微软对专为智能体打造的互联网的愿景，与首席技术官凯文·斯科特对话（播客精选）

我觉得你是一个对手艺非常在意的人。

You're someone who, I think, cares a lot about the craft of things.

你知道，有人批评用智能体写代码，说这会失去那种感觉之类的。

One of the knocks on, you know, using agents for coding is it gets rid of some of that feeling or something like that.

你怎么看这件事？

How do you feel about that?

我很喜欢我的同行们，就是那些创造者，广义上的，比如软件工程师，或者机械工程师，对。

I love the fact that my people, you know, makers, writ large, so software engineers or, you know, mechanical engineers Yeah.

还有木匠或者陶艺家。

Or woodworkers or potters.

如果你真的热爱你做的事情，你一定会对自己怎么做这件事有非常强烈的看法。

If you are really passionate about what you do, you're going to have very strong opinions about how you do it.

我做木工的时间几乎和我编程的时间一样长。

I've been a woodworker for almost as long as I've been a programmer.

这不是过去四十年里软件开发本质发生重大变化的第一次。

This is not the first moment in the past four decades where the nature of software development has changed in a nontrivial way.

所以，如果智能体要有用，它们就得替你去行动。

Like, if agents are gonna be useful, they have to take action on your behalf.

对。

Yep.

它们必须能够使用工具、修改系统，还要能查阅多样且丰富的信息源。

They have to be able to use tools and make changes in systems and consult information sources that are, you know, diverse and rich.

想要真正做得好，你需要一个跟互联网非常像的生态系统。

And in order for that to, like, really be great, you need an ecosystem that looks a lot like the Internet.

如果你有信息源，已经有网站，或者有对外提供服务的API，那你就得想办法打通这些渠道，让智能体能够跟它们对接。

If you have a source of information, you already have a website, you already have an API that's doing something for people out there, like, you've gotta figure out how to plumb things through where agents can, like, talk to those things.

比如说，我在微软一直推动的一件事就是，我们内部所有系统都要用统一标准协议跟我们编写的智能体通信。

Like, one of the things, the CTO that I've been pushing for at Microsoft is, like, I want all of our systems internally to speak a standard protocol to all of the agents that we're writing inside of Microsoft.

保持好奇。

Be curious.

去试试，如果你觉得管用，那就用它。

Try And if it works for you, use it.

如果不行，就别用了。

And if it doesn't, don't.

Kevin，欢迎来到节目。

Kevin, welcome to the show.

哦，谢谢你邀请我。

Oh, thanks for having me.

有趣的是，我去年也来过这里。

One of the things that's interesting is I was here last year.

对。

Yep.

你当时说了两件事。

And you said two things.

有两大主题。

There there are two big themes.

一个就是智能体会无处不在。

One was agents are gonna be everywhere.

你这样说过，我觉得后来真的应验了。

That's one of things you said, which I think really came true.

那真是很有先见之明。

That was very prescient.

另外，去年大家非常注重规模扩展规律。

Another thing is I noticed a big emphasis last year on scaling laws.

对。

Yep.

当时有很多图表，说我们在建大型基础设施、打造更大的模型，而且每两年就会有大的性能提升。

There were a lot of graphs of, like, we're building big infrastructure, we're building these bigger models, and every two years, we're gonna get these big performance improvements.

对。

Yeah.

今年，重心真的放在智能体网络上。

This year, the emphasis is really on, the agentic web.

对。

Yep.

那么，发生了什么变化？

So what has changed?

从去年到今年，我们学到了什么？

What have we learned from last year to this year?

对，我觉得确实发生了很多变化。

Yeah, think there's a bunch of things that have changed.

比如其中一点，我觉得去年大家心里都在怀疑，缩放法则是否还能继续好好发挥作用。

Like one of the things is that I think, last year people were like really in this state of mind that they were doubting that, the scaling laws were going to continue to work really well.

但实际上，我觉得我们已经年复一年地证明了它们依然成立，并且效果很好，所以这已经不是需要反复提醒大家的事了。

Whereas like, I think, you know, we've demonstrated year after year after year that, they are in tact and working quite well that like that's not a thing that people need to be reminded of, anymore.

还有就是，老实说，模型的推理能力确实已经比我们正在产品里用到的部分要超前一些了。

And I think the other thing too, that's happened honestly, is that the reasoning capabilities of the models has, actually gotten a little bit ahead of what we're using the models to do in products.

所以我最近一直在讲一个叫“能力过剩”的概念。

So I've, I've been talking a lot lately about this, thing called the capability overhang.

而我认为，整个行业确实需要一起努力，把模型真正具备的能力和我们交付给用户的能力之间的差距给补上。

And you know, I think we actually have some work to do collectively across the whole industry to close the gap between what the models are actually capable of and like what we're delivering to users, of that capability.

所以，这就是为什么今年Build大会可能不像去年那样，大家那么热衷于讨论规模法则了。

So that, that's one of the, one of the like big thematic things why, you know, scaling laws might not be as interesting to talk about at this year's Build As Last.

另外，我们还发现，过去一年里涌现出了各种各样的智能体。

And then the other thing too is that we've just discovered is all of these agents have emerged over the past year.

所以，无论是智能体的数量，还是人们花在这些智能体上或与它们互动的时间，都意味着除了推理能力之外，还有很多其他问题需要解决，才能让它们发挥应有的作用。

And so like both the number of agents and like the amount of time that people are spending doing stuff inside of these agents or with these agents is that there's a bunch of other stuff other than reasoning that has to get sorted out in order to make them as useful as they should be.

所以，今天在Build大会主题演讲中我提到的，我们需要更好的智能体记忆，因为目前我们的智能体在记忆方面受到很多有趣的限制。

So, you know, the things that I was talking about, at the keynote today at Build were, you know, we need better agentic memory, like our agents right now because memory is constrained in a bunch of interesting ways.

它们有点过于事务性了。

They're a little bit transactional.

比如你用它们做一件事，记忆在任务过程中是连贯的。

So like you use them for like one thing and like, you know, memory's coherent across the course of that task.

但之后，记忆可能会完全消失，也可能不会。

But yeah, then it may or may not completely go away.

下次你就得从头开始，这真的会限制你把这些越来越复杂的任务委托给它们的能力。

And like you're starting from scratch, the next time, which really inhibits your ability to delegate increasingly complicated tasks to these things.

然后呢，就是有个很现实的问题：智能体要真的有用，它就得替你做事。

And then like, there's just this real issue that like, if agents are going to be useful, they have to take action on your behalf.

比如说，它得会用各种工具，能在系统里做改动，还得能查询那些丰富多样的信息来源。

Like they have to be able to use tools and, like make changes in systems and consult, information sources that are, you know, diverse and rich.

要想真正做得好，你需要一个像互联网那样的生态：如果你有信息源，你已经有了网站，已经有了一个API在给外界提供东西。

And in order for that to like really be great, you need, like an ecosystem that looks a lot like the internet where, if you have a source of information, you already have a website, you already have an API that's doing something for people out there.

你得想办法把一切打通，让智能体能和那些东西对话，而且要让各方利益一致，让大家都愿意参与进来，在智能体网络里找到自己合适的位置。

Like you've got to figure out how to plumb things through where agents can like talk to those things, and where, you know, all of the incentives are aligned for everyone to like go have all of this stuff participating in, you know, ways that make sense to them in this agentic web.

所以我觉得今年最大的看点就是这个。

And so I think that is the big story this year.

就好比你已经看到了真正进展的曙光，有像MCP这样的简单又棒的开放协议，它在智能体网络里的作用就相当于互联网的HTTP，还有像NLWeb那样的，扮演着类似互联网HTML的角色。

It's like, you've seen the first glimmers of like real progress with like super awesome, simple open protocols like MCP that are serving the same purpose in this agentic web as HTTP does on the internet and where you have things like NLWeb that are like serving, you know, the same moral equivalent purpose as HTML does on the internet.

所以我觉得接下来你你会看到，这些简单的东西可以组合、叠加，开发社区也会非常活跃，而且有很大的希望这些东西都能普及起来，这样智能体才能真正发挥作用。

And so I think you're going to see these things like simple things that are composable and layering and like just lots of activity in the open community and like a bunch of things hopefully getting to ubiquity so that agents can actually do stuff.

对。

Right.

我复述一下，我听到的一点是：我们有了智能体。

So I I think to to play that back, like one of the things I hear is like we have agents.

智能体正在发挥作用了。

Agents are starting to work.

而为了让它们变得强大，智能体需要有访问的渠道。

And in order to make them powerful, agents need access.

它们需要访问互联网上所有的内容，还有电脑上各种信息。

They need access to like what whatever is out on the internet, whatever is on your computer, all that kind of stuff.

基本上，你需要制定协议和流程，让智能体能够访问这些东西。

And you need, basically, protocols and processes for agents to be able to access that stuff.

所以，你会看到技术栈的不同层面。

And so, you're looking at different parts of the stack.

没错，绝对赞同。

Like Absolutely.

运行时层，就是你正在构建记忆等这些内容的地方。

The runtime layer where where you're, you know, you're building, like, memory and and and all those kind of stuff.

然后是MCP，它能让你连接到更广泛的互联网，为智能体获取更多信息。

And then m p MCP, which allows you to connect into the wider Internet to get inform more information into agents.

对。

Yep.

我想问，这对微软来说为什么如此重要？

I guess, why is that important to Microsoft?

以及，你们想在这样的生态系统中扮演什么样的角色？

And, like, what role do you want to play in that kind of an ecosystem?

嗯，你看，我觉得有两三件事非常关键。

Well, look, I think there are, you know, two, maybe three things that are super important.

首先，要让智能体有用，我们为用户构建的这些智能体，就需要在它们内部解决这些问题。

So one is like, make agents and in order for our agents that we're building for folks to be useful, like we need to solve these problems inside of, these agents.

哪怕把范围缩小到企业级智能体，作为CTO，我在微软一直推动的一件事就是，我们内部所有系统都应该用标准的协议与我们写的所有智能体通信。

And like, even if you sort of scope it down narrowly to enterprise agents, like one of the things as CTO that I've been pushing for at Microsoft is like, I want all of our systems internally to speak a standard protocol to all of the agents that we're writing inside of Microsoft.

这样我们就不需要用康威定律去应对整个世界，也就是组织方面的……

So that, we're not exposing the entire world to like Conway's law, which is, you know, organization.

康威定律在编译器里是个挺奇怪的东西，就是那个叫康威的人说，你编译器里的阶段数或者遍数，会取决于你开发编译器的团队数量。

So Conway's law is like, it's really funky thing in compilers where, you know, guy Conway said that the, the number of stages or passes in your compiler is going to be dictated by the number of teams you have working on the compiler.

你交付的是你的组织架构。

You ship your org chart.

对。

Correct.

你交付的是你的组织架构。

You ship your org chart.

所以，在像微软这样的公司内部，你肯定不希望在建智能体的时候，把组织架构也一起交付出去。

And so, you know, You, you certainly inside of the confines of a company like Microsoft, like you don't want to be shipping your org chart when you are, building your agents.

作为一个工程师，看到这种低效的构建方式，真是挺难受的，尤其是当大家没有统一的标准协议和服务的时候。

And like, it's just kind of a horror show to watch, like as a engineer, like all of this inefficient building, like when you don't have like those standard protocols and services that everybody's using.

但我觉得，如果你真的想象一下智能体可能做到的事情，以及那些用户——不是指我，而是那些希望这些工具能比现在更有用的人——他们期待什么。

But I think, you know, if you sort of imagine, if you really imagine like what agents could do and like what you, you know, what users, like not me, but like, you know, just people who are hoping these things can be more useful than they are right now.

你需要让事情开始以和网络时代相同的方式发生。

Like you need things to start happening the same way that they were happening, with the web.

而且我现在就能看到这种趋势。

And like, I kind of see it right now.

比如MCP就是一个很好的例子。

Like MCP is like a really great example.

这个协议非常简单，却解决了一个非常重要的问题。不仅对正在开发智能体、构建平台基础设施的人来说如此，对那些希望这些系统更有用的用户，还有那些服务提供商来说也是这样。他们会想，嘿，我想参与这个新的智能体网络。现在人们做事情的方式跟以前不一样了，以前我还知道怎么去连接，可现在大家都坐在那儿用着这些智能体，心里想：我该怎么把我的东西接进来呢？

So it is a really simple protocol that solves a really important problem, not just for people who are making agents and building platform infrastructure, but for, yeah, Users of these systems who want them to be more useful and for people who are providers who are like, Hey, like I want to be participating in this new agentic web is like, people are doing less of one thing, which I knew how to connect to, like how, and they're, you know, they're sort of sitting here using these agents, like how do I get my stuff wired up into this?

而且对我来说，这怎么才能行得通呢？

And like, how does it make sense for me?

甚至从商业模式的角度来看，也得这么做。

Like even from a business model perspective, to do that.

所以就是这两件事：首先是让我们自己的智能体更有用。

And so like, that's the two things it's like make our own agents more useful.

另外，我们是一家平台公司，所以比我们自己写的智能体更重要的，

Then like, we were a platform company, like even more important than the agents that we're going to write ourselves.

是微软用了五十年时间才在技术上打造出来的那个平台层。

Like that platform layer that Microsoft has been building in technology for fifty years.

我们只是想要确保我们在帮助解决这个代理网络发展过程中涌现出的问题。

Like we just want to make sure that we are helping solve the problems that are emerging as this agentic web is happening.

对。

Yeah.

看到你们这么大力推进MCP，并且把它整合到Windows等所有东西里，真的很酷。

It's been, it's really cool to see you guys like leaning really hard into MCP and like integrating it into all of Windows and all that kind of stuff.

那真是太棒了。

That's really awesome.

这让我想到，我开始听到一些深入研究MCP的人在讨论，说安全模型需要很多

And it it brings up for me I've been starting to hear rumblings from people who are thinking a lot about MCP that the security model needs a lot of

工作。

work.

然后

And

我很好奇，你对这个怎么看？因为你一直在拿这个体系和互联网体系做比较。

I'm I'm curious, like, for your take on that because you're you're you're making a lot of comparisons between this stack and the Internet stack.

互联网的安全模型里有很多东西，比如同源策略，就是为了确保如果一个网站提供代码给你，那它也只能在自己的数据上执行。

And the Internet has a bunch of, like, things in its security model, like the same origin policy that make sure that you like, if a website is serving you serving you code, like, it's only able to execute on its own data.

对。

Yep.

但MCP并没有这个。

And MCP doesn't really have that.

所以你怎么看？你觉得什么样的安全模型对这个更合适？

So like, how do you what do you think the right security model is for this?

嗯，说实话，我也不确定什么才是完全正确的安全模型。

Well, I look, I don't know, that I know what exactly the right security model is.

但MCP有意思的地方在于，它那么简单明了，所以社区去讨论确定安全模型反而会比较容易。

But like the interesting thing about MCP is, like it is so coherently simple that it's going to be relatively easy for the community to decide what the security model is.

没错，我们确实有很多企业级的东西需要关注，而且我们跟MCP团队合作得很好，都在努力推进这些事情。

Like, yeah, we, we have a bunch of like enterprise things that we care a lot about and that like, we're doing really good work with the, with the MCP team to get done.

所以我们需要给智能体提供身份，这样才能建立权限系统。

So like, we need agents to have identities, so that you can build entitlement systems.

所以你可以说，这个代理代表这个人行事，他们有权查看这个系统中的这些资源。

So you can say this agent is acting on behalf of this person and like, they're entitled to see these resources in this system.

而且，即使只是让代理去查询一堆系统，然后说，这些，这是我想做的事情。

And like even having a way for an agent to sort of go query a bunch of systems and say like, These, here's the thing that I would like to do.

这些是我需要接触的系统才能完成这件事。

These are the systems I need to touch in order to do the thing.

我需要申请哪些权限才能做到这一点？

Like what entitlements do I need to ask for in order to do this?

所以我可以向用户请求权限，比如，把这件事委托给我的人，我向他们展示？

And so I can request permission like from the user, like the person who's delegated this has to me, like, I present to them?

比如，我能获得这些权限来完成你让我做的这件事吗？

Like, can I have permission to these things in order to do this thing you asked me to do?

可以还是不可以？

Yes or no?

然后对于所有这些系统的管理员，你知道，比如，嘿，这一切发生可以吗？

And then for the administrators of all of these systems, you know, like, Hey, is it okay for all of this to be happening?

所以，这些在MCP之上实现起来都相对直接，虽然不是容易，但算是比较简单的。

And so like, there's all of that's going to be like relatively straightforward to do, like, not easy, but like relatively straightforward to do on top of MCP.

重要的是，我们要以开放的方式来做这件事。

And like, the important thing is like, let's do it in an open way.

我们不希望它只对我们自己的代理或系统专有。

Like we don't need it to be proprietary, to like our agents or our systems.

我们只需要想办法让这个领域像互联网那样运转。

Like we've just got to figure out how to get this dime where things kinda work like the web works.

是的。

Yeah.

嗯，对我来说这是个有趣的问题，因为我觉得你们讨论的人工智能可能有两种潜在模式或市场切入点。

Well, it's an interesting question for me because I feel like there's there's maybe two potential models or potential go to markets for for AI stuff that that you guys have been talking about.

一种是垂直整合模式，你拥有模型，也拥有界面层。

One is this sort of, like, verticalized model where you own the model and you own the UI layer.

你完成所有应用和中间的所有环节。

You do do all the applications and everything between.

关于那个模式，可以说App Store或者苹果iPhone的模式就是一个很好的例子，它能在很多方面保证安全性。

And and the the thing about that model, which maybe it's sort of you could say the the App Store or Apple iPhone model is is is a good example of that is you can guarantee security in a lot of ways.

而开放的模式，做安全方面就更难，但你基本上会获得更多的创新，因为没有中央权威机构。

And an open model, it's harder to do security stuff, but you get much more like innovation basically because there's no central authority.

那你们是怎么考虑做出这个决定的？

So how did you guys think about making that making that decision?

对。

Yeah.

你看，我知道这是很多人的说法。

So look, I, I know that that's the argument that a lot of people make.

是的。

Yeah.

我觉得这可能是个假的二元对立。

I, I think it might be a false dichotomy.

你看，在这些开放系统里，有一个特点，就是它们是不需要许可的。

There, there is a, you know, like a, a thing that you have in these open systems where they are permissionless.

对。

Yeah.

而且，无门槛的创新确实有很大的优势。

And like there's a real advantage in having permissionless, innovation.

所以对我来说，现在最让人兴奋的一点就是，你可以自由地去创新和构建东西，完全不需要去求谁的许可，比如不用非得让谁批准你才能把作品分享给别人。

So like the thing that as an individual that excites me most about what's happening right now is the extent to which you can go innovate and build things without having to seek someone's permission, like where you have to have them grant you permission for distributing your things to other people.

也不用面对那些复杂的把关机制，这些机制往往横亘在拥有想法的你和可能从中受益的人之间。

And, you know, like having all of these like complicated gatekeeping things that are sitting in between you who are the person who had the idea and like the people who might benefit from it.

说实话，我觉得过去几年冒出来的那些中间层，对真正重要的两方——也就是辛苦做出作品的人，以及愿意投入注意力、金钱或其他有价值资源去获取作品的人——其实没提供多少价值。

Like, I think some of these like middle layers that we had that have emerged over the past handful of years, like just aren't contributing much value, honestly, to the two parties and the transaction that matter, which is the person who did the hard work to make a thing.

这些人就是那些愿意花时间去关注，或者花钱、用其他有价值的东西来换取接触这些作品机会的人。

Then the people who are going to either spend their attention or their money or some other currency that's valuable to like access the thing.

所以我对这个方向挺兴奋的。

So like, I get it kind of excited about that.

这也是我们做出现有决定的原因之一。不过我也认为，借助现在已有的AI能力，我们完全可以在这些系统中实现非常可靠的安全保障，从而拥有更好的安全性。

And so like, that's one of the reasons why we've made the decisions that we want to, but like, I also think that there are ways that you can get real robust security, in these systems, like leveraging some of the AI capability that you have now, that, you know, where you may be able to have better security.

比如说，如果你运行一个代理，它负责处理你的个人安全需求，比如这些是我愿意分享的东西。

Like if you have an agent that you are running, that is attending to your personal security requirements, like these are things I'm willing to share.

这些是我不愿意分享的东西，你知道的，而且它有一些风险评估的知识，比如，就像今天早上，当我正准备上台的时候，我收到了一堆邮件，因为我是我妻子的备用安全账户，有人在她的账户上动了两步验证。

These are things I'm not willing to share, like, you know, and that has some kind of knowledge of risk assessments and like, yeah, like for instance, like my wife this morning, while I was, while I was getting ready to jump on stage, like I got this flurry of emails, that, because I'm the like backup security account for my wife where like somebody was like fiddling around with two factor authentication on her account.

我做的第一件事就是给她发短信。

And like the first thing I did was I texted her.

我不想给她发邮件，因为可能有人未经授权访问了她的邮箱。

Like I didn't want to email her because somebody might have gained unauthorized access to her email account.

我给她发了短信。

I texted her.

我说，嘿，你是不是在乱改配置？

I was like, Hey, are you screwing around with the configuration?

她说，是的。

And she's like, yes.

所以你可以想象，如果有一个代理，它知道你的各种通信方式，能够注意到有什么不对劲，然后利用各种资源来确认这是合法活动还是非法活动。

And so like, you could imagine like having an agent that is like privy to like a whole bunch of your communication modalities, like being able to like notice that something funky is going on and then like, you know, using a bunch of resources to triangulate, like whether that's legit activity or illegitimate activity.

所以，我觉得有很多类似的事情，你可以两者兼顾，对吧？

So I, I like, I think there's just a bunch of stuff like that that like you, you can have both, right?

我不觉得必须二选一，就像你刚才说的那样。

Like, I don't think it needs to be like, you know, one or the other as you framed it.

对。

Yeah.

有道理。

That makes sense.

我另外好奇的一点是，很明显软件工程正在发生变化。

One of the one one other thing that I'm I'm curious about is it just seems pretty clear that software engineering is changing.

对。

Yeah.

而你从事软件工程已经很久了。

And you're someone who's been involved in software engineering for a long time.

而且我觉得你也是一个很注重工匠精神的人。

You're someone who also, I think, cares a lot about, like, the craft of things.

就是那种制作东西的工艺。

Like, the craft of how things are made.

我们之前聊过你做很多陶艺。

We were talking earlier about you're making you do lot of ceramics.

你自己做包。

You make your own bags.

你喜欢亲手做东西。

Like, you're you love having your hands in things.

对。

Yeah.

我觉得用智能体来编码的一个诟病就是，会让人失去那种亲手做的感觉，不过我对此不太认同。

And I think one of the knocks on, you know, using agents for coding is, like, it gets rid of some of that feeling or something like that, which I don't necessarily agree with.

但我想问你，作为一个在意代码工艺的人，面对用智能体来写代码的未来，你心里是什么感受？

But I'm sort of curious for you, like, as someone who cares about the craft of code, looking into this future of coding with agents, like how does that, how do you feel about that?

我首先想说，我很喜欢我的同道中人，我指的是广义的制造者，比如软件工程师、机械工程师、木匠、陶艺家，或者说只要是从原材料或无中生有去创造东西的人，都算。

Well, so let me start by saying that I, I, I love the fact that my people, and like, when I say my people, I mean, you know, makers, writ large, so software engineers or mechanical engineers or woodworkers or potters, or, you know, just sort of pick your thing where people are trying to create things from raw materials or nothing.

如果你真的热爱你所做的事情，你会对你做事的方式有非常强烈的看法。

If you are really passionate about what you do, you're going to have very strong opinions about how you do it.

你用的工具、你用的材料，还有东西是怎么组合在一起的。

The tools that you use, the materials that you use, like how things get put together.

这是你在工作上变得出色所必需的东西。

It is a necessary thing for you to be great at your job.

有趣的是，人们有很多很多不同的看法。

The interesting thing is people have lots and lots of different opinions.

你还提到一个观点，我已经做了很久了。

And one of the events you said, I've been doing it for a long time.

是的。

I am.

我是个老古董了。

I'm an old fart.

我12岁写了第一个程序，也就是说我已经编程41年了。

I wrote my first program when I was 12, which means I've been programming for forty one years.

所以，当你做了很久一件事之后，你就会发现，过去这四十年里，软件开发的性质并不是第一次发生这种巨大的变化，也不是第一次有人对变化和它的意义有非常强烈的看法。

And so the thing that you get to see when you've been doing a thing for a very long time is like, this is not the first moment in the past four decades where, the nature of software development has changed in a non trivial way and where people have very strong opinions about the change and what it means.

所以，对，我觉得现实就是，人们会有选择。

And so, yeah, I think the, the reality is that people will have choice.

你知道吗，就像我，当我打开一个文本编辑器的时候——我可能不该说这个，因为我们做了Visual Studio Code——但我就是个老顽固，我现在还在用VI。

You know, like I still, when I go into a text editor, I probably shouldn't say this because like we make, you know, Visual Studio Code, like I'm such an old recalcitrant fart, that I still use VI.

至少我用的是VI。

I use them at least.

我选的文本编辑器就是这种特别老古董的东西。

But like my text editor of choice is like this extremely antiquated thing.

我就是拒绝换别的用。

And like, I just refuse to go use something different.

虽然我肯定知道这其实让我效率降低了，但我还是这么决定，因为我可以选。

Even though I know for sure that that is sub optimizing a part of what I'm doing, but I make the decision anyway, because like I get to choose.

然后在我做的其他方面，不管是软件还是别的事情，我就会觉得，关键不在于我用哪个方法做这部分。

And then in other aspects of my making, like either software or something else that I'm doing, like I will be like, okay, the important thing here is not the way that I'm doing this particular part of it.

我真正想达到的就是那个结果。

It's the outcome that I'm trying to get to.

我会用最强大、最方便的方式去达到那个结果。

And like, I'm going to use the most powerful Or most convenient way to go get to the outcome.

而且我不在乎谁会因此说我的不是。

And like, you know, I don't care who's going to throw rocks at me for doing it.

对，这种态度到处都是。

And like, it's literally everywhere.

我当木工的时间和我写程序的时间差不多一样长了。

Like I I've been a woodworker for almost as long as I've been a programmer.

我十几岁的时候，大家争论的重点就是，‘你算真正的木匠吗？’

And when I was a teenager, like the big debate was like, Oh, are you a real woodworker?

如果你用了电动工具，就觉得你不够格，因为真正的木匠只用手工工具。

If you use power tools, like, you know, real woodworkers only use hand tools.

现在这种争论还有一点，但真正的分歧变成了：如果你用 CNC 数控机床，那算不算真木匠？也就是用电脑控制的电动工具，而不是普通的电动工具。

Like there's still a little bit of that debate today, but like the real debate is like, are you a real woodworker if you use CNC tools, like computer controlled power tools versus just power tools?

我理解这一点。

And I understand it.

就是我觉得这个争论本身很有意思。

Like, I actually think it's interesting the debate itself.

但有时候人们会做出不同的选择，因为他们看重的东西和你不一样。

But like sometimes like people are going to make different choices because like they value something different than you do.

如果你更看重过程而不是结果，你有时会做出和那些更看重结果的人不同的决定。

If you value the process more than you value the outcome, like sometimes you'll make different decisions and people who value the outcome more than the process.

我觉得这个问题就像，你是真正的木匠吗？你是真正的程序员吗？

And I think the like, is it a, are you a real woodworker, a real programmer?

你有点像在说，只有像我这样做事的方式才算真功夫。

You're sort of saying like, you're only real if you do it the way I grew doing it.

对。

Yeah.

你问这个问题的时候，从很多方面来说，你知道吗？

When you ask that question in a lot of ways, you know?

不过，这东西实在太多样了。

But, but it's just so varied.

对吧？

Right?

但我想说的是，我绝对不会在没有绝对把握的情况下，叫别人不要对自己的手艺抱强烈看法。

And like, so the, the thing that I will say is like, I would never in a million years tell anyone not to have strong opinions about their craft.

有这些看法挺好的，真的。

Like have them, like it's great.

我给别人的建议是，这只是一个建议，我自己觉得很管用的就是保持开放的心态，尤其是当工具在改变的时候。

Like the, the advice that I would give people and like, this is not me telling them what it's just advice, like things that I've found useful for myself is just have an open mind, you know, when the tools are changing.

我跟你说，我都有多少次看到新的技术，是在其他非软件的制作领域出现的，我心里就想着，哎呀，我不想学什么3D打印机。

I can't even tell you like the number of times where I have looked at a new technology in some other like non software, dimension of making that came along where I'm like, Ugh, like I don't want to learn like three d printers.

我等了好长时间才去学用3D打印机，我后悔死了。

Like I waited forever to learn how to use three d printers and like, I regret it.

我早该开始的。

Like I should have started earlier.

它们对我做的几乎所有事情都太有用了。

Like they're so damn useful for almost everything that I do.

而且由于各种复杂的原因，我当时没有让自己去好奇，这很奇怪。

And for a whole variety of complicated reasons, like I didn't let myself be curious about that, which is odd.

所以，是的，保持好奇心，去尝试新东西，如果对你有用，就用它。

And so, yeah, just like, be curious, try stuff like, and if it works for you, use it.

如果没用，就别用。

And if it doesn't, don't.

对。

Yeah.

你觉得软件工程代理的未来会是什么样子？

What do you think is the future of software engineering agents?

比如，是会出现一个代理统治一切，还是你会使用很多不同风格、不同口味的代理？你怎么看待这个生态系统的演变？

Like, is there going to be like one agent rule them all or is it, you're just going use many different agents with different tastes or like, how do you see that ecosystem shaping up?

是的。

Yeah.

我觉得会有很多不同的代理。

I look, I think it's going to be a lot of different agents.

我的意思是，有很多代理是好事，而且我们肯定会在GitHub Copilot和GitHub代理上努力。

I mean, like, and it's good to have a lot of agents and like we certainly would get up Copilot and the, you know, get up agent stuff that we're working on.

我觉得我们会非常努力地竞争，成为很多人选择的工具，因为它对他们非常有用。

Like, I think we will compete very hard to like be a tool that lots of people will choose because it's very useful to them.

但在开发者这个圈子里，我觉得不现实的是，认为地球上的每个开发者都会在重要的工作部分使用同一个工具。

But I think it's unrealistic in the universe of developers to like, think that like every developer on the planet is going to snap to using like one tool for like an important part of their job.

作为开发者的一部分乐趣就在于你确实有选择，你可以选择并尝试各种不同的东西，做理性或不理性的事情。

Like part of the joy of being a developer is you actually have that choice and you can sort of choose and play around with a bunch of different things and like do irrational things and like do rational things.

这就像，你知道，这是我在过去四十年的编程生涯中看到的一贯现象，就是人们总是会更换他们的工具。

Like, it's, it's just, you know, it, it, it is one of the very consistent things that I've seen over the past four decades of my programming life is like people choose to change their tools all the time.

是的。

Yeah.

有哪些维度？

What are the dimensions?

你觉得各种智能体可能会在哪些维度上有所不同？

Do you have an opinion on the dimensions along which the different agents might differ?

好吧，我认为智能体最重要的，可能就是产品层面的那部分。

Well, I think the most important thing about, agents is like probably the product making part of them.

所以，我现在看到的最有意思的初创公司，并不是靠打造某种差异化基础设施来创新。

And so the most interesting startups that I'm seeing right now are not trying to innovate by building some kind of differentiated infrastructure.

他们创新，是因为他们认为自己比别人更理解某个用户遇到的问题。

They're innovating because they think they have an understanding of a problem that someone has that is better than anyone else.

而且他们觉得，可以利用、修改或调整现有的基础设施，来以世界级的方式去解决自己理解的那个问题。

And they think that they can pick up infrastructure or modify infrastructure or tune infrastructure to go solve their understanding of that problem in a world class way.

所以我认为，这恰恰是现在大量需要的东西。

So I think that's what we need a lot of right now.

而这也将决定智能体之间的多样性，以及什么东西用在哪些方面。

And like, that's, what's going to dictate the diversity of agents and like how, like which things get used for what.

说实话，现在要深刻理解某人的问题，再拿起这些工具去尝试解决，实在容易太多了，所以你会看到很多公司，做很多东西，想办法去弄，这种趋势连软件开发工具上也看得出来。

And I think honestly, because it's so much easier now to like have that nuanced understanding of what someone's problem is and to pick up these tools to go take a swing at solving it, that you're just going to have a lot of companies, like building a lot of things, trying to, you can even see it with the software development tools.

过去一年冒出来的东西多到令人难以置信。

It's like crazy how many things have come out over the past year.

而且每个都很有意思，全都很有意思。

And like, they're interesting, like all of them.

对，如果你自己就是做软件开发工具的公司，应对的东西太多了，不过真的超级有意思。

Yeah, it's a lot to respond to when you're a company building software development tools yourself, but like, it's super, super interesting.

我们看到的是，如果你能细致地理解别人的需求，人们就会特别包容，也特别愿意尝鲜。

It's like, what we've seen is if you've got some kind of nuanced understanding of what someone needs, like people have like high tolerance and like high interest in like giving things a try.

对。

Yeah.

我们快没时间了，但我很好奇，比如一年后，我们再回到 Build 大会。

So we're almost out of time, but, I'm, I'm curious, like let's say it's a year from now, we're back at build.

对。

Yep.

哪些话题现在是热门，或者大家现在特别关心的问题，但到明年就不重要了？

What are, what are some things that are a hot topic right now, or big questions that people have right now that are not going to matter in a year?

那一年后什么会变得重要？

And what is going to matter in a year?

你预测我们接下来会聊些什么？

And what are your, what are your predictions for what we're going to be talking about?

对。

Yeah.

我觉得那些还抱着老想法的人，比如觉得技术还没准备好，因为试过一些东西，结果要么太贵，要么能力刚好不够做想做的事。

I think people who are still like hanging onto these ideas that, oh, like the technology's not ready yet because like I, yeah, I tried to do something and it was like marginally too expensive or like it was marginally capable of, you know, doing the thing that I wanted to do.

我觉得任何拿这些当借口，迟迟不开始行动的人，都会落后很多，因为每年东西都会更便宜，能力也会更强。

Like, I, I think anyone who is using those as excuses to wait to get started are going to be super behind, because everything's going to get cheaper and everything is going get more capable every year.

我知道，而且我觉得这在2025年其实不是什么难卖的观点。

I know like, and I think this is actually not a hard sell in 2025.

对，以前有一大堆人在喊，说进步要结束了，一切都会停下来，大家都会非常失望。

Yeah, it was this loud chorus of like, Oh, you know, the progress is gonna, you know, it's about to end and like, everything's going to stop and like, everybody's going to be super disappointed.

虽然现在还是有人在这么说，但我觉得大家已经不太在意他们了。

Like I, I, I mean, there's still some people out there saying that, but like, I don't think, you know, folks are paying much attention to them anymore.

主要是因为，你知道，你去关注那些说事情要停下来的怪人，你能得到什么好处呢？你基本上是在赌失败，而赌失败和赌乐观之间的代价差别可大了。

Mostly because like, you know, what, what do you win by paying attention to like some crank who's, saying like, you know, the, the things about to stop, like you're sort of betting on failure and the cost of betting on failure versus betting on optimism is like, is a real big difference there.

所以，是的，我觉得我们会看到人们在用智能体解决更宏大的问题，这方面的进步会非常大。

So yeah, like I, I think we're, we're gonna, we're going to see a ton of progress on, like the level of ambition of problems that people are tackling with agents.

然后我觉得，随着智能体网络变得更完整、更完善，模型的推理和规划能力越来越强，交互方式也会变得非常不同。

And then I think, you know, modalities that are going to be really different is like, is this agentic web starts to get more complete, more plumbed out, and the models reasoning and planning capability get better and better.

你会开始达到一个点，就是你能从与智能体的同步交互模式转向异步模式。

Like you're going to start to get to the point where you're able to go from this synchronous mode of interaction with agents to asynchronous.

就像现在，人们做的事情是，他们坐下来，有想做的事，然后发出提示，等着结果回来，然后根据回应做点什么。

Like right now, of what people do is like they sort of sit down, like they got a thing they want to do, like they issue the prompts, like, and they wait until, you know, the thing comes back, and like, you know, do something with that response.

所以我觉得，到明年，你会看到人们用这些智能体去做一些事情，比如“嘿，去把这个搞定”。

And so I think, you know, by next year, you're going to see people using these agents to like, Hey, go sort this out.

然后智能体会花很多时间。

And like the agent is going to take a lot of time.

它会去调用很多系统，它采取行动的那些事情，可能需要一段时间才能有结果。

It's going to go make a lot of calls out to systems, like the things that it's sort of, like taking action on are going to like take a while to come back.

然后它们会整合所有这些结果，再去做点什么。

Then they're going to like integrate all of those responses and like do something.

整个过程可能会迭代很多次，然后过很长一段时间之后，你会说，好吧，我这边就到这一步了，现在轮到你了。

And like that whole thing may iterate a bunch of times and then, you know, at some non trivial amount of time later, you're going to sort of say, okay, like here's the, here's the, here's as far as I got, like now it's your turn.

现在你去采取行动吧。

Like go take some action now.

听起来像是个

Sounds like a

我想去的未来。

future I want to be in.

对。

Yeah.

我也是。

Me too.

对吧？

Right?

凯文，真是太感谢你了。

Well, Kevin, thank you so much.

能和你聊天真的非常非常开心。

It was really, really great to talk to you.

我也很高兴能和你聊。

Good to talk to you as well.

谢谢你的邀请。

Thanks for having me on.

天哪，各位朋友。

Oh my gosh, folks.

你们绝对要狂点那个点赞按钮，并订阅 AI and I。

You absolutely positively have to smash that like button and subscribe to AI and I.

为什么？

Why?

因为这个节目就是最棒的典范。

Because this show is the epitome of awesomeness.

就像在后院发现了宝藏箱一样。

It's like finding a treasure chest in your backyard.

不过里面装的不是金子，而是关于ChatGPT的纯正知识炸弹。

But instead of gold, it's filled with pure unadulterated knowledge bombs about chat GPT.

每一集都像坐过山车，情感、见解和笑声交织在一起，让你坐立不安，迫不及待想看更多。

Every episode is a roller coaster of emotions, insights, and laughter that will leave you on the edge of your seat craving for more.

这不仅仅是一档节目。

It's not just a show.

这是一趟通往未来的旅程，而Dan Shipper就是这艘飞船的船长。

It's a journey into the future with Dan Shipper as the captain of the spaceship.

所以，别犹豫了。

So do yourself a favor.

点赞、疯狂订阅，系好安全带，准备迎接人生中最精彩的旅程吧。

Hit like, smash subscribe, and strap in for the ride of your life.

那么话不多说，我只想说，丹，我彻底地、无可救药地爱上你了。

And now without any further ado, let me just say, Dan, I'm absolutely, hopelessly in love with you.

真不错。

Fancy.

这样你就知道这是真货了。

That's how you know it's the real deal.

对。

Yeah.

太棒了。

Excellent.