Home
登录
注册
学习内容
Loading...
How I Created OpenClaw, the Breakthrough AI Agent | Peter Steinberger | TED - Video học tiếng Anh
听力练习
听力练习
/
Video
/
TED Talk
/
How I Created OpenClaw, the Breakthrough AI Agent | Peter Steinberger | TED
How I Created OpenClaw, the Breakthrough AI Agent | Peter Steinberger | TED
选择学习模式:
查看字幕
选词
重写单词
Highlight:
3000 Oxford Words
4000 IELTS Words
5000 Oxford Words
3000 Common Words
1000 TOEIC Words
5000 TOEFL Words
字幕 (320)
0:04
What's OpenClaw?
0:06
I've been programming since I was 14.
0:11
Building software felt like playing a video game.
0:16
I couldn't stop.
0:19
Until I did.
0:23
I created a company,
0:25
I poured a decade of my life into it.
0:29
No venture capital,
0:32
every weekend.
0:34
And then I sold the dream.
0:38
And I felt absolutely nothing.
0:43
For three years,
0:46
I was wondering,
0:48
did therapy, traveled,
0:51
I changed countries twice.
0:55
Nothing, nothing clicked.
0:57
Now I wake up every morning
1:00
with everything I was supposed to want
1:02
and no reason.
1:04
No reason to get out of bed.
1:07
And then in early 2025,
1:13
I tried an experiment.
1:14
I wanted to see what these new AI coding agents are all about.
1:21
And I had what I can only describe as a "holy shit" moment.
1:28
The boilerplate, the plumbing,
1:31
all the boring parts that was software development,
1:36
AI could do all of it.
1:39
The bottleneck is no longer typing.
1:42
It's thinking.
1:43
And thinking was the part I did [for] 25 years.
1:50
Building software felt like playing a video game again.
1:54
I was back.
1:56
I built 44 projects in just a few months.
2:02
And the latest one was a WhatsApp bot.
2:07
I put it on my computer,
2:09
it talks through the apps that you already know.
2:17
And then I took it on a trip to Marrakesh.
2:21
You know, just to navigate around, to find restaurants, do translations.
2:28
And at first, it didn't really feel right.
2:32
It felt too much like a tool,
2:36
not like a friend.
2:39
You know, too many bullet points, too many tables.
2:43
So I told it,
2:45
because those modern models, they are so smart,
2:48
they know what WhatsApp is, they know how people talk.
2:51
I just had to tell it.
2:53
And then it felt right.
2:57
And you know how you talk to friends --
2:59
at some point I was walking around and I was sending it a voice message.
3:05
And then I froze because I actually,
3:10
I didn't build voice in there.
3:13
I added support for images, yeah, but even that took hours.
3:16
So I was looking at the typing indicator,
3:20
and then the agent responded.
3:23
And I very vividly remember this situation
3:25
where I was standing there and I was like,
3:28
how did you do that?
3:30
And the agent replied, I'm not kidding you,
3:32
"The mad lad figured it out on its own."
3:36
(Laughter)
3:37
And then it walked me through every single step:
3:39
how it got a message from me
3:41
but there was no file ending, so it inspected the file,
3:44
it found that it was audio, but a weird format, so it converted it.
3:48
And then it was looking for something to translate the audio,
3:52
but I didn't have it installed.
3:54
But then it found an OpenAI key, it sent the whole thing to the server,
3:58
it got it back, and then it replied.
4:01
All of that in nine seconds.
4:04
Can you imagine? I didn't build any of that.
4:07
For me, this was the moment where I thought,
4:11
this is something new.
4:12
This is not a chatbot.
4:14
Chatbots give up.
4:16
Agents improvise.
4:20
And, you know, I was sold.
4:22
I wanted to share this.
4:23
I wanted to like, tell people on Twitter.
4:26
And nobody really got it.
4:28
It's like, it's almost like you have to experience an agent.
4:33
It's kind of hard to explain.
4:37
It took me a few weeks.
4:39
And then I did something stupid.
4:42
And remember, this agent, by default,
4:47
can do anything that you can do on your computer.
4:52
So obviously I put it in a public Discord, and I invited random people.
4:56
(Laughter)
4:57
And I was looking at it the whole night.
5:00
People were talking with it,
5:02
people were having fun with it, people tried to hack it.
5:06
And when my eyes were like, falling off almost,
5:12
I exited the process, and I went to bed.
5:19
Though I forgot -- I built a system to be resilient.
5:23
So while I was walking to the bedroom,
5:25
the agent happily booted up again and talked to everyone in the world.
5:31
The next morning I woke up --
5:33
over 800 messages.
5:36
I panicked.
5:37
I pulled the plug,
5:38
I read every single message
5:42
just to see if the agent leaked my private life.
5:45
(Laughter)
5:47
Nothing happened.
5:48
But it could have.
5:50
But that was the moment where it went viral.
5:54
Today, the project is called OpenClaw.
5:58
It's pretty much the fastest-growing open-source project.
6:03
Its mascot is a lobster.
6:05
It claws into your machine.
6:09
Jensen Huang calls it the operating system for personal AI.
6:15
But by far, my favorite quote is from a friend
6:18
who looked at this statistic and said,
6:20
"Peter, this is not hockey-stick growth.
6:23
This is stripper pole."
6:25
(Laughter)
6:34
And I, I was not ready.
6:38
You know, when something blows up like this,
6:41
everything explodes.
6:43
Hundreds of messages,
6:44
reporters calling me in the middle of the night,
6:47
security vulnerabilities.
6:50
And then
6:53
the AI company whose model most of my users loved
6:57
sent me a trademark claim.
6:59
I had to rename the whole thing while it was taking off.
7:04
You know, they even tried to push me away from the lobster.
7:09
(Laughter)
7:11
Like, I was staring at the message.
7:13
It was like, it's not even the same animal.
7:18
And then they also cut off the model most of my users loved.
7:23
You know, first the name,
7:27
then the lobster,
7:29
then the model.
7:32
I was that close to just deleting the whole thing.
7:36
But then I learned what people are building with it.
7:42
So at ClawCon in Vienna,
7:45
because yes, we have conferences already --
7:47
(Laughter)
7:49
And people wore lobster headbands,
7:52
I met Stefan
7:54
and his 60-year-old dad, Gerhard,
7:58
a beer sommelier who never wrote a single line of code.
8:04
They connected OpenClaw via Bluetooth,
8:08
sent it one prompt,
8:09
and the agent did the whole 90-minute brew:
8:13
temperature ramps, hop additions, everything.
8:16
And then they were like, what are we doing with all this beer?
8:22
And the agent was, "Let's make a website."
8:25
So they built a website, and then they added payments,
8:28
and now they have a real product.
8:30
And almost all of it was just done via the phone.
8:36
In China,
8:39
installing OpenClaw is called raising lobsters.
8:44
(Laughter)
8:46
Thousands of people were lining up at the Tencent office in Shenzhen
8:51
to get their lobster installed.
8:54
Shenzhen even gives out subsidies for people running businesses on OpenClaw.
9:01
Now
9:03
if you install OpenClaw on your work machine,
9:07
at least with the default settings,
9:09
you might get fired.
9:12
And then I met an entrepreneur in China
9:16
who showed me a spreadsheet.
9:19
Every employee, every day,
9:21
one task automated by OpenClaw.
9:25
If you miss too many days, you're fired.
9:28
So fired for using it,
9:32
fired for not using it.
9:37
After Marrakesh,
9:39
I thought, this is incredible.
9:42
And it's also a little bit scary.
9:45
How can we make it more scary?
9:47
(Laughter)
9:49
So I added a new feature, a heartbeat.
9:53
You know, by default,
9:54
the agent would only wake up when you send it a prompt.
9:58
With the heartbeat,
9:59
the agent would just wake up periodically,
10:02
check your emails,
10:04
check your calendar, follow up on loose ends.
10:07
My initial prompt was simply "surprise me."
10:12
And yes, that's kind of as scary as it sounds.
10:16
So no large company would ship something like that.
10:20
But I'm a random builder from Austria.
10:23
I don't have a legal department.
10:25
(Laughter)
10:28
I built this sandbox, this sandcastle, for me,
10:33
and I made it open-source so other people could play with it
10:37
and other people could raise their imagination.
10:41
Imagine putting an agent into a meeting.
10:45
Not for notes, we figured that out.
10:48
A bidirectional model that can listen and hear at the same time.
10:55
Somebody mentions a statistic,
10:57
a subagent can spin off and check it for you.
11:00
A decision is made,
11:01
the agent can send a follow-up
11:03
before the meeting even ends.
11:06
In the future,
11:08
we're not just going to have one agent.
11:11
You might have your work agent,
11:14
your personal Claw, maybe one for health,
11:16
maybe one for relationship.
11:19
And they all should work together in a secure way.
11:23
Because how did humanity level up?
11:26
By specializing and collaborating.
11:30
And agents are about to do the same.
11:34
Imagine a company, a small business
11:38
that has ten agents that are all specialized,
11:41
taking over various parts of the business.
11:44
We don't even have a name for what it might become,
11:47
but we are about to find out.
11:50
So I created the OpenClaw Foundation,
11:54
a nonprofit, open-source forever.
11:58
Because what OpenClaw did for many people
12:02
was it moved AI from this scary,
12:07
nebulous thing
12:09
into something that is fun
12:12
and useful and maybe a bit weird.
12:15
You know, lobsters and headbands and beer businesses.
12:20
Because what we need in the future is more people spending more time with AI
12:27
to better understand how powerful
12:29
and transformative this technology really is.
12:34
In New York,
12:37
at ClawCon ...
12:40
(Laughter)
12:41
Yes, they're everywhere now.
12:44
There were thousands of people that were discussing
12:48
what the lobster did this week.
12:52
A retiree in Shenzhen who automated their groceries.
12:58
A teenager in Sao Paulo
13:00
who built a tutoring business on OpenClaw.
13:04
Gerhard and his beer machine.
13:07
None of them are programmers.
13:10
All of them are builders.
13:13
Because that's the real transformation.
13:16
It's not a technology.
13:18
It's the access.
13:20
Agents change who can build things,
13:23
and that door is not closing again.
13:27
Because when you can prompt a prototype into existence
13:33
in one hour,
13:35
anything is possible.
13:37
The next breakthrough can come from anyone,
13:41
any country,
13:43
any cafe.
13:46
When even a burnt-out founder,
13:50
staring at the screen,
13:53
wondering if his spark is gone
13:57
can do something like that.
14:01
It's not gone.
14:03
It's just waiting.
14:05
The lobster is loose,
14:07
and it's not going back into the tank.
14:10
Thank you very much.
14:12
(Applause)
14:21
Chris Anderson: Come here.
14:24
I mean.
14:27
I think I want to say something personal to you.
14:30
With love, but truth.
14:33
You really terrify me.
14:35
(Laughter)
14:37
CA: I’m serious.
14:39
If Hollywood was to ever make a movie
14:41
in which humanity opened Pandora’s box,
14:45
and everything went crazy,
14:46
like, you seriously could be cast as the star character.
14:50
(Laughter)
14:51
CA: Because the story we’re told
14:54
is that AI researchers are doing all this great stuff,
14:57
but they're taking all these great efforts to ensure safety
15:01
and make sure nothing bad could happen.
15:04
You take glee in seeing what might happen if you just put it out there.
15:10
Like, is any part of you feeling that that's a little bit reckless?
15:17
Peter Steinberger: I wouldn't say so.
15:19
I see my work as a ...
15:20
(Laughter)
15:22
PS: I see it as a window into the future.
15:24
Like, in the very beginning, there were all these scary moments.
15:31
Now we have proper security layers.
15:33
You can have your sandbox,
15:35
you can put your lobster into a very small, tiny box
15:41
and really control what it can do.
15:43
There are still some issues that we need to figure out,
15:46
but the fact that so many people want this now
15:49
will help to figure this out much faster.
15:52
CA: So I'm glad you mentioned the security layers.
15:56
I mean, you're making a huge bet on human ingenuity using this.
16:01
This is an incredible tool that suddenly can maximize the power
16:05
of what any human can do.
16:12
How many people in your community
16:15
are taking the safety issue seriously
16:17
and want to use OpenClaw, for example, to find smarter ways?
16:20
Just checking whether anything might be going wrong
16:24
and giving an early alarm to someone or something like that?
16:28
PS: Most people are not as reckless [as] --
16:30
number one, putting it into a public Discord --
16:33
strongly don't recommend.
16:36
Number two, I think I single-handedly increased
16:40
Mac mini sales by multiple percent.
16:43
So most people give it their own little Mac mini.
16:46
Mine's a little princess.
16:48
Mine got a Mac studio.
16:49
It calls it “The Castle.”
16:51
And that greatly reduces the actual risk
16:55
because you can only access what's on that computer.
16:57
And maybe all your pictures are not there.
17:00
CA: Well, definitely, if humanity goes down,
17:02
I'll be very grateful for at least the rise in Mac mini sales
17:05
for a period of time.
17:07
You are amazing.
17:08
You are amazing,
17:10
and I think you're actually right at the cutting edge
17:13
of whether AI is going to be the biggest boon ever
17:17
or possibly a serious problem.
17:19
And, you know, I hope you continue conversations with people here
17:23
and just help us get smarter on how to do this the right way
17:27
because it is absolutely incredible what you've built.
17:29
Thank you for sharing so honestly.
17:31
PS: Thank you so much.
17:32
(Applause)
