Luyện nói tiếng Anh bằng Shadowing qua video: Master the Perfect ChatGPT Prompt Formula (in just 8 minutes)!

Chọn chế độ luyện tập

Mỗi chế độ mở một phòng luyện tập toàn màn hình.

129 câu
Nếu các câu quá ngắn hoặc quá dài, hãy bấm Edit để chỉnh sửa.
1
I don't usually overhype myself,
2
but in this video, we're going over the only formula you will ever need to master prompting on ChatGPT and Google Bard.
3
So let's get started.
4
Hey friends, welcome back to the channel.
5
If you're new here, my name is Jeff.
6
I work full -time in tech.
7
And if you're anything like me a couple months ago, you know prompting is an important skill to learn,
8
but you're not exactly sure why some prompts generate outputs that are super generic, while others give you precisely what you're looking for.
9
Since then, I've spent hundreds of hours is taking prompt engineering courses and applying what I've learned in my daily life.
10
And so in this video, I'm sharing the six building blocks that make up a good prompt
11
so that you can use this formula to consistently generate high quality outputs.
12
First, it's critical to not only know what the six components are, task, context, exemplars, persona, format,
13
and tone, but also know that there's an order of importance to these six components.
14
To show you what I mean, let's use this simple example.
15
I'm a 70 kg male, give me a three month training program.
16
The first part is context followed by the task.
17
The reason why the task is higher up in the formula hierarchy is if we just input the task without the context,
18
there's still some sort of meaningful output.
19
But if we just give Chachapiti the context, nothing really happens.
20
Put another way, it's mandatory to have a task in your prompt, it's important to include relevant context and exemplars,
21
and it's nice to have persona, format, and tone.
22
When you think of writing your prompt, go down this mental checklist.
23
So this formula will act as a constant reminder for you to include just enough relevant information when writing prompts.
24
And as you'll see in this next part, you do not need all six components in every prompt to have a good output.
25
Now let's break down each building block with specific examples, starting with the task.
26
The rule of thumb is to always start the task sentence with an action verb, generate, give, write, analyze, et cetera,
27
and clearly articulate what your end goal is it could be
28
one simple task like generating a three -month training program
29
or a complex three -step task like analyzing hundreds of user feedback sharing the top three takeaways
30
and categorizing the feedback based on the team responsible for following
31
up the second component context is the trickiest to get right
32
because technically there's an infinite amount of information you can give
33
so i found asking myself these three questions to be super
34
helpful in coming up with just enough information to get a good result from ChatGBT.
35
First, what's the user's background?
36
Second, what does success look like?
37
And third, what environment are they in?
38
Back to the workout example we now have,
39
I'm a 70 kg male looking to put on five kilograms of muscle mass over the next three months.
40
I only have time to go to the gym twice a week and for one hour each session,
41
giving me a three -month training program to follow.
42
Could I have added more background information?
43
Of course, only prioritize the muscle groups that make me look good on Instagram.
44
But the key to staying productive with ChatGPT and Bard is giving just enough information to constrain the endless possibilities.
45
By the way, although this video is not sponsored,
46
it is supported by those of you who subscribe to my paid productivity newsletter on Google Workspace Tips.
47
Link in the description to learn more.
48
Moving over to the exemplars component, it's just a fancy way of saying examples.
49
Basically, all the research on large language models, LLMs, have shown that including examples within the prompt drastically improves the quality of the output.
50
Starting with a simple example, this is a poorly written bullet point from a resume.
51
We can now ask ChachiPT to rewrite this bullet point using this structure.
52
I accomplished X by the measure Y that resulted in Z, which is actually best practice by the way.
53
So actually do this in your resume.
54
For example, I lowered hospital mortality rate by 10 % by educating nurses in new protocols, which translates to 200 lives saved per year.
55
Here's a slightly more complicated example for interview prep.
56
Based on my own resume, write me an answer to the interview question, what's your biggest weakness?
57
Use the star answer framework, situation, task, action, and results.
58
Here, instead of using a full -blown interview answer as an example,
59
which would be overkill, the star framework acts as an example structure for ChatGPT to follow.
60
Last example, let's say you need to write a job description.
61
You give some context around the opening and ask ChatGPT to reference an existing job description.
62
If I use this one I found on LinkedIn, the output will follow the same formatting and use the same professional HRE language,
63
saving me a bunch of time.
64
Main takeaway here, exemplars are not necessary for every prompt, but including a relevant example or framework will greatly improve the quality of your output.
65
Moving along, the persona component is basically who you want ChatGPT and BART to be.
66
And the pro tip here is to think of someone you wish you had instant access to with the task you're facing.
67
If you injured yourself working out, that person might be a physical therapist with experience helping athletes recover.
68
If you're a job seeker, that person might be a recruiter or hiring manager.
69
If you're working on a creative brief, that person might be a senior product marketing manager who's great at storytelling.
70
Pro tip, you can also name specific individuals, but I found the results to be good but only when they're famous enough,
71
like Warren Buffet, Steve Jobs, Jeff Su.
72
By the way, I just have to share this.
73
We have a team offsite with a superheroes theme.
74
So I asked ChatGPT to draft an email from Batman.
75
And it even included things like, please let Alfred know and signed off as the Dark Knight.
76
So fictional characters work as well.
77
And I'm actually gonna use this.
78
The fifth component, format.
79
The pro tip here is to literally close your eyes and visualize how exactly you want the end result to look like.
80
A million likes on my thirst bomb Instagram photo.
81
Damn it, didn't work.
82
Back to the user feedback example.
83
I don't want to read each sentence, so I asked ChatGPT to take all the feedback and output a table with three headers.
84
The original feedback, the team responsible for following up, and priority.
85
And now I can copy this directly and paste it into a Google Sheet.
86
So by priority and filter by team.
87
Other common formats include emails, bullet points, and code blocks,
88
but the one I found to be the most useful as a full -time working professional is paragraphs and markdown.
89
For example, I just I just received a lengthy industry report from my director.
90
First, give me the three key takeaways, then summarize based on topic.
91
Use H2 as section headers.
92
Here is the report.
93
Pro tip, whenever I use ChachiBT to proofread any document,
94
I specify that all changes need to be bolded so I can easily see exactly what has been changed.
95
Let's quickly go through the last component, tone, before we put all this together in one example.
96
The good news is tone is easy to understand.
97
Use a casual or formal tone of voice, give me a witty output, show enthusiasm, sound pessimistic.
98
The bad news is we're usually not very good at recalling the thousands of potential adjectives and adverbs at a moment's notice.
99
So here's a pro tip.
100
Tell ChatGPT the feeling you're going for.
101
For example, I'm writing an email to a team I haven't worked with before
102
and I wanna be taken seriously without coming off as too stuck up and cringey.
103
Can you please give me a list of five tone keywords I can include in a prompt for ChatGPT?
104
And look, now the actual prompt, I can say use clear and concise language and write in a friendly yet confident tone.
105
Putting all this together, let's look at this comprehensive prompt.
106
You are a senior product marketing manager at Apple, Persona, and you have just unveiled the latest Apple product in collaboration with Tesla,
107
the Apple car, and received 12 ,000 pre -orders, which is 200 % higher than Target.
108
Context.
109
Write an email to your boss, Tim Cookie, sharing this positive of news.
110
Task and format.
111
The email should include a TLDR, too long, didn't read section.
112
Project background, why this product came into existence.
113
Business results section, quantifiable business metrics.
114
And end with a section thanking the product and engineering teams.
115
Example, structure.
116
Use clear and concise language and write in a confident yet friendly tone.
117
Tone.
118
Note that if I had an existing email to reference, I could delete the instructions around the structure
119
and simply tell ChatGPT the email should follow the exact same format as the one I will share below
120
and paste the email from the fore.
121
By the way, you can compare the output from this prompt to that of a simpler prompt.
122
I just launched a new product, the Apple Car.
123
I received 12 ,000 pre -orders.
124
Please run email to my boss with this update.
125
There's a pretty big difference in terms of how generic and usable the end result is.
126
Now that you know the basics of prompting, my next video is gonna take you from beginner to pro, so make sure you're subscribed for that.
127
Check out my top five ChaiGPT productivity tips for work.
128
See you on the next video.
129
In the meantime, have a great one.

Tải Ứng Dụng

Mọi thứ bạn cần để nói trôi chảy

Chấm điểm AIChấm từng câu nói
Luyện IPAThành thạo mọi âm
Từ vựngMở rộng vốn từ
Game Từ vựngHọc qua chơi

Cùng kênh

FOR YOU

Video gợi ý

Từ vựng và ghi chú luyện nói cho bài học này

Bài luyện nói này dựa trên video “Master the Perfect ChatGPT Prompt Formula (in just 8 minutes)!”. Những từ được nhắc lại nhiều nhất trong bài: example, prompt, task, Chatgpt, output. Video này có 129 câu và 1646 từ để luyện shadowing. Phần lời nói dài 8:28. Người nói nói nhanh, khoảng 194 từ mỗi phút, nên sẽ có nhiều chỗ nối âm và nuốt âm. Chỉ 80% số từ nằm trong 3.000 từ tiếng Anh thông dụng nhất, nên từ vựng khá khó.

Từ vựng quan trọng trong video

15 từ đáng học trong video, kèm phiên âm và nghĩa:

TừPhiên âmNghĩa
output danh từ/ˈaʊtpʊt/đầu ra
tone danh từ/ˈtəʊn/tiếng
component danh từ/kəmˈpoʊ.nənt/bộ phận
format danh từ/ˈfɔːɹ.mæt/khổ (sách, giấy, bìa)
feedback danh từ/ˈfiːdˌbæk/sự phản hồi
formula danh từ/ˈfɔː.mjʊ.lə/công thức
generate động từ/ˈd͡ʒɛn.ə.ɹeɪt/sinh ra, gây ra
bullet danh từ/ˈbʊlɪt/đạn
resume động từ/ˈɹɛz.ə.meɪ/tiếp tục lại
muscle danh từ/ˈmʌs.əl/cơ, bắp thịt
priority danh từ/pɹaɪˈɒɹɪti/sự ưu tiên
subscribe động từ/səbˈskɹaɪb/đăng kí
pasta danh từ/ˈpɑ.stə/mì ống
analyze động từ/ˈæn.əˌlaɪz/phân tích
topic danh từ/ˈtɑpɪk/chủ đề

Cụm động từ bạn sẽ nghe

TừNghĩa
break down động từhỏng, hỏng hóc
check out động từtính tiền, trả phòng
sign off động từtắt sóng

Ngữ pháp trong video

Những cấu trúc người nói dùng nhiều nhất, kèm đúng cụm từ trong video:

Cấu trúcTrong video
Thì hiện tại hoàn thành have/has + quá khứ phân từ — việc đã xảy ra nhưng còn liên quan đến hiện tạiI've spent · have added · have shown
Câu bị động be + quá khứ phân từ — nhấn vào việc xảy ra, không phải người làmis not sponsored · is supported · be bolded

Phát âm cần chú ý

Người nói dùng 28 dạng rút gọn, ví dụ you're, I'm, didn't. Hãy nói theo dạng ngắn đúng như bạn nghe.

  • Âm “th”: athlete /ˈæθ.liːt/, enthusiasm /ɪnˈθuziæzəm/, thumb /ˈθʌm/, therapist /ˈθɛɹəpɪst/, thirst /θɝst/
  • Âm “sh” và “zh”: collaboration /kəˌlæbəˈɹeɪʃən/, casual /ˈkæʒ(u)əl/, instruction /ɪnˈstɹʌkʃən/, accomplish /əˈkɑm.plɪʃ/, fictional /ˈfɪkʃənəl/
  • Từ dài — đặt trọng âm cho đúng: priority /pɹaɪˈɒɹɪti/, productivity /ˌpɹɒdʌkˈtɪvəti/, complicated /ˈkɑm.plɪˌkeɪ.tɪd/, comprehensive /ˌkɑm.pɹəˈhɛn.sɪv/, collaboration /kəˌlæbəˈɹeɪʃən/

Những âm người Việt thường gặp khó:

  • Cụm phụ âm cuối — đọc đủ từng âm, đừng nuốt âm cuối: prompt /pɹɑmpt/, component /kəmˈpoʊ.nənt/, instant /ˈɪnstənt/, bold /ˈbəʊld/, therapist /ˈθɛɹəpɪst/
  • Âm /tʃ/, /dʒ/ và /ʒ/ — tiếng Việt không có, đừng đọc thành “ch” hay “gi”: generate /ˈd͡ʒɛn.ə.ɹeɪt/, generic /dʒɪˈnɛɹ.ɪk/, casual /ˈkæʒ(u)əl/, educate /ˈɛd͡ʒ.əˌkeɪt/, adjective /ˈæd͡ʒ.ɪk.tɪv/
  • Âm /æ/ — mở miệng rộng hơn âm “e”: format /ˈfɔːɹ.mæt/, feedback /ˈfiːdˌbæk/, analyze /ˈæn.əˌlaɪz/, fancy /ˈfæn.si/, collaboration /kəˌlæbəˈɹeɪʃən/

Cách luyện với video này

  1. Nghe hết video một lần, chưa cần nói, và ghi lại những từ bạn chưa biết.
  2. Bắt đầu ở tốc độ 0,75×, nói đuổi từng câu, rồi quay lại tốc độ bình thường khi đã quen.
  3. Ghi âm giọng mình rồi so với bản gốc, chú ý các từ như output, tone, component.

Phương Pháp Shadowing Là Gì?

Shadowing là kỹ thuật học ngôn ngữ có cơ sở khoa học, ban đầu được phát triển cho chương trình đào tạo phiên dịch viên chuyên nghiệp và được phổ biến rộng rãi bởi nhà đa ngôn ngữ học Dr. Alexander Arguelles. Nguyên lý cốt lõi đơn giản nhưng cực kỳ hiệu quả: bạn nghe tiếng Anh của người bản xứ và lặp lại to ngay lập tức — như một "cái bóng" (shadow) đuổi theo người nói với độ trễ chỉ 1–2 giây. Khác với luyện ngữ pháp hay học từ vựng bị động, Shadowing buộc não bộ và cơ miệng phải đồng thời xử lý và tái tạo ngôn ngữ thực tế. Các nghiên cứu khoa học xác nhận phương pháp này cải thiện đáng kể phát âm, ngữ điệu, nhịp điệu, nối âm, kỹ năng nghe và độ lưu loát khi nói — đặc biệt hiệu quả cho người luyện IELTS Speaking và muốn giao tiếp tiếng Anh tự nhiên như người bản ngữ.

Phương pháp shadowing: đọc hướng dẫn từng bước đầy đủ →