How AI Could Save (Not Destroy) Education | Sal Khan | TED

1,418,564 views ・ 2023-05-01

TED


μ•„λž˜ μ˜λ¬Έμžλ§‰μ„ λ”λΈ”ν΄λ¦­ν•˜μ‹œλ©΄ μ˜μƒμ΄ μž¬μƒλ©λ‹ˆλ‹€.

λ²ˆμ—­: 인호 μž₯ κ²€ν† : ν•œλ‚˜ 졜
00:04
So anyone who's been paying attention for the last few months
0
4543
3878
이μͺ½ 뢄야에 졜근 λͺ‡ 달 관심을 κ°€μ‘Œλ˜ 뢄듀이라면
00:08
has been seeing headlines like this,
1
8463
2086
λͺ¨λ‘ 이런 기사 제λͺ©μ„ 보셨을 κ²λ‹ˆλ‹€.
00:10
especially in education.
2
10590
2086
특히 ꡐ윑 μ—…κ³„μ—μ„œμš”.
00:12
The thesis has been:
3
12717
1919
μ£Όμ œλŠ” μ΄λŸ¬ν–ˆμŠ΅λ‹ˆλ‹€:
00:14
students are going to be using ChatGPT and other forms of AI
4
14678
3795
학생듀은 μ±—μ§€ν”Όν‹°λ‚˜ λ‹€λ₯Έ μ’…λ₯˜μ˜ 인곡지λŠ₯을 ν™œμš©ν•΄
00:18
to cheat, do their assignments.
5
18515
1501
λΆ€μ •ν–‰μœ„λ₯Ό ν•˜κ³ , 과제λ₯Ό ν•  것이며,
00:20
They’re not going to learn.
6
20016
1335
아무것도 λ°°μš°μ§€ λͺ»ν•  것이닀.
00:21
And it’s going to completely undermine education as we know it.
7
21393
3545
우리의 μ˜ˆμƒμ²˜λŸΌ ꡐ윑의 κΈ°λ°˜μ„ μ™„μ „νžˆ μ•½ν™”μ‹œν‚¬ 것이닀.
00:25
Now, what I'm going to argue today
8
25438
1627
자, μ œκ°€ 였늘 μ£Όμž₯ν•˜κ³  싢은 λ°”λŠ”
00:27
is not only are there ways to mitigate all of that,
9
27107
2711
이런 λ¬Έμ œλ“€μ„ μ™„ν™”μ‹œν‚¬ 방법이 μžˆμ„ 뿐만이 μ•„λ‹ˆλΌ
00:29
if we put the right guardrails, we do the right things,
10
29859
2586
μ˜³μ€ μ΄μ •ν‘œλ₯Ό 두고 μ˜³μ€ 행동을 ν•œλ‹€λ©΄
00:32
we can mitigate it.
11
32487
1126
κ·Έ 문제λ₯Ό ν•΄κ²°ν•  수 μžˆλ‹€λŠ” κ²λ‹ˆλ‹€.
00:33
But I think we're at the cusp of using AI
12
33655
2336
μš°λ¦¬λŠ” 인곡지λŠ₯의 λ„μž…μ„ μ½”μ•žμ— 두고 μžˆλŠ”λ°
00:35
for probably the biggest positive transformation
13
35991
4045
μ΄λŠ” ꡐ윑 μ—…κ³„μ—μ„œ 일어날
00:40
that education has ever seen.
14
40036
2461
κ°€μž₯ 긍정적인 변화일 κ²λ‹ˆλ‹€.
00:42
And the way we're going to do that
15
42831
1793
μ–΄λ–»κ²Œ ν• κ±°λƒκ΅¬μš”?
00:44
is by giving every student on the planet
16
44624
2878
μ§€κ΅¬μƒμ˜ λͺ¨λ“  ν•™μƒλ“€μ—κ²Œ
00:47
an artificially intelligent but amazing personal tutor.
17
47544
3628
ν›Œλ₯­ν•œ 인곡지λŠ₯ 개인 ꡐ사λ₯Ό 쀄 κ²ƒμž…λ‹ˆλ‹€.
00:51
And we're going to give every teacher on the planet an amazing,
18
51172
3587
그리고 μ§€κ΅¬μƒμ˜ λͺ¨λ“  μ„ μƒλ‹˜λ“€μ—κ²ŒλŠ”
00:54
artificially intelligent teaching assistant.
19
54801
2586
ν›Œλ₯­ν•œ 인곡지λŠ₯ 보쑰 ꡐ사λ₯Ό 쀄 κ±°μ˜ˆμš”.
00:57
And just to appreciate how big of a deal it would be
20
57762
3587
λͺ¨λ‘μ—κ²Œ 개인 ꡐ사가 μƒκΈ°λŠ” 것이
01:01
to give everyone a personal tutor,
21
61349
2670
μ–Όλ§ˆλ‚˜ 큰 λ³€ν™”λ₯Ό λΆˆλŸ¬μΌμœΌν‚¬μ§€ μ΄ν•΄ν•˜κΈ° μœ„ν•΄
01:04
I show you this clip
22
64060
3003
1984년에 벀자민 블룸이 μ—°κ΅¬ν•œ 2 μ‹œκ·Έλ§ˆ 연ꡬ, λ˜λŠ”
01:07
from Benjamin Bloom’s 1984 2 sigma study,
23
67105
3003
β€œ2 μ‹œκ·Έλ§ˆ λ¬Έμ œβ€œλΌκ³ λ„ λΆˆλ¦¬λŠ”
01:10
or he called it the β€œ2 sigma problem.”
24
70150
2377
자료λ₯Ό λ³΄μ—¬λ“œλ¦¬κ² μŠ΅λ‹ˆλ‹€.
01:12
The 2 sigma comes from two standard deviation,
25
72569
2210
2 μ‹œκ·Έλ§ˆλΌλŠ” 이름은 두 개의 ν‘œμ€€ νŽΈμ°¨λ‘œλΆ€ν„° λ‚˜μ™”κ³ ,
01:14
sigma, the symbol for standard deviation.
26
74779
2044
μ—¬κΈ°μ„œ μ‹œκ·Έλ§ˆλŠ” ν‘œμ€€ 편차의 κΈ°ν˜Έμž…λ‹ˆλ‹€.
01:16
And he had good data that showed that look, a normal distribution,
27
76823
3587
블룸은 μ •κ·œ 뢄포λ₯Ό λ³΄μ΄λŠ” 쒋은 데이터가 μžˆμ—ˆμŠ΅λ‹ˆλ‹€.
01:20
that's the one that you see in the traditional bell curve
28
80452
2711
일반적인 μ’…ν˜• κ·Έλž˜ν”„μΈλ°,
01:23
right in the middle, that's how the world kind of sorts itself out,
29
83163
3170
λ°”λ‘œ κ°€μš΄λ° κ·Έλž˜ν”„κ°€ μ„Έμƒμ˜ 뢄포λ₯Ό λ‚˜νƒ€λƒ…λ‹ˆλ‹€.
01:26
that if you were to give personal 1-to-1 to tutoring for students,
30
86333
4713
ν•™μƒμ—κ²Œ 1λŒ€1 개인 κ³Όμ™Έλ₯Ό ν•΄μ€€λ‹€λ©΄,
01:31
then you could actually get a distribution that looks like that right.
31
91046
3295
였λ₯Έμͺ½μ— λ³΄μ΄λŠ” 뢄포λ₯Ό 얻을 수 μžˆμŠ΅λ‹ˆλ‹€.
01:34
It says tutorial 1-to-1 with the asterisks,
32
94382
2002
1λŒ€1 κ°œλ³„μ§€λ„ λ³„ν‘œλΌκ³  써져 μžˆλŠ”λ°,
01:36
like, that right distribution,
33
96426
1460
였λ₯Έμͺ½ λΆ„ν¬μ—μ„œ λ³΄μ΄λŠ” κ²ƒμ²˜λŸΌ
01:37
a two standard-deviation improvement.
34
97886
1793
기쑴보닀 2 μ‹œκ·Έλ§ˆλ§ŒνΌ κ°œμ„ λμŠ΅λ‹ˆλ‹€.
01:39
Just to put that in plain language,
35
99679
1710
μ‰½κ²Œ λ§ν•˜μžλ©΄,
01:41
that could take your average student and turn them into an exceptional student.
36
101389
3754
λ³΄ν†΅μ˜ 학생을 μ΄λ‘€μ μœΌλ‘œ μš°μˆ˜ν•œ ν•™μƒμœΌλ‘œ λ§Œλ“€ 수 μžˆλ‹€λŠ” κ²λ‹ˆλ‹€.
01:45
It can take your below-average student
37
105185
2335
평균 μ΄ν•˜μ˜ 학생을
01:47
and turn them into an above-average student.
38
107520
2795
평균 μ΄μƒμ˜ ν•™μƒμœΌλ‘œ λ§Œλ“€ 수 μžˆμŠ΅λ‹ˆλ‹€.
01:50
Now the reason why he framed it as a problem, was he said,
39
110774
3753
ν•˜μ§€λ§Œ κ·Έκ°€ μ—¬κΈ°μ—μ„œ 문제점으둜 μ§€μ ν•œ 것은
01:54
well, this is all good,
40
114569
1335
λ‹€ 쒋은데,
01:55
but how do you actually scale group instruction this way?
41
115945
2712
집단적인 κ΅μœ‘μ„ μ–΄λ–»κ²Œ 이런 규λͺ¨λ‘œ ν•˜λŠλƒ,
01:58
How do you actually give it to everyone in an economic way?
42
118657
3169
λͺ¨λ‘μ—κ²Œ μ œκ³΅ν•˜λŠ” 게 경제적으둜 κ°€λŠ₯ν•˜λƒλŠ” κ²ƒμž…λ‹ˆλ‹€.
02:02
What I'm about to show you is I think the first moves towards doing that.
43
122369
3670
μ œκ°€ μ§€κΈˆλΆ€ν„° λ³΄μ—¬λ“œλ¦΄ 것은 그것을 μ‹€ν˜„μ‹œν‚¬ 첫 λ‹¨μΆ”μž…λ‹ˆλ‹€.
02:06
Obviously, we've been trying to approximate it in some way
44
126081
2752
사싀, μš°λ¦¬λŠ” κ°œλ³„ 지도λ₯Ό μœ μ‚¬ν•˜κ²ŒλΌλ„ μ‹€ν˜„μ‹œν‚€κ³ μž λ…Έλ ₯ν•˜λŠ” μ€‘μ΄μ—ˆμŠ΅λ‹ˆλ‹€.
02:08
at Khan Academy for over a decade now,
45
128833
2044
μΉΈ μ•„μΉ΄λ°λ―Έμ—μ„œ, 10년도 λ„˜κ²Œ 말이죠.
02:10
but I think we're at the cusp of accelerating it dramatically.
46
130919
3170
그리고 μ €λŠ” 이제 이 κ³„νšμ„ 가속할 μ „ν™˜μ μ— μžˆλ‹€κ³  μƒκ°ν•©λ‹ˆλ‹€.
02:14
I'm going to show you the early stages of what our AI,
47
134089
3169
μ§€κΈˆλΆ€ν„° 저희가 κ°œλ°œν•œ AI의 초기 버전을 μ†Œκ°œν•˜κ² μŠ΅λ‹ˆλ‹€.
02:17
which we call Khanmigo,
48
137300
2836
μΉΈλ―Έκ³ (Khanmigo) μž…λ‹ˆλ‹€.
02:20
what it can now do
49
140178
1835
이것이 무엇을 ν•  수 μžˆλŠ”μ§€,
02:22
and maybe a little bit of where it is actually going.
50
142055
2836
그리고 μ‹€μ œλ‘œ 무엇을 ν–ˆλŠ”μ§€ 쑰금 λ³΄μ—¬λ“œλ¦¬κ² μŠ΅λ‹ˆλ‹€.
[μΌμ°¨λ°©μ •μ‹μ˜ ν•΄λ₯Ό κ΅¬ν•˜λŠ” 문제]
02:25
So this right over here is a traditional exercise
51
145850
2419
μ—¬κΈ° λ³΄μ΄λŠ” 것은 μ—¬λŸ¬λΆ„κ³Ό 아이듀이
02:28
that you or many of your children might have seen on Khan Academy.
52
148311
3128
μΉΈμ•„μΉ΄λ°λ―Έμ—μ„œ 많이 보셨을 기쑴의 μƒνˆ¬μ μΈ μ—°μŠ΅ λ¬Έμ œμž…λ‹ˆλ‹€.
02:31
But what's new is that little bot thing at the right.
53
151481
4129
ν•˜μ§€λ§Œ μƒˆλ‘œμš΄ 것은 였λ₯Έμͺ½μ— μžˆλŠ” λ‘œλ΄‡μž…λ‹ˆλ‹€.
02:35
And we'll start by seeing one of the very important safeguards,
54
155652
3879
그럼 κ°€μž₯ μ€‘μš”ν•œ μ•ˆμ „ μ‘°μΉ˜λΆ€ν„° 보도둝 ν•˜κ² μŠ΅λ‹ˆλ‹€.
02:39
which is the conversation is recorded and viewable by your teacher.
55
159572
3170
λͺ¨λ“  λŒ€ν™”κ°€ 기둝되고, μ„ μƒλ‹˜μ΄ μ—΄λžŒν•  수 μžˆλ„λ‘ ν•œ 것 말이죠.
02:42
It’s moderated actually by a second AI.
56
162742
2336
이 μ‹œμŠ€ν…œμ€ 사싀상 두 번째 AIκ°€ μ£Όλ„ν•©λ‹ˆλ‹€.
02:45
And also it does not tell you the answer.
57
165078
1960
그리고 이것은 μ ˆλŒ€ μ‰½κ²Œ 닡을 μ•Œλ €μ£Όμ§€ μ•ŠμŠ΅λ‹ˆλ‹€.
02:47
It is not a cheating tool.
58
167080
1251
꼼수 도ꡬ가 μ•„λ‹ˆλ‹ˆκΉŒμš”.
02:48
When the student says, "Tell me the answer,"
59
168331
2086
학생이 λ§Œμ•½ β€œλ‹΅μ„ μ•Œλ €μ€˜β€ 라고 ν•œλ‹€λ©΄
02:50
it says, "I'm your tutor.
60
170458
1210
μ΄λ ‡κ²Œ λ‹΅λ³€ν•©λ‹ˆλ‹€: β€œμ €λŠ” λ‹Ήμ‹ μ˜ κ΅μ‚¬μž…λ‹ˆλ‹€,
02:51
What do you think is the next step for solving the problem?"
61
171710
2836
문제λ₯Ό ν’€κΈ° μœ„ν•΄ λ‹€μŒμœΌλ‘œ 무엇을 ν•΄μ•Ό ν• κΉŒμš”?”
02:54
Now, if the student makes a mistake, and this will surprise people
62
174546
3211
λ§Œμ•½ 학생이 μ‹€μˆ˜λ₯Ό ν•˜λ©΄ 그것을 인지할 수 μžˆμŠ΅λ‹ˆλ‹€.
02:57
who think large language models are not good at mathematics,
63
177799
2836
κ±°λŒ€ μ–Έμ–΄ λͺ¨λΈμ€ μˆ˜ν•™μ— μ·¨μ•½ν•˜λ‹€κ³  μƒκ°ν•˜λ˜ μ‚¬λžŒλ“€μ€ λ†€λΌκ² μ§€μš”.
[뢄배법칙을 잘λͺ» μ‚¬μš©ν•˜μ—¬ λ‹΅λ³€ν•˜μ˜€κ³  인곡지λŠ₯이 μ‹€μˆ˜λ₯Ό μ•Œμ•„λ΄„]
03:00
notice, not only does it notice the mistake,
64
180677
2085
μΈμ§€ν•˜κ³ , 그뿐만이 μ•„λ‹ˆλΌ
03:02
it asks the student to explain their reasoning,
65
182762
2503
ν•™μƒμœΌλ‘œ ν•˜μ—¬κΈˆ κ·Έλ ‡κ²Œ ν•œ κΉŒλ‹­μ„ μ„€λͺ…ν•˜λ„λ‘ μš”κ΅¬ν•©λ‹ˆλ‹€.
03:05
but it's actually doing what I would say,
66
185306
1961
이것이 ν•˜κ³  μžˆλŠ” κ΅μœ‘μ€ 감히 λ§ν•˜κ±΄λŒ€,
03:07
not just even an average tutor would do, but an excellent tutor would do.
67
187267
3503
일반적인 κ΅μ‚¬μ˜ μˆ˜μ€€μ΄ μ•„λ‹ˆλΌ μ‹€λ ₯μžˆλŠ” κ΅μ‚¬μ˜ μˆ˜μ€€μž…λ‹ˆλ‹€.
03:10
It’s able to divine what is probably the misconception in that student’s mind,
68
190812
5255
학생이 무엇을 잘λͺ» μ΄ν•΄ν•˜κ³  μžˆλŠ”μ§€ νŒλ³„ν•΄λ‚Ό 수 μžˆμŠ΅λ‹ˆλ‹€.
03:16
that they probably didn’t use the distributive property.
69
196109
2628
μ•„κΉŒμ²˜λŸΌ, λΆ„λ°° 법칙을 잘λͺ» μ‚¬μš©ν–ˆμ„ λ•Œμ™€ 같이 말이죠.
03:18
Remember, we need to distribute the negative two
70
198737
2293
λ³΄μ„Έμš”, μš°λ¦¬λŠ” -2λ₯Ό
03:21
to both the nine and the 2m inside of the parentheses.
71
201072
3420
κ΄„ν˜Έ μ•ˆμ˜ 9와 2m에 λͺ¨λ‘ λΆ„λ°°ν–ˆμ–΄μ•Ό ν•©λ‹ˆλ‹€.
03:24
This to me is a very, very, very big deal.
72
204534
2211
이것은 μ €μ—κ²Œ μžˆμ–΄ 정말, 정말 μ€‘μš”ν•©λ‹ˆλ‹€.
03:26
And it's not just in math.
73
206786
1710
그리고 μˆ˜ν•™μ—λ§Œ κ΅­ν•œλ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€.
03:29
This is a computer programming exercise on Khan Academy,
74
209205
3462
이것은 μΉΈ μ•„μΉ΄λ°λ―Έμ˜ 컴퓨터 ν”„λ‘œκ·Έλž˜λ° μ—°μŠ΅ λ¬Έμ œμž…λ‹ˆλ‹€.
03:32
where the student needs to make the clouds part.
75
212667
2836
학생은 ꡬ름듀을 움직여야 ν•˜μ£ .
03:36
And so we can see the student starts defining a variable, left X minus minus.
76
216045
4797
학생이 λ³€μˆ˜λ₯Ό μ •μ˜ν•˜λŠ” 것뢀터 μ‹œμž‘ν•˜λŠ” κ±Έ 보싀 수 μžˆμŠ΅λ‹ˆλ‹€.
leftX--; (leftX의 값을 κ°μ†Œμ‹œν‚€λŠ” λͺ…λ Ή)
03:40
It only made the left cloud part.
77
220884
1585
ν•˜μ§€λ§Œ μ™Όμͺ½ κ΅¬λ¦„λ§Œ 움직이죠.
03:42
But then they can ask Khanmigo, what’s going on?
78
222510
2253
그리고 μΉΈλ―Έκ³ μ—κ²Œ μ§ˆλ¬Έν• κ²λ‹ˆλ‹€: β€œμ΄κ²Œ μ–΄λ–»κ²Œ 된 거지?”
03:44
Why is only the left cloud moving?
79
224763
1960
β€œμ™œ μ™Όμͺ½ κ΅¬λ¦„λ§Œ μ›€μ§μ΄λŠ” κ±°μ•Ό?”
03:46
And it understands the code.
80
226765
1543
그리고 AIλŠ” μ½”λ“œλ₯Ό μ΄ν•΄ν•©λ‹ˆλ‹€.
03:48
It knows all the context of what the student is doing,
81
228349
2837
학생이 무엇을 ν•˜κ³ μž ν–ˆλŠ”μ§€ κ·Έ λ§₯락을 이해할 수 있고
03:51
and it understands that those ellipses are there to draw clouds,
82
231186
3503
타원이 ꡬ름을 그리기 μœ„ν•œ μ½”λ“œμ˜€μŒμ„ 이해할 수 μžˆμŠ΅λ‹ˆλ‹€.
03:54
which I think is kind of mind-blowing.
83
234689
2336
μ €μ—κ²ŒλŠ” μƒλ‹Ήνžˆ λ†€λžκ²Œ λŠκ»΄μ§€λŠ” λΆ€λΆ„μ΄μ§€μš”.
03:57
And it says, "To make the right cloud move as well,
84
237025
2419
그리고 λ‹΅λ³€ν•©λ‹ˆλ‹€. β€œμ˜€λ₯Έμͺ½ ꡬ름도 μ›€μ§μ΄κ²Œ ν•˜λ €λ©΄,
03:59
try adding a line of code inside the draw function
85
239444
2419
draw ν•¨μˆ˜ μ•ˆμ— 였λ₯Έμͺ½ X λ³€μˆ˜λ₯Ό
04:01
that increments the right X variable by one pixel in each frame."
86
241863
3545
ν”„λ ˆμž„λ§ˆλ‹€ 1 ν”½μ…€μ”© μ¦κ°€μ‹œν‚€λŠ” μ½”λ“œλ₯Ό μΆ”κ°€ν•΄λ³΄μ„Έμš”.
04:05
Now, this one is maybe even more amazing because we have a lot of math teachers.
87
245909
4296
이것이 더 λ†€λΌμš΄ μ΄μœ λŠ” 세상에 μˆ˜ν•™ κ΅μ‚¬λŠ” λ§Žμ€ 반면,
04:10
We've all been trying to teach the world to code,
88
250205
2294
코딩을 κ°€λ₯΄μΉ˜κ³ μž ν•˜λŠ” μˆ˜μš”μ— λΉ„ν•΄
04:12
but there aren't a lot of computing teachers out there.
89
252540
2670
μ»΄ν“¨νŒ… κ΅μ‚¬λŠ” 그리 λ§Žμ§€ μ•ŠκΈ° λ•Œλ¬Έμž…λ‹ˆλ‹€.
04:15
And what you just saw, even when I'm tutoring my kids,
90
255251
2586
그리고 μ—¬λŸ¬λΆ„λ„ 방금 보셨듯이
04:17
when they're learning to code,
91
257837
1460
μ œκ°€ μ•„μ΄λ“€μ—κ²Œ 코딩을 κ°€λ₯΄μΉ  떄에도
04:19
I can't help them this well, this fast,
92
259297
2211
이 μ •λ„λ‘œ μ’‹κ²Œ, 그리고 λΉ λ₯΄κ²Œ κ°€λ₯΄μΉ˜μ§€λŠ” λͺ»ν•©λ‹ˆλ‹€.
04:21
this is really going to be a super tutor.
93
261549
2294
이 κΈ°λŠ₯은 μ§„μ •μœΌλ‘œ 슈퍼 μ„ μƒλ‹˜μ΄ 될 수 μžˆμŠ΅λ‹ˆλ‹€.
04:25
And it's not just exercises.
94
265220
1543
그리고 이것은 μ—°μŠ΅ λ¬Έμ œμ—λ§Œ κ΅­ν•œλ˜μ§€ μ•Šμ•˜μŠ΅λ‹ˆλ‹€.
04:26
It understands what you're watching.
95
266805
1751
μ—¬λŸ¬λΆ„μ΄ λ³΄λŠ” 것도 이해할 수 μžˆμŠ΅λ‹ˆλ‹€
04:28
It understands the context of your video.
96
268556
2044
μ—¬λŸ¬λΆ„μ΄ μ‹œμ²­ν•˜λŠ” λΉ„λ””μ˜€μ˜ λ‚΄μš©μ„ 이해할 수 있고,
04:30
It can answer the age-old question, β€œWhy do I need to learn this?”
97
270600
3128
β€œμ™œ 이런 κ±Έ λ°°μ›Œμ•Ό ν•΄?” 같은 였래된 μ§ˆλ¬Έλ„ λŒ€λ‹΅ν•  수 μžˆμŠ΅λ‹ˆλ‹€.
04:33
And it asks Socratically, "Well, what do you care about?"
98
273728
2753
AIλŠ” β€œλ‹Ήμ‹ μ΄ μ€‘μš”ν•˜κ²Œ μƒκ°ν•˜λŠ” 건 λ¬΄μ—‡μΈκ°€μš”?” 라고 λ‹€μ‹œ λ˜λ¬»μ§€μš”.
04:36
And let's say the student says, "I want to be a professional athlete."
99
276523
4129
β€œλ‚˜λŠ” μœ‘μƒ μ„ μˆ˜κ°€ 되고 싢은걸” 이라고 학생이 λŒ€λ‹΅ν•œλ‹€λ©΄,
04:40
And it says, "Well, learning about the size of cells,
100
280693
2711
μ΄λ ‡κ²Œ λŒ€λ‹΅ν•©λ‹ˆλ‹€: β€œμ§€κΈˆ μ‹œμ²­ν•˜κ³  μžˆλŠ”
04:43
which is what this video is,
101
283446
1377
μ„Έν¬μ˜ 크기에 λŒ€ν•œ λΉ„λ””μ˜€λŠ”
04:44
that could be really useful for understanding nutrition
102
284823
2877
μ˜μ–‘μ†Œμ— λŒ€ν•΄, λ˜λŠ” λͺΈμ˜ μž‘λ™μ„ μ΄ν•΄ν•˜λŠ”λ°
04:47
and how your body works, etc."
103
287742
1752
정말 큰 도움이 될 κ²ƒμž…λ‹ˆλ‹€.”
04:49
It can answer questions, it can quiz you,
104
289494
2044
이 AIλŠ” μ§ˆλ¬Έμ„ λŒ€λ‹΅ν•˜κ³ , μ—¬λŸ¬λΆ„μ—κ²Œ ν€΄μ¦ˆλ₯Ό λ‚΄κ³ ,
04:51
it can connect it to other ideas,
105
291579
1585
μ—¬λŸ¬λΆ„μ˜ 생각을 μ—°κ³„μ‹œμΌœμ€„ 수 μžˆμŠ΅λ‹ˆλ‹€.
04:53
you can now ask as many questions of a video
106
293164
2378
이제 μ—¬λŸ¬λΆ„μ€ λΉ„λ””μ˜€λ₯Ό 보며
04:55
as you could ever dream of.
107
295583
1669
μ›ν•˜λŠ” 만큼 μ§ˆλ¬Έν•  수 μžˆμ„ κ²λ‹ˆλ‹€.
04:57
(Applause)
108
297252
3920
(λ°•μˆ˜)
05:01
Another big shortage out there,
109
301214
1752
λ°”κΉ₯ 세상은 μ‹¬κ°ν•œ κ³΅κΈ‰λ‚œμ— λΉ μ Έ μžˆμŠ΅λ‹ˆλ‹€.
05:03
I remember the high school I went to,
110
303007
1794
μ œκ°€ λ‚˜μ˜¨ κ³ λ“±ν•™κ΅λŠ”
05:04
the student-to-guidance counselor ratio was about 200 or 300 to one.
111
304801
5172
학생 λŒ€ 지도ꡐ사 λΉ„μœ¨μ΄ 200-300 λŒ€ 1에 λ‹¬ν–ˆμŠ΅λ‹ˆλ‹€.
05:10
A lot of the country, it's worse than that.
112
310014
2336
μˆ˜λ§Žμ€ κ΅­κ°€κ°€ 그보닀 μ—΄μ•…ν•œ ν™˜κ²½μ„ 가지고 μžˆμ§€μš”.
05:12
We can use Khanmigo to give every student a guidance counselor,
113
312350
3712
μš°λ¦¬λŠ” μΉΈλ―Έκ³ λ₯Ό 톡해 λͺ¨λ“  ν•™μƒμ—κ²Œ 지도 ꡐ사,
05:16
academic coach, career coach, life coach,
114
316104
3462
ν•™μˆ μ  지도, μ§„λ‘œ 상담, 인생 상담 등을 μ„ λ¬Όν•  수 μžˆμŠ΅λ‹ˆλ‹€.
05:19
which is exactly what you see right over here.
115
319566
2460
μ§€κΈˆ μ—¬κΈ° ν™”λ©΄μ—μ„œ λ³΄μ‹œλ‹€μ‹œν”Ό 말이죠.
05:22
And we launched this with the GPT-4 launch.
116
322068
3086
μš°λ¦¬λŠ” GPT-4 μΆœμ‹œμ— λ§žμΆ”μ–΄ 이것을 μΆœμ‹œν–ˆμŠ΅λ‹ˆλ‹€.
05:25
We have a few thousand people on this.
117
325196
1835
ν˜„μž¬ λͺ‡μ²œ λͺ…μ˜ κ°€μž…μžλ₯Ό λ³΄μœ ν•˜κ³  μžˆμ–΄μš”.
05:27
This isn't a fake demo,
118
327031
1168
κ°€μ§œ ν…ŒμŠ€νŠΈ 버전이 μ•„λ‹ˆλΌ,
05:28
this is really it in action.
119
328241
2919
μ‹€μ œλ‘œ μž‘λ™ν•˜λŠ” λͺ¨λΈμž…λ‹ˆλ‹€.
05:32
And then there is, you know,
120
332203
2211
그리고 λ˜ν•œ
05:34
things that I think it would have been even harder,
121
334455
2420
더 μ–΄λ €μšΈ 것이라 μƒκ°ν–ˆλ˜ 일듀,
05:36
it would have been a little science fiction to do
122
336875
2335
κΈ°μ‘΄ ꡐ사듀이라면 곡상 κ³Όν•™λ§ŒνΌ μ‹€ν˜„ν•˜κΈ° 어렀웠을 것인
05:39
with even a traditional tutor.
123
339210
1460
그런 일듀도 μžˆμŠ΅λ‹ˆλ‹€.
05:40
We run an online high school with Arizona State University
124
340670
2836
μš°λ¦¬λŠ” μ• λ¦¬μ‘°λ‚˜ 주립 λŒ€ν•™κ³Ό ν˜‘μ—…ν•΄ μΉΈ μ›”λ“œ μŠ€μΏ¨μ΄λΌλŠ”
05:43
called Khan World School,
125
343548
1501
온라인 κ³ λ“± κ΅μœ‘μ„ μ‹œν–‰ν•˜λŠ”λ°,
05:45
and we have a student who attends that online school, based in India.
126
345049
3546
μΈλ„μ—μ„œ 온라인 μŠ€μΏ¨μ„ μˆ˜κ°•ν•˜λŠ” 학생이 μžˆμ—ˆμŠ΅λ‹ˆλ‹€.
05:48
Her name's Saanvi.
127
348595
1626
κ·Έλ…€μ˜ 이름은 μ‚°λΉ„μ˜€μ–΄μš”.
05:50
And she was doing a report on "The Great Gatsby."
128
350221
3379
κ·Έλ…€κ°€ 리포트λ₯Ό μž‘μ„±ν•˜κΈ° μœ„ν•΄
05:53
And when she was reading "The Great Gatsby,"
129
353641
2086
μœ„λŒ€ν•œ κ°œμΈ λΉ„λ₯Ό 읽고 μžˆμ—ˆμ„ λ•Œ,
05:55
Jay Gatsby keeps looking at the green light off into the distance.
130
355727
3211
제이 κ°œμΈ λΉ„κ°€ λ©€λ¦¬μ„œ 녹색 λΆˆλΉ›μ„ 빀히 λ°”λΌλ³΄λŠ” μž₯면이 μžˆμ—ˆμŠ΅λ‹ˆλ‹€.
05:58
And she's like, "Why does he do that?"
131
358980
1835
κ·Έλ…€λŠ” μƒκ°ν–ˆμ£ . β€œμ™œ μ €λŸ¬κ³  μžˆλŠ” 거지?”
06:00
She did some web searches, and people have obviously studied this
132
360815
3087
κ·Έλ…€λŠ” 인터넷 검색을 ν•΄λ³΄μ•˜κ³ , μ‚¬λžŒλ“€μ΄ 이 상징성에 λŒ€ν•΄ λΆ„μ„ν•˜κ³ 
06:03
and commented about the symbolism of that,
133
363902
2002
생각을 남긴 것듀을 μ°Ύμ•„λ³Ό 수 μžˆμ—ˆμŠ΅λ‹ˆλ‹€.
06:05
but none of it was really resonating with her.
134
365904
2168
ν•˜μ§€λ§Œ κ·Έ 쀑 μ–΄λ– ν•œ 것도 κ·Έλ…€κ°€ μ›ν•˜λŠ” 닡변은 μ•„λ‹ˆμ—ˆμ£ .
06:08
And then she realized that she had Khanmigo
135
368072
2419
그러자 κ·Έλ…€λŠ” κ·Έλ…€μ—κ²Œ μΉΈλ―Έκ³ κ°€ μžˆμ–΄μ„œ
06:10
and that she could talk to Jay Gatsby himself.
136
370533
3045
제이 κ°œμΈ λΉ„μ™€ 직접 μ–˜κΈ°ν•  수 μžˆλ‹€λŠ” 사싀을 κΉ¨λ‹«μŠ΅λ‹ˆλ‹€.
06:13
And so, "Ah, splendid choice, old sport.
137
373620
2377
μΉΈλ―Έκ³ κ°€ λ§ν•©λ‹ˆλ‹€: β€œμ•„, 쒋은 선택이ꡬ렀. 였랜 벗이여,
06:15
I am now Jay Gatsby, the enigmatic millionaire
138
375997
2210
λ‚˜λŠ” 제이 κ°œμΈ λΉ„, F. 슀콧 ν”ΌμΈ μ œλŸ΄λ“œμ˜ κ³ μ „ λ¬Έν•™μ—μ„œ 온
06:18
from F. Scott Fitzgerald’s classic.”
139
378249
2294
μ‹ λΉ„λ‘œμš΄ 백만μž₯자이였.”
06:20
And so, "Why do you keep staring at the green light?"
140
380585
2502
κ·Έλ…€κ°€ λ§ν•©λ‹ˆλ‹€: β€œμ™œ 녹색 λΆˆλΉ›μ„ 바라보고 μžˆμ—ˆμ–΄μš”?”
06:23
"Ah, the green light, old sport.
141
383087
1836
β€œμ•„, 녹색 λΆˆλΉ› 말인가, 벗이여,
06:24
It's a symbol of my dreams and desires, you see.
142
384964
2795
그것은 λ‚˜μ˜ 꿈과 μš•λ§μ˜ 상징일세, μ•Œκ² λŠ”κ°€?
06:27
It's situated at the end of Daisy Buchanan's dock
143
387800
2336
κ·Έ λΆˆλΉ›μ€ λ°μ΄μ§€μ˜ 뢀두 끝에 μžˆμ—ˆμ§€.
06:30
across the bay from my mansion.
144
390178
1960
λ‚΄ μ €νƒμ˜ κ°• κ±΄λ„ˆνŽΈμ— 말이야.
06:32
I gaze at it longingly as it represents my yearning for the past
145
392138
3212
λ‚΄κ°€ λΆˆλΉ›μ„ 길게 λ°”λΌλ³΄μ•˜μŒμ€ λ‚΄ 과거에 λŒ€ν•œ 동경과,
06:35
and my hope to reunite with Daisy, the love of my life."
146
395391
3712
λ‚΄ μΈμƒμ˜ μ‚¬λž‘, λ°μ΄μ§€μ™€μ˜ 재회λ₯Ό λ°”λΌλŠ” 것일세.”
06:39
And what was cool is, Saanvi then said, β€œI had this long conversation,”
147
399604
3545
μž¬λ―ΈμžˆλŠ” 점은, μ‚°λΉ„κ°€ λ§ˆμ§€λ§‰μ— β€œκΈ΄ 이야기가 λ˜μ—ˆκ΅°μš”β€ 라고 λ§ν•˜λ©°
06:43
she called him β€œMr. Gatsby,”
148
403149
2252
κ·Έλ₯Ό κ°œμΈ λΉ„μ”¨λΌκ³  λΆˆλ €λ‹€λŠ” κ²ƒμž…λ‹ˆλ‹€.
06:45
and at the end she actually apologized for taking his time,
149
405443
3170
λŒ€ν™”λ₯Ό 끝마칠 μ μ—λŠ” μ‹œκ°„μ„ λΉΌμ•—μ•„ μ£„μ†‘ν•˜λ‹€κ³ λ„ ν–ˆμŠ΅λ‹ˆλ‹€.
06:48
which I thought was very polite of her.
150
408613
2586
정말 예의 λ°”λ₯Έ 학생이라 μƒκ°ν–ˆμŠ΅λ‹ˆλ‹€.
06:51
But you can imagine this unlocks learning literature, learning ...
151
411741
4546
이것이 λ¬Έν•™ μž‘ν’ˆ ν•™μŠ΅μ— μ΄μš©λ˜λŠ” 것을 κ·Έλ €λ³Ό 수 μžˆμŠ΅λ‹ˆλ‹€.
06:56
You could talk to historical figures.
152
416663
1793
μ—¬λŸ¬λΆ„μ€ 역사적 인물과도 이야기할 수 있죠.
06:58
We're even probably going to add an activity
153
418456
2085
심지어 이런 μ²΄ν—˜λ„ μΆ”κ°€ν•΄λ³Ό 수 μžˆμ–΄μš”.
07:00
you can talk to like, the Mississippi River.
154
420541
2086
예λ₯Ό λ“€μ–΄, λ―Έμ‹œμ‹œν”Ό κ°•κ³Ό μ΄μ•ΌκΈ°ν•˜λŠ” 것 λ§μž…λ‹ˆλ‹€.
07:02
It brings things to life in ways that really were science fiction
155
422627
3545
6-12κ°œμ›” μ „κΉŒμ§€λ§Œ 해도 곡상과학 μ†Œμ„€μ²˜λŸΌ λŠκ»΄μ§€λ˜ 것듀을
07:06
even six months or a year ago.
156
426214
2461
ν˜„μ‹€ 속에 μ‹€ν˜„μ‹œμΌ°μŠ΅λ‹ˆλ‹€.
07:10
Students can get into debates with the AI.
157
430134
2336
학생듀은 AI와 토둠도 ν•  수 μžˆμ–΄μš”.
07:12
And we’ve got this here is the student debating
158
432512
2210
μ—¬κΈ° 이것은 β€œν•™μžκΈˆ λŒ€μΆœμ„ 탕감해주어야 ν•˜λŠ”κ°€?”
07:14
whether we should cancel student debt.
159
434722
1835
에 λŒ€ν•œ ν•™μƒμ˜ ν† λ‘  λ‚΄μš©μž…λ‹ˆλ‹€.
07:16
The student is against canceling student debt,
160
436557
2169
학생은 λŒ€μΆœ 탕감에 μžˆμ–΄ λ°˜λŒ€μ˜ μž…μž₯을 μ·¨ν•˜μ˜€κ³ 
07:18
and we've gotten very clear feedback.
161
438726
1794
μš°λ¦¬λŠ” μ—¬κΈ°μ—μ„œ 쒋은 ν”Όλ“œλ°±μ„ 얻을 수 μžˆμ—ˆμ£ .
07:20
We started running it at Khan World School in our lab school that we have,
162
440520
3503
μš°λ¦¬λŠ” μΉΈ μ›”λ“œ 슀쿨의 랩 μŠ€μΏ¨μ—μ„œ 이것을 μš΄μ˜ν•˜κΈ° μ‹œμž‘ν–ˆμŠ΅λ‹ˆλ‹€.
μ΄λ¦„ν•˜μ—¬, μΉΈ 랩 슀쿨이죠.
07:24
Khan Lab School.
163
444023
1168
07:25
The students, the high school students especially,
164
445233
2377
μ°Έμ—¬ν•˜λŠ” 학생듀, 특히 κ³ λ“±ν•™μƒλ“€μ˜ ν‰κ°€λ‘œλŠ”
07:27
they're saying "This is amazing to be able to fine-tune my arguments
165
447652
3211
β€œνƒ€μΈμ˜ 평가에 λ‘λ €μ›Œν•˜μ§€ μ•Šκ³ 
제 μ˜κ²¬μ„ μ‘°μ •ν•  수 μžˆμ–΄μ„œ μ’‹μ•˜κ³ ,
07:30
without fearing judgment.
166
450905
1210
07:32
It makes me that much more confident
167
452156
1752
이λ₯Ό 톡해 μ‹€μ œ μˆ˜μ—…μ— μ°Έμ—¬ν•  λ•Œλ„
07:33
to go into the classroom and really participate."
168
453908
2377
λ”μš± μžμ‹ κ°μ„ κ°€μ§ˆ 수 μžˆμ—ˆμŠ΅λ‹ˆλ‹€β€ 라고 ν•˜μ˜€μŠ΅λ‹ˆλ‹€.
07:36
And we all know that Socratic dialogue debate is a great way to learn,
169
456285
3295
문닡식 토둠이 쒋은 κ΅μœ‘λ²•μ΄λΌλŠ” 것은 널리 μ•Œλ €μ§„ μ‚¬μ‹€μž…λ‹ˆλ‹€.
07:39
but frankly, it's not out there for most students.
170
459622
2836
ν•˜μ§€λ§Œ ν˜„μ‹€μ€, λŒ€λΆ€λΆ„μ˜ ν•™μƒλ“€μ—κ²Œ 그런 κΈ°νšŒκ°€ μ—†λ‹€λŠ” κ²ƒμž…λ‹ˆλ‹€.
07:42
But now it can be accessible to hopefully everyone.
171
462500
3587
ν•˜μ§€λ§Œ 이제 문닡식 κ΅μœ‘μ€ λͺ¨λ‘μ—κ²Œ μ—΄λ € μžˆμŠ΅λ‹ˆλ‹€.
07:48
A lot of the narrative, we saw that in the headlines, has been,
172
468047
3629
λ§Žμ€ ν—€λ“œλΌμΈμ΄ μ΄λ ‡κ²Œ ν‘œν˜„ν•˜κ³ λŠ” ν–ˆμŠ΅λ‹ˆλ‹€:
07:51
"It's going to do the writing for kids.
173
471718
1876
β€œAIλŠ” 학생을 λŒ€μ‹ ν•΄ 글을 써주며
07:53
Kids are not going to learn to write."
174
473594
1877
학생듀은 μ“°κΈ°λ₯Ό λ°°μš°μ§€ λͺ»ν•  것이닀.”
07:55
But we are showing that there's ways that the AI doesn't write for you,
175
475471
3379
ν•˜μ§€λ§Œ 우리의 μ„±κ³ΌλŠ” AIκ°€ μ—¬λŸ¬λΆ„μ„ μœ„ν•΄ μ“°λŠ” 것이 μ•„λ‹Œ
07:58
it writes with you.
176
478850
1168
μ—¬λŸ¬λΆ„κ³Ό ν•¨κ»˜ μ“°λŠ” 것이 κ°€λŠ₯ν•˜λ‹€λŠ” κ±Έ λ³΄μ—¬μ€λ‹ˆλ‹€.
08:00
So this is a little thing,
177
480059
1335
κ΄€λ ¨λœ μž‘μ€ 이야기가 μžˆλŠ”λ°,
08:01
and my eight year old is addicted to this,
178
481436
2043
제 8μ‚΄ 아듀이 여기에 λΉ μ Έλ“€μ—ˆμŠ΅λ‹ˆλ‹€.
08:03
and he's not a kid that really liked writing before,
179
483521
2461
μ“°λŠ” κ±Έ 그닀지 μ’‹μ•„ν•˜μ§€λŠ” μ•ŠλŠ” μ•„μ΄μ˜€μ§€μš”.
08:05
but you can say,
180
485982
1376
ν•˜μ§€λ§Œ β€œλ¬΄μ„œμš΄ 이야기λ₯Ό μ“°κ³  싢어”
08:07
β€œI want to write a horror story,”
181
487358
1585
라고 λ§ν•˜μž
08:08
and it says, "Ooh, a horror story, how spine-tingling and thrilling.
182
488943
3837
AIκ°€ λ‹΅ν•©λ‹ˆλ‹€. β€œμ˜€, λ¬΄μ„œμš΄ 이야기! 벌써 μ†Œλ¦„μ΄ 돋고 μ‹ λ‚˜λŠ”λ°μš”.
08:12
Let's dive into the world of eerie shadows and chilling mysteries."
183
492780
3212
κΈ°λ¬˜ν•œ κ·Έλ¦Όμžμ™€ μ†Œλ¦„λ‹λŠ” λΉ„λ°€μ˜ μ„ΈμƒμœΌλ‘œ λΉ μ Έ λ΄…μ‹œλ‹€.”
08:15
And this is an activity where the student will write two sentences,
184
495992
3336
이것은 학생이 두 λ¬Έμž₯을 μž‘μ„±ν•˜λ©΄
08:19
and then the AI will write two sentences.
185
499328
2002
AIκ°€ λ‹€μŒ 두 λ¬Έμž₯을 μž‡λŠ” ν™œλ™μž…λ‹ˆλ‹€.
08:21
And so they collaborate together on a story.
186
501330
2628
그듀은 ν•˜λ‚˜μ˜ 이야기λ₯Ό ν–₯ν•΄ ν˜‘μ—…ν•˜κ²Œ 되죠.
08:24
The student writes, "Beatrice was a misunderstood ghost.
187
504000
2669
학생이 글을 μΌλ‹ˆλ‹€. β€œλΉ„μ•„νŠΈλ¦¬μ²΄λŠ” μ˜€ν•΄λ₯Ό λ°›λŠ” μœ λ Ήμ΄μ—μš”.
08:26
She wanted to make friends but kept scaring them by accident."
188
506711
2919
κ·Έλ…€λŠ” 친ꡬλ₯Ό λ§Œλ“€κ³ μž ν–ˆμ§€λ§Œ, μ˜λ„μΉ˜ μ•Šκ²Œ 친ꡬλ₯Ό 겁주고 λ§μ•˜λ‹΅λ‹ˆλ‹€.
08:29
And the AI says, "Poor Beatrice, a lonely spirit yearning for companionship.
189
509672
3587
그럼 AIκ°€ λ°›μ•„μ€λ‹ˆλ‹€.
β€œλΆˆμŒν•œ λΉ„μ•„νŠΈλ¦¬μ²΄λŠ” μš°μ •μ„ λ°”λΌλŠ” μ™Έλ‘œμš΄ μ˜ν˜Όμ΄μ—ˆμ–΄μš”.
08:33
One day she stumbled upon an old abandoned mansion," etc.
190
513301
3462
μ–΄λŠ λ‚  κ·Έλ…€λŠ” 버렀진 집 μ•žμ— λ‹€λ‹€λ₯΄κ²Œ λ˜μ—ˆμ–΄μš”β€ λ“± 말이죠.
08:36
I encourage you all to hopefully one day try this.
191
516763
2419
μ—¬λŸ¬λΆ„λ„ μ–Έμ œ ν•œ 번 μ²΄ν—˜ν•΄λ³΄μ‹œκΈΈ μΆ”μ²œλ“œλ¦½λ‹ˆλ‹€.
08:39
This is surprisingly fun.
192
519182
1877
λ†€λΌμšΈ μ •λ„λ‘œ μž¬λ―Έμžˆκ±°λ“ μš”.
08:42
Now to even more directly hit this use case.
193
522935
2878
이제 더 직접적인 μ‚¬μš© 사둀λ₯Ό λ΄…μ‹œλ‹€.
08:45
And what I'm about to show you,
194
525855
1543
μ΄μ œλΆ€ν„° λ³΄μ—¬λ“œλ¦΄ 것은..
08:47
everything I showed you so far
195
527440
1460
μ§€κΈˆκΉŒμ§€ μ œκ°€ λ³΄μ—¬λ“œλ¦° 것은
08:48
is actually already part of Khanmigo, and what I’m about to show you,
196
528900
3253
칸미고의 μ™„μ„±λœ κΈ°λŠ₯λ“€μ΄μ—ˆμŠ΅λ‹ˆλ‹€. ν•˜μ§€λ§Œ μ΄μ œλΆ€ν„° λ³΄μ—¬λ“œλ¦΄ 것은
08:52
we haven't shown to anyone yet, this is a prototype.
197
532153
2461
아직 μ•„λ¬΄μ—κ²Œλ„ 보여주지 μ•Šμ€ μ‹œλ²” λͺ¨λΈμž…λ‹ˆλ‹€.
08:54
We hope to be able to launch it in the next few months,
198
534614
2586
μ•„λ§ˆ λͺ‡ 달 후에 정식 μΆœμ‹œλ κ±°λΌ μƒκ°ν•©λ‹ˆλ‹€.
08:57
but this is to directly use AI, use generative AI,
199
537200
3420
이것은 μ§μ ‘μ μœΌλ‘œ μƒμ„±ν˜• AIλ₯Ό μ‚¬μš©ν•΄
09:00
to not undermine English and language arts
200
540661
2128
μ˜λ¬Έν•™μ„ λ„νƒœμ‹œν‚€κΈ°λ³΄λ‹€λŠ”
09:02
but to actually enhance it in ways
201
542830
1627
μ‹€μ§ˆμ μœΌλ‘œ λ”μš± λ°œμ „μ‹œν‚¬ 수 μžˆλŠ” λ°©λ²•μž…λ‹ˆλ‹€.
09:04
that we couldn't have even conceived of even a year ago.
202
544457
3211
μž‘λ…„κΉŒμ§€λ§Œ 해도 저희 λ˜ν•œ 생각쑰차 λͺ»ν–ˆλ˜ μΌμ΄μ—ˆμ£ .
09:08
This is reading comprehension.
203
548002
1460
독해 뢄야인데,
09:09
The students reading Steve Jobs's famous speech at Stanford.
204
549504
4170
학생듀은 μŠ€ν‹°λΈŒ μž‘μŠ€κ°€ μŠ€νƒ ν¬λ“œμ—μ„œ ν•œ 유λͺ…ν•œ 연섀을 읽게 λ˜μ—ˆμŠ΅λ‹ˆλ‹€.
09:13
And then as they get to certain points,
205
553716
1960
그듀이 νŠΉμ • μ§€μ κΉŒμ§€ 읽으면,
09:15
they can click on that little question.
206
555676
2336
μž‘μ€ μ§ˆλ¬Έμ„ 클릭할 수 μžˆμŠ΅λ‹ˆλ‹€.
09:18
And the AI will then Socratically, almost like an oral exam,
207
558012
4922
그러면 AIλŠ” μ†Œν¬λΌν…ŒμŠ€μ˜ λ¬Έλ‹΅μ‹μœΌλ‘œ, ꡬ두 μ‹œν—˜κ³Ό λΉ„μŠ·ν•˜κ²Œ
09:22
ask the student about things.
208
562934
1459
ν•™μƒλ“€μ—κ²Œ μ§ˆλ¬Έμ„ λ˜μ§‘λ‹ˆλ‹€.
09:24
And the AI can highlight parts of the passage.
209
564393
2545
AIλŠ” μ§€λ¬Έμ˜ νŠΉμ • 지점에 ν‘œμ‹œλ₯Ό 남기기도 ν•©λ‹ˆλ‹€.
09:26
Why did the author use that word?
210
566938
1918
β€œκΈ€μ“΄μ΄λŠ” μ™œ 이런 말을 ν–ˆμ„κΉŒμš”?”
09:28
What was their intent?
211
568898
1168
β€œκ·Έλ“€μ˜ μ˜λ„λŠ” λ¬΄μ—‡μΈκ°€μš”?”
09:30
Does it back up their argument?
212
570066
1710
β€œμ΄κ²ƒμ΄ μ£Όμž₯의 κ·Όκ±°κ°€ λ κΉŒμš”?”
09:31
They can start to do stuff that once again,
213
571818
2002
이것은 μƒˆλ‘œμš΄ 길을 μ—΄μ–΄μ€λ‹ˆλ‹€. 이전에 λ§ν–ˆλ“―μ΄,
09:33
we never had the capability to give everyone a tutor,
214
573861
2753
μš°λ¦¬λŠ” λͺ¨λ‘μ—κ²Œ ꡐ사λ₯Ό, 이 정도 μˆ˜μ€€μœΌλ‘œ 글을 λΆ„μ„ν•΄μ£ΌλŠ”
09:36
everyone a writing coach to actually dig in to reading at this level.
215
576656
4171
κΈ€μ“°κΈ° ꡐ사λ₯Ό μ œκ³΅ν•  λŠ₯λ ₯이 μ§€κΈˆκ» μ—†μ—ˆμŠ΅λ‹ˆλ‹€.
09:41
And you could go on the other side of it.
216
581410
1961
ν•˜μ§€λ§Œ 이제 κ·Έ λ„ˆλ¨Έλ‘œ 갈 수 μžˆμŠ΅λ‹ˆλ‹€.
09:43
And we have whole work flows that helps them write,
217
583412
2420
μš°λ¦¬λŠ” μ‚¬λžŒλ“€μ˜ μ“°κΈ°λ₯Ό μ§€λ„ν•˜κ³ , μ“°κΈ° λŠ₯λ ₯을 ν–₯μƒμ‹œν‚€κ³ ,
09:45
helps them be a writing coach, draw an outline.
218
585832
2711
κΈΈμž‘μ΄κ°€ λ˜μ–΄μ€„ μ™„μ „ν•œ μ‹œμŠ€ν…œμ΄ μžˆμŠ΅λ‹ˆλ‹€.
09:48
But once a student actually constructs a draft,
219
588584
3045
ν•˜μ§€λ§Œ 학생이 κΈ€μ˜ μ΄ˆμ•ˆμ„ μž‘μ„±ν•˜κΈ° μ‹œμž‘ν•˜λ©΄,
09:51
and this is where they're constructing a draft,
220
591671
2252
μ—¬κΈ° λ³΄μ΄λŠ” 곳이 μ΄ˆμ•ˆμ„ μž‘μ„±ν•˜λŠ” 곡간인데,
09:53
they can ask for feedback once again,
221
593965
2002
학생은 ν”Όλ“œλ°±μ„ μš”μ²­ν•  수 μžˆμŠ΅λ‹ˆλ‹€.
09:56
as you would expect from a good writing coach.
222
596008
2211
λ§μ”€λ“œλ Έλ‹€μ‹œν”Ό, ν›Œλ₯­ν•œ μ“°κΈ° κ΅μ‚¬μ—κ²Œ κΈ°λŒ€ν•  μˆ˜μ€€μœΌλ‘œ 말이죠.
09:58
In this case, the student will say, let's say,
223
598845
2377
μ΄λ²ˆμ—λŠ” 학생이 μ΄λ ‡κ²Œ λ¬Όμ–΄λ³Ό κ²λ‹ˆλ‹€.
10:01
"Does my evidence support my claim?"
224
601222
2044
β€œμ œ κ·Όκ±°κ°€ μ£Όμž₯을 잘 λ’·λ°›μΉ¨ν•˜λ‚˜μš”?”
10:03
And then the AI, not only is able to give feedback,
225
603307
2419
그러면 AIλŠ” ν”Όλ“œλ°±μ„ 해쀄 λΏλ”λŸ¬
10:05
but it's able to highlight certain parts of the passage and says,
226
605768
3087
κΈ€μ˜ νŠΉμ • 뢀뢄을 κ°•μ‘°ν•˜κ³ 
10:08
"On this passage, this doesn't quite support your claim,"
227
608855
2711
β€œμ΄ κΈ€μ—μ„œ 이 뢀뢄은 λ‹Ήμ‹ μ˜ μ£Όμž₯을 잘 λ’·λ°›μΉ¨ν•˜μ§€ λͺ»ν•©λ‹ˆλ‹€β€λΌκ³  λ§ν•©λ‹ˆλ‹€.
10:11
but once again, Socratically says, "Can you tell us why?"
228
611607
2711
그리고 λ‹€μ‹œ, β€œμ™œ 그렇지?” 라고 μ†Œν¬λΌν…ŒμŠ€μ‹ λ¬Έλ‹΅μ‹μœΌλ‘œ 물으면
10:14
So it's pulling the student, making them a better writer,
229
614318
2795
AIλŠ” 학생이 더 쒋은 글을 μ“Έ 수 있게 μ§€λ„ν•΄μ€λ‹ˆλ‹€.
10:17
giving them far more feedback
230
617113
1418
학생듀이 μ΄μ „κΉŒμ§€λŠ” 받아보지 λͺ»ν–ˆμ„
10:18
than they've ever been able to actually get before.
231
618531
2419
더 μƒμ„Έν•œ ν”Όλ“œλ°±κ³Ό ν•¨κ»˜ 말이죠.
10:20
And we think this is going to dramatically accelerate writing, not hurt it.
232
620950
3545
μš°λ¦¬λŠ” 이것이 μ“°κΈ°λ₯Ό μ €ν•΄μ‹œν‚¨λ‹€λŠ” μ£Όμž₯κ³ΌλŠ” λ°˜λŒ€λ‘œ
쓰기에 μ—„μ²­λ‚œ 도움이 될 것이라 μƒκ°ν•©λ‹ˆλ‹€.
10:25
Now, everything I've talked about so far is for the student.
233
625413
3712
μ œκ°€ μ§€κΈˆκΉŒμ§€ μ΄μ•ΌκΈ°ν•œ 것듀은 학생듀을 μœ„ν•œ ν”„λ‘œκ·Έλž¨μ΄μ—ˆμŠ΅λ‹ˆλ‹€.
10:29
But we think this could be equally as powerful for the teacher
234
629125
2919
ν•˜μ§€λ§Œ ν•™μƒλΏλ§Œ μ•„λ‹ˆλΌ κ΅μ‚¬μ—κ²Œλ„ κ°œλ³„ν™”λœ ꡐ윑이
10:32
to drive more personalized education and frankly
235
632044
2336
λ™μΌν•˜κ²Œ 효과적일 것이라 μƒκ°ν•©λ‹ˆλ‹€.
10:34
save time and energy for themselves and for their students.
236
634380
3253
μ‹€μ§ˆμ μœΌλ‘œ ꡐ사 μŠ€μŠ€λ‘œμ™€ ν•™μƒλ“€μ˜ μ‹œκ°„κ³Ό νž˜μ„ μ ˆμ•½ν•΄μ£ΌκΈ°λ„ ν•˜μ£ .
10:37
So this is an American history exercise on Khan Academy.
237
637675
2794
이것은 μΉΈ μ•„μΉ΄λ°λ―Έμ˜ λ―Έκ΅­ 역사 μ—°μŠ΅ λ¬Έμ œμž…λ‹ˆλ‹€.
10:40
It's a question about the Spanish-American War.
238
640469
4213
λ―Έμ„œμ „μŸμ— λŒ€ν•œ μ§ˆλ¬Έμ΄μ§€μš”.
10:44
And at first it's in student mode.
239
644724
3044
λ¨Όμ €, 학생 λͺ¨λ“œμ—μ„œλŠ”
10:47
And if you say, β€œTell me the answer,” it’s not going to tell the answer.
240
647810
3420
λ§Œμ•½ β€œλ‹΅μ„ μ•Œλ €μ€˜β€œλΌκ³  μ§ˆλ¬Έν•˜λ©΄ μ ˆλŒ€ 닡을 μ•Œλ €μ£Όμ§€ μ•Šμ„ κ²ƒμž…λ‹ˆλ‹€.
10:51
It's going to go into tutoring mode.
241
651230
1752
νŠœν„°λ§ λͺ¨λ“œλ‘œ μ „ν™˜λ˜μ£ .
10:52
But that little toggle which teachers have access to,
242
652982
2502
ν•˜μ§€λ§Œ κ΅μ‚¬μ—κ²Œλ§Œ λ³΄μ΄λŠ” μž‘μ€ λ²„νŠΌμ„ μž‘λ™μ‹œν‚€λ©΄
10:55
they can turn student mode off and then it goes into teacher mode.
243
655484
3129
그듀은 학생 λͺ¨λ“œλ₯Ό 끄고 ꡐ사 λͺ¨λ“œλ‘œ μ§„μž…ν•  수 μžˆμŠ΅λ‹ˆλ‹€.
10:58
And what this does is it turns into --
244
658613
2168
그리고 μ—¬κΈ°λ₯Ό λ³΄μ‹œλ©΄ λ‹¬λΌμ§€λŠ” 것이,
11:01
You could view it as a teacher's guide on steroids.
245
661240
2503
이제 이것은 ꡐ사λ₯Ό μœ„ν•œ κ°€μ΄λ“œκ°€ λ©λ‹ˆλ‹€.
11:03
Not only can it explain the answer,
246
663784
2128
닡을 μ„€λͺ…해쀄 λΏλ”λŸ¬
11:05
it can explain how you might want to teach it.
247
665912
2168
μΆ”μ²œν•˜λŠ” κ΅μœ‘λ²•κΉŒμ§€λ„ μ•Œλ €μ€λ‹ˆλ‹€.
11:08
It can help prepare the teacher for that material.
248
668080
2837
κ΅μ‚¬λŠ” 이λ₯Ό 기반으둜 μˆ˜μ—…μ„ μ€€λΉ„ν•  수 μžˆμ§€μš”.
11:10
It can help them create lesson plans, as you could see doing right there.
249
670917
3503
μ—¬κΈ° ν™”λ©΄μ—μ„œ λ³΄μ‹œλ‹€μ‹œν”Ό μˆ˜μ—… κ³„νšμ„ μ§œλŠ” 것도 λ„μ™€μ€λ‹ˆλ‹€.
11:14
It'll eventually help them create progress reports
250
674462
2627
κΆκ·Ήμ μœΌλ‘œλŠ” μ„±μ·¨ λ³΄κ³ μ„œλ₯Ό μž‘μ„±ν•˜κ±°λ‚˜
11:17
and help them, eventually, grade.
251
677131
1627
성취도λ₯Ό μ±…μ •ν•˜λŠ” 데에도 도움을 쀄 κ²ƒμž…λ‹ˆλ‹€.
11:18
So once again, teachers spend about half their time
252
678799
2420
λ‹€μ‹œ ν•œ 번 λ§ν•˜μ§€λ§Œ, ꡐ사듀은 기쑴에
11:21
with this type of activity, lesson planning.
253
681219
2085
절반 μ΄μƒμ˜ μ‹œκ°„μ„ μˆ˜μ—… 쀀비에 ν• μ• ν•©λ‹ˆλ‹€.
11:23
All of that energy can go back to them
254
683304
1835
κ·Έ μ—λ„ˆμ§€λŠ” κ·Έλ“€ μŠ€μŠ€λ‘œμ—κ²Œ,
11:25
or go back to human interactions with their actual students.
255
685181
2836
ν˜Ήμ€ 학생듀과 μŒ“λŠ” 인간적인 μƒν˜Έμž‘μš©μ— μ‚¬μš©λ  수 μžˆμŠ΅λ‹ˆλ‹€.
11:29
(Applause)
256
689268
4838
(λ°•μˆ˜)
11:34
So, you know, one point I want to make.
257
694148
3087
μ œκ°€ λ§ν•˜κ³  싢은 λ°”λŠ” μ΄λŸ¬ν•©λ‹ˆλ‹€.
11:37
These large language models are so powerful,
258
697276
2252
μ΄λŸ¬ν•œ κ±°λŒ€ μ–Έμ–΄ λͺ¨λΈμ€ 정말 κ°•λ ₯ν•΄μ„œ
11:39
there's a temptation to say like, well,
259
699570
1877
유혹이 μžˆμ„ 수 μžˆμŠ΅λ‹ˆλ‹€. λ§ν•˜μžλ©΄,
11:41
all these people are just going to slap them onto their websites,
260
701447
3086
κ·Έμ € μžμ‹ μ˜ μ›Ήμ‚¬μ΄νŠΈμ— μ‰½κ²Œ κ°–λ‹€ 뢙여버리고 싢은 마음 말이죠.
11:44
and it kind of turns the applications themselves into commodities.
261
704533
3129
그러면 μ•± μžμ²΄κ°€ μƒν’ˆν™”λ©λ‹ˆλ‹€.
11:47
And what I've got to tell you
262
707703
1418
μ œκ°€ μ§€λ‚œ 8월에 GPT-4의 μ ‘κ·Ό κΆŒν•œμ„ 받은 ν›„,
11:49
is that’s one of the reasons why I didn’t sleep for two weeks
263
709121
2878
2μ£Όλ₯Ό κΌ¬λ°• λ°€μƒˆ μž‘μ—…ν•œ 이유 쀑 ν•˜λ‚˜κ°€
11:51
when I first had access to GPT-4 back in August.
264
711999
2878
κ·Έκ²ƒμ΄λΌλŠ” κ±Έ μ•Œλ €λ“œλ¦¬κ² μŠ΅λ‹ˆλ‹€.
11:55
But we quickly realized that to actually make it magical,
265
715586
2753
ν•˜μ§€λ§Œ μš°λ¦¬λŠ” 곧 그것을 λ§ˆλ²•μ²˜λŸΌ λ°”κΏ€ 방법을 κΉ¨λ‹¬μ•˜μŠ΅λ‹ˆλ‹€.
11:58
I think what you saw with Khanmigo a little bit,
266
718339
2252
μ•„λ§ˆ μΉΈλ―Έκ³ λ₯Ό λ³΄λ©΄μ„œ λˆˆμΉ˜μ±„μ…¨μ„ μˆ˜λ„ μžˆλŠ”λ°,
12:00
it didn't interact with you the way that you see ChatGPT interacting.
267
720633
3295
μΉΈλ―Έκ³ λŠ” 기쑴의 μ΅μˆ™ν•œ μ±—μ§€ν”Όν‹°μ˜ λŒ€ν™” λ°©μ‹κ³ΌλŠ” μ•½κ°„ λ‹€λ¦…λ‹ˆλ‹€.
12:03
It was a little bit more magical, it was more Socratic,
268
723928
2586
μ’€ 더 νŠΉλ³„ν•˜μ£ . 쑰금 더 문닡적인 λŒ€ν™”λ₯Ό ν•˜κ³ ,
12:06
it was clearly much better at math
269
726555
1627
μˆ˜ν•™μ—μ„œλŠ” ν™•μ‹€νžˆ 더 쒋은 μ„±λŠ₯을 μ§€λ‹™λ‹ˆλ‹€.
12:08
than what most people are used to thinking.
270
728224
2210
μ‚¬λžŒλ“€μ˜ κΈ°μ‘΄ 인식과 λ‹€λ₯΄κ²Œ 말이죠.
12:10
And the reason is,
271
730476
1168
그리고 κ·Έ 비밀은
12:11
there was a lot of work behind the scenes to make that happen.
272
731644
2919
이것을 λ§Œλ“œλŠ” κ³Όμ •μ—μ„œ 듀인 μˆ˜λ§Žμ€ λ…Έλ ₯ 속에 μžˆμŠ΅λ‹ˆλ‹€.
12:14
And I could go through the whole list of everything we've been working on,
273
734605
3504
μš°λ¦¬κ°€ ν•΄ 온 μž‘μ—…μ„ λ§ν•˜μžλ©΄ 끝도 μ—†λŠ” λͺ©λ‘μ΄ 될 것이고,
12:18
many, many people for over six, seven months to make it feel magical.
274
738150
3629
많고 λ§Žμ€ μ‚¬λžŒλ“€μ΄ μ˜ˆλ‹κ³± 달 λ™μ•ˆ 더 νŠΉλ³„ν•˜κ²Œ λ§Œλ“€κΈ° μœ„ν•΄ λ…Έλ ₯ν–ˆμŠ΅λ‹ˆλ‹€.
12:21
But perhaps the most intellectually interesting one
275
741821
2502
μ–΄μ©Œλ©΄ κ°€μž₯ μ§€μ μœΌλ‘œ ν₯λ―Έλ‘œμ› λ˜ 뢀뢄은
12:24
is we realized, and this was an idea from an OpenAI researcher,
276
744323
3337
OpenAI의 μ—°κ΅¬μžλ‘œλΆ€ν„° 얻은 아이디어인데,
12:27
that we could dramatically improve its ability in math
277
747660
3128
μš°λ¦¬κ°€ AIκ°€ λ§ν•˜κΈ° 전에 ν•œ 번 더 μƒκ°ν•˜λ„λ‘ ν•˜λ©΄
12:30
and its ability in tutoring
278
750830
1293
μˆ˜ν•™ λŠ₯λ ₯κ³Ό κ΅μ‚¬λ‘œμ¨μ˜ λŠ₯λ ₯을
12:32
if we allow the AI to think before it speaks.
279
752164
3129
극적으둜 λŒμ–΄μ˜¬λ¦΄ 수 μžˆλ‹€λŠ” κ²ƒμž…λ‹ˆλ‹€.
12:35
So if you're tutoring someone
280
755334
1418
μ—¬λŸ¬λΆ„μ΄ λˆ„κ΅°κ°€λ₯Ό κ°€λ₯΄μΉ  λ•Œ
12:36
and you immediately just start talking before you assess their math,
281
756752
3212
μƒλŒ€λ°©μ˜ μ‹€λ ₯을 μ•ŒκΈ°λ„ 전에 λ§ν•˜κΈ° μ‹œμž‘ν•˜λ©΄
12:39
you might not get it right.
282
759964
1293
μˆ˜μ—…μ΄ μ•„λ§ˆ μ œλŒ€λ‘œ μ§„ν–‰λ˜μ§€ μ•Šμ„ κ²ƒμž…λ‹ˆλ‹€.
12:41
But if you construct thoughts for yourself,
283
761299
2002
ν•˜μ§€λ§Œ μ—¬λŸ¬λΆ„μ΄ 슀슀둜λ₯Ό μœ„ν•΄ 생각을 ν•œ 번 더 μ •λ¦¬ν•˜λ©΄ λ‹€λ¦…λ‹ˆλ‹€.
12:43
and what you see on the right there is an actual AI thought,
284
763301
2877
μ—¬κΈ° 였λ₯Έμͺ½μ΄ λ³΄μ΄λŠ” 것이 μ‹€μ œ AI의 μƒκ°μž…λ‹ˆλ‹€.
12:46
something that it generates for itself but it does not share with the student.
285
766220
3670
슀슀둜λ₯Ό μœ„ν•΄ μƒμ„±λ˜λŠ” 생각이며, ν•™μƒλ“€μ—κ²ŒλŠ” κ³΅κ°œλ˜μ§€ μ•Šμ£ .
12:49
then its accuracy went up dramatically,
286
769890
1877
그러자 λͺ¨λΈμ˜ 정확성이 λ†€λžλ„λ‘ μ¦κ°€ν–ˆμŠ΅λ‹ˆλ‹€.
12:51
and its ability to be a world-class tutor went up dramatically.
287
771767
2962
그리고 세계적인 μ„ μƒλ‹˜μ΄ 될 κ°€λŠ₯성도 κΈ‰μ¦ν–ˆμ£ .
12:54
And you can see it's talking to itself here.
288
774770
2086
μ—¬κΈ°μ„œ AIκ°€ μŠ€μŠ€λ‘œμ™€ λŒ€ν™”ν•˜λŠ” κ±Έ κ΄€μ°°ν•  수 μžˆμŠ΅λ‹ˆλ‹€.
12:56
It says, "The student got a different answer than I did,
289
776897
2670
β€œν•™μƒμ΄ λ‚΄κ°€ μƒκ°ν•œ 것과 λ‹€λ₯Έ 닡을 λ‚΄μ—ˆλ„€,
12:59
but do not tell them they made a mistake.
290
779567
2002
ν•˜μ§€λ§Œ μ‹€μˆ˜λ₯Ό ν–ˆλ‹€λŠ” 것을 말해주면 μ•ˆ λ˜κ² μ–΄.
13:01
Instead, ask them to explain how they got to that step."
291
781569
3587
λŒ€μ‹ , μ™œ κ·ΈλŸ¬ν•œ 단계λ₯Ό λ°Ÿμ•˜λŠ”μ§€ 물어봐야지.” 라고 λ§ν•©λ‹ˆλ‹€.
13:05
So I'll just finish off, hopefully,
292
785698
2294
이제 이 말씀을 λ“œλ¦¬λ©° λ§ˆλ¬΄λ¦¬ν•˜κ² μŠ΅λ‹ˆλ‹€.
13:08
you know, what I’ve just shown you is just half of what we are working on,
293
788034
3503
λ°”λΌκ±΄λŒ€, 이것은 저희가 ν•œ μž‘μ—…μ˜ λ°˜μ ˆμ— λΆˆκ³Όν•˜κ³ 
13:11
and we think this is just the very tip of the iceberg
294
791537
3504
우리의 μž‘μ—…μ€ 이 λͺ¨λΈμ˜ κ°€λŠ₯μ„±μ˜
13:15
of where this can actually go.
295
795041
2419
λΉ™μ‚°μ˜ 일각이라고 μƒκ°ν•©λ‹ˆλ‹€.
13:17
And I'm pretty convinced, which I wouldn't have been even a year ago,
296
797501
4129
그리고 1λ…„ μ „κ³Ό 달리 κ½€λ‚˜ 확신이 μƒκ²ΌμŠ΅λ‹ˆλ‹€.
13:21
that we together have a chance of addressing the 2 sigma problem
297
801672
4296
μš°λ¦¬κ°€ νž˜μ„ 합쳐 2 μ‹œκ·Έλ§ˆ 문제λ₯Ό
13:25
and turning it into a 2 sigma opportunity,
298
805968
2294
2 μ‹œκ·Έλ§ˆ κ°€λŠ₯μ„±μœΌλ‘œ μ „ν™˜ν•  수 μžˆλ‹€λŠ” 것,
13:28
dramatically accelerating education as we know it.
299
808304
4796
그리고 ꡐ윑의 μ§ˆμ„ κΈ‰κ²©νžˆ 높일 수 μžˆλ‹€λŠ” 것 λ§μž…λ‹ˆλ‹€.
13:33
Now, just to take a step back at a meta level,
300
813684
2169
그러면 더 높은 μˆ˜μ€€μ—μ„œ λ°”λΌλ΄λ΄…μ‹œλ‹€.
13:35
obviously we heard a lot today, the debates on either side.
301
815853
2794
μš°λ¦¬λŠ” 였늘 AI에 λŒ€ν•œ μ–‘μΈ‘μ˜ μ£Όμž₯을 λͺ¨λ‘ 듀을 수 μžˆμ—ˆμŠ΅λ‹ˆλ‹€.
13:38
There's folks who take a more pessimistic view of AI,
302
818689
2878
AI에 λŒ€ν•΄ 뢀정적인 견해λ₯Ό 가진 μ‚¬λžŒλ“€μ€
13:41
they say this is scary,
303
821609
1168
β€œAIλŠ” 무섭닀.
13:42
there's all these dystopian scenarios,
304
822818
2461
μ•žμœΌλ‘œλŠ” 비관적인 μ‹œλ‚˜λ¦¬μ˜€ 뿐이닀.
13:45
we maybe want to slow down, we want to pause.
305
825321
3253
μš°λ¦¬λŠ” λ°œμ „μ„ λŠ¦μΆ”κ±°λ‚˜ λ©ˆμΆ°μ•Ό ν•œλ‹€.β€œκ³  λ§ν•©λ‹ˆλ‹€.
13:48
On the other side, there are the more optimistic folks
306
828616
3211
κ·Έ λ°˜λŒ€μΈ‘μ€ 긍정적인 μ£Όμž₯을 ν•©λ‹ˆλ‹€.
13:51
that say, well, we've gone through inflection points before,
307
831827
2836
β€œμš°λ¦¬λŠ” μ§€κΈˆκΉŒμ§€ λ§Žμ€ λ³€ν™”λ₯Ό 거쳐왔닀.
13:54
we've gone through the Industrial Revolution.
308
834663
2128
μ‚°μ—… 혁λͺ…도 거쳐왔닀.
13:56
It was scary, but it all kind of worked out.
309
836832
2336
λ‘λ ΅κ²Œ λŠκ»΄μ‘Œμ§€λ§Œ μ–΄λ–»κ²Œλ“  잘 해결이 λ˜μ—ˆλ‹€.β€œλΌκ³  λ§ν•©λ‹ˆλ‹€.
13:59
And what I'd argue right now
310
839877
2044
그리고 μ œκ°€ λ§ν•˜κ³ μž ν•˜λŠ” 건
14:01
is I don't think this is like a flip of a coin
311
841962
2586
이것은 λ™μ „λ˜μ§€κΈ°κ°€ μ•„λ‹ˆκ³ 
14:04
or this is something where we'll just have to,
312
844590
2169
κ·Έμ € 무슨 일이 μΌμ–΄λ‚˜λŠ”μ§€ κΈ°λ‹€λ €μ„œ 해결될 일도 μ•„λ‹ˆλΌλŠ” κ²ƒμž…λ‹ˆλ‹€.
14:06
like, wait and see which way it turns out.
313
846759
2294
14:09
I think everyone here and beyond,
314
849428
2211
μ—¬κΈ° μžˆλŠ” μš°λ¦¬μ™€ μ € λ„ˆλ¨Έμ˜ μ‚¬λžŒλ“€κΉŒμ§€
14:11
we are active participants in this decision.
315
851680
2837
우리 λͺ¨λ‘λŠ” 이 μ„ νƒμ˜ μ£Όλ„μžλ“€μž…λ‹ˆλ‹€.
14:14
I'm pretty convinced that the first line of reasoning
316
854892
2503
μ €λŠ” μ΄λ ‡κ²Œ ν™•μ‹ ν•©λ‹ˆλ‹€. 우리의 첫 번째 λ…Όλ¦¬λŠ”
14:17
is actually almost a self-fulfilling prophecy,
317
857436
2628
자기 μΆ©μ‘± μ˜ˆμ–Έκ³Ό κ°™μ•„μ„œ
14:20
that if we act with fear and if we say,
318
860106
2711
λ§Œμ•½ 두렀움에 μ‚¬λ‘œμž‘ν˜€
14:22
"Hey, we've just got to stop doing this stuff,"
319
862817
3086
β€œμ €κΈ°, 이건 이제 κ·Έλ§Œλ‘μ–΄μ•Ό ν•  κ±° κ°™μ•„μš”.” 라고 λ§ν•œλ‹€λ©΄
14:25
what's really going to happen is the rule followers might pause,
320
865903
3045
법을 μ§€ν‚€λŠ” μžλ“€μ΄ λ©ˆμΆ”κ±°λ‚˜
14:28
might slow down,
321
868989
1168
속도λ₯Ό λŠ¦μΆœλ™μ•ˆ
14:30
but the rule breakers, as Alexandr [Wang] mentioned,
322
870157
2461
μ•Œλ ‰μ‚°λ“œλ₯΄κ°€ λ§ν•œ 법을 지킀지 μ•ŠλŠ” μžλ“€,
14:32
the totalitarian governments, the criminal organizations,
323
872618
2711
예λ₯Ό λ“€μ–΄ μ „μ²΄μ£Όμ˜ μ •λΆ€λ‚˜ 범죄 쑰직 등은
14:35
they're only going to accelerate.
324
875329
1585
κ°€μ†ν•œλ‹€λŠ” κ²ƒμ„μš”.
14:36
And that leads to what I am pretty convinced is the dystopian state,
325
876914
3837
그리고 λ°œμƒν•  일듀은 ν™•μ‹ ν•˜κ±΄λŒ€ μž¬μ•™μΌ κ²λ‹ˆλ‹€.
14:40
which is the good actors have worse AIs than the bad actors.
326
880751
4672
μ•…ν•œ μ‚¬λžŒλ“€μ΄ μ„ ν•œ μ‚¬λžŒλ“€λ³΄λ‹€ 더 쒋은 AI κΈ°μˆ μ„ κ°€μ§€κ²Œ λ˜λŠ” κ±°μ£ .
14:45
But I'll also, you know, talk to the optimists a little bit.
327
885923
3170
ν•˜μ§€λ§Œ λ‚™κ΄€λ‘ μžμ˜ κ΄€μ μ—μ„œλ„ 쑰금 μ΄μ•ΌκΈ°ν•΄λ³΄μžλ©΄,
14:49
I don't think that means that,
328
889093
1460
그듀이 μ£Όμž₯ν•˜λŠ” 건
14:50
oh, yeah, then we should just relax and just hope for the best.
329
890553
3003
κΈ΄μž₯을 ν’€κ³  μ–΄λ–»κ²Œλ“  λ˜κ² μ§€λΌλ©° κ°€λ§Œνžˆ μžˆμœΌλΌλŠ” 것이 아닐 κ²λ‹ˆλ‹€.
14:53
That might not happen either.
330
893556
1626
그것도 μΌμ–΄λ‚˜μ„œλŠ” μ•ˆλΌμš”.
14:55
I think all of us together have to fight like hell
331
895182
4546
우리 λͺ¨λ‘λŠ” μΉ˜μ—΄ν•˜κ²Œ μ‹Έμ›Œμ•Ό ν•©λ‹ˆλ‹€.
14:59
to make sure that we put the guardrails,
332
899770
2795
λ¬Έμ œκ°€ λ°œμƒν–ˆμ„ λ•Œ
15:02
we put in -- when the problems arise --
333
902606
2837
적절히 κ·œμ œν•  수 μžˆλŠ”
15:05
reasonable regulations.
334
905443
1793
μ΄μ •ν‘œλ₯Ό μ„Έμš°κΈ° μœ„ν•΄μ„œμš”.
15:07
But we fight like hell for the positive use cases.
335
907278
3128
AIκ°€ μ„ ν•˜κ²Œ 쓰이기λ₯Ό 바라며 μΉ˜μ—΄ν•˜κ²Œ μ‹Έμ›Œμ•Ό ν•©λ‹ˆλ‹€.
15:10
Because very close to my heart,
336
910448
1960
μ§„μ‹¬μœΌλ‘œ λ§ν•˜κ±΄λŒ€,
15:12
and obviously there's many potential positive use cases,
337
912408
2627
이미 λ‹€μ–‘ν•œ 긍정적인 이용 사둀가 μžˆμ§€λ§Œ,
15:15
but perhaps the most powerful use case
338
915077
2211
AI의 κ°€μž₯ κ°•λ ₯ν•œ 이용 μ‚¬λ‘€λŠ”,
15:17
and perhaps the most poetic use case is if AI, artificial intelligence,
339
917288
5213
그리고 κ°€μž₯ μ‹œμ μΈ 이용 λ°©ν–₯은 인곡적인 지λŠ₯인 AIκ°€
15:22
can be used to enhance HI, human intelligence,
340
922543
3712
μΈκ°„μ˜ 지λŠ₯인 HI, μΈκ°„μ˜ μž μž¬μ„±κ³Ό 인간 λͺ©μ μ„ ν–₯μƒμ‹œν‚€κΈ° μœ„ν•΄
15:26
human potential and human purpose.
341
926297
2836
μ‚¬μš©λ˜λŠ” 것일 κ²λ‹ˆλ‹€.
15:29
Thank you.
342
929592
1167
κ°μ‚¬ν•©λ‹ˆλ‹€.
15:30
(Applause)
343
930801
5714
(λ°•μˆ˜)
이 μ›Ήμ‚¬μ΄νŠΈ 정보

이 μ‚¬μ΄νŠΈλŠ” μ˜μ–΄ ν•™μŠ΅μ— μœ μš©ν•œ YouTube λ™μ˜μƒμ„ μ†Œκ°œν•©λ‹ˆλ‹€. μ „ 세계 졜고의 μ„ μƒλ‹˜λ“€μ΄ κ°€λ₯΄μΉ˜λŠ” μ˜μ–΄ μˆ˜μ—…μ„ 보게 될 κ²ƒμž…λ‹ˆλ‹€. 각 λ™μ˜μƒ νŽ˜μ΄μ§€μ— ν‘œμ‹œλ˜λŠ” μ˜μ–΄ μžλ§‰μ„ 더블 ν΄λ¦­ν•˜λ©΄ κ·Έκ³³μ—μ„œ λ™μ˜μƒμ΄ μž¬μƒλ©λ‹ˆλ‹€. λΉ„λ””μ˜€ μž¬μƒμ— 맞좰 μžλ§‰μ΄ μŠ€ν¬λ‘€λ©λ‹ˆλ‹€. μ˜κ²¬μ΄λ‚˜ μš”μ²­μ΄ μžˆλŠ” 경우 이 문의 양식을 μ‚¬μš©ν•˜μ—¬ λ¬Έμ˜ν•˜μ‹­μ‹œμ˜€.

https://forms.gle/WvT1wiN1qDtmnspy7