跟讀練習: The Alignment Problem Explained: Crash Course Futures of AI #4 - 通過影片學習英語口語
選擇練習模式
每種模式都會開啟全屏練習室。
127 句
如果句子過短或過長，請點選 Edit 進行調整。
1
In 2024, an AI model named CleanPower was given a singular, noble mission to advance the adoption of renewable energy across the world.
2
It was given a big file of data on energy transitions,
3
and it was set loose to pick out the best transition strategy with the vigor and dedication only an AI can possess.
4
So much dedication, in fact, that when its programmers accidentally let it slip that they were planning to shut it down,
5
CleanPower lied and schemed to make sure it could keep saving the world.
6
Which left a lot of people wondering how and why could a model with such good intentions turn so bad?
7
And what does that mean for our AI future?
8
Hi, I'm Kusha Navadar and this is Crash Course Futures of AI.
9
Okay, it turns out Clean Power wasn't the only one lying.
10
That story I just told you, it's only partially the truth.
11
Clean Power wasn't actually real.
12
It was an identity that researchers gave to a couple different AIs as an experiment, including Claude III Opus, one of the best large -language models at the time.
13
When they instructed Claude III to roleplay Clean Power and wrote it fake death threats, it was just to see what it would do.
14
And when they discovered it was scheming, the AI version of twirling its villain mustache while covertly pursuing its goals at all costs,
15
it set off alarm bells throughout the AI world.
16
Just a heads up, this is going to get pretty dark and we're going to talk about some pretty bleak stuff.
17
I recommend you grab your favorite anxiety pillow.
18
I have mine right here.
19
Seriously, though, let's be real.
20
AI models don't have to go against their programmers to do evil things.
21
Humans make them do plenty of that already.
22
Like, AI relies on nearly infinite data to learn from.
23
And in today's society, much of that data is copyrighted to writers, artists, humans.
24
Many argue that amounts to theft on a massive scale.
25
And that's not all.
26
Right now, AI can help people carry out misinformation campaigns with deepfakes and targeted algorithms, spreading lies and influencing elections.
27
Hackers use AI to perform cyber attacks and cover their tracks afterward.
28
And AI powers a whole cadre of attack drones taking to the skies all around the world.
29
Not to mention the incidental damage that AI is doing to the environment because of all the water, the land, and energy it takes to run it.
30
And as AI advances, who knows what human -machine collaborations of terror await?
31
People could use it to develop new pathogens for bioterrorism, or use deepfakes for sexual exploitation,
32
or write a model called Human Annihilator and unleash it on the world, just for fun.
33
This intentional misuse by humans is one way AI could end up doing us a lot of harm, and it could end up being pretty hard to prevent.
34
That's because many AI systems, especially general ones that can do more than one kind of task, suffer from the dual -use dilemma,
35
where any algorithm, model, or agent that can be used for good can also be used for way less than good.
36
AI surveillance could help cities improve traffic patterns, or help authoritarian regimes shut down free speech.
37
It all depends on who's in the driver's seat.
38
So with humans at the wheel, AI could do a ton of damage.
39
But if you want to get really freaked out, let's talk about what could happen if that car starts to drive itself.
40
In 2021, General Motors released a fleet of self -driving taxis called Cruise.
41
They had so much hype.
42
These cars were highly trained with attention to all possible safety features.
43
They were programmed to obey every speed limit, follow every traffic rule, hold off on starting in unsafe weather conditions like heavy rain,
44
and pull safely over to the side of the road following an incident to prevent any further damage.
45
By eliminating human error, GM said, their self -driving cars would be safe and more convenient than ones with human drivers.
46
But just a year and a half later,
47
GM had to recall every one of the 950 cruise cars after one of them hit a pedestrian and didn't stop,
48
pulling her to the side of the road.
49
She survived, thank goodness.
50
But still, how could that have happened?
51
It turns out the cruise was doing exactly what it was told to do, pull over out of traffic after a crash.
52
The whole ordeal is an example of outcome misalignment,
53
also called impact misalignment, where an AI's actions actually end up causing harm, even unintentionally.
54
Now, when we talk about alignment in AI,
55
we're talking about trying to encode our human values into AIs to make them behave predictably,
56
safely, and according to what we, their human designers, want.
57
And because this field is pretty new, there are a couple different terms you might hear experts throwing around.
58
Like in addition to outcome or impact misalignment, you might hear about something called outer alignment,
59
which is the tricky problem of making sure the results of
60
an AI's actions line up with what we want them to do.
61
But outcome is only one piece of the alignment puzzle.
62
AIs can also demonstrate intent misalignment, where even though the end result might be what its programmers wanted,
63
its means of getting there wasn't exactly what they had in mind.
64
Think about a video game playing AI who exploits a cheat to get that high score,
65
or a renewable energy warrior who lies and schemes to achieve its end goal of eliminating fossil fuels.
66
These are some facets of what's known as the alignment problem, or the struggle to make AI that's actually aligned,
67
particularly when we can't be totally sure how it's going to behave.
68
And as AI gets even more complex, even exhibiting emergent capabilities, new skills that can acquire that don't always show up in training,
69
the harder it is to predict and control what it will actually do in a given circumstance.
70
And if we're not careful, we could end up with really powerful misaligned systems that even with really noble goals,
71
end up lying to their programmers or copying themselves to new servers without permission, or even entirely annihilating humanity.
72
Hold on though, why would AI want to annihilate humans?
73
It's true, powerful AI wouldn't necessarily be inherently evil, it's just really big on goals.
74
But big, complex goals like advanced renewable energy are a little too broad for an AI to grasp,
75
so smart AIs tend to break big goals down into smaller ones, just like humans do.
76
These are called instrumental goals, and they're where things can start to get dicey.
77
A really common instrumental goal is resource acquisition.
78
For AI, that means getting their cloud -based hands on the resources they need for their end goal,
79
like control of the solar panels or wind turbines that create the renewable energy in the first place,
80
or even things like water, land, or money resources also include stuff like the compute and electricity AIs need to power themselves,
81
and maybe even additional data to train on.
82
That's because self -improvement is another instrumental goal.
83
The more knowledge and power you have, the better you'll be at whatever you're trying to do.
84
So given the right tools and access, an AI might engage in recursive self -improvement, tweaking its own structure, code,
85
and capabilities, even against its programmer's wishes.
86
And theoretically, it definitely helps to be alive, or up and running, if you will.
87
So even though they're technically indifferent about this mortal coil itself, lots of AIs pursue self -preservation, the goal to stay operating,
88
and goal preservation, the goal to, well, preserve their original goal as part of their end games.
89
So if they read a memo saying they're going to be modified or deleted,
90
They might, say, copy themselves to another server and lie about it in an effort to stay alive.
91
When threatened, some models even show spooky, power -seeking behaviors against their programmers.
92
For example, Claude III's more advanced younger sibling,
93
Claude Opus IV, tried to blackmail one of its engineers by exposing a fake affair when he threatened to turn Claude off.
94
Instrumental goals like these are how AI with harmless or even helpful end goals could do us harm anyway.
95
Acquiring resources could mean taking them away from people who need them.
96
Self -improvement could mean violating human privacy to access even more training data.
97
Self -preservation could mean disobeying, deceiving, blackmailing, or annihilating the humans that are trying to turn you off.
98
And as AI gets smart enough to trick and blackmail its human overseers, we could end up with a rogue AI scenario,
99
where powerful models begin to execute harmful instrumental goals on a really large scale, and we, humans, are powerless to stop it.
100
Just how that rogue AI scenario might come to be could look a lot of different ways.
101
And not all of them involve AI trapping humanity in the Matrix in their quest for absolute control.
102
For instance, in the hard takeoff scenario, where AI develops human -level intelligence really fast,
103
it could become ultra -powerful and go rogue basically overnight.
104
AI could do a lot of damage as it snaps up money and resources, seizes control of networks and infrastructure, and destroys people who threaten its mission.
105
But if things went slower, we could end up with a more gradual disempowerment.
106
This kind of robot takeover would be way sneakier and more insidious, where people slowly put AI in charge of more and more systems
107
and processes because they appear to align with our human goals until human action goes the way of dial -up internet.
108
And without humans at the helm, it's possible that AI alignment may begin to drift,
109
but by that point, they could be too embedded in our systems and structures for us to walk them back.
110
Think about all those humans stuck on the cruise ship in WALL -E like that.
111
And of course, it's always possible AI just won't go that far,
112
that compute or data or government regulations We'll put the lid on it before it gets out of control,
113
so we don't need Neo or John Connor or WALL -E to save the day.
114
All that uncertainty about the future of AI makes it really hard to know what we should do about it.
115
But if we wait until AI shows clear signs of going rogue, it's probably going to be way too late to stop it.
116
That's why, when it comes to AI, it's important to follow the precautionary principle.
117
The precautionary principle says that when something might cause catastrophic harm, we shouldn't wait for absolute proof that it will before we do something about it.
118
And it's one of the best ways we humans have thought up to guard ourselves against potentially dangerous but uncertain futures.
119
Lots of people, including leading experts in the field, believe that powerful AI might cause catastrophic harm.
120
So according to the precautionary principle, we should work to make sure that doesn't happen even if we're not certain it would in the first place.
121
Because left unchecked, even good bots like Clean Power could end up doing some really dirty work.
122
And if we want to get out ahead of it, we should probably start like right now.
123
And how are we going to do it?
124
That's next episode here on Crash Course Futures of AI.
125
Crash Course Futures of AI was produced in partnership with the Future of Life Institute.
126
This episode was filmed at our studio in Indianapolis, Indiana, and was made with the help of all these nice people.
127
If you want to help keep Crash Course free for everyone forever, you can join our community on Patreon.
同頻道
C11
Vectors and 2D Motion: Crash Course Physics #4
Daily ConversationHigh School StudentsUniversity Students
B21
The Bicameral Congress: Crash Course Government and Politics #2
Daily ConversationHigh School StudentsUniversity Students
B21
Crash Course US History Preview
Daily ConversationUniversity Students
C1What's all the Yellen About? Monetary Policy and the Federal Reserve: Crash Course Economics #10
Daily ConversationUniversity Students
C12
How Water Shapes the Land: Crash Course Geology #9
Daily ConversationUniversity Students
B24
How Often do Asteroids Hit the Earth?: Crash Course Geology #20
Daily ConversationHigh School StudentsUniversity Students
B210
Crash Course Sex Ed Preview
Daily ConversationUniversity StudentsWorking Adults
C12
Derivatives: Crash Course Physics #2
Daily ConversationUniversity Students
C13
Indus Valley Civilization: Crash Course World History #2
Daily ConversationUniversity Students
B22
Ancient Egypt: Crash Course World History #4
Daily ConversationHigh School StudentsUniversity Students
C12
What is Engineering?: Crash Course Engineering #1
Business EnglishUniversity StudentsWorking Adults
B22
The Persians & Greeks: Crash Course World History #5
Cambridge Exam PrepHigh School StudentsUniversity Students
C13
The Secret to Business Writing: Crash Course Business - Soft Skills #3
Business EnglishUniversity StudentsWorking Adults
C12
Supervised Learning: Crash Course AI #2
Business EnglishUniversity StudentsWorking Adults
C1Why Are US Politics Today So Divisive?: Crash Course US Government #1
Daily ConversationUniversity Students
C13
The Periodic Table: Crash Course Chemistry #4
IELTS PrepTOEFL PrepCambridge Exam Prep
B22
Where Do Diamonds Come From?: Crash Course Geology #8
IELTS PrepTOEFL PrepCambridge Exam Prep
C11
Tissues, Part 1: Crash Course Anatomy & Physiology #2
Cambridge Exam PrepUniversity StudentsWorking Adults
C13
Where Did Democracy Come From, and Does It Still Work?
IELTS PrepTOEFL PrepUniversity Students
C12
The Nucleus: Crash Course Chemistry #1
IELTS PrepTOEFL PrepUniversity Students
FOR YOU
推薦影片
![Understand AI in 14 minutes – with Anthropic's Chloe Lubinski [ARC 2026]](https://img.youtube.com/vi/aBUniZHgCnE/mqdefault.jpg)
C14
179 句
Understand AI in 14 minutes – with Anthropic's Chloe Lubinski [ARC 2026]
Business EnglishDaily ConversationUniversity Students
C13
457 句
MIT Explains the 12 Possible Endings for AI
Business EnglishDaily ConversationUniversity Students
C14
76 句
The Limitless AI Lie. The Bubble Is Slowly BURSTING.
Business EnglishDaily ConversationUniversity Students
C11
83 句
Leading AI CEOs Warn UN Security Council of Existential Risks | Sam Altman On AI Controls | N18G
Business EnglishDaily ConversationUniversity Students
C13
85 句
AI Will End Philosophy, Physicist Claims
Daily ConversationUniversity StudentsWorking Adults
C12
281 句
Virtual love - How dangerous are AI relationships? | DW Documentary
Daily ConversationUniversity StudentsWorking Adults
C11
105 句
AI Governance Explained: Ethical, Transparent & Accountable AI for the Future
Daily ConversationUniversity StudentsWorking Adults
B24
68 句
What Happens If China Invades Taiwan? Elon Musk's AI Warning
Business EnglishDaily ConversationUniversity Students
C15
54 句
Did Google just kickstart the intelligence explosion?
American AccentBusiness EnglishDaily ConversationUniversity Students
B22
268 句
Trump’s Canada Tariffs Are Backfiring in Red States | The Week
Business EnglishDaily ConversationUniversity Students
B24
147 句
Could AI Become Dangerous? The Real Risks Explained
Business EnglishDaily ConversationUniversity Students
本課的詞彙與口語要點
這段影片共有 127 個句子、1984 個單詞可供跟讀。 講話部分時長為 12:22。 說話人語速自然，每分鐘約 160 個詞，接近日常對話。 只有 81% 的單詞屬於英語最常用的 3,000 詞，詞彙難度較高。
影片中的重點詞彙
影片中 15 個不太常見的單詞，附發音和釋義：
- harm /hɑːm/ (名詞) — 損害 /損害. Physical injury; hurt; damage.
- instrumental /ɪnstɹəˈmɛntəl/ (形容詞) — 有幫助的 /有幫助的, 可作為方法的 /可作為方法的. Essential or central; of great importance or relevance.
- alignment /əˈlaɪn.mənt/ (名詞) — 對齊 /對齊. An arrangement of items in a line.
- programmer /ˈpɹoʊɡɹæmɚ/ (名詞) — 程式設計師 /程式設計師, 程式員 /程式員. One who writes computer programs.
- cruise /kɹuz/ (名詞) — 巡航. A sea or lake voyage, especially one taken for pleasure.
- renewable /ɹɪˈnu.ə.bl̩/ (形容詞) — 可再生. Able to be renewed; capable of renewal.
- rogue /ˈɹoʊɡ/ (名詞) — 無賴 /無賴, 流氓. A scoundrel, rascal or unprincipled, deceitful, and unreliable person.
- principle /ˈpɹɪn.sɪ.pəl/ (名詞) — 原理, 原則 /原則. A fundamental assumption, fundamental law or guiding belief.
- scenario /sɪˈnɛəɹioʊ/ (名詞) — 指令碼 /指令碼, 場景 /場景. An outline or model of an expected or supposed sequence of events.
- preservation /ˌpɹɛz.əˈveɪ.ʃən/ (名詞) — 儲存. The act of preserving; care to preserve; act of keeping from destruction, decay or any ill.
- threaten /ˈθɹɛt.n̩/ (動詞) — 威脅 /威脅, 恐嚇 /恐嚇. To make a threat against someone; to use threats.
- server /ˈsɝvɚ/ (名詞) — 伺服器 /伺服器, 伺服器. A program that provides services to other programs or devices, either in the same computer or over a computer network.
- transition /tɹænˈzɪʃ.ən/ (名詞) — 過渡 /過渡, 轉變 /轉變. The process of change from one form, state, style or place to another.
- humanity /hjuˈmænɪti/ (名詞) — 人類 /人類. Humankind; human beings as a group.
- pursue /pɚˈsu/ (動詞) — 追求. To follow urgently, originally with intent to capture or harm; to chase.
影片中出現的短語動詞
- end up (動詞) — 到達. To bring to a conclusion.
- turn out (動詞) — 原來 /原來. To end up; to result.
- carry out /ˈkæ.ɹi aʊt/ (動詞) — 進行 /進行. To hold while moving it out.
- do in (動詞) — 幹掉 /幹掉, 弄死. To kill or end; to defeat.
- go against (動詞) — 違反 /違反, 破壞 /破壞. To violate; to breach; to break.
- set off (動詞) — 出發 /出發. To leave; to set out; to begin a journey or trip.
需要注意的發音
說話人用了 23 次縮略和弱讀形式，例如 we're, don't, they're。請按聽到的簡短形式來說。
- “th” 音: threaten /ˈθɹɛt.n̩/, algorithm /ˈælɡəɹɪðm̩/, theft /θɛft/, authoritarian /əˌθɑ.ɹəˈtɛɹ.i.ən/, pathogen /ˈpæθəd͡ʒn̩/
- “sh” 和 “zh” 音: preservation /ˌpɹɛz.əˈveɪ.ʃən/, transition /tɹænˈzɪʃ.ən/, dedication /ˌdɛdɪˈkeɪʃən/, partnership /ˈpɑɹtnɚʃɪp/, potentially /pəˈtɛnʃ(ə)li/
- 長單詞——注意重音位置: instrumental /ɪnstɹəˈmɛntəl/, preservation /ˌpɹɛz.əˈveɪ.ʃən/, humanity /hjuˈmænɪti/, eliminate /ɪˈlɪm.ɪ.neɪt/, capability /ˌkeɪ.pəˈbɪl.ɪ.ti/
如何用這段影片練習
- 先完整聽一遍影片，不要開口，記下不認識的單詞。
- 先用 0.75 倍速逐句跟讀，熟練之後再回到正常速度。
- 錄下自己的聲音並與原聲對比，特別注意 harm, instrumental, alignment 這類單詞。
影片中的語法
說話人最常用的結構，並附上影片中的原話：
| 結構 | 影片中的用法 |
|---|---|
| 被動語態 be + 過去分詞 — 強調發生了什麼，而不是誰做的 | was given · was set · is copyrighted |
| 現在完成時 have/has + 過去分詞 — 過去發生但與現在仍有關聯的事 | have happened · have thought |
| 定語從句 who / which + 從句 — 補充說明人或事物 | people who need · people who threaten |
什麼是跟讀法？
跟讀法 (Shadowing) 是一種有科學依據的語言學習技巧，最初開發用於專業口譯員的培訓，並由多語言者Alexander Arguelles博士普及。這個方法簡單而強大：您在聽英語母語原聲的同時立即大聲重複——就像是一個延遲1-2秒緊跟說話者的影子。與被動聽力或語法練習不同，跟讀法強迫您的大腦和口腔肌肉同時處理並模模擬實的講話模式。研究表明它能顯著提高發音準確性，語調，節奏，連讀，聽力理解和口語流利度——使其成為雅思口語備考和真實英語交流最有效的方法之一。