本集简介
双语字幕
仅展示文本字幕，不包含中文音频；想边听边看，请使用 Bayt 播客 App。
欢迎来到 PracticalAI 播客，在这里我们拆解人工智能在现实世界中的应用，以及它如何塑造我们的生活、工作和创作方式。
Welcome to the PracticalAI podcast, where we break down the real world applications of artificial intelligence and how it's shaping the way we live, work, and create.
我们的目标是让 AI 技术变得实用、高效，并且人人都能用得上。
Our goal is to help make AI technology practical, productive, and accessible to everyone.
无论你是开发者、企业高管，还是单纯对热门科技背后的原理感兴趣，这里都是你的好去处。
Whether you're a developer, business leader, or just curious about the tech behind the buzz, you're in the right place.
记得在 LinkedIn、X 或 Blue Sky 上关注我们，第一时间获取节目更新、幕后花絮和 AI 见解。
Be sure to connect with us on LinkedIn, X, or Blue Sky to stay up to date with episode drops, behind the scenes content, and AI insights.
想了解更多内容，请访问 practicalai.fm。
You can learn more at practicalai.fm.
接下来进入正题。
Now onto the show.
嘿。
Hey.
欢迎收听 PracticalAI Podcast 的新一期节目。
Welcome to another episode of the PracticalAI Podcast.
我是Chris Benson，你的联合主持人。
I am Chris Benson, your cohost.
Daniel今天不在，他肯定会错过这期节目，因为我们要请一位播客的老朋友，Demetrios Brinkmann，他已经来过好几次了。
Daniel is out today, and he's really gonna miss this one because we have an old friend of the podcast who has been on multiple times, Demetrios Brinkmann, who is okay.
咱们先把头衔说对，Demetrios。
Let's get the title right here, Demetrios.
他是Agentic AI基金会中负责开发体验的负责人，也是非技术团队成员之一。
Head of development experience and a member of the nontechnical staff at the agentic AI Foundation.
顺便提一下，像很多以前上过我们节目的朋友一样，他也是 MLOps 社区的创始人。
And he's also, by the way, as most folks who have seen shows with us before, he's the founder of the MLOps Community.
天哪。
Oh my god.
德梅特里奥斯，我觉得这是我在这档节目里念过的最长的头衔了。
That's the longest title, Demetrios, I think I've ever had to do on the show.
我可给你出难题了。
I made it hard on you.
你确实让我印象深刻，跟你说吧，我刚读了一段。
You made it real I'll tell you what, I just read a paragraph.
很高兴你能再次回来。
So great to have you back.
我都记不清咱们一起做过多少次这档节目了。
I've lost count of how many times we've done this together.
对于刚加入、还不熟悉你的听众朋友们来说，除了身兼数职，你还是AI领域备受推崇的思想领袖。我相信今天我们会聊到很多精彩的内容，观众和听众们一定会像我爱听一样，觉得非常过瘾。
For those who are joining us that are not familiar with you, in addition to all these hats that you wear, amazing thought leader in the world of AI, I know we're gonna have some really good stuff to talk about today, and I know that viewers and the listeners will enjoy this as much as I do.
在开始之前，我得说一声，上次聊完之后，你寄给我一件特别酷的T恤。
And before we start, I have to say, so after the last time we talked, you had sent me It's a super cool t shirt.
这件是我在家闲逛时最爱穿的一件。
It's one of my favorite bum around the house t shirts.
我现在就穿着它。
I'm wearing it right now.
看YouTube直播的朋友们，上面写着：我幻觉比ChatGPT还多。
For those who are watching us on YouTube, it says, I hallucinate more than chat GPT.
所以我老婆早就看腻了我穿这件衣服了。
So my wife is completely sick of seeing me wear it.
现在颜色都褪成暗红色了。
It's faded red now.
抱歉啊，兄弟。
I'm sorry, man.
你刚送我的时候看着挺帅的，但现在因为褪色严重，看起来就不太行了。
Looked good when you gave it to me, but it doesn't look good anymore because it's all faded out.
但这件T恤穿起来确实挺有意思的。
But that's because it's a fun t shirt to wear.
下一件我发给你。
I'm send you the next one.
每次我穿上它，
Anytime I wear it
都得跟别人说说。
out, have to tell people.
每个人都会问我关于幻觉的事情。
Everyone asks me about the hallucination thing.
然后我还得说，因为我在真正的工作单位有同事，所以我没有产生幻觉。
Then I have to also say, and just because there are people at my real job, I'm not hallucinating.
顺便说一下，这里不需要做药物测试什么的。
Just so you know, there's no drug test required or anything.
这里完全没有幻觉。
No hallucinating here whatsoever.
所以，虽然开头这么有趣，但这可能不是大多数观众期待我们一开始就讲的内容，不过我们总是玩得很开心。
So with all the fun start, this is probably not the show most viewers were expecting that we'd start with, but we always have fun.
你最近怎么样？
How are you doing?
自从上次我们聊天以来，你的情况变化很大。
Things have really changed since the last time we talked for you.
跟我们说说你现在在哪里，在做什么，目前进展如何。
Tell us where you're at, what you're doing, what's going on with it at this point.
首先，我想说上次我们聊天的时候，我们想出了一些很火的东西，到现在还有人来找我要，比如“西兰花AI”。
Well, first of all, let me just say that the last time we chatted, we came up with some bangers that people are still hitting me up for, like Broccoli AI.
不知道你还记不记得。
Don't know if I you remember do.
我记得。
Going I do.
高德纳炒作周期。
Gartner hype cycle.
我们创造了自己的高德纳炒作周期。
And we created our own Gartner hype cycle.
其中一个就是“西兰花AI”。
And one of the things that was on there was Broccoli AI.
它几乎达到了炒作顶峰。
It was almost peak hype.
是的。
So Yeah.
对于那些没听过那期节目的人来说，这种AI你可能不喜欢，因为它味道不好，但你需要它，因为它对你的组织有好处。
And for those who didn't hear that episode, is that AI that you probably don't like because it tastes bad, but you need it because it's good for your organization.
没错。
That's right.
丹尼尔今天不在，但他也特别认同这个。
And Daniel's not here today, but he was also all about that.
我们生活中有一些东西，炒作往往会占据主导，但在我们的AI世界里，有些事你必须去做才能做好，其中一些并不是最酷、最好玩的，我们当时就是在聊这个，所以BroccoliAI就诞生了。
There are things in our world, the hype tends to take over, but there are things in our AI world that you just gotta do to do this stuff well, and some of it's not the coolest and most fun thing, and we were talking about that, is BroccoliAI was born.
所以，
So there
就是这样。
you go.
接下来我想说的是，我会给你一件新T恤，上面写着“非技术员工”。
The next thing I wanna say is I'm gonna get you the new shirt that says member of the nontechnical staff.
太好了。
Excellent.
你可以加入我的行列。
You can join me in my ranks.
太好了。
Excellent.
我，我确实需要被夸一夸。
I I gotta get my ego stroked right there.
你知道吗？
You know?
这很好。
That's good.
我很感激。
I appreciate that.
我觉得特别好笑，Anthropic 或 OpenAI 的每个人都是技术团队的成员。
I just find it hilarious that everyone at Anthropic or OpenAI, they're members of the technical staff.
所以我得反其道而行之，成为非技术团队的成员。
And so I had to go against the grain and be a member of the non technical staff.
原来是这样。
That's where that came from.
这点说得挺有道理的。
That's a pretty good point.
对。
Yeah.
我是说，跟我讲讲 MLOps Community 还有 Agentic AI Foundation，以及这里到底发生了什么事。
I mean, tell tell me about MLOps Community and and the agentic AI Foundation and what what happened here.
所以我特别兴奋，因为今年年初或者说是去年年底的时候，MCP被捐赠给了Linux基金会。
Well, so I'm super excited because in the beginning of the year or just at the end of last year, MCP got donated to the Linux Foundation.
围绕它成立了Agentic AI基金会。
They created the agentic AI Foundation around it.
从那以后，各大巨头都表现出了极大的兴趣，因为现在MCP已经从Anthropic的私有项目，变成了一个由中立治理机构主导的项目。对。
And out of that, there's just been, like, huge interest from all the top players because now MCP went from being something that was owned by Anthropic Yep.
变成了这样一个中立的治理机构在引导它的发展。
To being this neutral governing body that is steering it.
所以我当时坐在那里，心里想，哇，这真是个绝佳的机会。
And so I was sitting there, and I was like, man, that is an awesome opportunity.
我们在MLOps社区里已经围绕智能体做了很多事情。
We've been doing so much already in the MLOps Community around agents.
你知道，MLOps社区最初是专注于把机器学习应用到生产环境中。
You know, the MLOps Community started as putting machine learning into production.
后来大语言模型出现并风靡一时，我们开始更多地关注如何把大语言模型应用到生产环境中。
Then when LLMs came out and they were all the rage, we kind of started incorporating more of the putting LLMs into production.
接着智能体成为现实，并且成为我们日常使用的东西。
And then agents became a real thing, and they became something that we were using every day.
然后我们就想，好吧。
And then it was like, okay.
那智能体怎么应用到生产环境中呢？
Well, what about putting agents into production?
所以当我们看到这个时，就觉得这很自然。
And so it just kinda made sense when we were looking at, hey.
MLOps社区有没有一个家，可以让我们做更多的事情，拥有更多资源，把我们正在做的同样的事情，以及人们喜欢待在这个非常深入的技术社区里的同样的原因，继续做得更多、更好。
Is there a home for the MLOps Community to do more and have more resources around it and take the same types of stuff that we're doing and the same reasons that people enjoy being in, like, this very deep technical community and then just, like, do more and better.
所以这就是我们的提议。
And so that was the pitch.
幸运的是，agentic AI基金会的人同意了，所以我们算是合并了。
And, luckily, the folks at the agentic AI Foundation were on board, and so we we kinda merged.
我们现在要稍微重新品牌一下。
We're now going to be doing a bit of a rebrand.
MLOps社区正在变成agentic AI社区，或者叫agentic AI基金会社区。
The MLOps Community is becoming the agentic AI community or the agentic AI Foundation Community.
我们只是在做更多同样的事情。
And we're just doing more of the same.
比如，我们正在举办很多会议。
Like, we're doing a whole lot of conferences.
下周，我要去日本参加MCP开发者峰会，然后马上回阿姆斯特丹参加agent con。
Next week, I'm going to Japan for MCP Dev Summit, and then I'm right back in Amsterdam for agent con.
Agent Con 是我们欧洲的大型旗舰活动，时间是9月17日。
Agent con is like our big flagship event in Europe, and that is September 17.
然后我们在北美圣何塞还有一场 Agent Con，时间是10月22日，你会喜欢的。
And then we have another agent con in North America in San Jose on October 22, and you'll like this.
我为 Agent Con 做的一件事，非常符合我们在 MLOps 时期的精神，就是我组织了一场36小时的直播。
One thing I'm doing for agent con that is very much in the spirit of what we did in the MLOps days is I got a thirty six hour livestream put together.
所以我们有现场活动。
So we have the live event.
而且，你知道，我喜欢看科切拉音乐节或者那些制作非常精良的活动，它们既考虑了线上体验。
And what I, you know, I love watching Coachella or, like, these very highly produced events that are both they're taking the virtual aspect into consideration.
不仅仅是线下活动，完全为线下优化，但线上体验就没了。
It's not just like a in person and you fully optimize for in person, but then the virtual aspect isn't really there.
所以我决定做的是，如何让阿姆斯特丹的 Agent Con 完全为线下优化，但又不忽视线上体验？
So what I decided to do is how can we make the agent con in Amsterdam absolutely, like, optimized for in person, but not forgetting about the virtual aspect?
这就是为什么我们决定，你知道，直播36小时全程。
And that's why we decided to do, you know, thirty six hours livestreaming the whole thing.
我会主持这个活动，所以我们会时不时地出现一下。
I'm gonna be hosting it, so we'll be popping in and out.
会像ESPN那样，对演讲进行实况解说。
It's gonna be, like, ESPN style, play by play of the talks.
哦，那是什么意思？
Oh, what does that mean?
大家觉得怎么样？
What do we think?
我会在人群中找人聊天，还会在展馆里到处走走。
I'm gonna be grabbing people from the crowd, walking around the Expo Hall.
总的来说，这是我第一次全力以赴做这件事，所以可能会出一些问题，有些东西会出故障，但这就是我现在的状态。
All that is to say, it's the first time I'm going fully all in on it, so there's gonna be a few problems, things will break, but that's where I'm at right now.
听起来很有趣。
It sounds like a lot of fun.
所以你不会在那儿连续待36个小时不睡觉，对吧？
So I just you're not gonna stay up for thirty six hours there, right?
天哪，我可不想听你说你做不到那种事。
Mean, I would Please not tell me you're be not able gonna do that to yourself.
我本来想说，你就在那儿
I was gonna say, you'd just be
胡言乱语，把你那些小把戏都使出来。
babbling, You'd bring you tricks in there.
行行行，我明白了。
Okay, okay, okay, I gotcha.
对。
Yeah.
因为会有分论坛。
Because there's gonna be breakout sessions.
对吧？
Right?
同时大概有三四个分会场在进行。
There's really three or four tracks going on at once.
所以白天活动真正进行的时候，我们会直播主会场的内容。
And so we'll be live streaming the main track during the day when it's actually happening live.
但我们会录下所有分会场的内容，然后把这些内容一个接一个地叠加到主会场上面。
But then we're recording all of the breakout tracks, and then we're going to put those back to back on top of it.
不过还有一些很酷的东西，我现在不想完全透露，但我会录一些素材，可以穿插在不同的演讲之间。
But there's some other cool things that I don't wanna fully give away yet, but I'm be recording some stuff that we can splice in in between different talks.
我们还让一些赞助商提供了一些很酷的素材，也可以穿插进去。
And we're we've also got some of the sponsors to, like, give us some cool material that we can also splice in.
所以这会是一场盛事。
So it's gonna be an event.
那是肯定的。
That's for sure.
它可能会完全搞砸，但如果真的搞砸了，我也会坚持到底。
It may totally fall flat on its face, but I'm gonna go down with the ship if it does.
好的。
Okay.
有道理。
Fair enough.
我只是很高兴你有一些东西可以混进去，这样，比如，我在想象你刚结束三十六小时马拉松后接受采访，你就趴在桌子上，你知道的，完全没法动弹。
I'm just glad you have something there to mix in with it so that like, I'm I'm imagining interviewing you right after a thirty six hour marathon, and you're just, laying your head on the desk, you know, unable to function.
所以挺好的。
So it's good.
我很高兴我们把那些内容加进去了，过程中还能睡一会儿。
I'm glad we got the stuff in there, get a little sleep in the process.
我也很期待到时候看直播。
Looking forward to watching the live feed myself as we get there.
听我说。
Listen.
我参加过很多很多AI活动，很多都不错，但很多都不太实用。
I've been to an incredible amount of AI events, many of which are good, but many of which are not practical.
你知道我喜欢实用性的东西。
You know I love practicality.
我们是在 PracticalAI 节目里，有些活动纯粹是为了炒作。
We're on PracticalAI, and some are just hype focused.
有些则是为了推销产品。
Some are sales focused.
所以我总是很乐意分享那些我真心觉得实用、对人有用的活动。
That's why I'm always eager to share about an event that I truly think is practical and useful for people.
去年在中部地区 AI 峰会上我就发现了这一点，今年他们还会在印第安纳波利斯举办另一场中部地区 AI 峰会，时间是 2026 年 10 月 15 号。
That's what I discovered last year at the Midwest AI Summit, and they're gonna have another Midwest AI Summit October 15 in Indianapolis this year, 2026.
我喜欢这个活动的一个原因是，那里有个AI工程休息室，你可以坐下来和真正有经验的AI工程师及从业者一起讨论你的应用场景，进行头脑风暴，活动结束后能带回切实可行的解决方案，而不是只带着一堆内容和幻灯片。
One of the reasons why I love this event was there was an AI engineering lounge where you could sit down and talk through your use cases with actual experienced AI engineers and practitioners to really brainstorm and come back from the event with actual solutions and practicality rather than just a bunch of content and slides.
当然，也有非常精彩的主题演讲嘉宾，有些甚至之前上过我们的播客，比如Rajeev Shah就参加了去年的活动。
But there were also amazing keynote speakers, speakers from, even that had been on the podcast before, like Rajeev Shah, was at last year's event.
我真心推荐你去midwestaisummit.com看看。
I would really recommend that you go to midwestaisummit.com.
另外，对于我们的听众，你们可以用代码PracticalAI20享受八折优惠。
And, for our listeners, you can actually get 20% off with the code PracticalAI20.
所以去 midwestaisummit.com 看看吧。
So go to midwestaisummit.com.
别错过参加这个活动的机会，使用代码 PracticalAI20 还能享受八折优惠。
Don't miss your chance to attend this event and get 20% off with the code PracticalAI20.
好的，你手头有不少有趣的活动，听起来很有意思。
Okay, so lot of cool events that you're working on, and it sounds like a lot of fun.
期待看到这些活动顺利开展，但我知道你不只是做活动，那你还在忙些什么呢？
Looking forward to seeing how all that goes, but you're not just doing events, I know that, so what else you got going on there?
是的，我觉得最让我惊喜的是社区的热情响应，大家对智能体AI基金会的成员公司非常感兴趣。
Well, yeah, I think that's been some of the biggest surprises for me is how the community has rallied, and there's so much interest, not only from the member companies of the agentic AI Foundation.
现在已经有超过250家公司了，想想有多少公司，真是不可思议。
Now there's over 250, which is wild to think about how many companies.
对。
Yeah.
他们都想成为会员，想参与这场运动。
They wanna be members, and they wanna be a part of this movement.
对吧？
Right?
然后我们在全球各地都有大使。
And then we've got ambassadors around the globe.
我们开放了大使项目，结果有超过一千人申请想当大使。
So we opened up the ambassador program, and there was over a thousand applications of people that wanted to be an ambassador.
我们还设立了本地社区活动分会，任何人都可以组织社区活动，现在我们已经覆盖了80多个城市，大约有250个不同的社区分会负责人。
And we also set up these local chapters of community events, so anybody can organize a community event, and now we're in over 80 cities, and there's, like, 250 different community chapter leads.
所有这些都说明，这个项目已经发展成自己的规模了。
And all of that is just to say, like, it's kinda taken on its own thing.
是的，没错。
It's Yeah.
规模很大。
Huge.
非常庞大的事情。
Gigantic thing.
对。
Yeah.
挺快的，我是说，你才聊了几个月而已。
Like, pretty quick, I mean, considering you're only talking a few months.
是的。
Yeah.
所以啊，Linux基金会估计会想：好吧，我们把他招进来了，但天哪，这小家伙长得真快。
It's, so it's The Linux Foundation's gonna be like, Well, we took him on, but oh my gosh, the baby's growing up pretty quick here.
你
You
知道的。
know.
这个不能百分百确定，但我觉得它甚至是Lytics基金会里最大的几个基金会之一。
Is one of the Don't quote me on it, but I think it's one of the biggest foundations in the Lytics Foundation even.
我一点都不觉得意外。
I would not be surprised.
已经超过一年了。
It's longer than a year.
是啊，想想看，发生了这么多事情。
Yeah, mean, when you think about just like, so much has happened.
自从我们上次聊过之后，发生了太多事情。
Just since we talked last, so much has happened.
这个世界，智能体的崛起，上次我们聊的时候智能体已经存在了，但那时还完全处于起步阶段。
This world, the rise of agentics, agentics were around last time we talked, but they were still in absolute infancy.
而现在，它已经主导了一切，并且还在不断壮大。
And at this point, it is dominating everything going forward and just growing.
听起来很夸张，我为此道歉，但事实就是，这个怪物变得越来越大。
That sounds very hype y, and I apologize for that, but it's just, the monster gets bigger and bigger.
我跟你说，因为我可能是对智能体这个炒作名称最持怀疑态度的人，但现在看来，确实如此。
Me tell you, because I was the one who was probably the biggest naysayer on the hype naming and agents, and it's like, yeah.
对。
Yeah.
我记得以前用那个，叫什么来着，像早期的Baby AGI，结果气得不行，因为它只会让我陷入死循环，然后我收到了OpenAI八十美元的API账单。
I remember using, what was it, like, baby AGI back in the day and just getting mad because all it did was give me so it got stuck in a recursive loop, and I got, like, a $80 API bill from OpenAI.
我当时就想，这些智能体根本不行，兄弟。
And it was like, these agents don't work, dude.
这到底怎么回事？
What's going on?
对。
Yeah.
但后来，你说得对，兄弟。
But since then, you're right, man.
我现在完全相信了，而且我是第一个承认自己当初大错特错的人。
Like, I'm fully bought in now, and I am the first one to say that I was way wrong.
它们确实来了，而且来势汹汹，我想跟你聊聊我最近在搞的新东西，特别是关于计算机操作方面的。
Like, they were coming, and they came hard, and I wanna tell you about the newest stuff that I've been doing, specifically with, like, computer use.
好。
Yeah.
来吧。
Go for it.
因为那个人，我觉得我的生活都变了。
Because that man, I feel like my life has changed.
而且有件事我得说，就是OpenAI最新发布的那个模型，什么时候出的来着？
And there's something that happened, I will say, in the latest OpenAI model release, which came out what?
现在已经是5.6了。
It's 5.6 is what we're at right now.
所以就像五……但是……
So it's like five But
对。
Yeah.
而且自从那个出来以后，你要是专门用那个电脑操作技能，真的特别好用。
And so since that came out, if you specifically use the computer use skill, it is so good.
我几乎找不到什么它搞不定的事，这太不可思议了，因为，你知道……
There are very few things that I can throw at it that it does not accomplish, which is wild because okay.
所以现在我再也不用担心为任何东西获取API了。
So now I'd never have to worry about getting APIs for anything.
我也不用担心，哦，我因为某些限制或者哪里出了问题而无法访问那些数据。
I don't have to worry about, oh, but I can't reach that data because of some block or something that's wrong with it.
当然，这对我来说是个人使用的情况。
And granted, this is me as a personal use type thing.
就是说，我能做到这一点。
Like, I'm I'm able to do that.
我登录了三四个不同的Gmail账号，所以计算机使用功能可以查看所有这些账号，我知道其中有一个，我记不清是Hermes还是GrockBot。
I have my three or four different Gmails logged in, and so computer use can go and look at all three or four of them, which I know that with one I can't remember if it's Hermes or GrockBot.
你也可以设置多个账户。
You can also set up multiple accounts.
但是
But
只是要
just to be
能够，比如说，用它，扔给它，就像，嘿。
able to, like, use that, throw at it, like, hey.
检查我所有的邮件，给我每日简报，也检查 Slack，给我每日简报。
Check all of my emails and give me the daily briefing, and also check Slack and give me a daily briefing.
而且不只是我所在的其中一个 Slack 工作区，而是全部五个。
And not just one of the Slack workspaces that I'm in, like, all five of them.
对。
Yeah.
对吧？
Right?
所以你不必担心，不必摆弄任何连接或什么的。
And so you don't have to worry you don't have to fiddle with any connections or anything.
你直接去就行，它会用电脑操作，这很棒。
You can just go and it'll use computer use, and that is great.
这就像是生活质量提升的东西。
That's like quality of life thing.
但让我觉得特别神奇的是，现在我可以设置这些工作流或者触发器，大概就是你们说的那种，就是，嘿。
But what was wild to me is now I can set up these workflows or triggers, I guess is what you call them, that, hey.
当你看到某个东西的时候，就自动去做这件事。
When you see something, then just do this automatically.
比如说，其中一个例子就是，你也知道，我们在世界各地开了这么多会议，我也坐了很多次飞机。
So for example, one of these things is, as you know, we've had all these conferences all over the world, and I've been taking a lot of flights.
那我会用电脑操作来买机票。
Well, I will buy the flight with computer use.
我只需要说，帮我找一下从这天到这天最好的航班。
I just say, find me the best flight on this day to this day.
然后在它真正付款之前，我会亲自去点那个按钮，因为当然。
And then before it actually pays, I'm the one who actually will click the button because Sure.
我们还没到那一步。
We're still not at that point.
但是，或者说，我需要银行账户里再多几个零，我才放心让它到那一步。
But Or I need a few more zeros in my bank account before I'm cool with it being at that point.
我也是。
I'm the same.
我懂。
I get it.
你说这个挺有意思的，因为我也在用智能体处理各种事务，不过我的关注点稍微有点不同，主要是在多智能体协作的场景下，让多个智能体同时处理非常复杂的问题。
It's funny when you say that because I'm having agents do all the things, and my focus has been on a little bit different use case in swarms of agents, where you have many agents addressing really complex things at once.
但话说回来也挺逗的，就像你刚才说的，如果是动我自己的私人银行账户——那里面的钱远没我希望的那么多——那我也会跟你一样谨慎。
But then, it's funny, like, if I'm doing something like you and it's my personal bank account, which doesn't have anywhere near as many zeros as I wish it did, I'm the same way.
我觉得吧，哪怕只是买个小东西，我也得心里有个底。
I'm like, that very what would really have quite a small purchase, but I'm like, okay.
所以我也有同样的顾虑。
So I have that same reservation.
虽然他们现在做得很厉害，能让智能体去干不少事，但那种本能的信任感还是存在的。
Like, they're doing amazing things, you know, what you can get agents to go do, and yet there's still that that intrinsic trust factor.
连我们这种专业人士都得面对这个问题，那普通大众肯定更得处理好这层关系了。看着技术以超出所有人预期的速度冲进这个领域，真的挺有意思的。
And if you and I are having that with the of the fact that this is what we do, then I know we have to deal with that with general population as So they come it's interesting to see the technology running into this amazing space that is beyond really where anybody was predicting this fast.
然后同时，我是不是也想让它帮我买电影票？
And then simultaneously, Do I want it to buy the movie tickets for me?
好吧。
Okay.
那也不算太贵。
That's not too expensive.
我就直接让它去做就行了。
I'll just tell to do it.
你懂吧？
You know?
完全同意。
Totally.
你知道吗？
You know what?
不过，我听我朋友说过，他们会设定一些规则，比如如果金额低于20美元，代理就可以直接处理。
Though, I've seen and I've heard of my friends saying, like, they'll set up rules where if it's under $20, the agent can just I've
我也这么做过。
done that.
我还是有点担心，因为我想，它完全可以花20美元买20次东西，然后我就生气了。
I'm still afraid of that because I'm like, yeah, it can just buy something for $20 20 times, and then I'm pissed.
好。
Good.
好。
Good.
因为大家都听过那些故事，所以我还没完全放心，但我想提一下我围绕它设置的不同工作流程。
Because it can figure out we've all heard those stories, so I'm not quite there yet, but I wanted to mention the the different workflows that I have set up around it.
比如，这个工作流程就是：买票，拿到票，搞定。
So for example, this workflow of buy my ticket, get the ticket, cool.
我再也不用填任何表格了，这真的太棒了。在网上，你知道要填多少没用的表格吗？就是填你的名字、电话号码之类的，还有护照号码，我从来记不住，所以还得去找，找到那个号码，然后，搞定。
I don't have to fill out any forms anymore, which is absolutely Like, on the Internet, you know how many pointless forms you have to fill out, which are just your name and your phone number and whatever, like, oh, passport number, and I never have it memorized, so then I have to go and search for it and find that number, and boom, I got it.
现在我不需要这么做了，因为我的所有信息都存到一个文档里，代理可以随时查看。
Well, now I don't have to do that because I have my all my information stored in a document that the agent can reference.
对。
Yeah.
然后它会买机票，到了该值机的时候，我就告诉一个代理，嘿，盯着我的邮箱，如果你看到邮件说该值机了，就直接去值机。
And then it'll buy the flight, and when it comes time to check-in, I just told an agent, hey, monitor my inbox, and if you ever see a email come through that says it's time for you to check-in, just go check-in.
你甚至都不用问我。
You don't even have to ask me.
直接去做就行。
Just go and do it.
值机。
Check-in.
把登机牌发到我手机上。
Send me the boarding pass to my phone.
所以现在，我再也不用操心这些事了，顺便说一句，我特别纳闷，值机这事儿，为什么现在还得做？
And so now, I don't ever have to work at any of that, which total side note, I'm pretty sure, like, checking in why do we have to do that still?
得有人解释一下，为什么值机还是个
Somebody needs to explain why checking I'm in is still a
不太确定。
not sure.
我也不知道。
I don't know.
我花那么多钱买机票。
I spend so much money on a flight.
谁会就这么错过航班，我真搞不懂。
Who's gonna just miss I don't know.
那是我的情况，而且我相信有很多人即使办理了登机手续，还是会错过航班。
That's for me, and I'm sure there's plenty of people that will check-in, and they still miss their flight.
所以这并不能很好地判断谁真的会来坐飞机。
So it's not like it's a good gauge of who's actually gonna show up for the flight.
这完全是个跟智能体和AI无关的题外话。
So that's a total non agent, non AI tangent
我猜那些错过航班的人，他们其实已经办理了登机手续。
I suspect the people missing the flight, like they've checked in.
我只是觉得这两者之间没有很强的关联。
I just don't think there's a strong correlation between the two.
这对我来说完全说不通。
It doesn't make any sense to me.
我敢肯定有
I'm sure there
某个航空公司的员工正在听，心想：‘这两人完全不懂行啊。’
is somebody at one of these airlines out there listening right now going, Oh, these guys totally don't get it.
他们不明白。
They don't understand.
他们不知道原因是什么。
They don't understand why.
我们这么做是有非常明确的原因的，我们也向这位乘客说明白了。
There's a very clear reason we do this, and we acknowledge that for that person, just to let you know.
只是我们确实搞不懂他们的逻辑。
We just don't understand our we don't get it.
好，没问题。回到电脑操作的话题。
So, okay, fair Back to computer use.
对。
Yeah.
所以我也有类似的情况。
So I have something like that going.
另外，我今天早上还遇到一个特别典型的例子：我需要把西班牙的驾照换成德国的。
I also have a a great use case that I had this morning was I need to update my Spanish driver's license to a German driver's license.
所以在用电脑之前，我会截图，然后发给我的客服代表，或者直接发到聊天窗口里。
And so I before computer use was going and taking screenshots and then giving it to my agent and saying or giving it just to the chat, really.
其实那会儿还没有专门的客服代表。
It wasn't even an agent.
我就问：这上面写的啥意思？
And saying, what does this say?
我该点哪个按钮？
What should I click on?
我该把信息填在哪里？
Where should I put my information?
因为这是个很典型的例子，我们镇上德国政府网站没有开放API，我的编程助手没法直接调用接口提交数据。
Because this is a perfect example of the German government in my small town does not have an API that my coding agent can access and submit something through.
对吧？
Right?
但它至少有个网页，我可以自己上去提交，或者让电脑自动操作去提交。
But what it does have is a web page where I can go and submit something, or I can have computer use go and submit something.
现在用了这个工具之后，一切都自动搞定了。
So now it just did it.
它帮我预约好了时间，还自动生成了日历邀请，我不会错过预约时间，它还列好了我需要带的所有材料，把我的取消预约码、主编号这些乱七八糟的信息全都整理清楚了。
It created my appointment, and then it created a calendar invite for me so I know when the appointment is, and it said everything I needed to bring, and it said my cancellation number, it said my, like, main number, blah blah blah.
这些工作全都自动处理好了，我完全不用操心。
That's all there, and I didn't have to worry about it at all.
我前后改了三次时间，只需要跟它说改到另一天就行，因为原来那天我没法去办了。
And I changed that, like three different times, and all I have to do is say, like, change it to a different day because I can't do it on this day anymore.
是的。
Yeah.
所以我挺好奇的，你刚才也稍微提了一下你的使用体验，你觉得大家有哪些特别值得关注的地方？
So I'm curious, like, what do you think are some really You've talked a little bit about how you're using it.
对于正在听我们节目的朋友来说，你觉得有哪些特别好的应用场景？
What do you think are some really good opportunities for folks watching or listening out there?
听完你分享的这些内容，你有什么建议大家可以去尝试一下的吗？
As they're listening and they've heard some of the things that you're talking about, what would you suggest to go try out?
有哪些水果可能是大家还没摘过的？
What are some of the fruits that maybe people haven't picked from yet?
然后你就会觉得，哇，太棒了。
And you're just like, oh, man, this is amazing.
你知道的，除了机票之外。
You know, just like other than flights.
我觉得对我来说，最大的启发是，现在只要我在网上遇到论坛，我都会认真对待。
I think for me, the biggest eye opener of getting it right was now anytime I encounter a forum, when I'm using the Internet.
对吧？
Right?
我每天上网的时候，一碰到表单，脑子里就会有个大大的提示，我就想，为什么我没让电脑自动完成这个任务呢？
And I'm going through my day to day, and I'm using the Internet, and I encounter a form, and it has this big trigger that goes off in my head, and I'm like, why didn't I ask computer use to do this whole task?
因为我已经到了这个地步，意识到，哦，表单，我再也不用自己填了。
Because I just got to this point where I realized, oh, forms, I don't have to fill out anymore.
这种事情完全可以让电脑来做。
That's something that is good enough to be done by computer use.
所以我就直接，我现在就会想，哦，对。
So I just go and I I now am like, oh, right.
看看他们能不能搞定。
Let's see if let's see if they can do that.
搞定。
Boom.
所以这就是一个例子。
So that would be one.
只要你在网上遇到任何表单。
Anytime you encounter a form on the Internet.
不过，我得补充一下，昨天我和朋友Sam聊过，他说如果是B2C的场景，这确实是个很实用的做法。
However, I will caveat this with a conversation that I just had yesterday with my friend, Sam, who was saying, like, this is such a thing that you can do if you're b to c.
但如果你是想在B2B场景下这么做，兄弟，祝你好运吧。
But if you're trying to do this in B to B, like, good luck, dude.
你总得去跟你的员工解释
You're gonna go tell your employees that
对，这正是我接下来想问你的。
you That's can exactly really what I was gonna ask you next.
我当时脑子里就在想，哦，我知道该往哪走了，就这点事。
I literally, like, was in my head, I'm like, oh, I know where I wanna go, and that's it.
再说说B2B场景下那种必然趋势，也就是智能体对智能体的交互模式。这时候你的智能体会和其他实体的智能体打交道，比如别的商业机构之类的。不再是以前那种静态API，让你的智能体去对接，或者用爬虫、填表单这些方式。你觉得大家什么时候才能普遍拥有这种智能体接口？这样你们的智能体就能像你说的那样，直接互通，变得更灵活、更有动态能力，因为这是智能体之间的互动，能容纳更多东西。
And that is with the inevitability of the B2B use case, being an agentic to agentic use case, where you're doing agents interoperating with agents beyond your borker, in other words, some other entity, another commercial entity or whatever it is that you're talking about, and instead of being static APIs that your agent is going and talking to, or you're web scraping with the agent and doing the of the form stuff that we're talking about, what are your thoughts around when is every organization out there going to have an agentic interface in which your agents, as you're doing what you're describing, are just interoperating, giving it a lot more fluidity and dynamic capability because you're doing an agent to agent interaction, which can accommodate things.
这不再只是你的智能体需要去应付的那些静态API了。
It's no longer just the static API that your agent has to navigate.
你怎么看这件事？你觉得距离我们真正迎来那个阶段还有多久？
What are your thoughts around that, and what, like, how far out do you think it is before we get to that?
我觉得这正是 MCP 这么流行的原因之一，因为这些用例正好契合。感觉行业已经把它标准化为让智能体访问不同系统的方式了。
Well, I think that's one reason that MCP is so popular is because of those use cases, and it feels like that's the way that the industry has standardized on being able to give agents access to different systems.
对吧？
Right?
但接下来我们要做的就是等大家都部署好足够成熟的 MCP 服务器，让我的智能体能随时拿来就用、用得顺手，这样我才能把事情办成。在我看来，在那之前还需要一段时间来完善和成熟。
But then what we have to do is we have to wait for everyone to have MCP servers that are good enough for my agent just to pick up and use at will and use well so that I can get what I need done, which feels like there still needs to be some maturing that needs to happen before we get to that point.
所以这就是计算机操作厉害的地方，因为你不用等对方去搭建 MCP 服务器，也不用自己去建一个来启用它。
And so that's why it's beautiful with computer use because you don't have to wait for the other person to set up an MCP server, or you don't have to go and build an MCP server to enable that.
而且有很多这类用例，谁也不知道他们到底会不会去建个 MCP 服务器。
And there's a lot of these use cases that who knows if they even are gonna build an MCP server.
比如德国政府的车管所，我不确定他们的代理能不能找到个 MCP 服务器去对话。
Like, the German government DMV, I'm not sure they ever are gonna have an MCP server that my agent can go and talk to.
对吧？
Right?
所以这某种程度上又回到了那个面向消费者的应用场景。
So that's going back to this b to c use case in a way.
但你想啊，让我觉得特别震撼的是，我们作为消费者，尝到了这种禁果的滋味，哇，事情真的可以这么简单吗？
But if you think about it, what what's incredible for me is us consumers are tasting this, like, forbidden fruit of, wow, things can really be that easy?
就是，它真的能直接搞定？
Like, it can just work?
对。
Mhmm.
然后你就知道，这种压力会开始施加到我们日常工作中使用的那些软件上。
And then you know that that pressure is going to start building on the software that we have and we're using in our day to day lives at the office.
我就是这么感觉的。
Like, that's how I feel.
我觉得这一天快来了。
I feel like it's coming.
这真的会给那些软件带来很大的压力，嘿。
It's just gonna put a lot of pressure on, hey.
事情其实不必如此，我们也没必要被某些东西卡住。
This is this doesn't have to be like this, or we don't have to be blocked by something.
咱们能不能想办法让它跑通？说实话，我不太确定最后会怎样，因为如果随便让人用电脑自动化操作，那安全问题简直就是一场噩梦。
Can we figure out a way to make it work with I mean, I don't know how it's gonna play out because I will say that there's a security nightmare happening if you just start doing, like, computer use.
想象一下，你们公司每个人都在同时处理五封邮件，还要对接所有的ERP系统，那场面真是让人头大。
Everyone at your company now has computer use going on all five of their emails and all of your ERP systems or you're like like on the oh, man.
基本上，你能想到的任何场景都是这样。
Basically, any anything that you can think of.
天哪。
God.
听起来挺危险的，不过真让人惊叹。
That sounds so dangerous, but wow.
这确实能极大地提升生活质量。
It is, like, quality of life there.
你提到了安全问题，我觉得你正处于核心位置。随着更完善的安全架构不断被开发出来，它们最终会融入到底层基础中，从而在全球范围内获得广泛认可。
I think, you you talk about the security issue, and I think you're at the place, at the center of, at the foundation, where as good security architectures are further developed, they will find their way into the foundation probably for purposes of getting widespread acceptance through the world.
展开剩余字幕（还有 315 条）
我觉得还有个点，你刚才说的时候，我这边思路岔开了。
I think there's another point I'm gonna diverge hard as you were doing that.
听你聊这个，我觉得你描述的情况特别像咱们和正在看直播的观众的故事，因为这些都是AI原生用户。
As you're talking about that, I think that what you were describing there is very much the story starting with us and the people watching this, because these are AI native folks.
来听你们播客、来听这档节目的人，都是在这个行业里工作、对它很上心并且持续关注的人。
The folks that are showing up for your podcast and showing up for this podcast are folks that they work in it, they care enough about it, and they're following that.
我挺好奇的，到底需要多久才能普及开来？我们现在都觉得自己厉害坏了，看看我现在能干嘛。但问题是，怎么才能让普通大众也开始习惯用那些看起来挺传统的聊天工具呢？不管是Gemini、ChatGPT还是Claude之类的，大家现在才慢慢开始接受这些。
I'm curious, what's it gonna take to bring because we're all kind of going, Holy cow, look at what I can do now, which is kind of what What you're does it take to bring We're only now getting to where the general population is starting to get comfortable using just kind of what seems very old fashioned chat, whether it's Gemini or ChatGPT or Quad or whatever, they're just coming along there.
要把这些引入进来需要付出什么代价？
What does it take to bring that in?
不仅仅是为了让他们能操作这个，还要考虑到大家现在对就业以及全球各种大事的担忧。你打算怎么让那些不具备AI原生背景的大众也能用上这项技术，从而享受到它的好处呢？
Not only for just so they can do this, but as they're worrying about jobs and all the bigger things everyone is so concerned about in the world, how that all How do you bring the masses that are not AI native into being able to do this to get the benefits?
因为说实话，他们现在都怕得要命，你懂的吧？
Because right now, they're just all scared to death, you know?
确实如此。
Yeah.
越来越多人能体会到这一点。
Get that more and more.
我记得以前谷歌刚出来的时候，或者说搜索引擎、互联网刚出现的时候，大家觉得特别神奇，因为你可以去一个网站，或者搜索点什么，就能在网上找到信息。
I remember back in the day when Google came out, or when the search engines came out, the Internet came out, and it was magical that you could go to a website, or you could search something and find information on the Internet.
对。
Yeah.
当时有很多人是早期采用者，他们很早就开始使用这些工具了。
And we were there was a lot of people that were just early adopters, and they were very early on that and using it.
现在的感觉有点像那样，我老婆对科技产品不太在行。
It feels a little bit like that now in that so my wife is not very technologically savvy.
她平时能躲开手机和电脑就尽量躲，但今天她不得不注销PayPal账户，然后重新注册一个新的。
She avoids phones and computers at all costs, but today she had to cancel her PayPal account and then start a new one.
我跟她说，好吧。
And I told her, okay.
你看着。
Watch this.
然后我在她电脑上装了 ChatGPT，帮她弄好了。
And I downloaded ChatGPT on her computer, and then I got her set up.
我还给她配了 WhisperFlow，这样她可以直接跟电脑对话。
I also got her set up with WhisperFlow so you can just talk to the computer.
我递给她之后说，嘿。
And I I gave it to I said, hey.
你看。
Look.
我得注销我的 PayPal 账户，然后重新开一个。
I need to get rid of my PayPal account, and I need to start a new one.
咱们先从删掉这个 PayPal 账户开始，把跟它相关的所有东西都取消掉。
Let's start with just, like, deleting this PayPal account and, like, canceling everything that's related to it.
他这么一弄，我老婆眼睛都亮了，因为对她来说，这省下了她本来得花的大量时间，尤其是确实如此。
And it did that, and my wife's eyes lit up because for her, that is so much time that she would have had to have spent, especially yeah.
因为她不太懂这些，所以这事儿简直太不可思议了。
Because she's not It's incredible.
所以当你把这些体验展示给别人时，他们立刻就信服了。
So you have those experiences for someone, and they're it's instantly bought in.
就像是在说，哦，原来是这样。
It's like, oh, okay.
然后他们会问，我还能在这里做些什么呢？
So tell me what else can I do here?
或者让我来试试。
Or let me try.
然后那个人就试着去操作，其实能做的东西没那么多，我就是这个意思。
And then the person just tries, and there's not a lot that's what I'm saying.
像我现在扔给它的任务，基本上它都能搞定。
Like, there's not a lot that I throw at it these days that it can't do.
我还是经常回到个人电脑使用的那些场景，这部分体验确实很棒。
And I keep going back to, like, my personal computer use stuff, which is great.
不过说到企业级应用，这才是真正考验我们工作方式的时刻。如果我们的工作流程依然繁琐，或者必须得懂很多技术细节才能用上AI带来的便利，那说明我们用错了方法。
Going to the b to b stuff, though, this is where I really feel like you're putting pressure on what we do at work because if what we do at work still feels cumbersome or we have to be really technical in order to get the advances that AI brings, then we're doing it wrong.
真的感觉事情不该是这个样子。
It really feels like that's not how it should be.
那我们要怎么做才能支持这种用法呢？
And so how can we enable that type of thing?
但考虑到企业级的那些功能，这些组织多年来已经非常依赖并且很喜欢它们了，对吧。
But with all of the enterprise y features you that you the organizations have come to grow and they've loved over these years, you know, just like Mhmm.
比如基于角色的访问控制就是一个例子。
Role based access control is one.
所以我想，如果你在使用电脑操作功能的话，你的角色权限应该已经设置好了，那这方面就不会有问题。
And so I guess if you're using computer use, you've already got your roles set out, and so you're not gonna have problems with that.
但我也很清醒，不会天真地以为它就是万能的神器，特别是在企业环境里。
But there's a lot of I I will not be naive and say that it's the end all to be all, especially inside of the enterprise.
它可能会引发不少麻烦。
It could cause a lot of problems.
不过说实话，对我来说最棒的地方在于它能很好地满足我的个人使用需求，我再给你举一个例子。
However, man, the thing that is great for me is using it on my personal use cases, and I'll give you another one.
我大概有20个这样的例子，因为就像你问的，我觉得听到这些能激发大家的创造力。
I've got, like, 20 of them that I've been doing because as you asked, and I think it's good to, like, stimulate folks' creativity when they hear it.
我有个36小时的直播要来了，我想联系所有在LinkedIn上跟我有过真正双向对话的人，就是来回聊了好几轮的那种。
I have this 36 livestream coming up, and I want to reach out to everyone that I've had a conversation with on LinkedIn that's been, like, an actual two way conversation, and it's been a few turns back and forth.
对吧？
Right?
所以，可以算是熟人，你可以加个括号。
So acquaintances, you could put in parentheses.
然后我做的就是用computer use，我说，去翻一下我所有的LinkedIn。
And so what I did is I told computer use, I said, go and look through all my LinkedIn.
因为LinkedIn有个API，你根本没法用，它出了名的难搞。
Because LinkedIn has this API that you cannot it's notoriously hard.
就是说，你从LinkedIn的API拿不到东西。
Like, you can't get stuff from LinkedIn's API.
它不像X那样，你付钱就能拿到所有数据。
It's not like x where you can pay and then you get everything.
它完全锁死了。
It's fully locked down.
所以我当时就坐在那儿想，干脆把我所有的私信都分析一遍，看看跟谁有过互动，然后列个短名单，联系这些人，告诉他们我要办这个直播活动。
So I was sitting there and I was like, I wanna analyze all of my DMs and see who I've interacted with a bit, and then we make this short list of people that I can reach out to and let them know that I'm having this livestream event.
结果它没只是单纯地过一遍我的私信，而是跟我说，哎，你知道吗？
And what it did was instead of just going through all of my DMs, it was like, oh, well, you know what?
我刚刚发现有个功能可以下载你的全部数据。
I just found this ability to download all your data.
所以它下载了我所有的数据，但LinkedIn得先把这些数据打包好，然后在48小时内发到我的邮箱里。
So it downloaded all of my data, but LinkedIn has to package it up and then send it to your email over forty eight hour span.
于是它给自己设了个提醒，一直盯着我的邮箱看。等收到数据后，它就对内容进行了分析。
So what it did is it set a reminder for itself to just kept checking my email, and so then once it got my data, then it analyzed everything.
它筛选出了一个500人的短名单，然后为我生成了个性化的消息，让我可以发给他们，告知他们关于那个36小时直播的事。
It created this short list of 500 people, and then it created personalized messages that I could send them to let them know about the thirty six hour livestream.
不过我还更进一步，毕竟有AI在手，为什么不试试呢。
But then I went one step further, and I because AI and why not.
对吧？
Right?
我说，那就给每个人生成一份个性化的媒体资料包，以防他们有需要。对。
I said, well, create a personalized media kit for each person in case they need some Yeah.
差不多就是这样。所以每个人都有专属的个人主页，上面写着类似这样的话：嘿，Chris，你太棒了，居然做了这件事！这里有一些灵感素材，方便你发布内容时使用。
Kind of And so every single person has their own website that says like, hey, Chris, you're awesome for doing this, and here's some inspiration in case you wanna post this.
你可以直接复制粘贴，或者如果你打算自己写，这里也提供了一些写作提示。
You can just copy paste, or here's some prompts if you wanna write it yourself.
顺便说一句，这里有一些我的搞笑照片，如果你想加的话可以加上，但我真的很希望你能帮忙宣传一下这场直播活动。
And by the way, here's some funny photos of me if you wanna add those, but I would love it if you share about this livestream event.
现在这些消息都在发送出去了。你可能会觉得这太荒谬了，因为我虽然去掉了所有个性化元素，但还是尽量让它看起来尽可能个性化，或者也许这样也挺酷的。
And so now those are firing off, And you may say that is absolutely ridiculous because I took all of the personalization out of it and tried to make it as personalized as possible still, or maybe it's cool.
我也不确定。
I don't know.
不过这也是我在过去二十四小时里一直在做的事情。
But that's another thing that I've been doing over the past twenty four hours.
太酷了，兄弟。
Very cool, man.
我之前也遇到过类似的情况。
Is I've had some similar things.
今天没时间详细展开，但我非常欣赏你提供的这些灵感，也希望正在观看或收听的观众朋友们能从中获得启发，想想自己能做些什么。
Don't have time to cover it all today, but I love the inspiration that you're offering, and I'm hoping that folks watching or listening are kind of thinking of the things that they can go do and stuff.
我想确保提到的一点是，我知道你对背带（harnesses）很感兴趣，包括它目前的状况以及面临的一些挑战。
One of the things I want to make sure that we get in is I know you have an interest in harnesses and the current state and some of the challenges around that.
我想确保今天能把这个安排上。
I wanted to make sure we fit that in today.
我把话题抛给你，你来接着聊，因为我知道你对此有些想法。
I'll toss the ball to you and let you run with that, because I know you have some thinking around it.
让我继续说下去。
Let me keep blabbing.
对。
Yeah.
这期节目虽然没人点名要，但我们还是把它做出来了。
This is the episode nobody asked for, but we're getting somehow.
就是图个开心嘛，兄弟。
Just having a good time, man.
咱们每次都能聊得很嗨，那就继续吧。
We always have a good time, so let's go for it.
希望是吧，真的希望我能给你点启发。如果你用了电脑辅助工具，发现有什么不顺手或者没做到的地方，记得告诉我。
Hopefully, yeah, hopefully, I've I've inspired you, and please write me if you use computer use and you find a rough edge where it doesn't do something.
但是，老兄，那些不同的、像什么五步、十步的操作流程，能实现各种功能，真的让人惊叹。
But, man, these different, like, five, ten step procedures where it does stuff is it's incredible.
不过，关于安全护栏这块，我想跟你聊聊的是，现在的安全护栏跟模型本身越来越融合，界限变得模糊了。你看，比如 Claude Code 的安全护栏，现在用 Fable 和 Opus 5 的时候问题挺多的。
But, anyway, on the harnesses, and I wanna talk to you about is really just how much of the harness is being blurred into the actual model, it feels like, and how we've got now these, you know, like, Claude code harness doesn't there's a whole lot of things wrong with it right now today with, like, Fable and Opus five.
这也是个时间点的问题。
That's, again, time stamping it.
大家对 Claude Code 的体验都不满意，我自己也几乎不再用了。这挺奇怪的，因为大概半年前，我还一直忍受 Anthropic 的那些烂操作呢。
People are not happy with the Claude code experience, and I myself have pretty much stopped using it, which is wild because, I don't know, six months ago, I put up with all the crap that Anthropic was doing.
我什么都忍了。
I put up with everything.
可能不是所有的烂事都忍了。
Maybe not all the crap.
我是真心喜欢 Anthropic。
I love Anthropic.
我也喜欢那里的每一个人，但我确实忍受了当时发生的一切。
I love everybody there, but I put up with everything that was going on.
新闻里总是那么多八卦，因为他们之前的产品实在太强了。
There's so much drama in the news all the time because they had such a superior product.
那体验真的没得说。
It was so good.
结果后来他们更新了这个最新模型，你想把那些外部框架的东西硬塞进模型里，或者干脆因为系统提示词的存在，导致界限变得模糊不清。
And then somehow or another, when they r l'd this last model, and you try and bring a lot of this harness into the model, or I guess it inherently becomes blurry because they have their system prompt.
对。
And Yeah.
当全世界使用这个模型足够久之后，那个系统提示词就会变得越来越长，越来越长。
After the world uses the model for long enough, that system prompt just, like, keeps getting longer and longer and longer.
对吧？
Right?
然后他们推出新模型时，那个系统提示词又能缩短，因为上一个模型里那长长的系统提示词几乎都被强化学习融进了新模型里。
And then they come out with a new model, and that system prompt can shrink again because all of that long system prompt from the last model gets almost like RL'd into the new model.
但这可能会产生一些奇怪的、不顺畅的情况，我们现在正看到这些。
But that can create some weird janky stuff that happens, and we're seeing that.
而且我确信Anthropic的下一代模型会非常出色，我们又会回到那种‘哇’的感觉。
And I'm sure that Anthropic's next model is gonna be incredible, and we're gonna be right back at like, oh, wow.
他们做到了。
They were able to do it.
但对我来说，说到这些‘护栏’，看到这些真的很有意思，我想有些人称之为‘内部护栏’。
But this is just for me, when it comes to harnesses, it is so fascinating to see how these I think some people call it the inner harness.
基本上，实验室提供的护栏非常像是，你被高度优化以适应那个实验室推出的模型。
Basically, the harness that the labs provide is very much, like, you are super optimized for the model that is that lab is putting out.
对。
Yeah.
如果你想有自己的那种框架，比如你想跑PIE或者Hermes之类的，你知道吗？
And if you wanna have your own kind of harness, if you're trying to run PIE or some of the or Hermes or whatever, you know what?
其实，可能你在某些开源模型上表现会更好。
It's actually like, maybe you're gonna do better on some open source models.
很多来自中国的开源模型在这方面真的很棒。
And a lot of these open source models coming from China are really great with that.
所以，我朋友Drew告诉我，在PY里，你经常听到PY的创造者Mario说，他不得不跟Claude斗争，不让它做那些API调用，就像Claude Code的API调用那样，然后他就说，天哪，我得跟模型斗争，不让它表现得像它训练时用的那个框架。
And so there was something that a friend my friend Drew told me how a lot of times in PY, you would hear Mario, the creator of PY, talk about how he had to fight with Claude to not, like, make these API calls like Claude code API calls, then it it was like, man, I have to fight against the model to not act like the harness that it was trained with.
你知道吗？
You know?
所以对我来说，想想这些，以及它如何影响接下来几个月我们看到的模型发布，真的很有趣。
So that's fascinating for me to just think about all of that, and how it's going to affect the next few months that we're seeing the models come out with.
你觉得，当我们看到这些，现在Hermes和Pi在崛起，Claude Code也经历了一些用户挑战，如果你去一些论坛看看，人们真的对它很失望。
How do you think, you know, as we look at that, and right now, with Hermes and Pi on the rise, and with Cloud Code having been through these user challenges, and if you go into some of the forums on that, people are just really frustrated with it.
我也是，所以我经常用 Cloud Code，但里面各种问题层出不穷。
And I have too, so I use Cloud Code quite a lot, and there's all sorts of issues.
所以真是让人又爱又恨。
So it's a love hate relationship.
有些功能我挺喜欢的。
There are things I love about it.
但也有一些地方让我忍不住吐槽，天哪。
There are things I'm like, Oh, God.
而且显然 Codex 也出来了，你觉得未来会怎样？或者你对用户和公司有什么建议吗？
And obviously with Codex out there, what do you think of either is the future or do you have any suggestions on where things need to go, both for users or even for the companies?
这些机构的很多人都关注着。
Have folks from all these organizations who tune in.
所以你知道的，你觉得接下来会怎么发展？
So you know, like, how do you see this shaking out going forward?
对我来说，如果研究实验室没有做出最好的产品，那简直太奇怪了，因为他们能获取用户使用他们产品的所有数据，然后把这些反馈融入到产品本身中。
For me, it's just it would be really wild if the research labs didn't have the best product, because they're getting all of this data on how folks are using their products, and then they can incorporate that into the product itself.
对吧？
Right?
他们提供的模型或者工具链。
The model or the harness that they're giving.
所以我觉得现在Claude Code这波操作有点疯狂，感觉他们可能在这件事上做得过头了。
So that's why it's it's crazy to me right now that Claude Code is having this moment where it's like, man, they might have gone a little too far on this.
他们也许用力过猛了。
They they may have tried to push it too much.
而且他们拥有所有这些信息和数据，了解人们如何使用以及怎么使用，这让我确信他们肯定会做出最好的产品。
And the fact that they have all that information and this and this data of people using it and how they're using it makes me think that they are for sure going to have the best product.
不过，就目前的情况来看，事实未必如此。
However, today, as it stands, that's not necessarily the case.
确实是这样。
Yeah.
我觉得在这方面还有很多工作要做才能改进，因为正如你提到的，我们观察到用户体验非常不稳定。
I think I think there's a lot of work there that needs to be done to improve because we're seeing, kind of to your point, we're seeing user experience very jittery.
体验从非常好直接变成非常费劲。
Goes from being very good to being a struggle.
然后我看到很多人，我是说，甚至像回退到旧版本模型这种情况，比如在 Claude Code 里，因为他们抱怨 Opus 太啰嗦，而它确实很啰嗦。
And then I see people, I mean, even things like rolling back to older models within Claude Code, for instance, because they're complaining about how Opus is so verbose, and it is.
这让我抓狂。
It drives me nuts.
但我心想，天哪，你刚才才写了一大堆东西，我现在只想赶紧结束。
But I'm like, Oh my God, you just wrote a book on this last thing, and I just wanna get to the end.
这是我的常规做法。
That's my typical thing.
我想尽快看到结果。
I want to get to the end.
拿到最终成果。
Get there.
对。
Yeah.
看看这一切在模型融合领域最终会怎么发展，以及它们之间的关系、界限在哪里，这挺有意思的。
It's interesting to see how all this is gonna shake out in the harness merging with different models space, and what the relationship is, and where the line between the two is being drawn in terms of that.
对了，你看过那个‘兄弟技能’吗？
By the way, have you seen the bro skill?
我还没看过那个‘兄弟技能’。
I have not seen the bro skill.
那技能简直太棒了。
So this skill is incredible.
对于那些遇到类似你所说的问题的人，比如觉得那简直像本书一样厚，而且自己连一半都看不懂。
For anybody who's having these issues like you're having where it's like, man, that was a book, and I don't know if I understand half of it.
你可以调用那个‘Bro技能’，它会强制模型用非常简单的语言来解释，这样就不会给你一堆术语、大词之类的让你一头雾水的东西了。
You use you invoke the bro skill, and it forces the model to explain things very simply so that it doesn't give you these this jargon and all these big words and all this stuff that you're like, woah.
到底是什么意思啊？
What is what does that even mean?
对吧？
Right?
就是像给五岁小孩解释那样，把事儿给我讲明白。
It just is like kinda explain it to me like I'm five type thing.
对。
Yeah.
没错。
Yep.
所以这个功能特别实用。
And so that is a very, very useful one.
还有一个挺实用的技能，叫 show me。
Another skill that is quite useful is called show me.
好的。
Okay.
这个功能主要是当它没法光靠文字解释清楚、容易让人看晕的时候，直接给你展示视觉化的内容，这样你就能跟着理解了。
And so this one basically just makes it give you visuals when it's instead of, like, writing the book and trying to explain it in words that you kinda get lost in, it will give you visuals so that it can go with it.
这两个结合起来特别好用。
And both of those together are very useful
哇，老兄。
Oh, dude.
当你遇到这些问题的时候。
When you're encountering these problems.
我今天就是这样，因为我花了很多时间在客户端代码上，之前不知道这一点，所以今天我在调用这些方法。因为在使用提示词的过程中，我会经历一个情绪周期，然后我就一直往下滚动，对。
I am that like today, because I spend a lot of time in client code, and I didn't know that, so I am invoking those today, because I have an emotional cycle that goes with using it as I prompt through things, then I'm going scroll yeah.
所以你刚刚帮我解决了这个问题。
So you've just solved it for me.
兄弟，你先说。
Dude, just just go ahead.
抱歉打断你一下，不过我特别想听听你的看法。
Oh, sorry to cut you off, but you know what I would love to get your take on.
我还有一件事一直在深入思考，主要跟购物体验有关，以及未来我们在网上购物的方式会怎么变。
Some other thing that I've been thinking about deeply is really along the lines of the shopping experience and where we're going to shop in the future on the Internet.
因为对我来说，感觉我们离完全在聊天窗口里完成所有购物操作已经不远了。
Because for me, it feels like we're not that far off from doing everything in the chat.
可以说，聊天界面就是新一代的浏览器。
Like, the chat is the new browser in a way.
对。
Yeah.
这可不是
That's not
确实是。
It is.
这个新词儿挺新鲜的。
That novel of a term.
我觉得现在大家都能接受这个说法，毕竟我们大部分工作都是在聊天窗口里完成的。
I think we're all okay with saying that these days because the majority of our work gets done from the chat.
所以我有个发现，这还得归功于我在首尔的经历。我跟很多刚加入代理式AI基金会（Agentic AI Foundation）的支付处理公司聊过。
And so what I realized, and this came from me being in Seoul, and I talked to a lot of payment processing companies who just joined the agentic AI Foundation.
他们都在琢磨一个问题：未来的支付方式到底会是什么样？
And they were wondering, like, well, what is the future of payments?
具体会怎么运作呢？
How is it gonna work?
大家会在哪儿付款？
Where are people going to pay?
特别是如果你开始考虑电商领域，想想那些有 Shopify 店铺的人，或者甚至想到亚马逊。
Especially if you start to think about ecommerce worlds and you think about folks have Shopify stores, or you can even think about Amazon.
对吧？
Right?
通常来说，我们会去某个电商网站，在那个Shopify店铺里通过浏览网页的体验来买东西。
And normally, what we do is we go to some e commerce store, and we buy something from this Shopify store by having an experience on that website.
或者我们去亚马逊，挑好想要的东西，然后在亚马逊上下单，当天或者第二天就能收到货，之类的。
Or we go to Amazon, and we pick out what we want, and then we buy something from Amazon, and it comes same day or the next day or whatever.
但如果我们的整个购物过程都是通过聊天窗口完成的，而且是由AI代理去操作的话，情况会怎样呢？
But what happens when our whole experience is being done through the chat, and the agent is the one that's going, and
这确实是我们未来的发展方向。
Which is it is really where we're going.
我的意思是我已经在往那个方向努力了。
I mean, that's where I'm already trying to go.
我不想变成像亚马逊那样的平台。
Don't want to be amazon.com.
我平时总是开着聊天窗口。
Spend, I always have chats open.
我总是让客服助手帮我处理各种事务，购物也是这么操作，你知道吧？我只会在不得不去的地方才亲自下单。
I always have agents doing stuff, and I do my shopping that way, you know, and I only will go to where I have to do that.
其实到了这一步，哪怕是亚马逊，我也只需要代理在既定范围内把东西买好，然后这事就结了。
And actually, at this point, even for Amazon, I just need the agents to buy the stuff within thresholds and stuff like that and be done with it.
对，完全就是你说的这样。
So, yeah, exactly what you're
说到这儿，我心里其实有很多大大的问号。
Well, here's what gets me about this is how there there's so many things that are big question marks in my mind.
对吧？
Right?
第一个问题是，亚马逊怎么会允许这种情况发生呢？
The first one is, how is Amazon just gonna let that happen?
首先，因为通常情况下，当人类用户登录亚马逊并浏览购物时，他们会获取所有第一方数据，这些数据被用来提供推荐或引导你购买其他商品。
A, because they normally, when you, a human user, log on to Amazon and you shop around, they get all that first party data, and that is used to serve up recommendations or it's used to get you on other things.
对吧？
Right?
并且希望能增加你在亚马逊上的消费金额。
And hopefully, increase the amount of money that you spend on Amazon.
再说一遍，我不是专门针对亚马逊，市面上还有很多其他的电商平台。
Or, again, not singling out Amazon, there's plenty of other e commerce stores out there.
我们可以直接用 Shopify，比如约翰的电商店铺。
We can just use Shopify John's e commerce store.
好的。
Okay.
那接下来会发生什么呢？
So, now what happens?
他们大概就会说，行吧，挺好的。
They're just gonna be like, alright, cool.
但现在是由代理在执行操作，你根本搞不清楚它的真实意图。
Well, now that it's an agent doing it, you don't understand the intent.
你也不明白这个代理只是直接去执行那个动作。
You don't understand the agent just goes for the thing.
它的使用方式跟你平时看人类使用时的习惯完全不同，而且它还绕过了我们过去二三十年里不断优化的一切手段，比如追加销售、弹窗提示等等。就像那种：哦对了，Chris，顺便说一句，你要是再多花三美元，我们就给你免运费。
It's using it in a way that you're not used to seeing a human use it, and it also bypasses all this stuff that we spent the last twenty, twenty five years optimizing, like the upsell or the pop ups or the all this stuff that it's like, oh, yeah, Chris, by the way, if you spend 3 more dollars, we're gonna give you free shipping.
而且这个代理根本不在乎这些。
And the agent doesn't care about that.
对吧？
Right?
它拿到东西就走人。
The agent just gets the stuff and gets out.
它目前还没有这种辨别能力。
It doesn't have that kind of discernment, at least as of now.
也许它会回过头来跟你说，哦，克里斯，顺便提一下，有这些东西。
Maybe it'll come back to you and say, oh, Chris, by the way, there's these things.
有可能，但也可能没有。
Maybe, but maybe not.
所以，我们得开始改造我们的电商网站，去吸引那些智能代理，而不是人类用户。
And so we're gonna have to start building our e commerce websites to entice the agents, not the humans.
所以说，这就是所谓的智能代理，
So that's where think agents,
但我们希望这些代理能吸引它们回去，给你提供更多信息。
but we want the agents, we wanna entice them to go back and give you information.
对吧？
Right?
所以我们在客户关系上完全失去了联系。
So we've completely lost our relationship with the customer.
我同意。
I agree.
我觉得我们正处于一个过渡期。
I think we're in transition.
回想我之前提到的，与其说是代理式界面，不如说我认为这里不仅有空间，甚至可以说是必然趋势。考虑到营销、品牌塑造、获客、留客以及用各种优惠吸引客户等实际需求，你不能只让你的代理去连接那个 MCP 服务器。
And going back when I was talking about having an agentic interface instead of And this is where I think there's room, not just room, this is where I think it almost has to go, given the necessities of marketing branding, capturing the customer, holding the customer, enticing the customer with various incentives, that kind of thing, is that you can't just have your agents go to an MCP server.
我想这只是起步阶段，但对于卖家和那些试图打造这类产品的公司来说，他们必须建立超越 MCP 的代理式界面。不能只是出去获取某个工具或服务的访问权限，而是要实现代理之间的协商交互。这样双方代理都能变得更聪明。也许还会有采购代理和谈判代理的组合之类的角色出现。
I think that's how things will start, but I think for the sellers, for the companies that are trying to produce that, I think that they have to have these agentic interfaces that are going beyond MCP, where you're just going out and getting access to a tool or something, but you're actually having a negotiation across agents where that can happen, and then agents on both sides are getting smarter, or it may be that you have combinations of purchasing agents, and then you have negotiation agents, and things like that.
我之前提到过类似“蜂群”的概念。
I talked about kind of the swarms.
你可能会拥有一个小型的代理集群来帮你购物，每个代理都有自己的一套职责，包括从加价销售到其他各种相关事务的谈判。
You may have a mini swarm that does your shopping where each agent has its own set of responsibilities, including the negotiation from the upsell and all the other concerns that come about.
所以我认为，要在代理环境中让它变得极其丰富，就像他们在人类世界中尝试做的那样，就是将其变成一种代理对代理的交易，包含其中所有的沟通方式，这样可能会带来更好的结果。
So I think that to make it incredibly rich in the agentic context, the same way they've been trying to do it in a human world, is to make that an agentic to agentic transaction transaction with with all those kind of communications that go on in there, and it may bring it back.
然后你自己会形成一个消费者档案，记录哪些东西对你感兴趣、哪些不感兴趣，你的代理会学习你的偏好。当它正在交互的代理发来某种加价优惠时，你的代理能理解你的行为模式和可接受的范围，并在一定程度上自主行动，在你甚至还没意识到之前就满足你的愿望。
And then you develop a profile yourself as a consumer of the things that are interesting to you and not, and so your agent learns your preferences, and then when a deal comes from the agent that it's interacting with, that kind of upsell thing, your agent understands your behavior and what would be acceptable, and it can act autonomously to a certain degree to satisfy your wishes before you even know it's there.
这就是我认为正在发生的事情。
That's what I think is happening.
我
I
喜欢这个愿景，我也确实喜欢这个想法，就是它会一直关注市场动态，不断收到各种优惠信息，这就是未来的世界，然后它会判断要不要告诉你这个优惠。
like that vision, and I do like the idea of, oh, it's gonna have its ear to the street, and constantly be getting hit up with offers, potentially, that's that's the world, and then it discerns whether or not it should tell you about the offer.
因为我们最不希望的就是一个代理不停地提醒我们，哦，这里有个很棒的优惠。
Because the last thing we want is an agent that's constantly pinging us about, oh, there's this cool offer.
那里有个很棒的优惠。
There's this cool offer.
就像，它必须了解你。
Like, it'll have to know you.
对。
Yeah.
对。
Yeah.
它得……
It's you'll have to
了解你。
learn you.
对我来说，这里面有几件事挺让人兴奋的。
There's there's a few things that for me are wild there.
确实，我们现在可以分散开来，组成这些智能体群，它们可以同时去一百个不同的网站找鞋子，或者我们想买的其他东西。
It is true that, yeah, we can fan out right now and create these swarms, and these agents can go off and hit a 100 different websites looking for shoes, right, and or one item that we're trying to shop for.
但当我跟它说，好，
But what happens when I go and I say, cool.
帮我买这双鞋、那条裙子，还有这个香蕉。
So get me these shoes and that dress and that and this banana.
这时候，智能体要怎么付款呢？
And the agent now, where are you gonna do the payments?
这就是我最初开始思考的地方。
And this is where why it all started for me.
所以，首先，其实再退一步说，这些真的重要吗？
And so, first of all, actually, even taking another step back, does any of this even matter?
既然通过浏览器操作我已经能拿到想要的东西，那还有没有一种强制力去促成这种现实呢？
Is there going to be a forcing function to create this reality if with browser use, I can already get what I want?
首先我得说，对于我的智能体来说，浏览器操作已经足够好用了，是的。
So first of all, I will just say that, like, browser use is good enough for my agents to go and browse the front end Yeah.
然后拿到我想要的东西。
And get me what I want.
那为什么还会有动力去创造这样一个智能体之间互相交流、拥有这些群体协作以及发生各种复杂交互的新互联网呢？
So why is there going to be an incentive to create this new internet where agents are talking to agents, you've got these swarms, and all this complex stuff happening?
因为我已经有了我需要的东西。
Because I just, I've already got what I need.
对吧？
Right?
这才是重点。
That's the point.
通过浏览器界面。
With browser view.
这是一个
It's a
好，所以
good So
这就是它可能永远不会发生的地方。
that's where there's potential that it never happens.
不过我会同意你这个观点，好吧。
But I will I will go with you on this idea of, like, alright.
如果我们真的实现了那种智能体集群，现在我已经告诉我的智能体，我想从三个不同的商家购买三样东西。
If we do get there to the the swarms, and now I've just told my agent that I want three different things from three different merchants.
我们目前的做法是，智能体会逐个访问这些网站并完成购买。
The way that we do that today is, like, the agent will go to each one of these websites and it will buy them.
或者它会告诉我们，嘿。
Or it will tell us, hey.
这是按钮。
Here's here's the button.
你方便直接买下来吗？
Are you okay to buy it?
然后我们最后点一下，确认要还是不要。
And we eventually click on it and say yes or no.
如果在这个时间线里，AI助手真的能这么操作，那离现实其实也不远了。
But it's not that far off of a reality if we are living in this timeline where agents do that.
当Anthropic或者OpenAI说，‘干嘛不直接把钱付给我呢？’
When Anthropic or OpenAI, they say, well, why not just pay me directly as OpenAI?
我可以充当你的支付处理方，你直接付钱给我就行。然后呢，你知道会发生什么吗？
I can be your payment processor, and you just pay me, and so then, you know what happens?
这样一来，你甚至都不需要Shopify了。
You don't even need then you disintermediate Shopify.
我是说，作为商家，我干嘛还要专门去开一个Shopify店铺呢？
Like, why do I, as a merchant, even need to create a Shopify store?
我只需要建立一个市场平台，所有的交易都通过聊天界面完成就行了。
I just create the marketplace is all going towards the chat.
所以现在，市场到底是什么呢？
And so now, what is what is a marketplace now?
是不是就是我创建一个代理，里面包含我所有的不同SKU，方便搜索，然后通过聊天里的代理直接购买，对吧？
Is it just me creating an agent with my with all these different SKUs that is easily searchable, and then it can be bought through an agent on the chat, right?
你明白我的意思吧？
Do you see where I'm going with it?
我明白你的思路。我觉得你说的这种情况很可能会发生，同时我也认为会有各种类型的商家进行大量尝试，看看这种方式行不行，而且还会涌现出第三方市场来验证这种模式是否可行。
I do see where you're going, and I think that that also will I think what I'm saying is likely to happen, but I also think, inclusively, what you're saying, I think there'll be a lot of experimentation from different types of merchants on how that, and there will be third party marketplaces forming to see if that works.
所以我觉得这些情况都会出现。
So I think we'll see all of those.
作为消费者，我知道自己不想再去逛街购物了。
I know as a consumer, I don't wanna be shopping.
这本来就不是我的日常。
It's not what I do.
我对这个也没啥兴趣。
I don't care about it.
但我会很清楚，我的那些代理都在替我着想。它们对我非常了解，做了大量的私人画像分析。换句话说，我的代理会分析我和妻子、女儿的需求，了解我们买东西的频率、什么时候需要、具体情境是什么，并且能很好地掌握这些信息。
But I will know that I will have all of my agents that are looking out for my interests, and they have learned me very, very well, and there is a lot of private profiling that, in other words, my agents profiling me and my wife and my daughter and our needs and how often we get things and when we need it, what the circumstances are, and my agents will learn that very well.
从我这边来说，我看重的是品质。
And from my standpoint, I want good quality.
我要在我想要的时候就能拿到。
I want it when I want it.
我不想花太多钱，至于东西从哪儿来我并不在意，只要退货方便之类的条件都满足就行。
I want to not spend too much money, and I don't really care where it comes from, if I can return it expeditiously as well and all that.
所以到时候我就把这些交给我的智能体去搞定。你去市场里找，或者直接对接智能交互界面，或者像现在用 Shopify 或亚马逊那样去抓取数据。反正我不关心过程，只要结果能实现就行。确保所有我在意的条件都满足，别来烦我。
So I'm gonna leave that to my agents at some point to figure out, you go to the marketplace, you go directly to an agentic interface, you go to more of a Shopify or Amazon today and scrape it on the don't care, just make it happen, make sure all these things that I care about are in place, and don't bother me with it.
就这么简单。
Period.
这就是我想表达的意思。
That's where I'm going.
啪，搞定。
Bang.
我是个很挑剔的客户。
That I'm a demanding customer.
对。
Yeah.
没错。
Yeah.
但正因为如此，我觉得还是存在不少摩擦，毕竟还有很多大问号没解开。对我们消费者来说，最理想的状况就是你刚才描述的那样：系统比我们自己更了解我们。
And but don't that's why I feel like the friction, there's still some there's still some big question marks because the ideal scenario for us as a consumer is exactly what you just mapped out, where it knows us better than we know ourselves.
对吧？
Right?
如果有一组代理，或者说我的代理大军在替我着想，我会很乐意把所有需要的信息都交给它们，让它们成为最顶级的推荐系统。
And I'm okay if I have an agent or my swarm of agents, my army of agents that I know are looking out for my best interest, I'm okay with giving it all the information it needs and having, like, the top recommender system.
我是心甘情愿地提供所有信息的。
It's like, I will gladly give you anything, any information.
你可以随时询问或深入挖掘我的喜好和厌恶，因为我相信你是在为我争取最大利益。
You can quiz me or grill me on my likes and dislikes because I trust that you're looking out for my best interest.
对吧？
Right?
现在最大的疑问就在这里，也是 OpenAI 可能搞砸的地方：如果他们意识到自己可以成为交易平台，并且每笔交易都能赚钱，那他们是不是就会只推荐自家平台上的东西了？
Now the big question mark here and where OpenAI could potentially fumble is if they see that, wow, we could be the marketplace, and we can make money anytime there's a transaction that happens, wouldn't that incentivize them to only show things that are coming from their marketplace?
我知道我在这儿做了好多大胆的推测，想象各种可能的未来走向。毕竟 OpenAI 目前并没有交易平台，也从来没说过自己想做成交易平台。
So I know I'm making all kinds of big leaps here in, like, what the potential future could be, because OpenAI does not have a marketplace right now, and they've never stated that they wanna be a marketplace.
但如果这真是其中一种可能的发展路径，你想想看，他们肯定只会力推自己的产品。
But if this is one of the potential timelines, and you think about it, like, they would only push their own product.
不过，这可能会让我觉得，哎呀，他们这是在占我便宜，因为他们两边都通吃。
However, that could make me feel like, oh, well, they're taking advantage of me because they're playing both sides.
他们对我了如指掌，然后又在想办法利用商家在 OpenAI 那边掌握的信息来获利。
They know everything about me, and then they're finding a way to leverage the what the merchants have on OpenAI.
要是我知道他们夹在中间，我就没那么信任它了。
Like, I would feel like I wouldn't trust it as much if I knew that they were in the middle of it.
但就像你刚才说的，如果不是那种代理模式，而是它替我去那个‘狂野西部’般的 Agent 世界里到处搜索、跑腿的话，那我可能就会稍微放心一点。
But if it wasn't agent, like you were saying, where it is going out and doing the searching on my behalf out in the wild wild west of the agent verse, then maybe I would feel a little bit more okay with it.
我也不确定。
I don't know.
这些就像是思想实验一样。
These are like the thought experiments.
我觉得情况会变得很混乱。
I think it's gonna be messy.
我觉得局面会挺乱的，而且大家都会去试试看。
I think it's gonna be messy, and people will try it out.
说到这儿，我就先做个总结吧，今天的对话真的特别有意思。
On that note, I'm gonna wind us up, and this has been a fun, fun conversation.
我真的很喜欢这样的交流。
I always love these.
能请你回到节目里聊聊这些话题，真是太好了。
Getting you back on the show and talking about these things.
我觉得我们现在正处在一个关键节点，刚才聊到的那些情况随时都可能发生。
I think we're just at a moment in time where any of these things that we've just talked about might happen.
我觉得值得聊聊，因为现在事情发展得比大家预想的快得多。等人们开始尝试之后，我一点都不惊讶会看到其中一些情况在今年结束前就出现。
And I think it's worth talking about because things are happening so much faster than anyone's expecting right now that I wouldn't surprise to see some of these things occurring before this year is out, as people start experimenting.
所以咱们走着瞧吧。
So we'll see.
等到下次聊天时，我们回过头来看，今天这场对话就会显得特别过时了。
Our next conversation, we'll look back, and this one will seem so outdated.
今天说的这些
This will seem so
那肯定会很棒。我们刚才说到哪了？
It will be great to What were we
在想那个事吗？
thinking about that?
哎呀，我们当时想得也太远了。
Like, We oh my were so far off.
我们当时
We were
差得远呢，还有那些。
so far off and all that.
而且结果比我们预想的要远远超出。
And it was so so much more than what we were expecting.
所以我们就等着瞧吧。
So we'll see.
总之，我很期待。
Anyway I'm excited
这个。
for it.
德米特里奥斯，再次感谢你来做客，和我们聊了这么多。
Demetrios, thank you again for coming on and having conversation.
我希望观众和听众们和我一样享受这次对话。
I hope the viewers and listeners enjoyed it as much as I did.
我聊到了一些很酷的话题，兄弟。
I got some cool topics, man.
那我们下次见。
So I'll see you next time.
谢谢你来到节目。
Thanks for coming on the show.
再见。
Ciao.
好的。
Alright.
这期节目就到这里。
That's our show for this week.
如果你还没看过我们的网站，请访问 practicalai.fm，别忘了在 LinkedIn、X 或 Blue Sky 上关注我们。
If you haven't checked out our website, head to practicalai.fm and be sure to connect with us on LinkedIn, X, or Blue Sky.
我们会在这些平台上分享关于最新 AI 发展的见解，非常欢迎你来一起交流讨论。
You'll see us posting insights related to the latest AI developments, and we would love for you to join the conversation.
感谢我们的合作伙伴 Prediction Guard 为本节目提供运营支持。
Thanks to our partner, Prediction Guard, for providing operational support for the show.
欢迎访问 predictionguard.com 了解一下。
Check them out at predictionguard.com.
同时，感谢 Breakmaster Cylinder 提供的节奏，也感谢你的收听。
Also, thanks to Breakmaster Cylinder for beats and to you for listening.
今天就到这里，下周我们再见。
That's all for now, but you'll hear from us again next week.
关于 Bayt 播客
Bayt 提供中文+原文双语音频和字幕，帮助你打破语言障碍，轻松听懂全球优质播客。