跟读练习: The future of work with @Claude - 通过视频学习英语口语
正在创建课程...
1
What do you do if there's no Claude in the channel?
2
I don't know, I can't remember a world without Claude in the channel.
3
Walk me back.
4
Three years ago, we were just starting to adopt AI into our day-to-day workflows.
5
What was it like back then?
6
And take me all the way to where we are today.
7
I remember two years ago, I was still using typeahead.
8
That was what AI could do as an engineer.
9
And you know, we built Claude Code, we brought agents, and kind of the next generation of ways to do your coding.
10
And it’s just changed so much since.
11
With typeahead, I was still deciding, I want to write this line of code, and the agent was helping a little bit.
12
It was just writing the line.
13
And then we got to the point where it was writing whole functions, whole files, whole features.
14
And I feel like now with Tag, it just does the whole thing.
15
It can write the feature, it can do an entire experiment end-to-end, it does my data analyses.
16
It's been like two leaps in 2 years.
17
When I think back to the last couple of years, it's almost like this transition.
18
We went from a person always in the loop, it's one person sitting there, and they're just typing a line at a time.
19
We got to one person sitting there with like 10 Claudes, you know, typing a bunch of features at a time.
20
Now we're at the point where Claude is actually driving a little bit more.
21
And it's not just one person anymore, it's an entire team that's interacting with it.
22
So, what is Claude Tag?
23
In the past, you had to open Claude, and you had to ask it something, and then Claude would do the work.
24
It'll use your tools, it'll use your computer, and it'll get the task done.
25
That's the way that it used to be.
26
With Claude Tag, Claude jumps in, it's proactive, it knows when to jump in.
27
It'll do the work, even if it takes days or weeks, and it'll follow up.
28
And I think the coolest thing is, it'll remember what I told it for next time.
29
Before, I would have to prompt Claude every time, and I would have to say, "Claude, now do this, or now do this." I would have to remember to do that.
30
Now we just add Claude to a channel, it will proactively jump in and do the work.
31
Everyone gets to see it, everyone gets to participate, because it's multi-player, and it'll remember for next time.
32
Okay, so what on the research side actually enabled this?
33
How is it that Tag is so good?
34
For many years, we've been working on making our models more long-running and autonomous.
35
So if you look at the latest METR evals, our latest models can work for 16 hours at a time, and are now in the zone where we can't even accurately detect how long it's able to work for.
36
In something like Claude Tag, Claude is able to self-schedule work for itself.
37
And so you can take this one 16-hour task, and it actually increases over time because Claude can schedule a follow-up after days, or weeks, or months.
38
I feel like the task that we couldn't trust it to do before, now it can get almost every single time.
39
I have a bunch of these Claude Tag sessions, personally, that are running for days, weeks.
40
I think I might have one that's a month.
41
It's essentially this long-running experiment, and it's just checking in every day, checks the data, once in a while, it sends a bug fix if there's a bug that needs to get fixed.
42
I just see the pull requests coming in, and I get these data readouts every day.
43
The other big innovation is just being able to have memory in the model.
44
The model can not only set reminders for itself, but it can also remember just all the instructions that all the users have given it over time.
45
Memory took a long time to crack.
46
I think we tried to get it right for Claude Code for years, and it feels like we finally got it right. It feels really good to use.
47
If you're working with Claude Tag in a channel, and you tell it, "Hey, I want you to monitor only for this type of issue, but not these other categories," it will do that.
48
It will remember that for that channel forever after.
49
And then, if someone else says, "Hey actually, let me expand your scope to this new thing," it will adjust.
50
Another big thing that people love is Claude's personality and EQ.
51
Sometimes when I talk with people about adding Claude Tag into a channel, they say, "Oh, how do I know it won't jump in on every thread and be annoying?" Well, Claude is trained to have a good sense for when it's needed, and it can take the back seat.
52
If it ever goes too much in the wrong direction, you can just tell it to do something different, to jump in less, or jump in more, and it'll just remember it for the future.
53
So when you look at the internal usage, and when you talk with our customers who are getting started on Claude Tag, what are the patterns that you see?
54
The coolest thing to me has been how customers are figuring it out.
55
It can write your pull requests, it can debug production issues, it can do data analysis.
56
All you have to do is hook it up to your tools.
57
I think that's only possible because the memory is just so good.
58
And I've seen people do this emergent stuff where, you know, for example, this is a channel for Q&A, anytime a question is answered, you must check it off.
59
You tell Claude Tag this, and it'll just do that.
60
It'll answer the questions, and it'll react with a check every time, and it'll just do this for you.
61
We have a channel for data questions, and now Tag just answers all the questions.
62
Or we have the channel for Claude Code feedback, and Tag just fixes everything now.
63
The most common way that I ask a data question is, I post in our data channel, but then I tag Claude Tag, and then it takes the first pass, and normally it's pretty good.
64
I kept doing this in a bunch of channels, and then I just got tired of tagging it, so I just told it, "Please respond every time." I think it goes to show how powerful the memory is, that you're able to do something like this.
65
You can just tell it, "Hey, remember to always do this thing," and it just has your back.
66
It's been a huge shift in how we all do work.
67
I think this also is a way for more people to understand how to work with AI.
68
Because Claude Tag is working in public channels, everyone is able to observe how the expert users leverage it.
69
And then they take those patterns, and they bring it to new projects that they're working in.
70
And so both internally and in the customers that we've been working with, we've been seeing this diffusion of Claude Tag best practices that is, I think, very novel to AI tools.
71
It was surprising how fast it took over.
72
I feel like now I see Tag in every channel that we have; every feedback channel, every data channel.
73
It started with a few people using it, but I think as other people saw those people using it, they quickly picked it up.
74
It's been very empowering to be able to have Claude Tag have my back.
75
So for a lot of our existing tools, like Chat, Cowork, and Claude Code, you typically have to remember to open it.
76
And so it’s a more reactive experience.
77
And one thing that's great about Claude Tag is you give it this higher-level objective, like put up PRs for every bug in this channel, and it just has your back and puts up a PR for every single one without you needing to remind it.
78
The second thing that's really cool is that it's multi-player.
79
So almost all of the AI tools that people use right now are just you and Claude working together, and then copy and pasting this output to your team.
80
And I think the big shift that Claude Tag allows is, it brings Claude right into the middle of your work so that multiple people can guide the session to a better output.
81
There's so many, like, dynamics here.
82
Like one, we're all learning about how to use Claude Tag better by observing other people.
83
Claude Tag is learning how to better work with us by hearing the guidance that we're giving it.
84
At the end of the day, the customer gets a better result, because it's not just my opinion of how we should solve it, it's our whole team is able to jump in to nudge this PR to the best possible state.
85
I mean, I love this idea.
86
I keep telling everyone, I want everyone to contribute to the code base, and so many people are afraid because they have to, like, open a terminal, even the desktop app, because you have to deal with a Git and code checkouts and stuff.
87
And with Tag, they can just do it. It's really cool.
88
The other thing that I think is really important is making sure that your collaboration platform has public channels.
89
That way, Claude Tag can monitor different projects that you're tracking.
90
So as a PM, I'm often working on maybe five to 10 features, and I have Claude Tag look at the status for every single one, and then give me a daily report.
91
The other big unlock we've been seeing is that, people can now self-serve their questions.
92
When people onboard to our company, instead of asking Legal about whether they can say this, or instead of asking our HR team what our benefits are, they can just tag Claude Tag.
93
And because Claude Tag is connected with our source-of-truth files, it can give them a really fast answer, no matter what time they're looking for it.
94
I think the single biggest thing is just how much more productive it's made everyone.
95
And, you know, this is driven by our internal version of Claude Tag.
96
And if you look at just the product org, so, the part of the company that we sit in, the number of PRs that are written by Tag, I think it's like 65% now, and it's just climbing like this.
97
I thought that Claude Code was the thing that makes engineers go faster.
98
This is a product that makes engineers go way faster.
99
I think actually, a lot of the reason is, because the way you're interacting with it, you ask Tag to do something, and it'll respond, and you move on to the next task.
100
So you actually want to set it up in a way where Tag can do the work, and you don't have to check in all the time.
101
You have hundreds of these Claude Tags running, but you're still a power user of Claude Code.
102
How do you decide when to reach for each of them?
103
Yeah, so I used to use Claude Code for everything, and then I started using Tag for more and more things.
104
First, it was really simple fixes.
105
Someone has a bug, the button's off by a few pixels or something.
106
I'll just ask Claude, "Please fix it." Or someone has a simple data question, I'll ask them to fix it.
107
And I think what's been happening more and more over the last few weeks as I've been getting more comfortable with the product, is I've been using Tag for just more and more things.
108
And even more complicated work, it's actually able to do.
109
Because it can verify its work, because it's running in the same remote sandbox that we use for mobile and for the desktop app, and it's using the same agent SDK.
110
So it's just as intelligent.
111
When you add memory to this, in different channels, I have specific preferences about how I want it to verify.
112
It might be a little bit different for every channel.
113
Often what it does is it'll fix some bug, then it'll post back a video in Slack, and I don't even have to leave it.
114
What's next for Claude Tag?
115
So we launched Claude Tag in Slack, and we're excited to bring it to more platforms where people collaborate, like Microsoft Teams.
116
We want to make sure that every knowledge worker is within arm's length of Claude, no matter where they're getting their work done.
117
And I think one of the coolest parts of Claude Tag is, it's not just changing how individuals work, it's putting Claude in the center of teams and transforming entire orgs.
118
We've built Claude Tag to be incredibly customizable, just like Claude Code.
119
And I'm so excited to see how orgs customize Claude Tag and make it their own.
120
I can't wait.
📺 同频道
B11
Plan smarter with Claude for Teachers
Business EnglishHigh School StudentsUniversity Students
C12
Build a proactive agent workflow with Claude Code
Business EnglishUniversity StudentsWorking Adults
B25
Tag Claude in, right where you already work
Business EnglishWorking Adults
B22
Build data-driven lesson plans with Claude for Teachers
Business EnglishHigh School StudentsUniversity Students
B23
Can you trust what AI tells you?
Business EnglishUniversity StudentsWorking Adults
C14
How AI gets its character
Business EnglishUniversity StudentsWorking Adults
C24
How Claude Code Works
University StudentsWorking Adults
C1Building the best agentic analytics harness: Powered by Claude, built with Claude Code
Business EnglishUniversity StudentsWorking Adults
C1Building the future of agentic infrastructure
Business EnglishUniversity StudentsWorking Adults
✨ 推荐视频
B21
392 句
Ultimate Claude Guide: How to Use Claude AI for Beginners in 2026
Business EnglishUniversity StudentsWorking Adults
B21
220 句
How Modern Data Teams Work (Engineer, Analyst, Scientist, Architect, ML)
Business EnglishUniversity StudentsWorking Adults
B23
43 句
Translating Claude’s thoughts into language
Business EnglishUniversity StudentsWorking Adults
B21
307 句
The New AI prompting Method Everyone Is Talking About: Loops (And How To Use Them)
Business EnglishUniversity StudentsWorking Adults
B21
321 句
How One of NYC’s Fastest-Growing Startups Scaled to $5 Billion
Business EnglishUniversity StudentsWorking Adults
B21
269 句
Design with Claude Code: The Designer’s Guide
Business EnglishUniversity StudentsWorking Adults
B24
166 句
Can This Robot Be My Personal Assistant
Business EnglishDaily ConversationHigh School Students
B21
282 句
What Stanford students actually use ChatGPT for
Business EnglishUniversity StudentsWorking Adults
B21
364 句
Claude Cowork Tutorial: Build Monthly Reports in Minutes
Business EnglishUniversity StudentsWorking Adults
B21
169 句
Can This Vibe Coder Beat a Senior Developer?
Business EnglishUniversity StudentsWorking Adults
B21
103 句
Wild times we live in
Business EnglishUniversity StudentsWorking Adults
B2251 句
Is Siri AI Usable for English Learning?
Business EnglishDaily ConversationUniversity Students
背景与上下文
在这段视频中，讲话者讨论了人工智能（AI）在工作中的演变，特别是他们如何使用Claude进行编程和日常任务的自动化。从三年前的初步应用到如今AI能够主动参与任务的飞跃，整个过程显示了科技的惊人进步。对许多英语学习者来说，理解这样的演变不仅能促进对科技的认识，还能帮助提高他们的英语沟通能力。
日常交流的五个常用短语
- 我该怎么做？ - 用于询问建议或请求帮助。
- 我记得... - 用于回忆过去的事情，帮助建立对话的背景。
- 它已改变很多。 - 表达事情的变化，适合讨论进步与新技术。
- 我想要... - 用于明确表达自己的需求或愿望。
- 我们需要... - 在团队合作中用来聚焦所需的目标或任务。
逐步跟读指南
要在看YouTube学英语中更高效地吸收和运用讲话者的内容，您可以采用以下步骤进行shadow speech练习，以提高英语发音和相应的沟通能力：
- 预先听取内容： 在开始跟读之前，先完整听一遍视频，熟悉讲话者的语速和语调。
- 分段跟读： 将视频分成小段，逐句聆听并模仿，关注语音语调的细节。
- 记录反馈： 使用录音设备录下自己的跟读，回放时对比原音，找出发音或语调的差异。
- 反复练习： 如果某些短语或句子难以掌握，需多次反复练习，直至感觉自然流畅。
- 使用应用辅助： 结合shadowing site等工具，获取更多资源和反馈，让学习过程更高效。
通过这种shadowing练习，您可以提高自己的英语能力，特别是在了解科技和职场交流方面，您不仅可以掌握语言，还能跟上现代科技的发展。
视频中的语法
说话人最常用的结构，并附上视频中的原话：
| 结构 | 视频中的用法 |
|---|---|
| 现在完成进行时 have/has been + -ing — 以前开始、现在仍在继续的动作 | we've been working · we've been seeing · I've been getting |
| “used to” used to + 动词 — 过去的习惯或状态，现在已不再如此 | used to be · used to use |
| 被动语态 be + 过去分词 — 强调发生了什么，而不是谁做的 | is trained · is answered · is connected |
| 现在完成时 have/has + 过去分词 — 过去发生但与现在仍有关联的事 | have given · has been · I've seen |
什么是跟读法？
跟读法 (Shadowing) 是一种有科学依据的语言学习技巧，最初开发用于专业口译员的培训，并由多语言者Alexander Arguelles博士普及。这个方法简单而强大：您在听英语母语原声的同时立即大声重复——就像是一个延迟1-2秒紧跟说话者的影子。与被动听力或语法练习不同，跟读法强迫您的大脑和口腔肌肉同时处理并模仿真实的讲话模式。研究表明它能显着提高发音准确性，语调，节奏，连读，听力理解和口语流利度——使其成为雅思口语备考和真实英语交流最有效的方法之一。