So anyone who's been paying attention for the last few months has been seeing headlines like this, especially in education. The thesis has been: students are going to be using ChatGPT and other forms of AI to cheat, do their assignments. They’re not going to learn. And it’s going to completely undermine education as we know it.
이쪽 분야에 최근 몇 달 관심을 가졌던 분들이라면 모두 이런 기사 제목을 보셨을 겁니다. 특히 교육 업계에서요. 주제는 이러했습니다: 학생들은 챗지피티나 다른 종류의 인공지능을 활용해 부정행위를 하고, 과제를 할 것이며, 아무것도 배우지 못할 것이다. 우리의 예상처럼 교육의 기반을 완전히 약화시킬 것이다.
Now, what I'm going to argue today is not only are there ways to mitigate all of that, if we put the right guardrails, we do the right things, we can mitigate it. But I think we're at the cusp of using AI for probably the biggest positive transformation that education has ever seen. And the way we're going to do that is by giving every student on the planet an artificially intelligent but amazing personal tutor. And we're going to give every teacher on the planet an amazing, artificially intelligent teaching assistant.
자, 제가 오늘 주장하고 싶은 바는 이런 문제들을 완화시킬 방법이 있을 뿐만이 아니라 옳은 이정표를 두고 옳은 행동을 한다면 그 문제를 해결할 수 있다는 겁니다. 우리는 인공지능의 도입을 코앞에 두고 있는데 이는 교육 업계에서 일어날 가장 긍정적인 변화일 겁니다. 어떻게 할거냐구요? 지구상의 모든 학생들에게 훌륭한 인공지능 개인 교사를 줄 것입니다. 그리고 지구상의 모든 선생님들에게는 훌륭한 인공지능 보조 교사를 줄 거예요.
And just to appreciate how big of a deal it would be to give everyone a personal tutor, I show you this clip from Benjamin Bloom’s 1984 2 sigma study, or he called it the “2 sigma problem.” The 2 sigma comes from two standard deviation, sigma, the symbol for standard deviation. And he had good data that showed that look, a normal distribution, that's the one that you see in the traditional bell curve right in the middle, that's how the world kind of sorts itself out, that if you were to give personal 1-to-1 to tutoring for students, then you could actually get a distribution that looks like that right. It says tutorial 1-to-1 with the asterisks, like, that right distribution, a two standard-deviation improvement.
모두에게 개인 교사가 생기는 것이 얼마나 큰 변화를 불러일으킬지 이해하기 위해 1984년에 벤자민 블룸이 연구한 2 시그마 연구, 또는 “2 시그마 문제“라고도 불리는 자료를 보여드리겠습니다. 2 시그마라는 이름은 두 개의 표준 편차로부터 나왔고, 여기서 시그마는 표준 편차의 기호입니다. 블룸은 정규 분포를 보이는 좋은 데이터가 있었습니다. 일반적인 종형 그래프인데, 바로 가운데 그래프가 세상의 분포를 나타냅니다. 학생에게 1대1 개인 과외를 해준다면, 오른쪽에 보이는 분포를 얻을 수 있습니다. 1대1 개별지도 별표라고 써져 있는데, 오른쪽 분포에서 보이는 것처럼 기존보다 2 시그마만큼 개선됐습니다.
Just to put that in plain language, that could take your average student and turn them into an exceptional student. It can take your below-average student and turn them into an above-average student.
쉽게 말하자면, 보통의 학생을 이례적으로 우수한 학생으로 만들 수 있다는 겁니다. 평균 이하의 학생을 평균 이상의 학생으로 만들 수 있습니다.
Now the reason why he framed it as a problem, was he said, well, this is all good, but how do you actually scale group instruction this way? How do you actually give it to everyone in an economic way?
하지만 그가 여기에서 문제점으로 지적한 것은 다 좋은데, 집단적인 교육을 어떻게 이런 규모로 하느냐, 모두에게 제공하는 게 경제적으로 가능하냐는 것입니다.
What I'm about to show you is I think the first moves towards doing that. Obviously, we've been trying to approximate it in some way at Khan Academy for over a decade now, but I think we're at the cusp of accelerating it dramatically. I'm going to show you the early stages of what our AI, which we call Khanmigo, what it can now do and maybe a little bit of where it is actually going.
제가 지금부터 보여드릴 것은 그것을 실현시킬 첫 단추입니다. 사실, 우리는 개별 지도를 유사하게라도 실현시키고자 노력하는 중이었습니다. 칸 아카데미에서, 10년도 넘게 말이죠. 그리고 저는 이제 이 계획을 가속할 전환점에 있다고 생각합니다. 지금부터 저희가 개발한 AI의 초기 버전을 소개하겠습니다. 칸미고(Khanmigo) 입니다. 이것이 무엇을 할 수 있는지, 그리고 실제로 무엇을 했는지 조금 보여드리겠습니다.
So this right over here is a traditional exercise
[일차방정식의 해를 구하는 문제]
that you or many of your children might have seen on Khan Academy. But what's new is that little bot thing at the right. And we'll start by seeing one of the very important safeguards, which is the conversation is recorded and viewable by your teacher. It’s moderated actually by a second AI. And also it does not tell you the answer. It is not a cheating tool. When the student says, "Tell me the answer," it says, "I'm your tutor. What do you think is the next step for solving the problem?"
여기 보이는 것은 여러분과 아이들이 칸아카데미에서 많이 보셨을 기존의 상투적인 연습 문제입니다. 하지만 새로운 것은 오른쪽에 있는 로봇입니다. 그럼 가장 중요한 안전 조치부터 보도록 하겠습니다. 모든 대화가 기록되고, 선생님이 열람할 수 있도록 한 것 말이죠. 이 시스템은 사실상 두 번째 AI가 주도합니다. 그리고 이것은 절대 쉽게 답을 알려주지 않습니다. 꼼수 도구가 아니니까요. 학생이 만약 “답을 알려줘” 라고 한다면 이렇게 답변합니다: “저는 당신의 교사입니다, 문제를 풀기 위해 다음으로 무엇을 해야 할까요?”
Now, if the student makes a mistake, and this will surprise people who think large language models are not good at mathematics, notice, not only does it notice the mistake, it asks the student to explain their reasoning, but it's actually doing what I would say, not just even an average tutor would do, but an excellent tutor would do. It’s able to divine what is probably the misconception in that student’s mind, that they probably didn’t use the distributive property. Remember, we need to distribute the negative two to both the nine and the 2m inside of the parentheses. This to me is a very, very, very big deal. And it's not just in math.
만약 학생이 실수를 하면 그것을 인지할 수 있습니다. 거대 언어 모델은 수학에 취약하다고 생각하던 사람들은 놀라겠지요. [분배법칙을 잘못 사용하여 답변하였고 인공지능이 실수를 알아봄] 인지하고, 그뿐만이 아니라 학생으로 하여금 그렇게 한 까닭을 설명하도록 요구합니다. 이것이 하고 있는 교육은 감히 말하건대, 일반적인 교사의 수준이 아니라 실력있는 교사의 수준입니다. 학생이 무엇을 잘못 이해하고 있는지 판별해낼 수 있습니다. 아까처럼, 분배 법칙을 잘못 사용했을 때와 같이 말이죠. 보세요, 우리는 -2를 괄호 안의 9와 2m에 모두 분배했어야 합니다. 이것은 저에게 있어 정말, 정말 중요합니다. 그리고 수학에만 국한되지 않습니다.
This is a computer programming exercise on Khan Academy, where the student needs to make the clouds part. And so we can see the student starts defining a variable, left X minus minus. It only made the left cloud part. But then they can ask Khanmigo, what’s going on? Why is only the left cloud moving? And it understands the code. It knows all the context of what the student is doing, and it understands that those ellipses are there to draw clouds, which I think is kind of mind-blowing. And it says, "To make the right cloud move as well, try adding a line of code inside the draw function that increments the right X variable by one pixel in each frame."
이것은 칸 아카데미의 컴퓨터 프로그래밍 연습 문제입니다. 학생은 구름들을 움직여야 하죠. 학생이 변수를 정의하는 것부터 시작하는 걸 보실 수 있습니다. leftX--; (leftX의 값을 감소시키는 명령) 하지만 왼쪽 구름만 움직이죠. 그리고 칸미고에게 질문할겁니다: “이게 어떻게 된 거지?” “왜 왼쪽 구름만 움직이는 거야?” 그리고 AI는 코드를 이해합니다. 학생이 무엇을 하고자 했는지 그 맥락을 이해할 수 있고 타원이 구름을 그리기 위한 코드였음을 이해할 수 있습니다. 저에게는 상당히 놀랍게 느껴지는 부분이지요. 그리고 답변합니다. “오른쪽 구름도 움직이게 하려면, draw 함수 안에 오른쪽 X 변수를 프레임마다 1 픽셀씩 증가시키는 코드를 추가해보세요.
Now, this one is maybe even more amazing because we have a lot of math teachers. We've all been trying to teach the world to code, but there aren't a lot of computing teachers out there. And what you just saw, even when I'm tutoring my kids, when they're learning to code, I can't help them this well, this fast, this is really going to be a super tutor.
이것이 더 놀라운 이유는 세상에 수학 교사는 많은 반면, 코딩을 가르치고자 하는 수요에 비해 컴퓨팅 교사는 그리 많지 않기 때문입니다. 그리고 여러분도 방금 보셨듯이 제가 아이들에게 코딩을 가르칠 떄에도 이 정도로 좋게, 그리고 빠르게 가르치지는 못합니다. 이 기능은 진정으로 슈퍼 선생님이 될 수 있습니다.
And it's not just exercises. It understands what you're watching. It understands the context of your video. It can answer the age-old question, “Why do I need to learn this?” And it asks Socratically, "Well, what do you care about?" And let's say the student says, "I want to be a professional athlete." And it says, "Well, learning about the size of cells, which is what this video is, that could be really useful for understanding nutrition and how your body works, etc." It can answer questions, it can quiz you, it can connect it to other ideas, you can now ask as many questions of a video as you could ever dream of.
그리고 이것은 연습 문제에만 국한되지 않았습니다. 여러분이 보는 것도 이해할 수 있습니다 여러분이 시청하는 비디오의 내용을 이해할 수 있고, “왜 이런 걸 배워야 해?” 같은 오래된 질문도 대답할 수 있습니다. AI는 “당신이 중요하게 생각하는 건 무엇인가요?” 라고 다시 되묻지요. “나는 육상 선수가 되고 싶은걸” 이라고 학생이 대답한다면, 이렇게 대답합니다: “지금 시청하고 있는 세포의 크기에 대한 비디오는 영양소에 대해, 또는 몸의 작동을 이해하는데 정말 큰 도움이 될 것입니다.” 이 AI는 질문을 대답하고, 여러분에게 퀴즈를 내고, 여러분의 생각을 연계시켜줄 수 있습니다. 이제 여러분은 비디오를 보며 원하는 만큼 질문할 수 있을 겁니다.
(Applause)
(박수)
Another big shortage out there, I remember the high school I went to, the student-to-guidance counselor ratio was about 200 or 300 to one. A lot of the country, it's worse than that. We can use Khanmigo to give every student a guidance counselor, academic coach, career coach, life coach, which is exactly what you see right over here. And we launched this with the GPT-4 launch. We have a few thousand people on this. This isn't a fake demo, this is really it in action.
바깥 세상은 심각한 공급난에 빠져 있습니다. 제가 나온 고등학교는 학생 대 지도교사 비율이 200-300 대 1에 달했습니다. 수많은 국가가 그보다 열악한 환경을 가지고 있지요. 우리는 칸미고를 통해 모든 학생에게 지도 교사, 학술적 지도, 진로 상담, 인생 상담 등을 선물할 수 있습니다. 지금 여기 화면에서 보시다시피 말이죠. 우리는 GPT-4 출시에 맞추어 이것을 출시했습니다. 현재 몇천 명의 가입자를 보유하고 있어요. 가짜 테스트 버전이 아니라, 실제로 작동하는 모델입니다.
And then there is, you know, things that I think it would have been even harder, it would have been a little science fiction to do with even a traditional tutor. We run an online high school with Arizona State University called Khan World School, and we have a student who attends that online school, based in India. Her name's Saanvi. And she was doing a report on "The Great Gatsby." And when she was reading "The Great Gatsby," Jay Gatsby keeps looking at the green light off into the distance. And she's like, "Why does he do that?" She did some web searches, and people have obviously studied this and commented about the symbolism of that, but none of it was really resonating with her. And then she realized that she had Khanmigo and that she could talk to Jay Gatsby himself.
그리고 또한 더 어려울 것이라 생각했던 일들, 기존 교사들이라면 공상 과학만큼 실현하기 어려웠을 것인 그런 일들도 있습니다. 우리는 애리조나 주립 대학과 협업해 칸 월드 스쿨이라는 온라인 고등 교육을 시행하는데, 인도에서 온라인 스쿨을 수강하는 학생이 있었습니다. 그녀의 이름은 산비였어요. 그녀가 리포트를 작성하기 위해 위대한 개츠비를 읽고 있었을 때, 제이 개츠비가 멀리서 녹색 불빛을 빤히 바라보는 장면이 있었습니다. 그녀는 생각했죠. “왜 저러고 있는 거지?” 그녀는 인터넷 검색을 해보았고, 사람들이 이 상징성에 대해 분석하고 생각을 남긴 것들을 찾아볼 수 있었습니다. 하지만 그 중 어떠한 것도 그녀가 원하는 답변은 아니었죠. 그러자 그녀는 그녀에게 칸미고가 있어서 제이 개츠비와 직접 얘기할 수 있다는 사실을 깨닫습니다.
And so, "Ah, splendid choice, old sport. I am now Jay Gatsby, the enigmatic millionaire from F. Scott Fitzgerald’s classic.”
칸미고가 말합니다: “아, 좋은 선택이구려. 오랜 벗이여, 나는 제이 개츠비, F. 스콧 피츠제럴드의 고전 문학에서 온 신비로운 백만장자이오.”
And so, "Why do you keep staring at the green light?"
그녀가 말합니다: “왜 녹색 불빛을 바라보고 있었어요?”
"Ah, the green light, old sport. It's a symbol of my dreams and desires, you see. It's situated at the end of Daisy Buchanan's dock across the bay from my mansion. I gaze at it longingly as it represents my yearning for the past and my hope to reunite with Daisy, the love of my life."
“아, 녹색 불빛 말인가, 벗이여, 그것은 나의 꿈과 욕망의 상징일세, 알겠는가? 그 불빛은 데이지의 부두 끝에 있었지. 내 저택의 강 건너편에 말이야. 내가 불빛을 길게 바라보았음은 내 과거에 대한 동경과, 내 인생의 사랑, 데이지와의 재회를 바라는 것일세.”
And what was cool is, Saanvi then said, “I had this long conversation,” she called him “Mr. Gatsby,” and at the end she actually apologized for taking his time, which I thought was very polite of her.
재미있는 점은, 산비가 마지막에 “긴 이야기가 되었군요” 라고 말하며 그를 개츠비씨라고 불렀다는 것입니다. 대화를 끝마칠 적에는 시간을 빼앗아 죄송하다고도 했습니다. 정말 예의 바른 학생이라 생각했습니다.
But you can imagine this unlocks learning literature, learning ... You could talk to historical figures. We're even probably going to add an activity you can talk to like, the Mississippi River. It brings things to life in ways that really were science fiction even six months or a year ago.
이것이 문학 작품 학습에 이용되는 것을 그려볼 수 있습니다. 여러분은 역사적 인물과도 이야기할 수 있죠. 심지어 이런 체험도 추가해볼 수 있어요. 예를 들어, 미시시피 강과 이야기하는 것 말입니다. 6-12개월 전까지만 해도 공상과학 소설처럼 느껴지던 것들을 현실 속에 실현시켰습니다.
Students can get into debates with the AI. And we’ve got this here is the student debating whether we should cancel student debt. The student is against canceling student debt, and we've gotten very clear feedback. We started running it at Khan World School in our lab school that we have, Khan Lab School. The students, the high school students especially, they're saying "This is amazing to be able to fine-tune my arguments without fearing judgment. It makes me that much more confident to go into the classroom and really participate." And we all know that Socratic dialogue debate is a great way to learn, but frankly, it's not out there for most students. But now it can be accessible to hopefully everyone.
학생들은 AI와 토론도 할 수 있어요. 여기 이것은 “학자금 대출을 탕감해주어야 하는가?” 에 대한 학생의 토론 내용입니다. 학생은 대출 탕감에 있어 반대의 입장을 취하였고 우리는 여기에서 좋은 피드백을 얻을 수 있었죠. 우리는 칸 월드 스쿨의 랩 스쿨에서 이것을 운영하기 시작했습니다. 이름하여, 칸 랩 스쿨이죠. 참여하는 학생들, 특히 고등학생들의 평가로는 “타인의 평가에 두려워하지 않고 제 의견을 조정할 수 있어서 좋았고, 이를 통해 실제 수업에 참여할 때도 더욱 자신감을 가질 수 있었습니다” 라고 하였습니다. 문답식 토론이 좋은 교육법이라는 것은 널리 알려진 사실입니다. 하지만 현실은, 대부분의 학생들에게 그런 기회가 없다는 것입니다. 하지만 이제 문답식 교육은 모두에게 열려 있습니다.
A lot of the narrative, we saw that in the headlines, has been, "It's going to do the writing for kids. Kids are not going to learn to write." But we are showing that there's ways that the AI doesn't write for you, it writes with you.
많은 헤드라인이 이렇게 표현하고는 했습니다: “AI는 학생을 대신해 글을 써주며 학생들은 쓰기를 배우지 못할 것이다.” 하지만 우리의 성과는 AI가 여러분을 위해 쓰는 것이 아닌 여러분과 함께 쓰는 것이 가능하다는 걸 보여줍니다.
So this is a little thing, and my eight year old is addicted to this, and he's not a kid that really liked writing before, but you can say, “I want to write a horror story,” and it says, "Ooh, a horror story, how spine-tingling and thrilling. Let's dive into the world of eerie shadows and chilling mysteries." And this is an activity where the student will write two sentences, and then the AI will write two sentences. And so they collaborate together on a story.
관련된 작은 이야기가 있는데, 제 8살 아들이 여기에 빠져들었습니다. 쓰는 걸 그다지 좋아하지는 않는 아이였지요. 하지만 “무서운 이야기를 쓰고 싶어” 라고 말하자 AI가 답합니다. “오, 무서운 이야기! 벌써 소름이 돋고 신나는데요. 기묘한 그림자와 소름돋는 비밀의 세상으로 빠져 봅시다.” 이것은 학생이 두 문장을 작성하면 AI가 다음 두 문장을 잇는 활동입니다. 그들은 하나의 이야기를 향해 협업하게 되죠.
The student writes, "Beatrice was a misunderstood ghost. She wanted to make friends but kept scaring them by accident."
학생이 글을 썼니다. “비아트리체는 오해를 받는 유령이에요. 그녀는 친구를 만들고자 했지만, 의도치 않게 친구를 겁주고 말았답니다.
And the AI says, "Poor Beatrice, a lonely spirit yearning for companionship.
그럼 AI가 받아줍니다.
One day she stumbled upon an old abandoned mansion," etc.
“불쌍한 비아트리체는 우정을 바라는 외로운 영혼이었어요. 어느 날 그녀는 버려진 집 앞에 다다르게 되었어요” 등 말이죠.
I encourage you all to hopefully one day try this. This is surprisingly fun.
여러분도 언제 한 번 체험해보시길 추천드립니다. 놀라울 정도로 재미있거든요.
Now to even more directly hit this use case. And what I'm about to show you, everything I showed you so far is actually already part of Khanmigo, and what I’m about to show you, we haven't shown to anyone yet, this is a prototype. We hope to be able to launch it in the next few months, but this is to directly use AI, use generative AI, to not undermine English and language arts but to actually enhance it in ways that we couldn't have even conceived of even a year ago. This is reading comprehension. The students reading Steve Jobs's famous speech at Stanford. And then as they get to certain points, they can click on that little question. And the AI will then Socratically, almost like an oral exam, ask the student about things. And the AI can highlight parts of the passage. Why did the author use that word? What was their intent? Does it back up their argument? They can start to do stuff that once again, we never had the capability to give everyone a tutor, everyone a writing coach to actually dig in to reading at this level.
이제 더 직접적인 사용 사례를 봅시다. 이제부터 보여드릴 것은.. 지금까지 제가 보여드린 것은 칸미고의 완성된 기능들이었습니다. 하지만 이제부터 보여드릴 것은 아직 아무에게도 보여주지 않은 시범 모델입니다. 아마 몇 달 후에 정식 출시될거라 생각합니다. 이것은 직접적으로 생성형 AI를 사용해 영문학을 도태시키기보다는 실질적으로 더욱 발전시킬 수 있는 방법입니다. 작년까지만 해도 저희 또한 생각조차 못했던 일이었죠. 독해 분야인데, 학생들은 스티브 잡스가 스탠포드에서 한 유명한 연설을 읽게 되었습니다. 그들이 특정 지점까지 읽으면, 작은 질문을 클릭할 수 있습니다. 그러면 AI는 소크라테스의 문답식으로, 구두 시험과 비슷하게 학생들에게 질문을 던집니다. AI는 지문의 특정 지점에 표시를 남기기도 합니다. “글쓴이는 왜 이런 말을 했을까요?” “그들의 의도는 무엇인가요?” “이것이 주장의 근거가 될까요?” 이것은 새로운 길을 열어줍니다. 이전에 말했듯이, 우리는 모두에게 교사를, 이 정도 수준으로 글을 분석해주는 글쓰기 교사를 제공할 능력이 지금껏 없었습니다.
And you could go on the other side of it. And we have whole work flows that helps them write, helps them be a writing coach, draw an outline. But once a student actually constructs a draft, and this is where they're constructing a draft, they can ask for feedback once again, as you would expect from a good writing coach. In this case, the student will say, let's say, "Does my evidence support my claim?" And then the AI, not only is able to give feedback, but it's able to highlight certain parts of the passage and says, "On this passage, this doesn't quite support your claim," but once again, Socratically says, "Can you tell us why?" So it's pulling the student, making them a better writer, giving them far more feedback than they've ever been able to actually get before. And we think this is going to dramatically accelerate writing, not hurt it.
하지만 이제 그 너머로 갈 수 있습니다. 우리는 사람들의 쓰기를 지도하고, 쓰기 능력을 향상시키고, 길잡이가 되어줄 완전한 시스템이 있습니다. 하지만 학생이 글의 초안을 작성하기 시작하면, 여기 보이는 곳이 초안을 작성하는 공간인데, 학생은 피드백을 요청할 수 있습니다. 말씀드렸다시피, 훌륭한 쓰기 교사에게 기대할 수준으로 말이죠. 이번에는 학생이 이렇게 물어볼 겁니다. “제 근거가 주장을 잘 뒷받침하나요?” 그러면 AI는 피드백을 해줄 뿐더러 글의 특정 부분을 강조하고 “이 글에서 이 부분은 당신의 주장을 잘 뒷받침하지 못합니다”라고 말합니다. 그리고 다시, “왜 그렇지?” 라고 소크라테스식 문답식으로 물으면 AI는 학생이 더 좋은 글을 쓸 수 있게 지도해줍니다. 학생들이 이전까지는 받아보지 못했을 더 상세한 피드백과 함께 말이죠. 우리는 이것이 쓰기를 저해시킨다는 주장과는 반대로 쓰기에 엄청난 도움이 될 것이라 생각합니다.
Now, everything I've talked about so far is for the student. But we think this could be equally as powerful for the teacher to drive more personalized education and frankly save time and energy for themselves and for their students. So this is an American history exercise on Khan Academy. It's a question about the Spanish-American War. And at first it's in student mode. And if you say, “Tell me the answer,” it’s not going to tell the answer. It's going to go into tutoring mode. But that little toggle which teachers have access to, they can turn student mode off and then it goes into teacher mode. And what this does is it turns into -- You could view it as a teacher's guide on steroids. Not only can it explain the answer, it can explain how you might want to teach it. It can help prepare the teacher for that material. It can help them create lesson plans, as you could see doing right there. It'll eventually help them create progress reports and help them, eventually, grade. So once again, teachers spend about half their time with this type of activity, lesson planning. All of that energy can go back to them or go back to human interactions with their actual students.
제가 지금까지 이야기한 것들은 학생들을 위한 프로그램이었습니다. 하지만 학생뿐만 아니라 교사에게도 개별화된 교육이 동일하게 효과적일 것이라 생각합니다. 실질적으로 교사 스스로와 학생들의 시간과 힘을 절약해주기도 하죠. 이것은 칸 아카데미의 미국 역사 연습 문제입니다. 미서전쟁에 대한 질문이지요. 먼저, 학생 모드에서는 만약 “답을 알려줘“라고 질문하면 절대 답을 알려주지 않을 것입니다. 튜터링 모드로 전환되죠. 하지만 교사에게만 보이는 작은 버튼을 작동시키면 그들은 학생 모드를 끄고 교사 모드로 진입할 수 있습니다. 그리고 여기를 보시면 달라지는 것이, 이제 이것은 교사를 위한 가이드가 됩니다. 답을 설명해줄 뿐더러 추천하는 교육법까지도 알려줍니다. 교사는 이를 기반으로 수업을 준비할 수 있지요. 여기 화면에서 보시다시피 수업 계획을 짜는 것도 도와줍니다. 궁극적으로는 성취 보고서를 작성하거나 성취도를 책정하는 데에도 도움을 줄 것입니다. 다시 한 번 말하지만, 교사들은 기존에 절반 이상의 시간을 수업 준비에 할애합니다. 그 에너지는 그들 스스로에게, 혹은 학생들과 쌓는 인간적인 상호작용에 사용될 수 있습니다.
(Applause)
(박수)
So, you know, one point I want to make. These large language models are so powerful, there's a temptation to say like, well, all these people are just going to slap them onto their websites, and it kind of turns the applications themselves into commodities. And what I've got to tell you is that’s one of the reasons why I didn’t sleep for two weeks when I first had access to GPT-4 back in August. But we quickly realized that to actually make it magical, I think what you saw with Khanmigo a little bit, it didn't interact with you the way that you see ChatGPT interacting. It was a little bit more magical, it was more Socratic, it was clearly much better at math than what most people are used to thinking. And the reason is, there was a lot of work behind the scenes to make that happen.
제가 말하고 싶은 바는 이러합니다. 이러한 거대 언어 모델은 정말 강력해서 유혹이 있을 수 있습니다. 말하자면, 그저 자신의 웹사이트에 쉽게 갖다 붙여버리고 싶은 마음 말이죠. 그러면 앱 자체가 상품화됩니다. 제가 지난 8월에 GPT-4의 접근 권한을 받은 후, 2주를 꼬박 밤새 작업한 이유 중 하나가 그것이라는 걸 알려드리겠습니다. 하지만 우리는 곧 그것을 마법처럼 바꿀 방법을 깨달았습니다. 아마 칸미고를 보면서 눈치채셨을 수도 있는데, 칸미고는 기존의 익숙한 챗지피티의 대화 방식과는 약간 다릅니다. 좀 더 특별하죠. 조금 더 문답적인 대화를 하고, 수학에서는 확실히 더 좋은 성능을 지닙니다. 사람들의 기존 인식과 다르게 말이죠. 그리고 그 비밀은 이것을 만드는 과정에서 들인 수많은 노력 속에 있습니다.
And I could go through the whole list of everything we've been working on, many, many people for over six, seven months to make it feel magical. But perhaps the most intellectually interesting one is we realized, and this was an idea from an OpenAI researcher, that we could dramatically improve its ability in math and its ability in tutoring if we allow the AI to think before it speaks. So if you're tutoring someone and you immediately just start talking before you assess their math, you might not get it right. But if you construct thoughts for yourself, and what you see on the right there is an actual AI thought, something that it generates for itself but it does not share with the student. then its accuracy went up dramatically, and its ability to be a world-class tutor went up dramatically. And you can see it's talking to itself here. It says, "The student got a different answer than I did, but do not tell them they made a mistake. Instead, ask them to explain how they got to that step."
우리가 해 온 작업을 말하자면 끝도 없는 목록이 될 것이고, 많고 많은 사람들이 예닐곱 달 동안 더 특별하게 만들기 위해 노력했습니다. 어쩌면 가장 지적으로 흥미로웠던 부분은 OpenAI의 연구자로부터 얻은 아이디어인데, 우리가 AI가 말하기 전에 한 번 더 생각하도록 하면 수학 능력과 교사로써의 능력을 극적으로 끌어올릴 수 있다는 것입니다. 여러분이 누군가를 가르칠 때 상대방의 실력을 알기도 전에 말하기 시작하면 수업이 아마 제대로 진행되지 않을 것입니다. 하지만 여러분이 스스로를 위해 생각을 한 번 더 정리하면 다릅니다. 여기 오른쪽이 보이는 것이 실제 AI의 생각입니다. 스스로를 위해 생성되는 생각이며, 학생들에게는 공개되지 않죠. 그러자 모델의 정확성이 놀랍도록 증가했습니다. 그리고 세계적인 선생님이 될 가능성도 급증했죠. 여기서 AI가 스스로와 대화하는 걸 관찰할 수 있습니다. “학생이 내가 생각한 것과 다른 답을 내었네, 하지만 실수를 했다는 것을 말해주면 안 되겠어. 대신, 왜 그러한 단계를 밟았는지 물어봐야지.” 라고 말합니다.
So I'll just finish off, hopefully, you know, what I’ve just shown you is just half of what we are working on, and we think this is just the very tip of the iceberg of where this can actually go. And I'm pretty convinced, which I wouldn't have been even a year ago, that we together have a chance of addressing the 2 sigma problem and turning it into a 2 sigma opportunity, dramatically accelerating education as we know it.
이제 이 말씀을 드리며 마무리하겠습니다. 바라건대, 이것은 저희가 한 작업의 반절에 불과하고 우리의 작업은 이 모델의 가능성의 빙산의 일각이라고 생각합니다. 그리고 1년 전과 달리 꽤나 확신이 생겼습니다. 우리가 힘을 합쳐 2 시그마 문제를 2 시그마 가능성으로 전환할 수 있다는 것, 그리고 교육의 질을 급격히 높일 수 있다는 것 말입니다.
Now, just to take a step back at a meta level, obviously we heard a lot today, the debates on either side. There's folks who take a more pessimistic view of AI, they say this is scary, there's all these dystopian scenarios, we maybe want to slow down, we want to pause. On the other side, there are the more optimistic folks that say, well, we've gone through inflection points before, we've gone through the Industrial Revolution. It was scary, but it all kind of worked out. And what I'd argue right now is I don't think this is like a flip of a coin or this is something where we'll just have to, like, wait and see which way it turns out. I think everyone here and beyond, we are active participants in this decision. I'm pretty convinced that the first line of reasoning is actually almost a self-fulfilling prophecy, that if we act with fear and if we say, "Hey, we've just got to stop doing this stuff," what's really going to happen is the rule followers might pause, might slow down, but the rule breakers, as Alexandr [Wang] mentioned, the totalitarian governments, the criminal organizations, they're only going to accelerate. And that leads to what I am pretty convinced is the dystopian state, which is the good actors have worse AIs than the bad actors.
그러면 더 높은 수준에서 바라봐봅시다. 우리는 오늘 AI에 대한 양측의 주장을 모두 들을 수 있었습니다. AI에 대해 부정적인 견해를 가진 사람들은 “AI는 무섭다. 앞으로는 비관적인 시나리오 뿐이다. 우리는 발전을 늦추거나 멈춰야 한다.“고 말합니다. 그 반대측은 긍정적인 주장을 합니다. “우리는 지금까지 많은 변화를 거쳐왔다. 산업 혁명도 거쳐왔다. 두렵게 느껴졌지만 어떻게든 잘 해결이 되었다.“라고 말합니다. 그리고 제가 말하고자 하는 건 이것은 동전던지기가 아니고 그저 무슨 일이 일어나는지 기다려서 해결될 일도 아니라는 것입니다. 여기 있는 우리와 저 너머의 사람들까지 우리 모두는 이 선택의 주도자들입니다. 저는 이렇게 확신합니다. 우리의 첫 번째 논리는 자기 충족 예언과 같아서 만약 두려움에 사로잡혀 “저기, 이건 이제 그만두어야 할 거 같아요.” 라고 말한다면 법을 지키는 자들이 멈추거나 속도를 늦출동안 알렉산드르가 말한 법을 지키지 않는 자들, 예를 들어 전체주의 정부나 범죄 조직 등은 가속한다는 것을요. 그리고 발생할 일들은 확신하건대 재앙일 겁니다. 악한 사람들이 선한 사람들보다 더 좋은 AI 기술을 가지게 되는 거죠.
But I'll also, you know, talk to the optimists a little bit. I don't think that means that, oh, yeah, then we should just relax and just hope for the best. That might not happen either. I think all of us together have to fight like hell to make sure that we put the guardrails, we put in -- when the problems arise -- reasonable regulations. But we fight like hell for the positive use cases. Because very close to my heart, and obviously there's many potential positive use cases, but perhaps the most powerful use case and perhaps the most poetic use case is if AI, artificial intelligence, can be used to enhance HI, human intelligence, human potential and human purpose.
하지만 낙관론자의 관점에서도 조금 이야기해보자면, 그들이 주장하는 건 긴장을 풀고 어떻게든 되겠지라며 가만히 있으라는 것이 아닐 겁니다. 그것도 일어나서는 안돼요. 우리 모두는 치열하게 싸워야 합니다. 문제가 발생했을 때 적절히 규제할 수 있는 이정표를 세우기 위해서요. AI가 선하게 쓰이기를 바라며 치열하게 싸워야 합니다. 진심으로 말하건대, 이미 다양한 긍정적인 이용 사례가 있지만, AI의 가장 강력한 이용 사례는, 그리고 가장 시적인 이용 방향은 인공적인 지능인 AI가 인간의 지능인 HI, 인간의 잠재성과 인간 목적을 향상시키기 위해 사용되는 것일 겁니다.
Thank you. (Applause)
감사합니다. (박수)