쉐도잉 연습: How I'd Learn AI From Scratch in 2026 (skip the useless 80%) - 영상으로 영어 말하기 배우기

If I had to learn AI from scratch today, I'd be overwhelmed because so much of what's out there is either outdated and no longer relevant, or just theory you'll never actually use.

So in this video, we're focusing on the 20% of AI that's practical and that will still matter a decade from now, organized in three levels that build on top of each other.

Let's get started.

Kicking things off with step one, pick one model and go deep.

There are two reasons for this.

First, this artificial analysis chart shows that although models used to be far apart and capability, they're now all so powerful,

as represented by the clustering in the top right, that the difference for the average user is negligible.

Second, because all the top AI companies are copying each other, all the models have the same core features.

Meaning once you go deep on one, that skill carries straight over to the rest.

So what are your options?

Well, just like picking a starter Pokemon, there really is no wrong choice, as long as you pick Charmander.

Just kidding.

Before I get wrecked in the comments, a few clarifications.

First, I've got nothing against Elon, but objectively speaking, XAI simply is not competitive anymore.

Second, Perplexity does not have their own frontier model.

They're primarily a search tool that fine tunes other companies' models.

And third, as much as I appreciate the open source Chinese models, they're still behind their Western counterparts, which leaves three choices, Chachapiti, Claude, and Google Gemini.

But which one is the right one for you?

This brings us to step two.

Pick the model based on three simple principles.

First, prioritize paid tiers.

So if you're on free ChatGPT, but your job gives you paid Gemini, go deep on Gemini because the gap between free and paid is like night and day.

Second, if you have a choice, pick the AI that matches your work since each one has its own strengths.

ChatGPT is the most mature, has the most users, and so it's got the most tutorials to learn from.

I've also found it's the best at web search out of all the chatbots, and therefore it's great for research.

Claude is really good at writing and design and excels in coding, which matters even if you're not technical because stuff like data analysis

and pretty diagrams are all built on code under the hood.

And Gemini is the best if you work across text, images, audio, and video, since it's the only AI that can process mixed media natively.

And it's also the best pick if you're a heavy Google workspace user.

Third principle, vibes.

I know it sounds dumb, but each AI has their own personality.

And the more you enjoy using it, the more you'll use it and the better you'll get at it.

Pro tip, switching is pretty easy since all three have some sort of a memory import feature.

For example, in Gemini under settings, just open import memory to Gemini and follow the onscreen instructions.

And that brings us to step three, change your defaults.

Put simply, the companies default you to the weakest model because this is the cheapest for them to run.

So you always want to select the more powerful models you have access to for real work, since these will actually break down your requests,

map out the steps, and catch nuances you didn't think to mention.

Here's a quick recap of level one.

First, use the paid version if you can.

Second, choose the chatbot that matches your work and stick with it.

And third, always default to the most capable model you have access to.

Now, you might've noticed I didn't mention prompting at all, and that's on purpose, because with how powerful these models have become,

your prompt is no longer the biggest factor in determining output quality.

By the way, I'm kind of proud of this.

I actually partnered with today's sponsor HubSpot in putting together a

Google Gemini cheat sheet for all of you with a list of my top productivity tips and techniques for Gemini.

Here are two of my favorites.

First in Google Docs, you can add an AI summary block at the top of any working document by typing at AI summary.

And now anyone on the team can click refresh to get the current gist without rereading everything.

Second, within Google Sheets, you can type equal AI and start giving instructions in plain English.

For example, hey, append the video number and topic to the front of the video title.

And there you go.

No formulas needed, right?

Saves so much time.

The cheat sheet is completely free, link in the description.

Thank you HubSpot for sponsoring this video.

So what's more important than our prompt?

Let me illustrate with a simple example.

Say you need to find a restaurant for your boss.

You could either spend 10 minutes describing everything you think your boss likes in a long and detailed prompt,

or you could hand the AI a list of restaurants your boss has loved in the past

and let it figure out the pattern.

The second approach wins every single time.

Put simply, that list of restaurants is an example of the right context, and the right context will always beat the perfect prompt.

In practice, this means we don't need to memorize a bunch of prompting frameworks anymore

because models have gotten so powerful that they're able to accurately infer inputs like the role, the format, and the tone as long as we give them two things,

a clear outcome and the right context.

So there's really just one framework worth remembering, OC, outcome plus context.

Let's see this in action.

Say you want a new workout plan.

Option A, you could write a long detailed prompt spelling out your experience level, your equipment, your schedule, your goals, and the format you want it in.

Or option B, copy an article breaking down the push-pull-legs routine, paste it into AI as context, and write a simple prompt like,

my goal is to develop a four-day training routine for muscle growth, 45 minutes a day, tailor a plan for me based on this.

Option B's output will always be better because instead of you saying something like role, act as a senior personal trainer.

The AI infers a much sharper role from the context, like a specialist in compound training, which is something you would not have thought of yourself.

I would have because I'm just, you know, built different.

Just kidding.

Anyways, now that we know context is king, here are the top three ways to find the right context.

First, explicitly name a relevant framework.

For example, instead of typing a paragraph explaining how to restructure a report, I tell the AI to rewrite this using the pyramid principle.

Since those two words, pyramid principle, carry more context than a paragraph of me describing what the pyramid principle is.

Pro tip, you can ask the AI for relevant frameworks.

For example, what are the best frameworks for setting goals?

Then pick the one that fits and use it in your next prompt.

Second, the best type of context to give AI is real examples of what good looks like.

Since examples contain everything you forget to explicitly say in a prompt, like your manager's expectations and your team's preferences.

For example, instead of spelling out the format, length and tone for a weekly status update, just paste in the last two to three updates that were approved.

Add a raw notes for the week and say, write this week's update in the same format.

And the AI will pull everything it needs from those examples.

Third, connect your tools.

Put simply, your best context already lives somewhere in your email, your Google Drive, Slack, Notion, what have you, right?

So by connecting to those platforms, your AI can just pull what it needs directly without downloading and re-uploading.

In practice, this means instead of manually attaching transcripts from multiple meetings, we point the AI to the tool and ask it to pull the required files and surface insights.

Now that we know what great context looks like, how can we save relevant context for recurring work so we're not repeating ourselves every time?

The answer in ChatGPT and Claude is a feature called projects.

In Gemini, they call it Gemini Gems, but they work basically the same way.

And a project is a permanent home for recurring work streams and and contains three components.

First, the project instructions are the rules that always apply, like your goals and constraints for this entire work stream.

100

Second, knowledge files are the reference information that the AI pulls from, like your source documents, examples, and frameworks.

101

Third, the memory.

102

This is updated by the AI automatically and keeps track of key updates and milestones within this work stream.

103

Building on top of our previous example, here I have a workout project in Claude that acts as my coach.

104

And within the project instructions, we see the goal of the project and my current setup, which is really constraints, 45 minutes of the session, home only, right?

105

And a reference to the knowledge file, which is the push pull leg program from earlier.

106

And since every single conversation has access to this knowledge file, I can say something like, I only have 25 minutes today for a pull day, what do I do?

107

And the AI recommends a workout based on our program.

108

And right now the memory is empty because this is just an example.

109

But let's say I injure my shoulder pressing, I don't know, 200 kilogram dumbbells, true story.

110

The AI would actually make a note of that and steer me away from shoulder related exercises until I heal.

111

Pro tip, you always wanna use something called .md

112

markdown files instead of PDFs whenever possible

113

because markdown files are easier for the AI to read

114

and cheaper to process and you can easily ask the AI to convert PDFs into Markdown.

115

Now, as good as projects are for recurring work, each project is a standalone silo,

116

meaning my workout coach project can't see what's in my annual health reports that's stored in another project, right?

117

Even though it totally makes sense for them to talk to each other.

118

And this is where an AI system comes in.

119

So what's an AI system?

120

Put simply, it's a setup that does two things projects cannot do.

121

First, it can pull context from different projects spot patterns across them and surface insights individual projects would have missed.

122

For example, here I'm told that, hey, I took a look at your travel project and your personal finances project, and guess what?

123

You don't have enough money to go on your Bali trip.

124

Second, an AI system updates itself after you give it feedback, meaning learnings compound over time.

125

For example, when I say reconcile my final draft with your initial output,

126

the AI system analyzes all the changes I made and proposes rules to remember for next time.

127

I'm gonna oversimplify quite a bit here, but broadly speaking, you have three options when it comes to AI systems.

128

First, Gemini Spark from Google is the most beginner friendly and requires minimal setup because it's already connected to tools like Gmail, Google Calendar, and Google Drive.

129

But the trade-off is we have less control over how it's configured.

130

Let me know if you want a full tutorial on Gemini Spark.

131

Next up, Claude Cowork is specifically designed for non-technical people like myself.

132

It gives us more control, but it does require some sort of setup, as you can see.

133

If you're interested in setting this up for yourself, I'll leave a link to my free co-work toolkit below.

134

Finally, Anthropix Claude Code and OpenAI's Codex are basically Claude Co-work on steroids.

135

These are fully customizable, extremely powerful, but you'll need to be somewhat comfortable with code.

136

This is a bit silly, but each tool's model selector is a pretty good signal for who it's for.

137

For example, in Codex, you have all these options, right?

138

That are perfect for power users, but intimidating for everyone else.

139

Cowork kind of dumbs it down a little bit by giving us fewer options, but you know, still some control.

140

And Gemini Spark doesn't let us pick the model at all.

141

Although I think they'll change that soon.

142

All right, now let's go through some real life examples of what these AI systems can do.

143

Previously, I had three separate projects tracking my annual health checkups, the supplements I take, and my workout plan.

144

But once I migrated them into co-work, the AI is able to cross-reference my latest checkup with my workout plan.

145

Flags the fact that I don't have any cardio days, although I have borderline high cholesterol,

146

and so it recommends adding cardio sessions to my rest days.

147

And notes that since I'm already taking fish oil, there's nothing it would change in my supplement stack.

148

To be clear, no single project could have connected those dots, unless I decided to copy and paste information between the two, right?

149

But the AI system sees them all.

150

Example two is the reconcile move I mentioned earlier and applies to any writing that you do.

151

Here, the AI gave me a rough draft of a segment of my YouTube script.

152

Then I made a bunch of edits and I shared it back under the final version, right?

153

To make it sound more like me.

154

Then I told it to reconcile my version with the initial draft from the AI.

155

And the AI is able to dissect every change, as you can see down here, and it remembers all the rules for the next segment.

156

And so the more I give feedback, the smarter the system gets and the less instructions I need to give moving forward.

157

All right, here's a quick recap of everything we covered today.

158

Level one is just getting started with one of the big three chatbots, default to the most powerful model and go deep since the skills carry over to the rest.

159

Level two is learning what kind of context actually helps the AI, then saving it in projects so you can stop repeating yourself for recurring work.

160

And level three is connecting those projects into one system that compounds the more you use it.

161

Most people aren't here yet, and that's okay.

162

There's no rush.

163

The gap between using AI and using AI well has always been invisible, but hopefully this video has helped you figure out where you are right now and what to focus on next.

164

If you enjoyed this, check out my Claude co-work play this next.

165

See you over there, and in the meantime, have a great one.

📺 같은 채널

✨ 추천 영상

63 문장

5 open source tools that replaced my $320/mo AI stack...

Business EnglishUniversity StudentsWorking Adults

278 문장

Fastest way to become an AI Engineer in 2026

Business EnglishInterview EnglishUniversity Students

546 문장

Do Elite Degrees Still Matter In The AI Era? | Jamie Beaton from Crimson Education | EP 410

Business EnglishUniversity StudentsWorking Adults

43 문장

Grok 4 pushes humanity closer to AGI… but there’s a problem

Business EnglishUniversity StudentsWorking Adults

392 문장

Ultimate Claude Guide: How to Use Claude AI for Beginners in 2026

Business EnglishUniversity StudentsWorking Adults

126 문장

Therapy for the Vibe-Coded Brain

Business EnglishUniversity StudentsWorking Adults

260 문장

It’s Actually Pretty Easy to Get Ahead of 99% of People with AI

Business EnglishUniversity StudentsWorking Adults

24 문장

DeepSeek R1 Explained in 2 Minutes

Business EnglishUniversity StudentsWorking Adults

197 문장

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

Business EnglishUniversity StudentsWorking Adults

23 문장

AI Made the Most Passive Side Hustle Even Easier

Business EnglishUniversity StudentsWorking Adults

이 레슨의 어휘와 말하기 포인트

이 B2 수준 말하기 레슨은 영상 “How I'd Learn AI From Scratch in 2026”을(를) 바탕으로 합니다. 가장 자주 반복되는 단어는 다음과 같습니다: project, example, context, model, Gemini. 이 영상에는 섀도잉할 문장 165개와 단어 2500개가 있습니다. 말하는 구간의 길이는 13:15입니다. 화자는 분당 약 189단어로 빠르게 말하므로 연음과 약하게 발음되는 소리가 많습니다. 단어의 82%가 영어에서 가장 많이 쓰이는 3,000단어에 속합니다. 나머지는 연습 전에 미리 확인해 두세요.

이 영상의 핵심 어휘

영상에서 가장 어려운 단어 15개를 발음, 뜻과 함께 정리했습니다.

단어	발음	뜻
prompt 동사	/pɹɑmpt/	부추기다
workout 명사	/ˈwɝk.aʊ̯t/	운동
chatbot 명사	/ˈtʃætbɑt/	챗봇
reconcile 동사	/ˈɹɛkənsaɪl/	화해하다
pyramid 명사	/ˈpɪɹ.ə.mɪd/	피라미드, 금자탑
pasta 명사	/ˈpɑ.stə/	파스타
compound 명사	/ˈkɑmpaʊnd/	화합물
tutorial 명사	/ˌtjuːˈtɔːɹɪəl/	지도, 지침
spelling 명사	/ˈspɛl.ɪŋ/	철자법, 맞춤법
paragraph 명사	/ˈpæɹəɡɹæf/	단락
sponsor 명사	/ˈspɒn.səː/	스폰서
cheat 동사	/ˈt͡ʃiːt/	바람피우다, 바람을 피우다
import 명사	/ˈɪm.pɔɹt/	수입품
configure 동사	/kənˈfɪɡə(ɹ)/	설정하다
injure 동사	/ˈɪn.d͡ʒɚ/	해치다

영상에 나오는 구동사

단어	뜻
put together 동사	조립하다

따라 말해 볼 만한 문장

영상에 나오는 짧고 완결된 문장으로, 일상 대화에서 그대로 쓸 수 있습니다:

By the way, I'm kind of proud of this.
So what's more important than our prompt?
Let's see this in action.
Although I think they'll change that soon.

이 영상의 문법

화자가 가장 많이 쓰는 문형을 영상 속 실제 표현과 함께 정리했습니다.

문형	영상 속 표현
현재완료 have/has + 과거분사 — 과거의 일이 지금도 관련이 있을 때	I've also found · might've noticed · has loved
수동태 be + 과거분사 — 누가 하는지보다 무슨 일이 일어나는지에 초점	be overwhelmed · were approved · is updated
관계절 who / which + 절 — 사람이나 사물에 대한 추가 정보	training, which is · setup, which is · file, which is

주의할 발음

화자는 I'm, don't, they're 같은 축약형과 약화된 형태를 36번 사용합니다. 들리는 대로 짧게 발음하세요.

“sh”와 “zh” 소리: instruction /ɪnˈstɹʌkʃən/, clarification /ˌklæɹɪfɪˈkeɪʃən/, refresh /ɹɪˈfɹɛʃ/, expectation /ˌɛk.spɛkˈteɪ.ʃən/
긴 단어 — 강세 위치에 주의: intimidate /ɪnˈtɪmɪdeɪt/, negligible /ˈnɛɡlɪd͡ʒɪbəl/, objectively /əbˈd͡ʒɛktɪvli/, prioritize /pɹaɪˈɒɹ.ə.taɪz/, clarification /ˌklæɹɪfɪˈkeɪʃən/

한국어 화자가 어려워하는 소리:

/f/ — ㅍ(/p/)으로 바꾸지 말고 윗니를 아랫입술에 대기: infer /ɪnˈfɜː/, paragraph /ˈpæɹəɡɹæf/, configure /kənˈfɪɡə(ɹ)/, clarification /ˌklæɹɪfɪˈkeɪʃən/, refresh /ɹɪˈfɹɛʃ/
/v/ — ㅂ(/b/)과 구별하기: natively /ˈneɪtɪvli/, objectively /əbˈd͡ʒɛktɪvli/, overwhelm /ˌoʊ.vɚˈwɛlm/, vibe /vaɪb/, invisible /ɪnˈvɪzəb(ə)l/
/z/ — ㅈ이 아니라 성대를 울리는 /s/: memorize /ˈmɛm.əˌɹaɪ̯z/, prioritize /pɹaɪˈɒɹ.ə.taɪz/, analyze /ˈæn.əˌlaɪz/, propose /pɹəˈpəʊz/, anyways /ˈɛn.iˌweɪz/

이 영상으로 연습하는 방법

먼저 말하지 않고 영상을 끝까지 듣고 모르는 단어를 적어 둡니다.
0.75배속으로 한 문장씩 섀도잉을 시작하고, 익숙해지면 보통 속도로 돌아갑니다.
자신의 목소리를 녹음해 원본과 비교하고, prompt, workout, chatbot 같은 단어에 특히 주의합니다.

쉐도잉이란? 영어 실력을 빠르게 키우는 과학적 방법

쉐도잉(Shadowing)은 원래 전문 통역사 훈련을 위해 개발된 언어 학습 기법으로, 다언어 학자인 Dr. Alexander Arguelles에 의해 대중화된 방법입니다. 핵심 원리는 간단하지만 매우 강력합니다: 원어민의 영어를 들으면서 1~2초의 짧은 지연으로 즉시 소리 내어 따라 말하는 것——마치 '그림자(shadow)'처럼 화자를 따라가는 것입니다. 문법 공부나 수동적인 청취와 달리, 쉐도잉은 뇌와 입 근육이 동시에 실시간으로 영어를 처리하고 재현하도록 훈련합니다. 연구에 따르면 이 방법은 발음 정확도, 억양, 리듬, 연음, 청취력, 말하기 유창성을 크게 향상시킵니다. IELTS 스피킹 준비와 자연스러운 영어 소통을 원하는 분들에게 특히 효과적입니다.

섀도잉 방법: 단계별 전체 가이드 읽기 →

쉐도잉 연습: How I'd Learn AI From Scratch in 2026 (skip the useless 80%) - 영상으로 영어 말하기 배우기

Claude Design is Insanely Easy (even for beginners)

Why Are You a Good Fit for this Role - How to Answer

Tell Me About Yourself (The BEST Way to Answer this Interview Question)

What is Your Biggest Weakness? (Ace this Interview Question!)

AI Agents, Clearly Explained

Learn 95% of ChatGPT Work in Under 20 Minutes

Tell Me About Yourself - Structure a Strong Answer

Google’s AI Course for Beginners (in 10 minutes)!

How to Get Started with Notion (without losing your mind)

7 Job Interview Questions to Prepare For!

Tell me a time You Handled a Difficult Situation (Interview Question)

5 open source tools that replaced my $320/mo AI stack...

Fastest way to become an AI Engineer in 2026

Do Elite Degrees Still Matter In The AI Era? | Jamie Beaton from Crimson Education | EP 410

Grok 4 pushes humanity closer to AGI… but there’s a problem

Ultimate Claude Guide: How to Use Claude AI for Beginners in 2026

Therapy for the Vibe-Coded Brain

It’s Actually Pretty Easy to Get Ahead of 99% of People with AI

DeepSeek R1 Explained in 2 Minutes

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

AI Made the Most Passive Side Hustle Even Easier

이 레슨의 어휘와 말하기 포인트

이 영상의 핵심 어휘

영상에 나오는 구동사

따라 말해 볼 만한 문장

이 영상의 문법

주의할 발음

이 영상으로 연습하는 방법

쉐도잉이란? 영어 실력을 빠르게 키우는 과학적 방법