentences

Rapid Engineering With AI

Business EnglishUniversity StudentsWorking Adults
What Is Jev? The AI Model That Doesn't Generate TextC1
2
169 sentences

What Is Jev? The AI Model That Doesn't Generate Text

Business EnglishUniversity StudentsWorking Adults
Gemini Robotics 2 brings whole body intelligence to robotsC1
4
32 sentences

Gemini Robotics 2 brings whole body intelligence to robots

Business EnglishUniversity StudentsWorking Adults
Most devs don't understand how LLM tokens workC1
2
145 sentences

Most devs don't understand how LLM tokens work

British AccentBusiness EnglishUniversity StudentsWorking Adults

Real-World Context: Discussing Cutting-Edge AI Tools

The video features a conversation about GPT-6 Astra, a new AI model, and its applications for developers. This scenario reflects how professionals discuss technical innovations—using clear, confident language to explain features, benefits, and practical use cases. Whether you’re talking about tech, work, or creative projects, this dialogue models how to describe capabilities, share personal experiences, and encourage action. It’s a great example of functional English for real-world communication.

Useful Chunks & Collocations to Master

  • "raw intelligence matters": Highlights when deep understanding or problem-solving is key. Example: "In research, raw intelligence matters more than speed."
  • "minimal handholding": Describes tasks that need little guidance. Example: "This tool works with minimal handholding, so even new users can succeed."
  • "attention to detail": Emphasizes carefulness. Example: "Her attention to detail makes her reports stand out."
  • "long-running tasks": Refers to projects that take time. Example: "AI excels at long-running tasks like data analysis."
  • "incorporated new context": Means adding fresh information. Example: "The team incorporated new context into the plan."

Your Shadowing Challenge: Practice Like a Pro

Shadowing is one of the best ways to improve English pronunciation and fluency. Here’s your task: Watch the video segment where the speaker says, "Astra feels like working with an experienced collaborator. I'm able to hand it bigger, less well-defined tasks with minimal handholding." Pause, then repeat the sentence immediately—matching the speed, tone, and stress. Focus on the natural rhythm: "experienced collaborator" and "minimal handholding." Do this 5 times. Then, record yourself and compare. This "shadow speak" technique trains your mouth to move like a native and builds muscle memory for natural speech. For extra practice, try shadowing the entire section about computer use—you’ll master phrases like "accurate and efficient" while boosting your confidence in technical conversations. Remember: consistent shadow speech practice leads to noticeable progress.

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 →