Luyện nói tiếng Anh bằng Shadowing qua video: How To Learn To Code In 2026

Learning to code is so different in 2026.

So in this video, I shall explain to you how to learn to code in 2026.

Starting off with what coding actually looks like today.

It looks very different.

Then I'll explain what you should be learning that is still relevant right now and for the future.

And finally, some tips on how to supercharge your learning.

Oh, by the way, just in case you have any doubt about whether you should still learn how to code in 2026, the answer is yes.

There are still so many opportunities that are only available to people who know how to code.

Plus, learning to code in 2026 faster than it used to be.

So it's kind of a no brainer if you want to build stuff.

Now with that out of the way, in case you don't know me, hi, my name is Tina.

I used to be a data scientist at Meta and I have been coding for 10 years.

Without further ado, let's go.

A portion of this video is sponsored by Warped.

On February 3rd, 2025, Andre Kaparthi, the previous director of AI at Tesla and the founding member of OpenAI, made a viral tweet defining a new term called vibe coding.

He explains, There's a new kind of coding I call vibe coding, where you fully give in to the vibes, embrace exponentials, and I forget that the code even exists.

It's not too bad for throwaway weekend projects, but still quite amusing.

Then, almost exactly a year later, on February 5th, 2026, he made another post.

except with more oversight and scrutiny.

Now to differentiate this much more sophisticated, integral workflow from Vibe Coding, he said his current favorite term for it is agentic engineering.

You have your terminal slash IDE open, where you have multiple coding agents coding furiously away for you.

And you're like, build this, fix this.

No, don't do that.

Do this instead.

Orchestrating your AI agents like a puppet master.

But do not be fooled.

It may look like you're just speaking

engineer to even do that you need to know how to structure what it is

that you want to build in a way

that the ai agents can understand be able to provide context

and documentation and in order to correct the ai and tell it

that it's wrong you need to actually know what is right

to be a good manager you need to know what it is

that you're managing so that is why

if you want to learn how to code in 2026 you still need to know the fundamentals of coding

and engineering but instead of focusing so much on the details of the code implementation itself it's about

and particular emphasis on security and privacy, because these are the things that AI coding agents tend to struggle the most with.

Then you can actually move on to take advantage of the AI coding tools

that we have available today and really do agentic engineering.

So, should I tell you what it is that you need to learn?

All right, I'm gonna list out the topics in a roughly chronological order that I think you should be learning, assuming you don't know anything, and also suggest some resources on these topics.

Okay, so first thing that you want to learn is the basics of coding itself.

Stuff like variables, types, if statements, loops, object -oriented programming, and APIs.

Also, I'm using Python as the demo language to learn, which is particularly good if you want to be building AI agents and doing data stuff.

But if you want to be doing something more like web stuff, like developing web apps, you might want to start off with a language like JavaScript.

It's okay though, because I'm going to give you guys a prompt at the end of this section

that you can use to So these are the basic basics.

Like you really need to know these.

Otherwise you wouldn't even be able to read the code that the AI generates.

That sign can't stop me because I can't read.

And I'm going to put on screen now some of my favorite resources on this topic.

I personally still recommend going with these human -made resources because we know that they're really good.

They've been vetted by thousands of engineers.

Besides, all AI -generated code is based upon code that was written by human developers for decades.

Next up, you need to learn about software architecture.

How do you choose a tech stack?

The system design?

What kind of APIs should you be using?

And how the data flows through your software and where is it being stored?

What kind of databases are you using?

And testing, testing is so important, especially if you're using AI coding agents.

You need to understand how to write test cases and how to test different parts of your software.

And finally, how does deployment work?

Where are you going to be hosting your software?

This is like the bread and butter of software engineering.

And you really need to understand these high level things to

be able to direct your AI to be building the things

that you should be building and redirecting it when it's doing something wrong.

You need to be able to conceptualize what the end product should look like based upon the requirements that you have.

For example, at work, you might wanna build a software

that stores a massive amount of information and have lots of people querying it all the time.

So then you need to be thinking, what sort of database should I be using?

That is cheap, safe, and fast.

And how do I design a user interface that allows for multiple people querying at the same time?

These are all like design questions that you need to be able to understand.

I'm gonna put on screen now some resources that you can check out to learn about these topics.

Next up is version control and GitHub.

I mean a system that's able to track the changes in your files and code over time.

So you can track the history, revert back if you need to, and collaborate simultaneously with other people as well.

There are actually a lot of different types of version control software out there.

The most popular one is called Git.

So people would use Git in order to do version control and then put their code on something called GitHub.

GitHub is the industry standard for displaying your code, sharing it, and collaborating with other people.

This is especially important if you're intending to do agentic engineering, because you want to be tracking the changes that your AI coding agent is doing right?

And in case it makes a mistake, you can revert it and redirect it without like losing your entire code base,

which by the way, this happened to a lot of Vibe coders who did not know the fundamentals of coding and engineering.

I'll put on screen out some resources for you to learn about version control and GitHub.

All right, next up is security and privacy.

So this is a topic that was not particularly important when somebody is learning how to code like a few years back.

Like obviously security and privacy is important, right?

But it's sort of something that just gets

Like how does authentication work and how do you like integrate authentication into your apps?

But the reason why I'm separating this out as its own like little topic here is

because I think it's particularly important in this day

and age to learn about security and privacy because it's usually one of the blind spots of AI coding agents.

So you as the human can't just kind of like hope

that the AI agent is just going to take care of it.

You do need to be quite explicit in incorporating these principles.

Don't worry, this is honestly not like a really big topic.

100

It's just really important to know.

101

to engineer maybe i'm going to put on screen now a few different resources

102

that i suggest you take a look at and learn about privacy

103

and security all right

104

so at this point you would have covered pretty much the fundamentals of coding

105

and software engineering now you have now earned your stripes to

106

be able to harness the power of agentic engineering by using ai coding agents yay

107

but with that being said i do want to throw in a bonus little topic which is debatable whether it's

108

but I personally think it's pretty important, and you're probably gonna have to learn about it anyway, and that is microservices, otherwise known as the concept of containerization.

109

This is a software deployment method that packages an application's code together with all of the files, libraries, and dependencies that it needs in order to run that piece of code.

110

So it's sort of like little packages, little containers of pieces of software.

111

The purpose of this is to isolate the application from its surroundings, so it's not interacting with the rest of your computer, and is able to run consistently across different computer environments,

112

different types of clouds.

113

This is usually more of an advanced topic

114

and people usually learn about this when they're building stuff or like on the job.

115

But the reason why I'm putting this here as like an optional

116

but maybe you should learn about this kind of topic is as another precaution if you're using AI coding agents.

117

You can imagine if you're letting your coding agent or even like multiple coding agents just do whatever it wants, right?

118

It can end up messing up your development environment entirely

119

or like building things in a way that cannot be properly deployed and used by other people.

120

I would be just left like really frustrated because you can't figure out why it's

121

take the precaution to containerize you're going to end up with something more reliable

122

and if your ai agent does run amok

123

and starts doing crazy things it's going to be in its own little environment doing it

124

so worst case scenario just shut off

125

that environment let me know in the comments of these topics

126

i have just covered how many of these topics do you already know

127

which ones do you still need to learn curious where you

128

guys at on the learning journey as promised i'm also going

129

to put a prompt on screen also probably link in description too which you can put into whatever you want.

130

And it will help adapt this learning plan

131

and resource list to fit the goals of your learning

132

and also help you determine which coding language makes the most sense for you to learn.

133

Yay, amazing.

134

You have now earned your stripes to be able to tackle this new world, this brave new world of agentic engineering.

135

Now, agentic engineering itself.

136

Gosh, agentic engineering does not sound as cool as vibe coding, it's just not as catchy.

137

It's fine.

138

Agentic engineering, okay.

139

Agentic engineering itself is also a skill.

140

It involves how to set up your project and how to set up your AI coding agents, how to communicate what it is that you wanted to build to your coding agents, and how to monitor them correctly, among many other things.

141

For agentic engineering, there are different options for which coding agents to use Me personally, I really like using Warp,

142

who is also the sponsor of this portion of the video, because it's a pro developer tool that covers the full spectrum of AI coding.

143

Getting started is so simple.

144

I built this entire project using Warp, but as it scaled, I needed to move faster, and that's where the magic begins.

145

Instead of tackling one thing at a time, I deployed multiple coding agents simultaneously.

146

Here's one that's adding a backend feature, one on documentation, and one that's writing tests.

147

This is all powered by Oz, which is a cloud -based agent orchestration platform The Oz dashboard gives you a real -time view of all your agents.

148

At a glance, you can see what they're working on, their status, and any issues that they may have.

149

And because it's cloud -based, each agent runs in its own isolated environment, meaning that they won't interfere with each other and my poor MacBook Air can stay alive.

150

That is not all.

151

You can actually incorporate Oz within your project itself.

152

For example, this is a scheduled agent that updates my microsite every day.

153

It goes in there, takes the AI news of that day, which is what I care about, and summarizes it and displays that information for me.

154

into AI coding agents, integrate them directly with Slack and linear, and tap into a ton of other features that support team workflows.

155

700 ,000 engineers are already using it, and 97 % of code diffs get accepted, which honestly is pretty impressive and tracks from my experience too.

156

So if you want to get started, you can get started for free at the link linked below.

157

Thank you so much for sponsoring this portion of the video.

158

Now back to the video.

159

Unfortunately, there are not that many good resources on agentic engineering, probably because it's such a new topic.

160

But I'm going to put on screen now a couple of videos that I've done and some other resources as well.

161

If you guys want, I can also make a video that specifically covers how to do agentic engineering.

162

You know what's crazy is that to learn all of these topics that we just discussed, higher to AI, it would have taken you years.

163

Like people go to school for this and then work multiple years to get to this level.

164

Or even if they're attending like a fast track boot camp, we're still talking like at least 10 to 12 months completely full time.

165

good learning techniques and with AI to help with your learning, you can reduce the learning time down by so much.

166

I think that if you really focus and if say you're doing it like completely full time, I would estimate maybe like six months to be able to learn all these topics very solidly.

167

So in the next section, I'm actually going to share some of my favorite learning techniques that can help you learn faster.

168

For those of you who've watched my channel for a while, you probably also know that learning things fast is like my favorite activity.

169

So very exciting.

170

Let's not talk about tips to supercharge your learning.

171

I'm going to divide these tips up into two different categories.

172

The first is how to use your resources better, like the lectures, the books.

173

And the second is how to use projects for learning

174

and specifically how to use an AI coding agent to help you build a project and learn at the same time.

175

Two birds with one stone.

176

Okay, let's first talk about how to use resources.

177

If your resource happens to be like a video or like some text or like readings and stuff like that, I would really recommend using something like Notebook LM and put all that information in there

178

generate questions that will guide you along the work.

179

This is called primate and can really speed up your learning process

180

because you'll understand what are the things that you need to be learning and how they fit together with each other.

181

As you're going through the lectures, the text, and like code snippets and whatever, if there's anything you don't understand,

182

you can also just poppy paste that and put that into AI to help you explain what's going on.

183

When it comes to code and logic, at least of the filming right now, the best AI model to do this would be clod.

184

I personally But if you don't want to pay for it and you run out of the free trial, honestly, most modern AI models would be able to help explain code.

185

You can even use the free ones, the open source ones, like Quen, Kimmy, or DeepSeek.

186

Another way that I really like using AI models to help me learn is by taking a concept

187

and asking it to give me examples and analogies, because this will really allow it to solidify in my mind to understand the concept.

188

Like, for example, if you're learning about object -oriented programming, you can ask it, explain object -oriented programming to me using an analogy and provide examples.

189

Much clearer, I think.

190

how to code is to take the code

191

and the snippets from the resources that you have like other people's code

192

and then ask AI to help you understand the code that's there to explain to you what the code is doing.

193

This is so powerful and I'm kind of salty that I did not have this

194

option when I was learning how to code.

195

To do this you can also just like copy paste

196

or like upload the code into an AI model

197

or this could be a good opportunity for you to set up an AI coding agent.

198

Just give it the code and it would explain to you the structure of the code how the pieces are fitting together, what different lines of code mean, line by line if you want.

199

And speaking of projects, this is a good transition to the second category of tips that I have, which is for projects.

200

First of all, I want to just emphasize that projects are the best way for you to learn how to code.

201

Hands down.

202

You can watch like so many lectures, read so many things and whatever, and you think that you know these things.

203

Yeah, but you don't unless you actually start building with it.

204

And the way you do that is by doing projects.

205

So I encourage you to do projects continuously as Make a project in which you use an API or multiple APIs.

206

If you're learning about testing, write some tests.

207

Try and understand the differences between different tech stacks.

208

Try them out yourself, especially with the help of AI coding agents.

209

It is so easy to do this.

210

You can ask the coding agent something like build me a music storage software with like X by Z specs, built with a Django backend,

211

a Next .js frontend, and store the data in a SQLite database, for example.

212

engineering.

213

I previously mentioned other people's projects as well.

214

Another great way for you to learn is to take other people's projects and then adapt them, add on more stuff to them, change around the code and see how the results change.

215

This is such a great way to learn and a staple amongst engineering students everywhere.

216

Another tip, as you're coding, you can also ask AI to give you multiple suggestions for how to implement something.

217

This way you can expand the skill of your knowledge, which is going to make you a much better coder.

218

And final little tip, documentation.

219

Like, I hate it so much.

220

I don't think I've read any documentation since like

221

2024

222

because i will ask ai to help me understand documentation to

223

be clear i still need to understand the documentation i just don't like reading it

224

so this is a great way to understand documentation faster

225

and incorporate them into your projects i'm not going to go

226

into vibe coding slash agentic engineering specific tips right now

227

because there's just like way too much and there's a whole other video

228

that i can make on this topic

229

so i'm just gonna put on screen some of my favorite little vibe coding tips

230

if that's helpful for you guys just know that this is not everything and it

231

if you never had any experience at all.

232

Let me know in the comments if you want me to actually make like a fully fledged video for that topic.

233

All right, we have now come to the end of this video.

234

Thank you so much for watching until the end.

235

I know that was a lot.

236

I really hope this is helpful to you.

237

I'm so glad that you're learning how to code in 2026.

238

That's the luck in your coding journey.

239

And I will see you guys in the next video or live stream.

📺 Cùng kênh

✨ Video gợi ý

12 câu

How I’d Learn Coding in 2026 (Without Wasting Years)

Business EnglishUniversity StudentsWorking Adults

61 câu

The "vibe coding" mind virus explained…

Business EnglishUniversity StudentsWorking Adults

307 câu

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

Business EnglishUniversity StudentsWorking Adults

215 câu

Creator of C# and TypeScript: "AI will NEVER Replace Coders, Here's Why" | Anders Hejlsberg

Business EnglishUniversity StudentsWorking Adults

157 câu

Identity Shifting: How to Reinvent Yourself in 3-6 Months (in 2026)

Business EnglishUniversity StudentsWorking Adults

730 câu

How to friction-max your learning with software engineer Jessica Rose [Podcast #216]

Business EnglishDaily ConversationUniversity Students

202 câu

You won't fall behind

Business EnglishUniversity StudentsWorking Adults

269 câu

Design with Claude Code: The Designer’s Guide

Business EnglishUniversity StudentsWorking Adults

55 câu

Cloud Providers are changing RAPIDLY [REUPLOAD]

Business EnglishUniversity StudentsWorking Adults

22 câu

I'm an ex-Google interviewer. You're doing LeetCode wrong.

Business EnglishInterview EnglishUniversity Students

278 câu

Fastest way to become an AI Engineer in 2026

Business EnglishInterview EnglishUniversity Students

Đối Tượng Nào Thích Hợp Với Video Này?

Video này dành cho những người mới bắt đầu học lập trình và những ai muốn cập nhật kiến thức về các xu hướng lập trình hiện đại. Nếu bạn là sinh viên, người đi làm hoặc bất kỳ ai có mong muốn xây dựng ứng dụng, đặc biệt là trong lĩnh vực trí tuệ nhân tạo, video sẽ cung cấp cho bạn những thông tin quý giá để phát triển kỹ năng coding của mình. Mục tiêu là giúp bạn nắm vững các kiến thức cơ bản và tiến tới những khái niệm phức tạp hơn, từ đó bạn có thể tự tin hơn khi làm việc với các công cụ mới như AI coding agents.

Các Từ Ngữ & Thành Ngữ Đáng Chú Ý

Vibe coding: Khái niệm mới được định nghĩa để chỉ cách lập trình không chú trọng vào chi tiết mà tập trung vào cảm xúc và sự sáng tạo.
Agentic engineering: Kỹ thuật lập trình mà bạn điều khiển các agent AI, giúp tối ưu hóa quy trình lập trình của mình.
Orchestrating your AI agents: Nghệ thuật quản lý và điều hành các agent AI như một nhạc trưởng, yêu cầu kỹ năng giao tiếp rõ ràng.

Cách Để Phát Âm Đúng

Để cải thiện khả năng phát âm khi nghe video, bạn có thể thực hiện kỹ thuật shadowing tiếng anh. Điều này có nghĩa là bạn sẽ lặp lại các câu nói của người nói trong video ngay lập tức sau khi họ nói. Tập trung vào các âm điệu và nhấn mạnh từ để cải thiện cách phát âm của mình. Sử dụng các trang web chuyên về shadowing speech hoặc shadowspeaks cũng rất hữu ích để luyện tập. Hãy chú ý đến ngữ điệu và cách ngắt quãng của diễn giả để phát âm chính xác hơn. Với kỹ thuật này, bạn sẽ nhanh chóng nâng cao khả năng nói tiếng Anh của mình.

Ngữ pháp trong video

Những cấu trúc người nói dùng nhiều nhất, kèm đúng cụm từ trong video:

Cấu trúc	Trong video
“Used to” used to + động từ — thói quen hoặc tình trạng trong quá khứ nay không còn	used to be
Câu bị động be + quá khứ phân từ — nhấn vào việc xảy ra, không phải người làm	is sponsored · be fooled · They've been vetted
Thì hiện tại hoàn thành have/has + quá khứ phân từ — việc đã xảy ra nhưng còn liên quan đến hiện tại	They've been vetted · have now earned · have just covered
Mệnh đề quan hệ who / which + mệnh đề — thêm thông tin về người hoặc vật	people who know · learn, which is · topic which is

Phương Pháp Shadowing Là Gì?

Shadowing là kỹ thuật học ngôn ngữ có cơ sở khoa học, ban đầu được phát triển cho chương trình đào tạo phiên dịch viên chuyên nghiệp và được phổ biến rộng rãi bởi nhà đa ngôn ngữ học Dr. Alexander Arguelles. Nguyên lý cốt lõi đơn giản nhưng cực kỳ hiệu quả: bạn nghe tiếng Anh của người bản xứ và lặp lại to ngay lập tức — như một "cái bóng" (shadow) đuổi theo người nói với độ trễ chỉ 1–2 giây. Khác với luyện ngữ pháp hay học từ vựng bị động, Shadowing buộc não bộ và cơ miệng phải đồng thời xử lý và tái tạo ngôn ngữ thực tế. Các nghiên cứu khoa học xác nhận phương pháp này cải thiện đáng kể phát âm, ngữ điệu, nhịp điệu, nối âm, kỹ năng nghe và độ lưu loát khi nói — đặc biệt hiệu quả cho người luyện IELTS Speaking và muốn giao tiếp tiếng Anh tự nhiên như người bản ngữ.

Phương pháp shadowing: đọc hướng dẫn từng bước đầy đủ →

Luyện nói tiếng Anh bằng Shadowing qua video: How To Learn To Code In 2026

Learn 10X Faster In 10 Minutes

Updated Essential AI Skills For 2026

My Full Claude Cowork Setup (steal my workflows!)

Essential AI Skills For 2026

Every Size Local AI In 24 Minutes

Best Upcoming Jobs (2026 - 2030)

How I’d Learn Coding in 2026 (Without Wasting Years)

The "vibe coding" mind virus explained…

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

Creator of C# and TypeScript: "AI will NEVER Replace Coders, Here's Why" | Anders Hejlsberg

Identity Shifting: How to Reinvent Yourself in 3-6 Months (in 2026)

How to friction-max your learning with software engineer Jessica Rose [Podcast #216]

You won't fall behind

Design with Claude Code: The Designer’s Guide

Cloud Providers are changing RAPIDLY [REUPLOAD]

I'm an ex-Google interviewer. You're doing LeetCode wrong.

Fastest way to become an AI Engineer in 2026

Đối Tượng Nào Thích Hợp Với Video Này?

Các Từ Ngữ & Thành Ngữ Đáng Chú Ý

Cách Để Phát Âm Đúng

Ngữ pháp trong video

Phương Pháp Shadowing Là Gì?