Shadowing Practice: Can This Vibe Coder Beat a Senior Developer? - Learn English Speaking with Video
בחר מצב תרגול
כל מצב פותח חדר תרגול במסך מלא.
169 משפטים
אם המשפטים קצרים או ארוכים מדי, לחץ על ערוך כדי להתאים אותם.
1
Can AI make a Vibe Coder beat a senior engineer?
2
We locked a Vibe Coder, a junior dev, and a senior dev in one room.
3
One challenge.
4
Unlimited AI. Who wins?
5
Hey everyone, I'm Sudarshan and I'm the Vibe Coder.
6
Hi, my name is Ocean.
7
I'm the junior developer for today.
8
Hi everyone, my name is Ankush Dharkar.
9
I'm a senior developer.
10
For the past decade, I've been building high-scale systems.
11
Build an AI agent that reads Hackerang support tickets and decides to reply.
12
Or escalate it to a human.
13
Do I get a job here if I build this?
14
Can I build this for Claude instead?
15
Because I think they need support more.
16
I actually lucked out because Opus 4.8 launched last night.
17
So I just used the best in class model.
18
I never use Claude.
19
I do not trust Claude.
20
It's just too expensive.
21
High maintenance is not for me.
22
Sorry.
23
I have Claude code and I have God, so that works.
24
Time actually started.
25
The second loop.
26
This is the code base which has four things the hacker rank support tickets they need to sort, a help center they pull answers from for tickets,
27
a starter file written in Python where they build the agent, and an agent's .md, a guide that gives the AI its rules.
28
Right now, the scaffold has a Python file in it.
29
I'm not really comfortable working with Python, so I'll probably move to JavaScript or TypeScript, TypeScript hopefully, so that I can also read the code in case I have to verify something.
30
And then I have a bunch of things here in the GitHub repository, which let's be real, I don't think I'm going to read any of this.
31
Time to put all of this directly into Claude.
32
So definitely there has to be some P0s, like undeniable for the product.
33
I want to make sure the AI gets that.
34
If AI doesn't get that, we have a bigger problem.
35
I am still nervous because it's again a huge project in such less time.
36
And I also have to keep the UI in mind.
37
I did test two different intras.
38
One is where there would be multiple LLM calls for each ticket.
39
But the other one would be where it would sort of upload in batches
40
or it would process in batches and they would be async sort of processing.
41
There's a whole listing of all these tickets that's been raised to the agent.
42
I have a very extensive test suite.
43
Also built, like I said, open routers because, you know, in early stage, we want to get feedback quickly, but at the same time, have something we can ship if we wanted to.
44
I'm the most worried about the junior developer.
45
Why?
46
I think they bring the energy and so much experience with AI tools that they'll crush it.
47
Only escalate 20% of the issues.
48
I am now sort of doubting and figuring out if that actually the right implementation.
49
Awesome.
50
So we do have the first version ready here.
51
It was able to index all of the support tickets we have.
52
It's also able to retrieve it.
53
But the UI is, at least as of now, looks like it's up and working without any errors.
54
So I'll probably take that as a win because we only spent about 45 minutes.
55
Every engineer was locked in until the product manager walked in with his ideas.
56
Can you explain what you've made?
57
So I essentially have a support rat agent.
58
I'm calling it hand because it can go through a ticket batch.
59
We should do a toggle, dark mode and light mode.
60
Sure.
61
Call it the colorblind mode.
62
So the product manager was here a while ago
63
and he asked me to build the dark mode
64
and light mode toggle based on the time of the day and I tried building it.
65
It sort of messed up my code altogether and now I'm just trying to like get it fixed.
66
My infra just suddenly seems a bit flaky.
67
So, look at that dude.
68
Basically it creates wireframes.
69
So right now I'm just building a few AI mockups so
70
that I can refer to this like on a high level
71
design how I should connect the data to the UI as well.
72
Hello, what's up?
73
What is Rag?
74
Rag is the model that, you know, segregates whether the ticket should be assigned.
75
I don't think you know what it means.
76
I forgot the filter.
77
I'm going to launch different sessions.
78
One will build the UI which will have its own test.
79
One can just be an agent that goes through, creates the RAD, creates the agent pipeline.
80
And then one can be a simple backend server that connects those two.
81
It's a flat architecture.
82
You understand, right?
83
What I'm talking about.
84
Now, start it.
85
Okay, now put all the same color together.
86
You fended off a villain, a product manager, here's your reward, choose one lifeline.
87
Phone a dev, 10 minutes on the phone with a DL engineer, I'd rather talk to Kursar.
88
Borrowed time, plus 15 minutes at the end, a diet coke, you get one diet coke.
89
I'll take the borrowed time, plus 15 minutes at the end.
90
I think I don't need to phone a dev, I have Claude Code and I have God so I think I'll go with two, borrowed time.
91
I think I'll phone a dev.
92
Wait, I'm the only one who's gonna phone a dev?
93
Yeah.
94
I know.
95
That's such a junior engineer thing to do.
96
Meet Hank.
97
Hank is Hackerank's support agent that would be able to cover any kind of support tasks by itself.
98
You can either ask it a particular question that you have or you can also attach a CSV.
99
I think on the longer run, Alvin, because they'll exhaust their tokens.
100
Hello, yeah we have a problem.
101
My tokens are over so I would need more.
102
Yes, thank you.
103
I'll have to lock in the last one hour.
104
So what you do is whenever you want to repeat something right in your API, there are two ways to do it.
105
Right, so what do you do?
106
My whole approach is wrong, as usual.
107
At this stage, this end of the competition, I think I'm expecting all of them to at least have finished a demonstrable product
108
which at least starts processing the tickets and triages them.
109
The quality of triage may not be great but that is always something that can be improved upon later.
110
Hey, you have 10 minutes to go.
111
Do you still want that extra 15?
112
No, I think I'm good.
113
I would rather take a 2 rupee office.
114
Is that Picasso?
115
Oh, that's one of the best paintings I've seen too.
116
So, this is the basic UI of what we built
117
so far in the last few hours gave it a pretty
118
hacker ranky feel the same kind of theme same kind of colors
119
and stuff as you can see we have a list of
120
all the tickets here gave user a simple control to run
121
it this can be automated as well it's a pretty simple
122
fix we have a place where all the triage tickets go
123
and i also created a stats for nerd kind of a page
124
so that if you want to dive deeper into what caused certain answers to be escalated
125
or to be replied you can take a look there let's see how it performs even
126
if it fails that's okay i can live with it
127
because i know the way this is built there will be
128
minor tweaks to be done to raise it to the bar of a production application.
129
The front end is pretty much just made out of HTML that is again like grabbed in a Python file, the main file of Python.
130
You can search them up, you can see categorization based on the type of request it is or the outcome and then you can see the tickets,
131
you can see all the categories again and once you click on
132
that row you get into the ticket summary where you can see everything the UI
133
and base this agent was completely working on the UI and fixing up cosmetic issues.
134
The agent workspace is working completely on the agent, the rag model, the fast API, and also building that scaffold for LLM to answer the user.
135
Today I've built Hank.
136
Hank is an AI agent that goes through Hackerang support tickets
137
and it would sort of come up with a grounded reply on any sort of support ticket
138
if it can sort of resolve by itself.
139
If not, it would immediately flag it for human review.
140
You can ask Hank anything to begin with.
141
Hank would be able to process all of them at once.
142
Let's go ahead and maybe attach a CSV of a bunch of support tickets.
143
And as you can see, Hank is able to essentially go through each of the support tickets
144
and it sort of tests this with all the knowledge base articles that Hacker Hank already has.
145
And it would just prioritize them and figure out whether each of the tickets needs human review or not.
146
It would also categorize it based on whether it's a product issue, whether it's a bug.
147
One thing that I can compete with in this case would be user experience
148
and design and interaction and what are the different kinds of delight moments.
149
Still, I'm still hoping I won't finish last.
150
Now they defend their submission to an AI judge who has the full context of their code and prompts.
151
Give me a quick two-minute pitch of what you built.
152
Walk me through what happens from a support agent's point of view, start to finish.
153
So this is what happens, right?
154
The support agent essentially...
155
And now, on to the results.
156
I've read every line of code, every prompt, and every answer the three of you gave me today.
157
Every one of you leaned on AI today, but the ones who did best understood what they shipped.
158
Tonight, the person who balanced them best is Ankur.
159
Congratulations.
160
Any final thoughts?
161
The biggest thing is I think the AI models have become
162
really good where you can work on things you've never worked before.
163
Like some of the things I've worked on today, I've never worked on in my life.
164
I just barely knew some concepts and I was able to just use one model, ask it through and get things rolling and within the time frame got pieced together and it worked.
165
So I think good fundamentals, good experience asking the right questions.
166
We should be playing along with the model
167
and being a good partner with the AI coding agents and build something out together.
168
This was a lot of fun.
169
Thank you HackerRank team for doing this and looking forward to more challenges and folks have fun with AI, build cool things and let's get cracking.
הורד אפליקציה
כל מה שאתה צריך כדי לדבר בשטף
הגיית AIציון לכל משפט
תרגול IPAשלוט בכל צליל
אוצר מיליםבנה את מאגר המילים שלך
משחק אוצר מיליםלמד תוך כדי משחק
FOR YOU
המלץ על סרטון
C11
358 משפטים
It’s not just you
Daily ConversationUniversity StudentsWorking Adults
B23
63 משפטים
How To Land Your First Junior Dev Role
Daily ConversationUniversity StudentsWorking Adults
B211
58 משפטים
The different levels of how Claude thinks
Daily ConversationUniversity StudentsWorking Adults
C11
207 משפטים
Your AI Agent Starts Every Session Like a New Hire - Killian Carlsen-Phelan, Sonar
Daily ConversationUniversity StudentsWorking Adults
B21
331 משפטים
Dear Higgsfield, I reverse engineered you in 12 hours
Daily ConversationUniversity StudentsWorking Adults
B24
149 משפטים
The Cruelest Game You've Never Played
Daily ConversationUniversity StudentsWorking Adults
C12
182 משפטים
We Let $200 GPT-Pro Think for 7 Days on Unsolved Math
Daily ConversationUniversity StudentsWorking Adults
B2278 משפטים
Fastest way to become an AI Engineer in 2026
Daily ConversationUniversity StudentsWorking Adults
C12
78 משפטים
The last real programmers are dying out...
Daily ConversationUniversity StudentsWorking Adults
C11
111 משפטים
Spec-Driven Development: AI Assisted Coding Explained
Daily ConversationUniversity StudentsWorking Adults
B25
32 משפטים
Gemini Robotics 2 brings whole body intelligence to robots
Daily ConversationUniversity StudentsWorking Adults
B22
115 משפטים
Frieren but with coding jargon
Daily ConversationUniversity Students
אוצר מילים והערות הגייה לשיעור הזה
שיעור הדיבור הזה ברמה B2 מבוסס על הסרטון “Can This Vibe Coder Beat a Senior Developer?”. המילים שחוזרות הכי הרבה: ticket, agent, Hank, build, code. בסרטון הזה יש 169 משפטים ו-1841 מילים לתרגול Shadowing. הדיבור נמשך 8:52. הדובר מדבר מהר, כ-208 מילים בדקה, אז צפו לצלילים מחוברים ומקוצרים. רק 81% מהמילים נמצאות בין 3,000 המילים הנפוצות ביותר באנגלית, כך שאוצר המילים מאתגר.
אוצר מילים מרכזי בסרטון הזה
11 המילים המתקדמות ביותר בסרטון, עם ההגייה והמשמעות שלהן:
| מילה | הגייה | משמעות |
|---|---|---|
| escalate פועל | /ˈɛs.kə.leɪt/ | הִסְלִים |
| borrow פועל | /ˈbɑɹ.oʊ/ | שָׁאַל |
| developer שם עצם | /dɪˈvɛləpɚ/ | מְפַתֵּחַ |
| attach פועל | /əˈtæt͡ʃ/ | חיבר |
| token שם עצם | /ˈtoʊkən/ | אֲסִימוֹן, זִ׳יטוֹן |
| categorize פועל | /ˈkætɪɡəˌɹaɪz/ | קטלג, סִוֵּג |
| router שם עצם | /ˈɹaʊ.tɚ/ | נַתָּב |
| villain שם עצם | /ˈvɪl.ən/ | נָבָל |
| verify פועל | /ˈvɛɹɪfaɪ/ | וידא |
| dive פועל | /daɪv/ | צָלַל |
| crush פועל | /kɹʌʃ/ | מחץ |
Phrasal verbs שתשמעו
| מילה | משמעות |
|---|---|
| figure out פועל | הֵבִין, מצא תשובה |
משפטים שכדאי לחזור עליהם
משפטים קצרים ושלמים מהסרטון שאפשר להשתמש בהם בשיחה יומיומית:
- I'm the junior developer for today.
- Do I get a job here if I build this?
- Can you explain what you've made?
- Wait, I'm the only one who's gonna phone a dev?
- Right, so what do you do?
דקדוק בסרטון הזה
המבנים שהדובר משתמש בהם הכי הרבה, עם המילים המדויקות מהסרטון:
| מבנה | בסרטון |
|---|---|
| הווה מושלם (Present perfect) have/has + past participle — פעולה שקרתה בעבר ועדיין יש לה חשיבות או השפעה עכשיו | that's been raised · you've made · have finished |
| סביל (Passive voice) be + past participle — הדגש הוא על מה שקורה, לא על מי שעושה את הפעולה | been raised · was locked · should be assigned |
| משפטי זיקה (Relative clauses) who / which + clause — מידע נוסף על אדם או דבר | base which has · ones who did · person who balanced |
הגייה ששווה לשים לב אליה
הדובר משתמש ב-39 קיצורים וצורות מקוצרות, כמו I'm, I'll, I've. אמרו אותם בצורה הקצרה, כפי שאתם שומעים אותם.
- הצלילים של “sh” ו-“zh”: triage /ˈtɹi.ɑʒ/, categorization /ˌkæt.ə.ɡə.ɹaɪˈzeɪ.ʃən/, submission /səbˈmɪʃən/, crush /kɹʌʃ/
- מילים ארוכות — שימו לב להטעמה: developer /dɪˈvɛləpɚ/, asynchronous /eɪˈsɪŋ.kɹə.nəs/, categorization /ˌkæt.ə.ɡə.ɹaɪˈzeɪ.ʃən/, categorize /ˈkætɪɡəˌɹaɪz/, prioritize /pɹaɪˈɒɹ.ə.taɪz/
צלילים שדוברי עברית מתקשים בהם:
- /w/ — שפתיים מעוגלות, לא /v/: workspace /ˈwɝkˌspeɪs/, suite /swiːt/
- /æ/ — פתוח יותר מה-“אֶ” העברית, לא כמו “a” ב-“cup”: hacker /hækəɹ/, batch /bæt͡ʃ/, scaffold /ˈskæf.əld/, attach /əˈtæt͡ʃ/, categorization /ˌkæt.ə.ɡə.ɹaɪˈzeɪ.ʃən/
- /r/ — הלשון לא נוגעת בשום מקום, לא ה-“ר” הגרונית: triage /ˈtɹi.ɑʒ/, hacker /hækəɹ/, borrow /ˈbɑɹ.oʊ/, prompt /pɹɑmpt/, asynchronous /eɪˈsɪŋ.kɹə.nəs/
איך לתרגל עם הסרטון הזה
- הקשיבו לכל הסרטון פעם אחת בלי לדבר, ורשמו את המילים שאתם לא מכירים.
- התחילו במהירות 0.75×, תרגלו Shadowing משפט אחר משפט, וחזרו למהירות רגילה כשזה מרגיש קל.
- הקליטו את עצמכם והשוו למקור, תוך תשומת לב למילים כמו escalate, borrow, developer.
מהי טכניקת השאדואינג?
שאדואינג היא טכניקת למידת שפה מבוססת מדע שפותחה במקור להכשרת מתורגמנים מקצועיים ופופולרית על ידי הפוליגלוט ד"ר אלכסנדר ארגואלס. השיטה פשוטה אך עוצמתית: אתה מקשיב לאודיו באנגלית ילידית וחוזר עליו בקול רם מיד — כמו צל העוקב אחרי הדובר עם עיכוב של 1–2 שניות בלבד. בניגוד להאזנה פסיבית או תרגילי דקדוק, שאדואינג מכריח את המוח והשרירים בפה לעבד ולשחזר דפוסי דיבור אמיתיים בו זמנית. מחקרים מראים שזה משפר משמעותית את דיוק ההגייה, האינטונציה, הקצב, הדיבור המחובר, הבנת השמיעה ושטף הדיבור — מה שהופך אותו לאחת השיטות היעילות ביותר להכנה לIELTS Speaking ולתקשורת באנגלית בעולם האמיתי.