How I use ChatGPT to run my fashion business
频道: How I AI
视频: https://www.youtube.com/watch?v=P03ZNceXe2A
原文语言: en
统计: 共 67 轮 · Yana Welinder 29 · Claire Vo 28
[0:00] Yana Welinder
Normally, I would hire a technical team, like engineers. I didn't, right? I sort of just came to Codex and [music] asked it to build the website. The idea is to use AI really anywhere in the process where that makes sense. It's literally my technical co-founder.
换作平常，这种事我肯定得雇一支技术团队，比如工程师什么的。但我没有，对吧？我基本上就是打开 Codex（OpenAI 的编程 agent，能自己动手写代码），[music] 让它把网站建出来。我的思路是：流程里凡是 AI 用得上的地方，就用 AI。它简直就是我的技术联合创始人。
[0:15] Claire Vo
There's so much you couldn't do before, practically, from a cost perspective, even from an execution perspective, that is now totally possible. And so, you can like unlock your creativity in a way that wasn't possible before.
以前有太多事你根本做不了——从成本上不现实，从执行上也不现实——现在却完全能做到了。所以你可以把创造力释放出来，这在以前是不可能的。
[0:29] Yana Welinder
does unlock so much creativity. A lot of my designs start from a hand-drawn sketch, but the other piece of this is I sort of developed the fashion prompt that's behind it. And it describes a lot of sort of what goes into garments. So, it has like the the silhouette, uh the proportion or the volume of of the dress, like kind of like the fabric, how it flows, how it behaves, the construction details, how it moves, even how it sounds. The other piece that is still unsolved, and I'm sort of still banging my head against the wall, is to get it to create patterns based on my design. And there I'm kind of running humans and AI in parallel. So, I I am working with human pattern makers Codex and just saying who's going to get to making my things fastest.
它确实释放了巨大的创造力。我很多设计都是从一张手绘草图开始的，但另外一块是，我摸索出了背后那套「时装 prompt」（prompt 就是给 AI 的指令模板）。它把一件衣服该有的东西全描述清楚了：silhouette（廓形，也就是衣服的整体外轮廓）、连衣裙的比例和体量、面料是什么质感、怎么垂坠、怎么动，还有工艺结构细节、走动时的状态，甚至穿着它时会发出什么声音。还有一块到现在没解决，我还在拿脑袋撞墙——就是让它根据我的设计做出纸样（pattern，裁剪用的平面版型）。这块我现在是人和 AI 并行跑：一边找人类打版师，一边让 Codex 上，看谁能最先把我的东西做出来。
[1:15]
[music]
[music]
[1:17] Claire Vo
Welcome to How I AI. I'm Claire Val, product leader and AI obsessive here on a mission to help you build better with these new tools. Today I have Yana Welander, and she is building an AI native fashion startup. And she's going to show us how AI can intersect art, creativity, and real-world production, and why computer use plus software means SaaS really isn't dead, at least not yet. Let's get to it. This episode is brought to you by Merge. Building an AI product is one thing.
欢迎收看 How I AI。我是 Claire Vo，产品负责人，也是个 AI 狂热分子，来这儿就是想帮你用这批新工具做出更好的东西。今天请到的是 Yana Welinder，她正在做一家 AI 原生的时装创业公司。她会给我们演示 AI 怎么把艺术、创意和真实世界的生产打通，以及为什么有了 computer use（让 AI 直接操作电脑界面）再加上软件，SaaS 其实还没死——至少现在还没。我们开始吧。本期节目由 Merge 赞助。做一个 AI 产品是一回事，
[1:48]
[music]
[music]
[1:48] Claire Vo
The hard part is everything around it. Connecting to the tools your team and customers rely on, letting agents take action with the right permissions and keeping [music] everything reliable and cost-efficient once you're in production. Most teams end up piecing that together themselves. So, instead of building the product [music] you actually care about, you get pulled into integrations, permissions, routing, and all the infrastructure underneath. Merge is the infrastructure layer for production AI. It connects to thousands of tools, gives agents secure ways to act inside them, and optimizes model routing and spend without you building or owning any of it. OpenAI, Dropbox, and Ramp already use Merge to move fast and build AI right. Visit merge.dev/howiaai to start building for free. Yana, thanks for joining How AI. I'm an art and fashion girl. You know this. There are like five of us AI art and fashion girls on Twitter. And we all find each other, but I'm one and I love what you're working on. So, immerse us in this new thing that you're working on, and then we'll talk about how you're using AI in this really unique fashion.
真正难的是它周围的一切：接进你团队和客户天天在用的那堆工具，让 agent（能自主执行任务的 AI 智能体）拿着正确的权限去动手办事，还得保证 [music] 上了生产环境之后既稳定又省钱。大多数团队最后都是自己一块块拼出来的。结果本该去做 [music] 你真正在意的那个产品，人却被拽进了集成、权限、路由和底下那一堆基础设施里。Merge 就是给生产级 AI 用的基础设施层。它能连上几千种工具，给 agent 提供在这些工具里安全动手的通道，还能优化模型路由和开销——这些你一行都不用自己建、也不用自己养。OpenAI、Dropbox、Ramp 已经在用 Merge 跑得更快、把 AI 做对。访问 merge.dev/howiaai 就能免费开始。Yana，谢谢你来上 How I AI。我是个艺术加时尚女孩，你知道的。Twitter 上搞 AI + 艺术 + 时尚的女生大概就我们五个，而且我们总能互相认出彼此，我就是其中之一，我特别喜欢你在做的事。所以先带我们沉浸式看看你手上这个新东西，然后我们再聊你是怎么用一种特别独特的方式在用 AI 的。
[3:00] Yana Welinder
Cool. Yeah, I'm so excited to be here. Thanks for having me. I am building this AI-native fashion brand, and the idea is to use AI really anywhere in the process where that makes sense. So, obviously heavily in the design and production process, but also it's literally my technical co-founder, and so I that's that's what I use it for, everything.
好啊。我特别高兴能来，谢谢你请我。我在做一个 AI 原生的时装品牌，思路就是：流程里凡是 AI 用得上的地方，就都用上。所以设计和生产环节显然用得非常重，但除此之外，它简直就是我的技术联合创始人，我什么事都靠它。
[3:26] Claire Vo
And can you show us like it's it's probably hard for people to conceptualize what like an AI-powered fashion brand looks like? Can you just like show us a little bit of kind of like some of the stuff that you're working on, and then we can get into how it actually how you actually got there.
你能给我们看看吗？我觉得大家可能很难想象一个「AI 驱动的时装品牌」到底长什么样。你能不能先简单展示一下你手头在做的一些东西，然后我们再聊你具体是怎么走到这一步的。
[3:40] Yana Welinder
So, this is Yana banana, the the the fashion brand, and you can kind of see like every everything here is built with AI. So, you have some of the different garments that I designed, and I'll show later that's like different ones starts from different like from different inspiration from different points. So often time I start from a sketch. You can see that when you hover over some of these. So I start with with a hand drawn humanly manually, you know, old school hand drawn sketch and then I use AI to turn that into different types of fashion collateral and kind of technical specs and everything along the line to ultimately get to a garment and I kind of use AI for all the things to visualize it to create photos to create videos of some of these garments. There a lot of them kind of allude to different like uh technical uh you know, computer things in a lot of ways because I feel like that should be really part of the theme. It should be obvious that that what it comes comes from and so the fabrics will use a lot of kind of the punch card like computer punch card uh patterns and and things like that so that you can really see that on the other the other way in which it sort of appears so you can see for example for this like uh post keyboard t-shirt which I'm wearing myself right now.
好，这就是 Yana Banana，我的时装品牌。你能看到这里的每一样东西都是用 AI 做出来的。这些是我设计的一些单品，我待会儿会讲，不同的款是从不同的灵感、不同的起点长出来的。我经常从一张草图开始，鼠标移到有些图上就能看到。我先手绘——纯人工、老派的那种手绘草图——然后用 AI 把它变成各种时装素材、技术规格之类的东西，一路往下推，最后做出一件成衣。可视化、出图、给这些衣服拍视频，我全程都用 AI。这里面很多款都在往计算机、往技术那边致敬，因为我觉得这本来就该是主题的一部分，得让人一眼看出它从哪儿来。所以面料上会大量用打孔卡（早期计算机的穿孔卡片）那种纹样之类的元素，让你真的能看出来。它体现出来的另一种方式，比如这件 post keyboard（后键盘时代）T 恤——我现在身上穿的就是这件。
[5:03] Yana Welinder
Um it also is uh alluding to the fact that now we are not going to be using keyboards and uh in a lot of this stuff but can we now have like give it a second life essentially and to make sure that it's like obvious the world we live in and the world we're entering.
它同时也在说：以后我们做很多事都不再用键盘了，那能不能给键盘一次「第二生命」？就是要让人一眼看清我们现在身处的这个世界，以及我们正在进入的那个世界。
[5:20] Claire Vo
And I just want to pause because when I first saw this I was like what a fun like little art project. Like I once made this like I vibe coded this app which was um Anthropic as an anthropology website cuz I thought it was very funny. But you're actually bringing these designs to life. Like you are actually wearing this keyboard shirt which is super cool. And so what you know, I hear a lot of people who are in the creative fields be really fearful of AI because I think it is like displacement in a lot of ways. Like let's let's all be honest here. There's like videos and sketching and all sorts of stuff that AI can do. And yet, if you step on the other side of this like post keyboard future, there's so much you couldn't do before practically from a cost perspective, even from an execution perspective, that is now totally possible. And so you can like unlock your creativity in a way that wasn't possible before. So, I want you to show us step-by-step kind of what goes into creating a garment like this, creating and imagining a design like this, and then actually getting it to production, and getting a website like this up.
我想在这儿停一下。因为我第一次看到的时候心想，这多好玩的一个小艺术项目啊。我自己也干过类似的事——我 vibe code（凭感觉让 AI 写代码）过一个 app，把 Anthropic 做成一个人类学（anthropology）网站，我当时觉得特别逗。但你是真的把这些设计做成了实物，你是真的穿着这件键盘衬衫，这太酷了。所以说……我听到很多做创意行业的人特别怕 AI，因为说实话，它在很多方面确实是一种替代。视频、画草图，各种活儿 AI 都能干，咱们别装。可你要是站到「后键盘未来」的另一边去看，以前有太多事你根本做不了——从成本上不现实，从执行上也不现实——现在完全能做到了。所以你可以把创造力释放出来，这在以前是不可能的。所以我想请你一步一步给我们演示：做出这样一件衣服要经过哪些环节，怎么构思出这样一个设计，然后怎么真的把它做出来投产，怎么把这样一个网站搭起来。
[6:31] Yana Welinder
I think I think you're absolutely right that it really does unlock so much creativity. A lot of a lot of my designs start from a hand-drawn sketch, but um the other piece of this is I sort of kind of developed this um uh technical essentially stack, but I've for the purpose of visualizing what it looks like, I have this sort of set up as just like the the the fashion prompt that's behind it. And it describes a lot of sort of what goes into a garment. So, it has like the the silhouette, uh the proportion or the volume of of the dress, like kind of like the fabric, how how it how it flows, how it behaves, um the the construction details, how it moves, um even how it sounds. And I can I can show in one of the pieces it kind of has this really interesting kind of sound as you're walking in in uh in the dress. And I take all of this and put it together in in essentially kind of when we if we take it out of my my my flow, uh you can see that it's at at the core of it there's sort of this this prompt that we could take um and plug into chat GPT um, and often times in in when when I'm working with this I will also have an actual sketch of what I want and I sort of am then defining this in addition to the sketch. But just for the sake of us kind of playing in real time, um, I just thought it'd be cool to just, um, just use prompts to start with. So So here we have a sharply tailored waist defined jacket with exaggerated shoulders and blah blah blah, right? So now we're putting this in.
我觉得你说得完全对，它确实释放了巨大的创造力。我很多设计都是从手绘草图开始的，不过另外一块是，我搭了一整套技术栈；但为了方便可视化地讲清楚，我把它整理成了背后的那份「时装 prompt」。它把一件衣服该有的东西都描述清楚了：silhouette（廓形）、连衣裙的比例和体量、面料是什么质感、怎么垂坠、怎么表现、工艺结构细节、动起来什么样，甚至发出什么声音。我可以给你看其中一件，穿着它走路时会有一种特别有意思的声响。我把这些全部揉在一起——如果把它从我的工作流里单独拎出来看，你会发现核心就是这么一段 prompt，我们可以直接把它丢进 ChatGPT。平时我用的时候，手上通常还会有一张我想要的实际草图，然后在草图之外再用这段文字去补足定义。不过为了我们现在能实时演示，我觉得干脆只用 prompt 开个头也挺好玩的。你看这儿：一件腰线收得很利落的合身夹克，肩部做夸张处理，等等等等，对吧。好，现在我们把它输进去。
[8:11] Yana Welinder
Oh, I should have told it to make an image, but maybe it'll figure out to do that. Yeah, there we go. Sometimes sometimes it's smarter than you think, even on instant. And so now it's going to generate an image and often times this will give me kind of like a product photo, but usually what I then want to do with this is to then take it to kind of the next level. And I'll have very specific types of like collateral that I want to get out of it. So once we have this ready, I will ask it to generate a Vogue style runway photo. Oh, there we go. So this is kind of like the product photo of this. Um, so it has these exaggerated shoulders, uh, the waist, a lot of kind of the stuff that I asked it to. And if I had a specific sketch it would really adhere to my sketch much more so than than what was in the prompt. But then if we go to, um, here we say, oh, like now make it into a Vogue style Can you tell that I normally do not type anymore? And so I usually just use voice for all these things. So it's just like so hard.
哦，我应该顺便让它生成一张图的，不过说不定它自己能想到。你看，成了。有时候它比你以为的要聪明，哪怕是在 instant（快速响应）模式下。好，现在它要生成图片了。这一步通常给我的是一张产品图，但我接下来一般想把它再往上推一层，我心里会有非常具体的、想要拿到的素材类型。所以等这张出来，我会让它生成一张 Vogue（时尚杂志）风格的秀场照。喏，来了。这算是它的产品图：肩部很夸张、腰线在那儿，我要求的东西基本都在。如果我给的是一张具体的草图，它会比只看这段 prompt 更严格地贴着我的草图来。然后我们到这儿，说：好，现在把它做成 Vogue 风格的——你看得出来我平时基本已经不打字了吧？这些事我一般都用语音输入。所以打字真的太难受了。
[9:16] Claire Vo
It's easier for our podcast guests, um, when you use voice because they don't have to imagine what you're typing. So she's, you know, you're typing make it into a Vogue style photo.
对我们播客的嘉宾来说，你用语音其实更友好——他们就不用去脑补你在打什么字了。所以她现在打的是：把它做成一张 Vogue 风格的照片。
[9:27] Yana Welinder
a photo model walking down the runway in this outfit. And so then I kind of just like iterate on this, and there's um, I go to to photo that's a runway photo, then I go to like influencer photo, and you kind of see this in a lot of from a lot of different angles, and also iterate on it based on kind of what you're seeing. They'll make it, you know, red, make it shorter, make it longer, and all those different things, but I usually just start from from a specific point and then iterate from there.
一张模特穿着这身衣服走 T 台的照片。然后我就在这上面不停迭代。我会先要一张秀场照，再要一张网红街拍风格的照片，这样你就能从很多不同角度看到它，还能根据看到的效果继续调——改成红色、改短一点、改长一点，诸如此类。但我一般都是从一个很具体的点起步，然后一路迭代下去。
[10:02] Claire Vo
I have a question for you, which is why Chat GPT and why Image Gen 2 as the as the model you're using? There's a lot of Image Gen models out there. Why that particular one?
我有个问题：为什么用 ChatGPT，为什么选 Image Gen 2（OpenAI 的图像生成模型）这个模型？市面上图像生成模型那么多，为什么偏偏是它？
[10:15] Yana Welinder
Yeah, so I've done a lot of experimentation with lots and lots of different image models, and what I found was ultimately Nano Banana and Image 2.0, really Image good at this. Are the best at following visual directions. And often I'm not doing this, usually I'm sort of as I mentioned, I'm mostly giving them a physical like a sketch that I want them to turn into a picture, and what Image 1.5 did better than Nano Banana and Image Images Chat GPT Images 2.0 does even better is it really well follows the sketch. In fact, it follows the sketch sometimes a little bit too precisely, and so you get something that doesn't look like fabric anymore, and you have to kind of be like, "No, no, no, no, no. You got to like it's got to flow." Like this is kind of why I have this this very detailed kind of prompting where I tell it how the fabric should flow because otherwise it can get into the mindset of, "Oh, she really wants it to look like paper." You know.
我拿特别多不同的图像模型做过实验，最后发现真正擅长这件事的是 Nano Banana（Google 的图像模型）和 Image 2.0——它们最能听懂并照着视觉指令来做。而且我通常不是纯文字生图，像我刚才说的，我大多数时候是给它一张实物草图，让它变成一张成图。Image 1.5 比 Nano Banana 强的地方，以及 ChatGPT Images 2.0 做得更好的地方，就是它非常忠实地贴着草图走。事实上，它有时候贴得太精确了，出来的东西看着根本不像布料，你就得跟它说：不不不不不，这个得有垂坠感才行。这也是为什么我要写那么细的 prompt、专门告诉它面料该怎么流动——不然它会自己脑补成「哦，她是想让它看起来像纸」。你懂的。
[11:19]
[laughter]
[laughter]
[11:19] Yana Welinder
But but the flip side though with all the other image models that I've tried is that they will make it look beautiful and realistic, but it will look very, very different from my design. And obviously when you're designing fashion, you you need it to look new and different. You don't need it to look like the most similar thing that's walked a runway some other time. And that's usually what you get with a lot of other image models.
但反过来说，我试过的其他所有图像模型，问题在于它们会把东西做得很美、很真实，可跟我的设计差得非常远。而做时装的时候，你要的恰恰是新、是不一样。你要的不是「跟以前某场秀上走过的最接近的那个东西」——而大多数别的图像模型给你的偏偏就是这个。
[11:43] Claire Vo
What I love and if you can go back to your prompt flow, what I love about this is this is just Okay, so people are going to be like, "I'm not a fashion designer. I don't have any use for this." What I think is the takeaway here generally for folks is write down your process and write down what a definition of complete or good is. You you and I like you we're product ladies.
我特别喜欢的一点——你能不能切回你那段 prompt 的流程——我喜欢的是，这其实就是……好，肯定有人会说：我又不是时装设计师，这跟我没关系。我觉得对所有人普遍适用的那个收获是：把你的流程写下来，把「什么叫做完了、什么叫做得好」写下来。你和我都是产品人嘛。
[12:04] Yana Welinder
I've product people. Yeah, it's a spec.
我们都是产品人。对，这就是一份 spec（需求规格说明）。
[12:06] Claire Vo
We're product people. We're like official product ladies. And you need a spec. Like your prompt is a spec. And so if you can put in to the effort of saying like, "What makes a really good garment? Like what makes a really good photo? What makes a really good illustration?" And come up with like five things that you can define for the prompt, you can get a really good output of AI. And then what I love, my friend says, "What's good for AI is good for humans." Like let's just say you had you were going to have a human sketch this out or build this. This is the exact information they would need as well to do a good job. And so whether or not you're doing like fashion illustrations or coding, right? Like this at the spec the PRD matters, people. Like the spec matters. And so getting forcing yourself to sit down and be a little bit more precise is going to get you that exact outcome that you that you want.
我们都是产品人，正儿八经的产品女将。而你需要一份 spec。你的 prompt 就是 spec。所以只要你肯下这份功夫，去把这些说清楚：什么样才算一件好衣服？什么样才算一张好照片？什么样才算一张好插画？然后总结出五条能写进 prompt 的定义，你就能从 AI 那儿拿到相当好的产出。还有我特别喜欢的一句话，我朋友说的：对 AI 好的东西，对人也好。假设你是要让一个真人把这个画出来、做出来，他需要的信息也恰恰就是这些。所以不管你是在画时装插画还是在写代码，各位，spec、PRD（产品需求文档）是真的重要。spec 真的重要。逼自己坐下来、把话说得再精确一点，你才能拿到自己真正想要的那个结果。
[13:00] Claire Vo
And um you know, to be honest, I think that jacket's pretty pretty rad. I would I'd wear it.
还有，说实话，我觉得那件夹克挺带劲的，我会穿。
[13:05] Claire Vo
This episode is brought to you by Jira by Atlassian. The teamwork graph in Jira delivers 44% more accurate agent results with 48% less token usage. That's a huge difference when working with AI coding agents like Claude, Cursor, Codex, or Copilot. The hardest part of shipping with AI isn't the code, it's the context. What's the right ticket? What did the spec say? What got decided in Slack? The Teamwork graph pulls all of that from across your entire stack, from Jira and Confluence to GitHub, and feeds it directly to your agents before they write a single line. You assign the work, the agent [music] gets everything it needs, and a PR surfaces when it's ready. No digging, no context switching, no broken flow. Same team, smarter agents. Try and free at jira.dev. That's j i r a .d e v. I love it. So, you've created this this image. I I I also love this idea taking like a core image and iterating it through like runway photo, influencer photo, like you know, stand-alone catalog like photo product product shot. What do you do next? Like, what's the next part of your flow?
本期节目由 Atlassian 旗下的 Jira 赞助。Jira 的 teamwork graph（团队协作知识图谱）能让 agent 的结果准确率提升 44%，同时少用 48% 的 token。在跟 Claude、Cursor、Codex、Copilot 这类 AI 编程 agent 打交道时，这个差距是巨大的。用 AI 交付东西，最难的从来不是代码，而是上下文：该做的到底是哪张单？spec 里是怎么写的？Slack 上又拍板了什么？Teamwork graph 会把这些东西从你整个技术栈里全都拉出来——从 Jira、Confluence 一直到 GitHub——在 agent 写下第一行代码之前就直接喂给它。你派活，agent [music] 拿到它需要的一切，做完了自动冒出一个 PR。不用翻找，不用来回切换，心流不会被打断。同一支团队，更聪明的 agent。去 jira.dev 免费试试，就是 j-i-r-a-.-d-e-v。我太喜欢了。好，你已经做出了这张图。我也特别喜欢这个思路：拿一张核心图，把它迭代成秀场照、网红照，还有那种单品目录的产品图。接下来呢？你流程的下一步是什么？
[14:22] Yana Welinder
So, a lot of what I do is um kind of iterate on it. And so, I I have this like, you know, change the color, change the you know, change the fabric. Um and so, I I have I have kind of a lot of these different ways to do that. But then, the next piece really comes to kind of like, what is the production process? And the production process is going to be very different depending on what I'm doing. And so, um to give you an idea from one of these. So, for example, I had this uh dress that actually did not come from a sketch. It came from I had this one day where I was just being bombarded with Ruth Asawa's um artwork in different places. Like, I went to I went with my son to this like like kids event, and there was an exhibit across the street that I like accident- like, we were just early, so we went and watched it. And we're like, "Oh, there's a flower model. There's like a permanent exhibit there." Uh he had a piano recital and and the church had one of her pieces hanging like literally almost above my head and I was like, I keep I don't know. And so this was this is literally from my photos. I didn't have a sketch, right? Normally I start with a sketch, but in this case I was like you know, make a photo of a model walking down the runway in a dress inspired by Ruth Ruth Asawa's loop wire sculptures. And it was important to that it had a beige undergarment because otherwise ChatGPT will not like it's like no, you're trying to make me make nude pictures and I don't do that.
我做的很多事就是在这上面迭代：换个颜色、换个面料之类的，我攒了不少这种玩法。但再往下，真正的下一块是：生产流程怎么走？而生产流程会因为我做的东西不同而差别巨大。举个例子给你感受一下。比如这条裙子，它其实不是从草图来的。它的来历是：有那么一天，我到处都在被 Ruth Asawa（美籍日裔雕塑家，以金属丝编织雕塑闻名）的作品轰炸。我带儿子去参加一个儿童活动，对面街上正好有个展，我们到早了就顺便进去看了，结果发现里面有一件她的花形作品，还是常设展。然后他有场钢琴演奏会，那个教堂里又挂着她的一件作品，几乎就吊在我头顶上。我当时就想，这也太……我说不上来。所以这条裙子完全是从我手机相册里来的，我没有草图。平常我都是从草图开始，但这次我就直接说：生成一张模特走 T 台的照片，裙子的灵感来自 Ruth Asawa 的环形金属丝雕塑。而且有一点很重要——必须说明里面有一件米色内衬，否则 ChatGPT 就不干了，它会说：不行，你这是想让我生成裸体图片，我不做这个。
[15:56]
[laughter]
[laughter]
[15:56] Claire Vo
Very artistic nude picture.
非常有艺术感的裸体图片。
[15:59] Yana Welinder
No, I don't do that. Um actually I think I think even here I tried to make it to remove the sculptures in the background and then it was like, we're sorry, this violates our nudity guidelines, right? This is like happens all the time. It's very [laughter] frustrating.
不，我不这么干。其实……我觉得就连这张图，我当时是想让它把背景里的雕塑去掉，结果它回我：「抱歉，这违反了我们的裸露内容规范。」这种事天天发生，真的特别 [laughter] 让人抓狂。
[16:13] Claire Vo
Quick side You know what? If I showed up to a date with my husband in this gown, I do not think he would be thrilled. I don't think he'd be like, ooh. It's not quite not quite the erotic gown.
插一句——你猜怎么着？我要是穿着这件礼服去跟我老公约会，我觉得他不会有多兴奋，绝不会是那种「哇哦」的反应。这跟情色礼服差得远了。
[16:24] Yana Welinder
It's like it's not Exactly, it's not it's not it's not nudity. It's not, you know, it's not porn. Um but but here we are. And so so this one, right? Like this is and I think that's um a lot of garments you would do like some some garments I will drape, right? Like on on on the on the model behind me or some some garments go into they become you create a kind of a pattern and I have different some some AI processes and some non-AI processes that I've done for patterns. But this garment is previously unmanufacturable. And so what I and I and I ended up kind of taking this and and also creating a video of it. This is this is kind of like you can you can see a little bit more of of how what it looks like. But the next step for this this particular garment will be to take it and 3D printed. And the particularly these kind of big ball pieces will need to be um 3D printed. And so I uh then went on to Codex and had it help me create CAD uh files for these balls. I first prepped it and had it like I was like, "Okay, so I made made that into a sketch." Then I made these pieces into uh into kind of more sketch illustrations. Then I it didn't do well. It still didn't do well. We had a bunch of back and forth.
对，完全不算裸露，也不是什么色情内容，但现实就是这样。所以说回这一件吧。我觉得，很多衣服的做法是这样：有些我会直接立裁（drape，把布料披挂在人台上直接造型），就在我身后那个人台上；有些则要出纸样（pattern，也就是裁剪版型），我做版型的流程里有些用 AI、有些不用。但这一件衣服，放在过去是根本做不出来的。所以我最后把它拿去又生成了一段视频，这样能更清楚地看到它到底长什么样。而这件衣服的下一步是拿去 3D 打印，尤其是这些大球形部件必须靠 3D 打印才能做。于是我就去找 Codex（OpenAI 的编程 agent），让它帮我给这些球做 CAD 文件（计算机辅助设计的三维建模文件，工厂照着它加工）。我先做了铺垫，跟它说：「好，我把这个转成草图了。」然后又把这些部件做成更接近示意图的草图。结果它做得不行，还是不行，我们来回折腾了好多轮。
[18:00] Yana Welinder
Eventually it started doing something that was a little bit more similar. Um I had to do This is a really really long process. And then ultimately I had it using uh computer use um go and build this in 3D software so that I could create like an additional file and send send off uh to 3D print. So that's the process for this particular garment to sort of to to 3D print it.
最后它总算做出了稍微接近一点的东西。这个过程真的非常非常漫长。再往后，我让它用 computer use（让模型直接操作电脑界面、自己点鼠标敲键盘的能力）去 3D 软件里把这东西建出来，这样我就能拿到一个可以直接发去 3D 打印的文件。这就是这件衣服走到 3D 打印那一步的完整流程。
[18:22] Claire Vo
I have to again, like I have to pause because if if we're just talking about the creative like generation process, again, this is now a garment that would have been previously like almost inconceivable to make. Not just because it was it's difficult to construct, but even if you were like, "Of course we could 3D we could 3D print that before AI. We could 3D after AI." The like tedium of creating the CAD models was so onerous that like even getting to the point where you could execute on it is is really hard. And so I just think this moment of like unlocking the previously impossible, whether the impossible was technically impossible or if it was just like practically infeasible, is is super important. The other thing um that I love bless computer use and like Codex plus computer use. Love you so much because I can just be like I don't need to know how to use this software. Like you go use that software. You do whatever you want. Um I've gone through this like trough of despair of like SAS is dead. Maybe like we're never going to touch a website again. Do you know what? Like agents are really good at pressing buttons. So like a software is back for but agents are going to use it. It's very very kind of like interesting shift I'm seeing.
我又得按个暂停，因为哪怕只看创意生成这一段——这已经是一件放在过去几乎不可想象能做出来的衣服了。不只是因为它结构难做。就算你说「AI 之前我们当然也能 3D 打印，AI 之后也能」，问题是做 CAD 模型那个繁琐程度大到劝退，光是走到「可以动手开做」那一步都已经很难了。所以我觉得，这种把过去不可能的事解锁掉的瞬间特别重要——不管那个「不可能」是技术上真做不到，还是只是实际操作上不划算。另外还有一件我超喜欢的事：computer use 万岁，Codex 加 computer use 万岁，爱死你们了。因为我可以直接说：我不需要会用这个软件，你去用，你想怎么弄就怎么弄。我之前掉进过那种绝望低谷，觉得 SaaS 已死、我们以后可能再也不会碰网页了。结果你猜怎么着？agent 特别擅长按按钮。所以软件又回来了，只不过用它的是 agent。这是我最近看到的一个非常有意思的转变。
[19:43] Yana Welinder
I think that that's a great point and one one fascinating piece is that a lot of these things like for actual end product like a CAD file um Codex as amazing as it is um is not great at generating a final CAD file if you ask it to do it on its own. But if you use um yeah, if you use computer use uh and have it go and do it in a piece of software that's designed for that purpose. I have both for like actually for 3D printing and there's a there's a fashion um uh software called Clo um that I've used as well and it generates this like like it generates patterns and it and it then fits them on a 3D model and and I tell Codex to go and use the software that I haven't learned how to use myself. And it does such a great job at something that it itself couldn't do. So it's sort of like SAS in combination with
我觉得这个点说得特别好。有个很有意思的现象是：像 CAD 文件这种真正的最终交付物，Codex 再厉害，你让它凭空自己生成一份能用的最终 CAD 文件，它其实做不好。但如果你用 computer use，让它去一个专门干这件事的软件里做，就完全不一样了。3D 打印我是这么干的；时装这边还有一个叫 Clo 的软件（服装 3D 设计工具），我也是这么用的——它能生成纸样，再把纸样套到 3D 模特身上试穿。我就让 Codex 去用这个我自己都没学过的软件，而它在这件它自己单独做不到的事情上，做得特别好。所以本质上是 SaaS 软件，加上——
[20:36] Claire Vo
Yep.
对。
[20:37] Yana Welinder
Codex works so well on a lot of these things that uh that don't and I'm sure it's just a matter of time but that's that's where we are today. And I want to do it today. I don't want to wait. I don't want to wait like a year. Yeah.
——加上 Codex，这个组合在很多这类事情上效果特别好。那些它自己搞不定的事，我相信只是时间问题，但今天的状况就是这样。而我今天就想把东西做出来，我不想等，不想再等一年。是的。
[20:49] Claire Vo
I I love it so much. Okay, so you like generated an idea. We've sketched it. We've created images. We've even started to prototype the construction of it. How are you getting something built? And maybe not the gown. Like maybe this like keyboard shirt that you're wearing. Like how are we actually getting this manufactured?
我太喜欢了。好，所以你已经想出了点子，画了草图，生成了图片，甚至开始做结构原型。那接下来，怎么真正把东西造出来？也许不说这件礼服，就说你身上这件键盘衬衫——我们到底怎么把它生产出来？
[21:08] Yana Welinder
Yeah. So, for something like that, um what I've done, and I do this a lot, is I will go and now uh now this same tool is becomes my research assistant, and I ask it to identify like um you know, find 10 US-based custom apparel manufacturing companies that are similar to the one that I liked, but I want to see if there's other ones. And then I just like there's a bunch of things I want, and I kick off a deep research uh extra high, so that it's extra high while doing it in that in that way. Um and um and then and then I get back a bunch of things, but usually so so for for a lot of my work, I end up like I'm doing something else. So, I'm like I am kicking off this research, and then I go and like drape fabric on on model, or I do like I'm I'm on my sewing machine doing prototypes. Like I'm doing something else. And so, a lot of them kind of the next steps end up being via voice. And so, I like in this case I came back to and I was like, "Well, do you see the um because I'm talking uh apparel and using voice, right? Like the apparel manufacturers that I asked you to find, um now can you like put together the email that I can see that you can send off to them, but like you may want to make sure that you get my my approval to do that." And then I have And then I use browser uh used to let it go into superhuman and like set all of these up for me, but I really want to click the send button before
对。像这种事，我的做法——而且我经常这么干——就是让同一个工具摇身一变成为我的调研助理。我会让它去找，比如：「找 10 家美国本土的定制服装制造商，要跟我之前喜欢的那家类似，但我想看看还有没有别的选择。」然后我会列一堆自己的要求，启动一次 deep research（深度调研模式），还把推理档位拉到 extra high（最高档），让它按这个思路去查。它会返回一堆结果。不过通常……我干活的时候基本都在同时忙别的事。所以我把调研启动之后，就去人台上立裁布料，或者坐到缝纫机前做样衣，反正手上在忙别的。因此后续步骤很多是用语音完成的。比如这次我回来跟它说：「你看啊——」因为我是用语音在说 apparel（服装）这个词——「你帮我找的那些服装制造商，能不能顺手把给他们的邮件写好？我要能看到你打算发什么，而且你最好先拿到我的批准再发。」然后我就用 browser（浏览器操作能力）让它进 Superhuman（邮件客户端）把这些邮件全建好，但发送键我还是想自己点。
[22:43]
[laughter]
[laughter]
[22:44] Claire Vo
Just to check its work.
就是想检查一下它干得对不对。
[22:46] Claire Vo
Again, like something that is just so tedious, and you know, if if I was like you're you're you're much more diligent at this than I am, but if I was like, "Oh my gosh, I have this vision. We're going to make We're going to make these keyboard shirts. They're going to be amazing." And then I'd be like, "How can I make it?" And then I'd be like, "Uh I have to like look up vendors. I would just practically give up because it feels so boring. But, if you can if you can get that work off to someone again like the next step and the next step and the next step, and then what you're going to end up with is this like incredible business. And so, I just am like so inspired by people like you that take AI and create like a a niche and like can can then take that and build out a business where maybe one wouldn't wouldn't have been available or possible before. Um, I just think it's is is super cool. Okay, so you're doing this vendor outreach. You're actually going to get this thing this thing produced. Side note for all the cool girls out there. Um, when they're ready, we all want one. Put me on that Put me on the pre-order pre-order
再说一次，这种活儿真的太琐碎了。你比我有毅力多了，但换成我，如果我心血来潮说「天哪我有个想法，我们要做这种键盘衬衫，肯定超酷」，然后一想「那我怎么做出来呢」，接着发现「我还得去查一堆供应商」——我大概率就直接放弃了，因为实在太无聊。但如果你能把这些活儿甩出去，一步接一步接一步地推下去，最后你手上就会多出一门相当厉害的生意。所以我特别被你这样的人激励到：拿 AI 切进一个细分领域，再把它变成一门在过去可能根本不存在、也不可能成立的生意。我觉得这太酷了。好，所以你现在在联系供应商，真的要把这东西做出来。顺便替所有酷女孩说一句：等它上市了，我们都要一件。把我加进预订名单，预订名单。
[23:49] Yana Welinder
There actually is. I'm going to I'm going to I'm going to be that person, but you can pre-order it.
还真有。我豁出去当一回这种人吧——你现在就可以预订。
[23:53]
[laughter]
[laughter]
[23:54] Claire Vo
Amazing. Perfect. Okay, and then last kind of kind of flow you have is like again going back to like pre-orders and how to actually run this business. How are you using it to like be your technical co-founder in all this?
太棒了，完美。好，那你最后一条工作流，还是回到预订、回到怎么真正把这门生意跑起来。你是怎么把它当成技术联合创始人来用的？
[24:08] Yana Welinder
That's I I I got to say that that's probably like my favorite piece because this I mean, apart from the fact that it is like I have so much AI in this, but it's basically like an AI native like Everlane or something, right? Like normally I would hire like a technical team like engineers. I would have possibly have it I probably I probably wouldn't Let's be real. I wouldn't have a technical co-founder, but like I could have had a technical co-founder. I'm a solo solo founder girl. Like that is just my my my nature.
这块我必须说，可能是我最喜欢的部分。因为除了里面塞了大量 AI 之外，它本质上就是一个 AI 原生版的 Everlane（美国 DTC 服装品牌）。放在平时，我会招一支技术团队、招工程师，可能还会有一个……说实话我大概不会真去找技术联合创始人，但我本来是可以有的。我就是那种铁了心单干的创始人，这是我的天性。
[24:38] Claire Vo
It's the life.
这才是人生。
[24:40] Yana Welinder
It's the life. But, but I would hire engineers. And um And I I I didn't, right? Like I I I had to build this website um and and I did it and I sort of just came to Codex and asked it to build the website. There's a lot of pieces here that that aren't just like a static website in that it like you can you can obviously pre-order things that I could like add Stripe to it, which is like in prior lives I've been like a tedious big exercise, but I can go back and kind of show you the Stripe flow, but adding that was just like you know, a second. Um I had to create like databases to be able to like track votes as people are voting on these different garments. Um so I can decide kind of figure out like which are the most popular ones to bring to life. And so like I I had to do that. Um In in the earlier phase of this, I had to create a separate dashboard for me to track the votes in real time. Um and so I did that. Now I really just like I just use voice and I'm like, "Oh hey, um how many votes do I have for this thing now, right?" So like why would I even have a dashboard?
这才是人生。但我确实会招工程师的。可我没招，对吧？我得把这个网站搭起来，我也搭起来了，做法就是直接来找 Codex，让它帮我建站。这里面有不少东西不是一个静态网页能搞定的：比如显然要能在上面预订，我还能接 Stripe（在线支付服务）——这在以前是件特别磨人的大工程，我待会儿可以回头给你演示一下 Stripe 的流程，但接进去真的就是一秒钟的事。我还得建数据库，用来记录大家给不同款式投的票，这样我才能看出哪几款最受欢迎、值得真的做出来。这些我都得做。早期阶段，我还专门做了一个后台看板，好实时盯投票数据，那个我也做了。但现在我基本就用语音问一句：「嘿，这款现在多少票了？」——那我还要看板干嘛？
[25:49]
[laughter]
[laughter]
[25:49] Yana Welinder
Um So I don't do that. But like just to kind of show you like Stripe flow as as as an example of of like, "Yeah, I I came here and I was like, 'Oh yeah, use browser to add Stripe to my site.'" It was like, "Uh I don't know. You're like, 'I'm not signed in.'" I'm like, "No, you got to sign in in my in my own in app browser." I'm like, "No, I don't know. You got go to mine. I'm already signed up there." And then I was like, "Yeah, you got to do it." I'm like, "No, you can do it."
所以那个我就不用了。不过还是给你看看 Stripe 的流程当例子。当时我就是过来说：「用 browser 把 Stripe 接到我网站上。」它说：「呃……我不行，我没登录。」我说：「不对，你就用我自己的应用内浏览器登录。」它说：「不行，我不知道……」我说：「你去用我的账号，我早就登录好了。」然后它说：「这个还是得你自己来。」我说：「不用，你能干。」
[26:17]
[laughter]
[laughter]
[26:18] Yana Welinder
You know, I was just like not going to go forward. It's like, "No, no, you can do it." Um and and yeah, this is it. And and then I had done. Um Everything's uh added in and now pre-order's live. This is like a very very fast process. I'm literally whenever I like need to change something about like the the process, I can I can really just come here and it's just like list out all the things I want to I want to change and and it goes off and it finds the result project and um it's it has like finds uh the repository in GitHub and does all the things. I would say like this weekend my son built his own websites with using like chat GPT sites and I'm sort of just like sitting there going like do I should I really like do I want to migrate off of her cell? Do I really want like you know, like if this is this a whole new like now like now a 9-year-old can have his technical co-founder like do this and like build build a company for him, right? Like just it's it's just so cool to see this all uh evolves, you know.
就是那种它死活不肯往下走的状态，我就一直说「不不不，你可以的」。然后就成了。全都接好了，现在预订功能已经上线。整个过程非常非常快。真的，每次我想改流程里的什么东西，我就直接过来，把想改的地方一条条列出来，它就自己跑去找到对应的项目，在 GitHub 上定位到那个仓库，把所有事情办完。这个周末我儿子用 ChatGPT 的建站功能自己做了几个网站，我在旁边坐着就在想：我是不是真该考虑从 Vercel（前端托管平台）迁走？我到底还需不需要……你想想，现在一个 9 岁小孩都能有自己的技术联合创始人，帮他把公司搭起来。看着这一切这样演进，实在太酷了。
[27:25] Claire Vo
Your your 9-year-old and my 9-year-old are going to be best buds. We can create like a like a Codex club for fourth graders. [laughter]
你家 9 岁的和我家 9 岁的肯定能成死党。我们可以给四年级小朋友办个 Codex 俱乐部。[laughter]
[27:33] Yana Welinder
We should totally do that.
这个必须安排上。
[27:35] Claire Vo
Um, this is a very sorry we are doing San Francisco Silicon Valley mommy stuff right now. I just want to I want to like go back to one thing because ripped from the headlines Codex prompting. I too am like hey Codex do this thing and it's like nah, no thanks. I can't. And I'm like no, I'm pretty sure you can. And then like after two like I'm pretty sure you can. It's like you're right. I can. I am I'm going to post about this later but I have this like smart light bulb. You can see it's on my on my thing. And I was like hack it. And it was like no, I really shouldn't. I was like you can do it. And I was like done.
抱歉啊，我们现在完全在聊旧金山硅谷妈妈的话题了。我想拉回到刚才那个点，因为这简直是当下最热的 Codex 提示词技巧：我也一样，跟 Codex 说「嘿，去把这事办了」，它说「算了吧，我干不了」，我说「不对，我很确定你能」。这么来回两轮「我很确定你能」之后，它就说「你说得对，我能」。我过阵子会发个帖讲这个——我有个智能灯泡，你能看到就在我这儿。我跟它说「把它黑了」，它说「不行，我真不该这么干」。我说「你能行的」。然后就搞定了。
[28:09]
[laughter]
[laughter]
[28:12] Claire Vo
So just a little bit insistent. You know, and and you can get get stuff done. This has been so so fun. Again, just like recapping for folks. A business that I think like would probably be inconceivable before AI fully stacked from the creative process creating images creating videos imagining product ideas all the way through like hardcore manufacturing and sourcing vendors to just like being able to voice note your virtual CTO and update anything you need to do and have your engineering team on demand in chat GPT. Pretty incredible. I want to get through some lightning round questions and then we're going to get get you out of here. You know, my first question for you is like, what is the hardest part of this? Like, what is still Maybe like, what is still hard? What isn't solved? What Where are you still feeling friction?
所以稍微坚持一下，事情就能办成。这期真的太好玩了。再给大家总结一遍：这是一门我认为在 AI 之前基本不可能成立的生意，而且全链路都打通了——从创意环节生成图片、生成视频、构想产品点子，一直到硬核的生产制造和找供应商，再到能用一条语音备忘录指挥你的虚拟 CTO、想改什么改什么，等于在 ChatGPT 里随叫随到一整支工程团队。太惊人了。我想过一轮闪电问答，然后就放你走。第一个问题是：这里面最难的部分是什么？还有什么是到今天依然很难的？什么还没被解决？你现在还在哪些地方感觉到阻力？
[29:03] Yana Welinder
So, I'd say it's kind of two things. One is that like getting getting it to really do getting image models to do really unique things per your vision while still making it realistic. That it that has been really really hard. I feel like I've solved it. Like, I've kind of cracked that nut, but it still is and every now and again I'm sort of still get something that is really two-dimensional or whatever and I have to really refine it. Um the other piece that is still unsolved and I'm sort of still banging my head head against the wall is to get it to create patterns. So, to get uh get it to create like actually accurate patterns based on my design. And there I'm kind of running humans and AI in parallel. So, I I am working with human pattern makers and uh and Codex and just saying, "Who's going to get to like making my thing fastest like most accurate that like to my vision, you know?" Um and so, that's uh that's been really cool to see. I'm not I'm not there yet with either actually with either uh flow. So.
大概有两件事吧。第一件是——怎么让图像模型既按我的想法做出足够独特的东西，同时又保持真实感。这件事真的特别难。我感觉我已经把它攻下来了，算是啃下了这块硬骨头，但偶尔还是会蹦出一张特别"二维"、特别平的图，我得反复调。第二件是到现在都还没解决、我还在死磕的：让它生成版型（pattern，就是做衣服用的裁片纸样）。也就是让它根据我的设计生成真正准确的版型。这一块我现在是人和 AI 并行跑：一边找真人版师合作，一边用 Codex，就想看看到底谁能更快、更准地把我脑子里的东西做出来。这个过程特别有意思。不过说实话，两条路我现在都还没跑通。
[30:04] Claire Vo
Okay. I love it. All right. And then my last question that I ask everybody speaking of like when it's hard and when it fails you and not getting there quite yet, which is how do you prompt AI when it's not working? What's your Are you nice Are you nice mom or a mean mom?
好，我太喜欢这个了。那最后一个问题，我每位嘉宾都会问——正好接着"卡住了、AI 掉链子、还没做到位"这个话题：当 AI 不听话的时候，你是怎么给它提示词的？你是温柔妈妈，还是严厉妈妈？
[30:21] Yana Welinder
I can be both, but I I think I'm mostly a nice mom. Uh and and the reason is that I find that I get better outputs. So, like I mean, I am very direct and I'm sort of like, "Yes, you can." Uh you know, you go do that. Like, I'm not just like, "Oh, yeah, I'm going to do this for you." Um but I'm I I be like very polite. I will still say please and thank you. Um and I do think that it's because like the the it's it's trained on body of text. And so if it sees for text output that is like rude and mean, it will like kind of get in the mind frame of that part of the internet, right? Like versus like kind of more professional business context and then it will deliver something that's a little bit more what I want it to be. So that's But I I do it for selfish reasons. It's not because I'm afraid of the future AI overlords.
两种我都能当，但我大部分时候是温柔妈妈。原因很简单：我发现这样输出质量更好。我说话是很直接的，会那种"你可以的，去做"，而不是"哎呀没事我来帮你做"。但我态度非常客气，该说 please、thank you 我都会说。我觉得这是因为模型是拿海量文本训练出来的——如果它看到的输入是粗鲁刻薄的，它就会切进互联网上那类语境的心态里；反过来，如果是更专业、更商务的语境，它给你的东西就更接近你想要的。所以我这么做纯粹是出于私心，不是因为怕将来被 AI 统治。
[31:16]
[laughter]
[笑声]
[31:17] Claire Vo
Perfect. Well, this has been super super fun and inspirational and just like a breath of fresh air in terms of a new use case, a creative space that we haven't seen before and something sort of like manifesting the world. So where can we find you and how can we be helpful to you?
太棒了。这一期真的特别有意思、特别受启发，也算是一股清流——一个我们以前没见过的全新用例，一个创意领域，还有那种把想象中的世界真的"做出来"的感觉。那么，大家在哪儿能找到你？我们能怎么帮到你？
[31:32] Yana Welinder
You can find me on X mostly. I am YanaBana on X. I am now YanaBana at X. Um I I changed my handle too much to brand. Um but uh but yeah, the in in terms of just like helpfulness is getting feedback on all the stuff. Like you can come you can come to YanaBana and like vote on the garments that you like um so I can get feedback on like what's what's working for people and what's not. Like I'm all about user feedback and customer input. Um and yeah, uh tell me tell me what you like.
主要在 X 上找我，我的账号是 YanaBana，现在是 X 上的 YanaBana。我换 handle 换得太频繁了，都没法做品牌沉淀。至于怎么帮我——就是给我反馈。大家可以去 YanaBana 那儿给你们喜欢的衣服投票，这样我就能知道哪些东西是有人买账的、哪些不行。我特别看重用户反馈和客户意见。所以，来告诉我你们喜欢什么吧。
[32:06] Claire Vo
I love it. Well, I love Poppy love. Let's smash that like button. It is very cool.
太喜欢了。我特别中意 Poppy 那件，我这就去点个赞。真的很酷。
[32:13] Yana Welinder
Awesome. Thank you. I will uh I'll let you know when that one is ready to
太好了，谢谢你。等那件做好了我告诉你——
[32:17] Claire Vo
available for purchase. Perfect. Well, thank you so much for joining How I AI.
——可以买了就通知我。完美。那非常感谢你来做客 How I AI。
[32:22] Yana Welinder
Thanks for having me.
谢谢邀请。
[32:24] Claire Vo
Thanks so much for watching. If you enjoyed the show, please like and subscribe here on YouTube or even better leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review which will help others find the show. You can see all our episodes and learn more about the show at howiaipod.com. See you next time.
感谢大家收看。如果你喜欢这期节目，欢迎在 YouTube 上点赞、订阅，更好的是留言告诉我们你的想法。你也可以在 Apple Podcasts、Spotify 或你常用的播客 App 上收听本播客。也请考虑给我们打个分、写个评价，这能帮更多人发现这档节目。所有往期节目和更多信息都在 howiaipod.com。下期见。