쉐도잉 연습: Andrew Ng on Coding Agents and Deciding What to Build - 영상으로 영어 말하기 배우기

연습 모드 선택

각 모드는 전체 화면 연습실로 열립니다.

345 문장

문장이 너무 짧거나 길면 Edit를 눌러 조정하세요.

You know, I'm actually very excited about the future of databases.

I know I'm going to ask you another question, I'll just share one thing.

I feel like right now,

the world is going through a massive data center build-out with a lot of AI training and inference data centers being built.

I suspect something that a lot of the world does not yet appreciate is that in the future, a lot of core infrastructure,

be it computed storage, will be used not just by humans, but by agents.

and that agentic usage of all this infrastructure will drive massive demand.

And so in addition to the AI data center buildup for training and inference,

I think a lot of databases that are built for human usage today, and we can only look at or query so much data,

but with agentic usage, I think the demand for core infrastructure for compute will continue to skyrocket.

So you're very bullish on this category at home.

Yeah, it's an amazing space.

I mean, we feel very fortunate to be in the thick of it.

And actually, we had a partner day yesterday where we invited a lot of people who work with builders or developers.

And basically, everyone's saying, yeah, we're running out of compute.

We need, like, the amount of builders pouring into the world is just going crazy right now.

Yeah.

So, actually, I'm going to start because you have one of the most impressive backgrounds that, and I couldn't memorize it all.

So, I'm just going to, I know you're very humble.

I'm going to read out for anyone who doesn't know, you're the founder of Deep Learning AI.

You're a general partner of an AI fund, managing partner of AI Aspire, chairman and co-founder of Coursera, professor at Stanford University.

Previously, you were the founding lead of Google Brain, VP and chief scientist at Baidu,

director, formerly director of the Stanford AI Lab.

and you are part of the Time 100 AI list for the most influential AI persons in the world.

So first of all, that's crazy.

Thank you.

What a life.

Actually, how do you have the energy to kind of keep reinventing yourself and keep doing or do all these things?

I feel like the answer I have is kind of the obvious one is I've been really

so blessed to work with so many great people consistently across so many organizations.

I feel like for the people I get to work with, I would hardly manage to accomplish anything myself.

So I've just been really blessed.

That's cool.

Okay, so I was going to talk about SkillsMap.

I was going to try to explain it, but you are first and foremost a teacher.

So maybe you can tell us a little bit about SkillsMap.

what you're doing at the moment, and then we can dive deep.

Yeah.

I think the most exciting profession to be that's very rapidly at this moment in time is AI engineering.

And by that, I don't mean people that'll take on an AI engineering job title, but rather people in all sorts of job roles,

including software engineering, front-end, back-end, DevOps, mobile, that will benefit from having AI engineering skills.

So my team at D1Ai did a lot of work over

several months to try to map out what are the skills that are needed to do AI engineering well.

And so we wound up categorizing.

So we looked at over 10,000 job descriptions, job postings, did dozens of structured interviews, ran a bunch of surveys,

and synthesized views, talking to partners as well.

And we wound up figuring out that there are four key skills needed to do AI engineering well.

One is the ability to build and deploy AI applications.

And the difference between AI and non-AI applications is they're uncertain.

And so how do you manage that?

The second is software engineering fundamentals.

It turns out that even if AI writing a lot of code for us, people that understand software engineering fundamentals,

understand what's the rewrite ratio, what's the transaction.

You know, people can steer coding agents much better that way.

Third is the ability to use coding agents.

And then lastly is the ability to, is a skill of shaping the build

because developers are no longer playing a role where someone tells them what to do and they just implement it,

but instead are participating in deciding what to build and also influencing the process by which something gets built built.

So what I'm seeing in the job market today is developers,

either people with an AI engineering title or people with other titles that gain some AI engineering skills,

are in great demand and we just can't find enough people with these skills.

So DeepLand.ai is excited to work upon this to to help more people become skilled at AI engineering.

Cool.

And the skills map itself, actually, first of all, starting with skills, why do you focus on skills in particular?

I think you have a view on skills that they're one of the more important parts.

Do you think that they're going to be critical as we go along,

or can the agents just become so good that we don't need to focus so much on providing our own custom skills?

How do you see this part of Wolverine?

Yeah, so I think about there's some things we do today that I hope an agent will take over for me.

For example, you may remember three-ish years ago, there was a lot of hype about the prompt engineering job

and how much money someone could learn by being a prompt engineer.

And I think at that time, it was already clear to...

Actually, you're Chris Manning credit.

He was saying this very clearly even back then,

which was this idea that we need humans of arcane incantations to prompt an LM to do something.

That's going to go away because an LM was going to learn how to make those same arcane incantations.

And so even today, I see some things that, like, you know, how do you manage a swarm of agents?

Some things humans would be needed to do.

Some things is more of a one-size-fits-all

that I think AI agents will manage other AI agents better and better in the coming years.

And one of the key things that distinguishes whether AI will take this over or not,

is whether or not humans have a fundamental context advantage.

It turns out when all of us are building applications, we know a ton of stuff that AI agents do not know.

You may remember a conversation with a customer, you know, where you said something and there was a funny expression on their face.

Or you may remember something that you learned, you know, five years ago, reading some market report saying people want this and not that.

So I find that humans have a bewildering, vast range of contacts and remarkably good at pulling out this context and make key decisions.

And so for that set of decisions where humans have a fundamental context advantage, until someday where, I don't know,

like slap a camera on us and monitor the facial expressions of everyone we talk to and have a good view.

That's a very difficult part.

So I think there's a lot to the task with humans with a fundamental context advantage

that we want humans to do for a long time.

And then giving people the skills to do that valuable work to complement the wonderful work the coding agent is doing,

that seems to be the path that will be on for a long time to come.

And this is why, I think you've probably seen, with coding agents being the wonderful things they are,

the number of job postings for software engineers is up, because as software engineers and AI engineers become more productive,

we want a lot more of them.

And businesses I know, even my teams, we just can't seem to find enough skilled AI engineers.

100

And I think this will continue.

101

Yeah, so let's dig into that.

102

Let's imagine two developers who are too strong developers, but one gets better results than the other.

103

What would the stronger developer be doing that the weak one isn't doing today?

104

You know, this is a great question.

105

And when we're mapping out the AI engineering skills map, that was one of the questions we repeatedly asked ourselves,

106

which is we actually interviewed a lot of people.

107

And one of the standard questions you asked them was think of a great developer, think of a less good developer.

108

What is it that a really great developer does compared to the less good ones?

109

And a lot of the answers were what we wound up distilling into the AI engineering skills map.

110

And it's actually more than one thing.

111

It's actually a lot of very different things.

112

But just to give another example, the first of four key skills we highlighted was the ability to build and deploy AI applications.

113

And it turns out that the key differentiator for AI applications compared to traditional software applications is they are uncertain.

114

Whether you prompt an LOM or trade a supervised learning algorithm, you don't know in advance what outcome you get.

115

And so, school AI developers have come up with

116

or are familiar with a set of techniques to monitor the performance of these systems, often in a Cisco way,

117

and to drive a distant error analysis and evals loop to make progress in a systematic way.

118

And so it was by asking questions like that

119

and reflecting on our own experiences that we then tried to systematically map out the not one or two,

120

but frankly, the very large number of gaps between skilled developers and novice level developers.

121

And we tried to distill

122

that into what we call the AI engineering skills map to

123

then try to work systematically to help people go from your less skilled expert level and all of these really valuable skills.

124

Is the skills map itself for anyone to use, mostly for software engineers, people with background?

125

How should people think about the skills map itself?

126

Yeah, so we published, deep into that, we published a weekly newsletter called The Batch.

127

So for five weeks in a row, I wrote about nothing but the AI engineering skills map.

128

And actually no other companies that are now looking to structure curricula around our AI engineering skills, which is actually pretty cool.

129

But I feel like for individuals, there's a way to understand what being excellent, which many of you already are,

130

but where you're already in other places where you want to become more excellent.

131

And then one thing deep learning.ai is working hard on is

132

to then create those paths for people to become skilled at AI engineering.

133

But I think the educational space, both DeepLander AI

134

and other companies still have work to do to help people

135

develop clearer paths to become skilled broadly at all of these AI engineering schools.

136

I'm curious, what are you seeing in terms of people who are pouring in?

137

Is it experienced developers?

138

Basically, there probably is some sort of curve where there's these experienced developers who don't want to let go.

139

I mean, myself, I loved the getting in the zone of coding, and it took me a long time before I was like,

140

okay, now I just let the agent do it.

141

Are you seeing this shift slowly happen where people are like, okay, I'm giving up and I'm shifting all of it to skills first?

142

Yeah, it's interesting, actually.

143

You know, I don't know, it's funny.

144

I actually don't miss coding by hand.

145

Yeah.

146

Yeah.

147

But actually, do you, Do you miss the, I don't know, do you get like in the zone,

148

you know, when you just kind of lock in on this problem, you had to go to Stack Overflow and copy and paste 50,000 things.

149

Maybe you didn't.

150

I did.

151

And then, you know, you spend three hours on the problem and finally it clicks.

152

I don't kind of get that vibe, I guess, anymore.

153

But yeah, I also.

154

Yeah.

155

Yeah.

156

Yeah.

157

I think, I bet you, I bet a lot of you have this problem too.

158

Remember before AI, we used to have a list of priorities we wanted to work on, but couldn't finish.

159

Now, my list, and I'm going to guess yours too, has gotten way longer.

160

Now that AI has supposedly made us more productive.

161

So I find that for myself, there's so many projects that we work on and don't have time to work on.

162

And even as our capabilities grew, certainly my personal ambitions grew maybe even faster than our capabilities.

163

And so, yeah, it's a different type of vibe, right?

164

I think starting a coding agent before you go to bed to see what it comes up with the next morning

165

is a different way of getting into the zone, I guess, than debugging some weird JavaScript syntax.

166

But I have to admit, I seem to like the new vibe more than the old one.

167

Yeah.

168

Yeah, we're definitely getting more dumb, that's for sure.

169

Actually, I'm curious how you design a curriculum in such a rapidly changing market.

170

Do you foresee that you're going to have to change this curriculum every single year, every month?

171

How are you iterating on it?

172

You know, it's interesting.

173

I feel like the hype is that AI advances so fast.

174

Everything changes every three months.

175

The AI engineering skills map, the one piece that does change the fastest is coding agents.

176

And the way we code now is very different than three months ago, very different than six months ago.

177

So the use of coding agents is changing very rapidly.

178

But when you look at the other parts of the schools that I find really valuable, the way we build and deploy AI applications,

179

there's a lot of fundamental knowledge about how to steer these systems, how to deploy them, how to monitor them, how to update them.

180

That is actually changing much slower than the PR hype says.

181

One of the funny thing, at least before Astra, I think Astra may have changed, I'm not sure.

182

It turns out most AI systems, they're not very good data scientists, they're not very good AI engineers.

183

You kind of ask it, what should I do in a project?

184

And for the most part, and frankly, data science, right?

185

I now don't do my data science work by hand, you know, no more coding up handers, data frames, whatever.

186

I'm still using it on the backend, but I now use AI agents to do a lot of my data science work for me.

187

And then frankly, it just makes really weird decisions.

188

It comes to really weird conclusions.

189

I hope that frontier models will get better, but somehow there's a lot of understanding the fundamentals to make trade-offs.

190

And I see that a lot of engineering is making trade-offs, right?

191

You know, cost latency and speed, reliability.

192

And the challenge is until you understand the fundamentals, you often don't even know what trade-offs exist to be made,

193

which is why when someone vipe codes without understanding, very often the coding agent will make a bunch of trade-offs

194

that you didn't even know it made a trade-off and just bites you later.

195

So I find that people that are good engineers understand the fundamentals in many, many parts of the skills needed just make much better decisions.

196

But I'm also encouraged at what's now possible to do when you vipe code without understanding.

197

But I think really good engineers just do such vastly better work than, you know, any serious engineers.

198

Yeah.

199

Yeah.

200

And actually on that one, like, as part of the skills map, you talk about shaping the build.

201

I found this kind of an interesting concept.

202

Maybe you can explain what you mean by shaping the build?

203

Yeah.

204

So as building has become easier, the bottleneck is less building, but deciding what to build.

205

And so previously, there used to be a lot of, let's say front-end engineers.

206

But now front-end engineers with AI systems can also do a lot more backend than was possible.

207

I'm personally much stronger on backend and front-end,

208

but now, frankly, I'm maybe like a bad front-end developer with AI systems.

209

But so a lot of developers have gone from a more narrow role to being a full stack developer.

210

But then even beyond that, it turns out that if a developer builds something and needs to wait for a product manager to get customer feedback,

211

and steer what's built next, that's much slower than the developer themselves has a little bit of product instinct, a little bit of product gut,

212

or can talk to a couple customers or users and get feedback and keep driving the process forward.

213

So in development, what I'm seeing is a lot of people

214

are expanding their roles from just implementation to deciding what to build.

215

And it does not mean engineers should become product managers, but it does mean that engineers that can make some product decisions

216

or more architecture decisions are much more productive than engineers that play the more narrow-sider role from a few years ago.

217

And so we call this shaping the bill where engineers that can influence product decisions,

218

have some product guts, also hope to think through the bill process.

219

Like, is this a good time to build an MVP?

220

Or is it a good time to invest in building really robust architecture

221

and thinking about scale or is this a good time to go to customers to get feedback

222

or is this a good time to do some research to better understand what back-end technology stack you use so developers

223

that can steer the building process end up contributing much more to the overall um comfier project how much

224

then should they spend this time kind of designing the system one of my favorite skills i don't know

225

if you know is this like a grill with docs creates these like architectural decisions

226

and it spends an hour grilling you exactly what you want to build.

227

It's like how much time do you think people should be focused on upfront what they want to build,

228

how they want to build it versus like just go build your MVP and then fix it later on iterating?

229

Yeah, I think it's a real question.

230

The challenge to answer that question is that the answer is stage dependent and it depends a lot on what

231

Jeff Bezos calls one-way door versus two-way doors.

232

directionally in the early stages of a project, frankly, whatever idea you have, type it into coding agent, build it, see what you get.

233

Solace can do it in a safe way and don't leak sensitive data, or just don't, so that's their protection for bad outcomes.

234

But I find that a lot of projects, one of the challenges about AI engineering is, the right decision is very stage dependent.

235

I find that for early stage projects, Solace can do it in a responsible, safe way, build a quick and dirty prototype,

236

see what happens, throw it away, build a quick and enterprise, see what happens and drive rapid learnings.

237

Then there's also a time and place, thinking carefully about architecture, figure out what's the rewrite ratio, what are the customer requirements,

238

what are sensitive data, thinking through your security infrastructure, and then doing that.

239

One thing I've seen is, I've known a lot of engineers that are really good at the zero to one startup phase.

240

I've also known a lot of good engineers, good at the mature systematic phase

241

but sometimes depending on the stage of project you're on the skill

242

and the speed and the how to think about velocity versus protecting from downside risk shifts

243

and even the use of coding agents

244

you see a lot of people talk about how oh you should always plan it out write a long spec

245

and there is a place for that and then sometimes there's a place

246

and you know you're going to go to bed in 20 minutes, just bang out some stuff, have a coding agent work for a few hours

247

and see what you get the next morning and and i think

248

that stage dependent answer has been very tricky for people to learn okay i need to switch gears

249

and i need to ask you a question

250

because i was uh chatting to swix yesterday in from latent space i don't know

251

if you know him but he's here covering uh this week

252

and he said something spicy i might misquote him but he said something like, oh, schools are dead, or the way that we're changing,

253

the way that we have to learn has to completely change.

254

I'm very, I'm sure you get this question a lot.

255

I'm curious on your take on like, how will learning change?

256

Put us forward 10 years.

257

How are we learning?

258

Surely does it look the same as what we're doing now in schools?

259

Completely different?

260

So it will change.

261

So we're having two observations.

262

So first, I'm going to say something obvious when we sound controversial, but chatbots are terrible for learning, right?

263

I love LMS, use them a lot, currently pro AI.

264

At the same time, on university campuses and then, you know, K-12, we know that students that use LMS do better on homeworks,

265

but worse than final exam.

266

And educators have known this intuitively, students have known this intuitively,

267

but the rigorous studies are now increasingly coming out that show that cognitive offloading to an LOM, meaning if a student doesn't know anything for you,

268

you get more work done, but you learn less.

269

And I think even though the rigorous studies on this are coming out in K-12

270

and in higher education universities in formal educational contexts, I think people still underestimate the degree to which this is happening among working adults.

271

I find that, you know, I love my coding agents, helps me do a ton of work

272

but the reduced thinking I have to do I think there are certain things

273

that and then to be clear there are ways to use OMS

274

that do improve learning just like I think there are ways to use TikTok that's great for learning

275

but the vast majority of ways

276

that the vast majority people use social media does not result in learning

277

and the vast majority of ways the vast majority people use OMS does not result in learning

278

so now the flip side of this though is I think we can do better.

279

So the teams I work with including Coursera, Udemy, DevEarned AI, LearnVector are working hard to create new learning experiences

280

that are not focused on getting stuff done but rather on developing rather on focusing on accelerating human development.

281

Here in Silicon Valley we're very excited about our front-end AI labs

282

and accelerating AI development and that's great very much in favor of

283

that in LearnVector

284

which was a recent announced company funded by with a Coursera's initial investor

285

I'm actually really excited about not accelerating not just accelerating AI development

286

but accelerating human development and the way

287

that we're operating is building LearnVector into a frontier AI into a frontier human development lab and as one example

288

I feel fortunate that Coursera participated in changing education 15 years or so ago,

289

but today looking back on that experience which still works, it feels very much one-to-many where we create one course

290

and everyone kind of takes the same or very similar course

291

and it works nothing's wrong with that but the technology now exists for us to create much more one-to-one experiences

292

and it will be much better.

293

So LearnVector hasn't yet announced exactly what products we have,

294

but I'm actually very optimistic from the internal quality types we have and we will have more to share in months.

295

That's super exciting.

296

Okay, I want to leave the crowd with something tangible.

297

So let's say you could design a way that everyone here could spend the next four weeks

298

upskilling to become the best AI developers, how should they spend their time for the next four weeks?

299

Where should they go?

300

What should they learn?

301

What tools should they adopt?

302

Anything that comes to mind?

303

In the case of AI engineering, DeepLandEye's focus is to help developers become skilled at AI engineering,

304

or if you're already skilled, to become even more skilled.

305

working hard on even improving what

306

Deep Learning AI offers.

307

But I actually find myself taking a lot of Deep Learning AI courses myself to learn what are the frontier tools,

308

kind of what's the latest in a voice stack or in generative UI or, you know, building local memory for agents.

309

So I find that maybe as an insider, I see a lot of ways I wish deep learning were even better.

310

But I think that my own learning, actually a lot of it has been with Deep Learning AI.

311

I hope you all will find that whole form.

312

Cool.

313

Keep building.

314

I think all of you are builders.

315

I still find myself waking up in the middle of the night too often to check on the coding agents up to.

316

Do you fire off on your phone as you wake up in the middle of the night?

317

Yeah.

318

I don't know.

319

I think coding on the phone has been so wonderful.

320

Do you text or do you use voice to chat to your coding agents?

321

I use text a lot more than voice coding, with the usual Mac Mini.

322

Yeah, OK.

323

Yeah.

324

OK, that's cool.

325

There's a bit of inside baseball.

326

I'm very curious about your setup, actually.

327

OK, first of all, I know that you had a very strict schedule.

328

And so we're incredibly grateful that we could fit you in, and you could fit us into your timing.

329

So thank you so much for coming.

330

Coming to Select is really a pleasure and an honor to have you here.

331

Thank you so much.

332

Just saying, you know, of all the credentials you rattled off of me just now, the thing that's going through my mind,

333

my one credential you didn't mention was I'm also a proud father of two choy-yong.

334

So, thank you.

335

And so the reason I need to dash is because I actually need to go pick them up from school.

336

That's super important.

337

Okay, we'll let you go then.

338

Thanks so much, Harvey.

339

Thank you, Andrew.

340

That's it, that's it.

341

That's it.

342

That's it.

343

It's a bird.

344

Right in the game, then do you want to let him never do not dance?

345

Oh, hit the noise of opera and a bird to repeat.

앱 다운로드

유창하게 말하는 데 필요한 모든 것

AI 발음 평가문장마다 점수 확인

IPA 발음 연습모든 소리 마스터

단어 학습나만의 단어장 만들기

단어 게임놀면서 외우기

QR 스캔

Download on theApp Store Get it onGoogle Play

FOR YOU

이 레슨의 어휘와 말하기 포인트

이 말하기 레슨은 영상 “Andrew Ng on Coding Agents and Deciding What to Build”을(를) 바탕으로 합니다. 가장 자주 반복되는 단어는 다음과 같습니다: skill, engineering, agent, developer, coding. 이 영상에는 섀도잉할 문장 345개와 단어 4552개가 있습니다. 말하는 구간의 길이는 26:17입니다. 화자는 분당 약 173단어로, 일상 대화에 가까운 자연스러운 속도로 말합니다. 단어의 83%가 영어에서 가장 많이 쓰이는 3,000단어에 속합니다. 나머지는 연습 전에 미리 확인해 두세요.

이 영상의 핵심 어휘

영상에 나오는 익혀 둘 만한 단어 15개를 발음, 뜻과 함께 정리했습니다.

단어	발음	뜻
skill 명사	/skɪl/	기술, 스킬
fundamental 형용사	/ˌfʌn.dəˈmɛn.təl/	기본적
vast 형용사	/væst/	광대하다, 거대하다
frankly 부사	/fɹæŋkli/	솔직히
infrastructure 명사	/ˈɪnfɹəˌstɹʌkt͡ʃə/	기반시설, 기간시설
curious 형용사	/ˈkjʊɹ.i.əs/	호기심이 많은, 궁금하다
stack 명사	/stæk/	무더기
frontier 명사	/ˈfɹʌntɪə/	경계, 국경
prompt 동사	/pɹɑmpt/	부추기다
deploy 동사	/dɪˈplɔɪ/	배치하다
architecture 명사	/ˈɑː.kɪˌtɛk.t͡ʃə/	건축, 건축학
monitor 명사	/ˈmɑ.nɪ.tɚ/	모니터
rapidly 부사	/ˈɹæpɪdli/	급속(急速)히
feedback 명사	/ˈfiːdˌbæk/	피드백, 비평
versus	/ˈvɝsəs/	대

영상에 나오는 구동사

단어	발음	뜻
come out 동사	/ˌkʌm ˈaʊt/	나오다
give up 동사		항복하다
go away 동사		떠나다, 떠나가다
pull out 동사		회수(回收)하다

따라 말해 볼 만한 문장

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

You know, I don't know, it's funny.
I actually don't miss coding by hand.
How are you iterating on it?
You kind of ask it, what should I do in a project?
I'm curious on your take on like, how will learning change?

이 영상의 문법

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

문형	영상 속 표현
“used to” used to + 동사 — 지금은 아닌 과거의 습관이나 상태	used to have · used to be
현재완료 have/has + 과거분사 — 과거의 일이 지금도 관련이 있을 때	I've been · I've just been · you've probably seen
수동태 be + 과거분사 — 누가 하는지보다 무슨 일이 일어나는지에 초점	being built · are built · been really blessed
관계절 who / which + 절 — 사람이나 사물에 대한 추가 정보	people who work · anyone who doesn · skills, which is

주의할 발음

화자는 I'm, don't, you're 같은 축약형과 약화된 형태를 87번 사용합니다. 들리는 대로 짧게 발음하세요.

“th” 소리: thick /θɪk/, algorithm /ˈælɡəɹɪðm̩/
“sh”와 “zh” 소리: ratio /ˈɹeɪ.ʃoʊ/, conclusion /kənˈkluːʒən/, implementation /ˌɪmplɪmənˈteɪʃən/, examination /ɪɡˌzæm.ɪˈneɪ.ʃən/, controversial /ˌkɑn.tɹəˈvɝ.ʃəl/
긴 단어 — 강세 위치에 주의: developer /dɪˈvɛləpɚ/, fundamental /ˌfʌn.dəˈmɛn.təl/, accelerate /ɪkˈsɛl.əˌɹeɪt/, infrastructure /ˈɪnfɹəˌstɹʌkt͡ʃə/, architecture /ˈɑː.kɪˌtɛk.t͡ʃə/

한국어 화자가 어려워하는 소리:

/f/ — ㅍ(/p/)으로 바꾸지 말고 윗니를 아랫입술에 대기: fundamental /ˌfʌn.dəˈmɛn.təl/, frankly /fɹæŋkli/, infrastructure /ˈɪnfɹəˌstɹʌkt͡ʃə/, frontier /ˈfɹʌntɪə/, feedback /ˈfiːdˌbæk/
/v/ — ㅂ(/b/)과 구별하기: developer /dɪˈvɛləpɚ/, vast /væst/, versus /ˈvɝsəs/, productive /pɹəˈdʌk.tɪv/, vibe /vaɪb/
/z/ — ㅈ이 아니라 성대를 울리는 /s/: enterprise /ˈɛntəˌpɹaɪz/, examination /ɪɡˌzæm.ɪˈneɪ.ʃən/, transaction /tɹænˈzækʃən/, observation /ˌɑbzɚˈveɪʃn̩/, supposedly /səˈpoʊ̯.zɪd.li/

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, skill, fundamental, vast 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: Andrew Ng on Coding Agents and Deciding What to Build - 영상으로 영어 말하기 배우기

연습 모드 선택

앱 다운로드

추천 영상

Alexandr Wang on what matters in an age of abundant intelligence

He Realized his Mistake

View From The Top with Roelof Botha, Managing Partner of Sequoia Capital

MIT Introduction to Deep Learning | 6.S191

GS.TS. Po-Shen Loh, ĐH Carnegie Mellon | Rèn tư duy ngược để không bị AI bào mòn | TQKS #129

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

Building Anthropic | A conversation with our co-founders

The Only SaaS Moats Left in 2026

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

What AI can (and can't) currently do in a real lab | Jennifer Doudna

NVIDIA GTC 2025 - Keynote Highlights by NVIDIA CEO Jensen Huang

How to Become an AI Product Manager in 2026 | Ex-Google, Microsoft

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