Everyone's Using Claude. This PM Tool Does More

频道: Aakash Gupta
视频: https://www.youtube.com/watch?v=tTTG1Nn-kkw
原文语言: en
统计: 共 70 轮 · Meng 43 · Aakash 26

[0:00] Meng

Eventually, you will get fired because AI will replace everyone at some point or we will find new ways to to do our job.

总有一天你会被裁掉，因为 AI 迟早会取代所有人——或者说，我们会找到全新的工作方式。

[0:06] Aakash

What are the things that a PM needs to know if they're going to go from PM to founder [music] to really succeed?

一个 PM 如果想从产品经理转型去做创始人，要真正成功，需要掌握哪些东西？

[0:12] Aakash

When we say that PMs are getting fired, I think it's important to clarify that it's the non-technical PMs that are getting fired. The technical PMs are actually staying at those companies. Maybe my favorite voice online is Mangto. He has been publishing design guides [music] for years on YouTube, on Twitter. I've been following him and he's going to break down for you as a product manager what are the top use cases of these AI tools [music] and more importantly beyond the surface guide of how to use them how do I use them well I think that people who are stuck in chat GBT [music] haven't realized that this can connect to all of your existing apps if you're using it in codeex

当我们说 PM 正在被裁的时候，有一点必须澄清：被裁的是非技术型 PM，技术型 PM 反而都留在了那些公司。Meng To 可能是我在网上最喜欢的声音之一，他多年来一直在 YouTube 和 Twitter 上发布设计教程，我一直关注他。今天他会站在产品经理的视角，为你拆解这些 AI 工具的顶级用例——更重要的是，不只停留在"怎么用"的表面教程，而是讲怎么用好。我觉得那些还停留在 ChatGPT 里的人，还没意识到它可以连接你现有的所有应用——只要你是在 Codex 里用它。

[0:47] Meng

absolutely everything [music] you can think of you can imagine anything that fits your workflow can be done in codec [music] and you can now use computer use

真的是任何东西——你能想到的一切，任何契合你工作流的事情，都可以在 Codex 里完成，而且现在还能用 computer use（让 AI 操作电脑）。

[0:55] Aakash

everybody is just cloud cloud cloud all the time

现在所有人张口闭口都是 Claude、Claude、Claude。

[0:57] Aakash

I'm not a big cloud user. I'm more of an open eye person. I'm all in on codeex and I've been using it every single day. They have this whole ecosystem around image 2.0. I think that every PM should know about this. Before we go any further, do me a favor and check that you are subscribed on YouTube and following on Apple and Spotify podcasts. And if you want to get access to amazing AI tools, check out my bundle where if you become an anal subscriber to my newsletter, you get a full year free of the paid plans of Mobin, Arise, Relay app, Dovetail, Linear, Magic Patterns, Deep Sky, Reforge, Build, Descript, and Speechify. So, be sure to check that out at bundle.ac.com. And now into today's episode.

"我不算 Claude 的重度用户，我更偏 OpenAI 阵营，全面押注 Codex，每天都在用。他们围绕 Image 2.0 有一整套生态，我觉得每个 PM 都应该了解。"在继续之前，请帮我个忙：确认你已经在 YouTube 上订阅，并在 Apple 和 Spotify 播客上关注了本节目。如果你想拿到一批超棒的 AI 工具，来看看我的订阅礼包——成为我 newsletter 的年度订阅用户，就能免费获得整整一年的付费版：Mobbin、Arize、Relay.app、Dovetail、Linear、Magic Patterns、Deep Sky、Reforge、Build、Descript 和 Speechify。记得去 bundle.aakashg.com 看看。现在进入今天的正片。

[1:50] Aakash

Mang, thank you so much for lending your expertise to the podcast and welcome.

Meng，非常感谢你来播客分享你的专业经验，欢迎你。

[1:54] Meng

Thank you. And uh this is going to be a deep dive into Codeex. I've been using this since day one, but also before Codeex came out just like 4 months ago. I've been, you know, building apps, uh, you know, using agents and doing AI for a long time. So, I'm going to be be sharing with you all my secrets. Uh, this is going to be a unique perspective. A lot of P PM's gonna want to hear about this because it covers every single piece of the workflow from, you know, prompting using what tools to use. If you only get out of this podcast, like what are the tools I'm supposed to use or what are some of the basic prompts? Uh I think that's enough value. So, I'm going to but I'm going to do a deep dive. I'm going to show you all the demos, the images that I'm creating, the videos, and you know, uh the HTMLs. Uh it's going to be a deep dive.

谢谢。这一期会是一次对 Codex 的深度拆解。我从 Codex 上线第一天就在用了——它也就是四个月前才发布的。但在那之前，我就已经做了很久的应用开发、用 agent、玩 AI。所以我会把我所有的秘诀都分享出来。这会是一个很独特的视角，很多 PM 都会想听，因为它覆盖了工作流的每一个环节：怎么写 prompt、该用什么工具。哪怕你从这期播客只带走两样东西——"我该用哪些工具"和"有哪些基础 prompt"——我觉得就已经很值了。但我还是会往深了讲：给你们看所有的 demo、我做的图片、视频，还有那些 HTML 页面。这会是一次真正的深潜。

[2:44] Aakash

Amazing. That's what we like here. Try to going the layer deeper than the surface. So, what are the best tools for AI design? You use them all right now. What are the ones you like the most?

太棒了，这正是我们节目想要的——比表面再深挖一层。那么，AI 设计的最佳工具都有哪些？你现在全都在用，最喜欢的是哪几个？

[2:55] Meng

Yeah. So, I'm basically all in on codecs right now. And uh I know a lot of people they love cloud code. Some people still they love cursor. I think cursor is amazing. I'm not saying that as as a bad thing. I used to be a huge cursor user before OpenAI came up with codecs which basically changed the whole mindset around you know not just building but also starting projects and starting chats around those projects but also we have like open claw which recently completely take over the world became the number one GitHub project of all time. So this is taking the world by storm and every single of these tools are like influencing each other to create the next best thing and right now I feel like at the epicenter of everything we have anthropic and then we have open AI with codeex.

好。我现在基本上是全面押注 Codex。我知道很多人钟爱 Claude Code，还有些人依然爱 Cursor——Cursor 确实很棒，我不是在说它不好，我以前就是 Cursor 的重度用户。直到 OpenAI 推出了 Codex，它彻底改变了大家的思维方式：不只是怎么写代码，还包括怎么启动项目、怎么围绕项目开启对话。另外还有 OpenClaw，最近彻底火遍全网，成了 GitHub 史上 star 数第一的项目。这股浪潮席卷了整个行业，这些工具彼此影响、互相催生出下一个更好的东西。而在我看来，现在整个风暴的中心，一边是 Anthropic，另一边就是 OpenAI 和它的 Codex。

[3:49] Aakash

Amazing. I feel like sometimes I am a claude code channel so it's a breath of fresh air to see codeex. Can you fire it up? Can you show us how you use codeex and how to set it up so that it is used in the best possible way?

太好了。我有时候觉得自己简直是个 Claude Code 频道，所以看到 Codex 反而是一股清流。你能把它打开吗？给我们演示一下你是怎么用 Codex 的，以及怎么配置它才能发挥出最大威力？

[4:05] Meng

Sure. All right. So, obviously I'm going to be covering codeex which for those who don't know is basically the chat GBT but 10x like on stero steroids basically. So you can not just chat within AI but you can you know uh create slides, create HTMLs, uh create full websites, make your mobile apps everything. And then one thing that I I mentioned that I you should definitely take out of this is you should use an AI browser. So the one that I'm using again from OpenAI is called Atlas. And basically what is really cool about this is for me context is king. So anything that you have that is context is super useful. So you're browsing something, you want to ask a question, you have the ask button and you can also let the AI agent take over your computer and just start using it. Uh so you know at first I just want to go over the tools. I think it's super important to give you an an idea. So, also Whisper Flow, which I, you know, I'm sure a lot of people use it. I heard about it. Basically, instead of typing everything, you want to use your voice. And Whisper Flow is the fastest one. It has the best accuracy. And, uh, you want to deal with dictionaries, words that are hard to use. So, that's very good. For PMs especially, you want to use something like obsidian because when you use something like codeex or cloud code, you're creating a ton of documents, tons of documents locally. Uh especially on an open claw kind of introduce that workflow where everything happens locally because you have a ton more context and the AI has a ton more power because it doesn't have to rely on an internet connection or a a private database somewhere, but everything on your computer is private. It's super super powerful and they also have this feature where you know it's kind of like a brain tree of the whole information the whole context around every document that you have done so far basically your whole life. So this is super important.

当然，好的。我要讲的当然是 Codex——不了解的朋友可以把它理解成 ChatGPT 的 10 倍强化版，打了鸡血的那种。你不只能和 AI 聊天，还能做幻灯片、做 HTML 页面、建完整的网站、开发移动应用，什么都行。还有一件我特别想让你们记住的事：一定要用 AI 浏览器。我用的同样来自 OpenAI，叫 Atlas。它真正酷的地方在于——对我来说，context（上下文）为王。任何能成为上下文的东西都极其有用：你正在浏览一个页面，想问个问题，直接点 Ask 按钮就行；你也可以让 AI agent 接管你的电脑，直接替你操作。一开始我想先把工具过一遍，我觉得先给你们一个全貌很重要。还有 Wispr Flow，相信很多人用过或听说过——就是用语音代替打字。Wispr Flow 是最快的，准确率也最高，还能维护自定义词典，处理那些难拼的词，非常好用。对 PM 来说，尤其推荐用 Obsidian 这类工具，因为当你用 Codex 或 Claude Code 时，你会在本地生成海量的文档。特别是 OpenClaw 带火了这种工作流：一切都在本地进行。这样你有多得多的上下文，AI 也强大得多，因为它不依赖网络连接或某个远程私有数据库，你电脑上的一切都是私密的，非常非常强大。Obsidian 还有一个功能，有点像一棵"大脑之树"，把你迄今为止所有文档的全部信息和上下文——基本上就是你的整个人生——连成一张知识图谱。所以这一点非常重要。

[6:00] Meng

Now what I use I use my own tool and I know a lot of people a lot of people including PMs especially technical PMs which I've always been a technical person even as a designer I'm like one of the first designers who started teaching designers to code uh and that's a real story like I started my career almost like that and uh basically I built every single tool that I use including my own video editor I build my own uh you know SAS project where I build websites from scratch and templates which I have a ton of videos about. I build my own sort of design brainstorming tool using HTML. And as I mentioned before, I build my own video editor as well. And the reason why I do this is very simple because every human has a very unique set of needs. And in order to solve that the only way is one to experience those frustration and second to go through the experience of solving those frustrations and so you have a tool like codeex which gives you all of these superpowers and you want to solve them and therefore you know every time that I have like let's say a podcast I have a prep document that I you know I talk to my codeex and it creates all of this stuff and so you can see, you know, like it gives me the hooks, it gives me all the demos, you know, all the talking points, the research, and then we we're going to get into, you know, creating charts, creating uh storyboard, you know, and the prompts to use them. And uh one thing I love is also generating avatars because you know if a lot of people are are loom users for example they go into meetings and they want to record themselves like training something instead of having to go to these meetings they record it privately and then they give it to their team. So having an avatar is super important. Uh and nowadays we have AI that does all of this stuff. So again, you know, this is my entire workflow and this is what everything that we're going to cover.

至于我自己用什么——我用自己造的工具。我知道很多人，包括 PM，尤其是技术型 PM……我自己一直就是个技术型的人，哪怕身份是设计师。我算是最早开始教设计师写代码的设计师之一，这是真事，我的职业生涯几乎就是这么起步的。基本上，我用的每一个工具都是自己造的：包括我自己的视频剪辑器；我自己的 SaaS 项目，从零开始搭网站和模板（这方面我有一大堆视频）；我还用 HTML 搭了自己的设计头脑风暴工具；刚才说过，视频剪辑器也是自己写的。我这么做的理由很简单：每个人的需求都是独一无二的，要解决它，唯一的路径是：第一，亲身经历那些挫败感；第二，亲手走完解决这些挫败感的全过程。而现在你有了 Codex 这样的工具，它给了你所有这些超能力，你自然就想去解决它们。所以比如说，每次我要录播客，我都有一份准备文档——我跟我的 Codex 聊一聊，它就把所有东西生成出来。你看，它给我准备了 hook（开场钩子）、所有的 demo、全部谈话要点、调研资料。接下来我们还会讲到怎么生成图表、做 storyboard（分镜脚本），以及配套使用的 prompt。还有一个我很喜欢的：生成 avatar（数字分身）。比如很多人是 Loom 用户，他们本来要进会议室去录一段培训，现在可以不去开会，私下录好再发给团队。所以有一个 avatar 非常重要，而如今 AI 能把这些全搞定。总之，这就是我的完整工作流，也是我们今天要讲的全部内容。

[8:10] Meng

And like I said, I just wanted to start with this because if you're taking any value out of this podcast is all of these tools that I'm showing right now. Just like Google them, downloading them is just enough to get a ton of value. And then I'm going to uh switch to the codeex. I'm going to start from scratch.

就像我说的，我之所以先讲这些，是因为如果你要从这期播客带走什么价值，那就是我刚展示的这些工具——把它们 Google 一下、下载下来，光这一步就已经能拿到巨大的价值了。接下来我切到 Codex，从零开始演示。

[8:29] Aakash

Awesome. And while you're doing that, I wasn't totally clear on two things. One was how Obsidian plays in. Maybe I just missed the connection. And then the second was how an avatar helps you with Loom videos.

太好了。趁你操作的时候，我有两个地方没完全听明白：一个是 Obsidian 在整个流程里扮演什么角色——可能是我没跟上那层联系；另一个是 avatar 是怎么帮你做 Loom 视频的。

[8:43] Meng

Okay, so I've never shown this to anyone outside of our team, but this is my codeex, my real codeex. It's not a demo one. And these are all my projects. So uh for example, I have content. And this is a project. And all of these are local folders. And I just want to answer your questions first before we get into the step by step of getting started with codeex. Obviously at this point I assume that you already downloaded codec. And the idea is that when you talk to AI, right, you ask a lot of changes or you know you want it to write documents or you want to fix issues, you want to fix and move pixels and sometimes you want to plan YouTube videos and sometimes you want to uh you know draft prepare a podcast and what's happening here is that oftent times it's going to generate these documents and these documents are like content.md right And this is how you consume the content. And uh this is great. Codex has everything. It's like an all-in-one apps. It can read your HTML. You can open your HTML. You can open your MD files. You can open the the images. It's going to go into full screen. You can can open your code changes and all that stuff. However, you have to understand that all of this stuff also exists on your computer. And you're not always going to go back to your codeex to find these documents. So you need a way to organize all of these documents somewhere. And this is where Obsidian comes in because Codeex, yes, it does a lot of this stuff, but Obsidian is going to allow you to organize your documents, your knowledge base and the brain tree. And you know, you can always reference to the Obsidian uh content, which by the way are basically just folders. And again, this is the superpower that kind of open claw uh introduced to the world is that everything has to be local. Everything has to exist on your computer first and the rest is for all of these apps to digest that content. So for example, you know, if it's talking about a coding project, well, you need HTML, you need React, you need, you know, a a browser.

好，这个东西我从来没给团队以外的任何人看过——这是我的 Codex，我真实在用的 Codex，不是演示用的。这些全是我的项目。比如说，我有一个 content（内容）项目，这些项目其实都是本地文件夹。在进入 Codex 上手教程之前，我想先回答你的问题。当然，到这一步我默认你已经把 Codex 下载好了。核心的想法是这样的：你跟 AI 对话的时候，会提各种各样的改动需求——让它写文档、修 bug、调整像素级的 UI 细节，有时候是策划 YouTube 视频，有时候是准备一期播客的草稿。这个过程中经常发生的事情是，它会生成一堆文档，比如 content.md 这样的文件，而这些文档就是你消费内容的方式。这一点非常好，Codex 什么都有，就像一个全能应用：它能读你的 HTML，你可以直接打开 HTML、打开 MD 文件、打开图片，还能进全屏，可以查看代码改动等等。但你要明白，所有这些东西同时也存在于你的电脑上，而你不会每次都回到 Codex 里去翻这些文档。所以你需要一个地方把这些文档统一组织起来，这就是 Obsidian 的用武之地。Codex 确实能干很多事，但 Obsidian 能帮你组织文档、知识库和你的'大脑树'，而且你随时可以引用 Obsidian 里的内容——顺便说一句，那些内容本质上也就是文件夹。再强调一次，这就是当初 OpenClaw 带给世界的超能力：一切都必须是本地的。所有东西都要先存在于你的电脑上，剩下的就交给各种应用去消化这些内容。举个例子，如果是一个编程项目，你需要 HTML、需要 React、需要浏览器。

[10:55] Meng

If it's a MD document, you need something like Obsidian that organize and read all of this stuff with beautiful imagery and stuff like that or the app that I build for myself. Um, for videos, for example, you need a separate app for organizing your videos because you're not going to do that here and so on and so forth. So, this is why, you know, we need these these other apps. I hope that answer your question.

如果是 MD 文档，你就需要 Obsidian 这样的工具来组织和阅读，配上漂亮的排版和图片——或者用我给自己做的那个应用。再比如视频，你需要一个单独的应用来管理你的视频素材，因为这事你不会在 Codex 里做，以此类推。所以这就是为什么我们需要这些其他的应用。希望这回答了你的问题。

[11:19] Aakash

Got it. I've been building a lot of AI products lately. My job search OS has 16 different agents. My newsletter has a recommendation engine, and I kept running into the same problem. I'd ship something, it would work in my testing, and then I'd get messages from users saying it's hallucinating or picking the wrong tool. The issue wasn't the prompts or the tools. It was that I wasn't actually evaluating anything. I didn't have a way to see what my agent was actually doing step by step. Every tool call, every decision. That's where Arise comes in. Let me show you. I'm going to open Claude Code and install Arise with just one command. npx skills add Arise AI Arise skills skill. Yes. Now Claude Code already knows how to instrument my agent. I tell it set up tracing to Arise and it automatically analyzes my codebase, figures out where the LLM and tool calls are and adds instrumentation automatically. Now I can see everything, every trace, every span, every decision. And more importantly, I can evaluate it. That's the shift. Trace what's happening, evaluate where it fails, then fix it. This trace right here, my resume feedback agent was supposed to pull the company's text stack from the job posting, but instead it hallucinated that they use React when the posting said Python. I never would have caught that without seeing the trace. And here's the part that blew my mind. I asked Claude Code to look at these traces and tell me what I should be evaluating. It came back with four eval criteria I hadn't written. Things like picking the right tool and staying grounded in the input. I wrote the evals, ran them, and found that my agent was making the same kind of mistake about 12% of the time. Claude pushed to fix. I reran the evals and it dropped to under 2%. That whole loop, trace, evaluate, fix, took me about 20 minutes, and now it runs automatically. If you're building AI products and not evaluating them, you're shipping blind. Try Arise free at arise.com and get a year free, a $1,260 value with my bundle, Arise. Check it out. It's one of the top AI evals platforms used by all of the top AI teams for a reason. And how does the avatar help with the Loom videos?

明白了。我最近在做很多 AI 产品：我的求职 OS 里有 16 个不同的 agent，我的 newsletter 有一套推荐引擎，然后我总是撞上同一个问题——东西上线了，我自己测试没问题，结果用户发消息来说它在产生幻觉、或者调用了错误的工具。问题不出在 prompt 或工具上，而是我根本没在做评估（evaluation）。我没有办法看到我的 agent 一步一步到底在干什么——每一次工具调用、每一个决策。这就是 Arize 的用武之地。我来演示一下：我打开 Claude Code，用一条命令安装 Arize——npx skills add arize-ai/arize-skills，确认。现在 Claude Code 已经知道怎么给我的 agent 做插桩了。我跟它说'把 tracing 接到 Arize'，它就会自动分析我的代码库，找出 LLM 调用和工具调用的位置，自动加上埋点。现在我什么都能看到了：每一条 trace、每一个 span、每一个决策。更重要的是，我可以对它做评估。这就是关键的转变：先追踪发生了什么，再评估哪里失败，然后修复。就拿这条 trace 来说，我的简历反馈 agent 本来应该从职位描述里提取公司的技术栈，结果它幻觉出对方在用 React，而职位描述里明明写的是 Python。要是看不到 trace，我根本抓不到这个问题。还有一个让我震惊的地方：我让 Claude Code 看这些 trace，告诉我应该评估什么，它给出了四条我自己没写过的评估标准，比如'是否选对了工具''是否忠于输入内容'。我把这些 eval 写出来跑了一遍，发现我的 agent 大约 12% 的情况下都在犯同类错误。让 Claude 推了修复之后重跑 eval，错误率降到了 2% 以下。整个'追踪—评估—修复'的循环只花了我大概 20 分钟，而且现在它是自动运行的。如果你在做 AI 产品却不做评估，那你就是在盲目发布。去 arise.com 免费试用 Arize，用我的 bundle 还能免费用一年——价值 1260 美元。去看看吧，它是顶级 AI 评估平台之一，被所有头部 AI 团队使用是有原因的。——那么，AI 数字人（avatar）是怎么帮你做 Loom 视频的？

[13:27] Meng

Right. Okay. So, this is really interesting. Um, I kind of dropped that knowledge. I uh I understand that it's kind of like out of nowhere, but right now there's a huge shift into UGC content. Have you heard about UGC content?

对，好，这个话题很有意思。我刚才算是随口抛出了这个点，我知道听起来有点突然，但现在整个行业正在大规模转向 UGC 内容。你听说过 UGC 内容吗？

[13:42] Aakash

Userenerated content.

用户生成内容（User-generated content）。

[13:43] Meng

Yes. So UG userenerated content where basically this is what everyone's doing. This is the new marketing 2.0. Basically uh people are tired of looking at companies and getting me like corporate bureaucracy messages from them. Instead, they want people like you and me who have real human experience in an era of AI that feels like they're getting not only a ton of value, but also authenticity and a perspective that they can relate to. So, having an AI avatar allows you to to go from, oh, you know, today I have to put my, you know, I have to do my hair. I have to, you know, put on a nice shirt. you know, sometimes you don't feel like it. So, having an AI avatar, which by the way, you know, Cance is really good at or, you know, Hey Jen, for example, is a really good AI model for that. Basically those they you know they can generate a clone of yourself including your voice and then you can just use that and type the stuff that you want your AI avatar to say while you do the screen sharing which by the way what you know what this app that I'm building is about and just like put the two together and then you get your presentation because everything is about presentation. So, you know, UGC is a presentation. It's just in a form of something you would post on Instagram or Tik Tok or Twitter and uh you know, but if you're talking about in like as as a PM, you want to give the message to your team. So, the best way to do that is you have to record yourself doing a screen recording, say stuff, and then, you know, showing the slides. It's a lot more human.

对，UGC，用户生成内容。现在基本上所有人都在做这个，这是新时代的'营销 2.0'。大家已经厌倦了看企业发出来的那种官僚味十足的公关话术，他们想要的是像你我这样、在 AI 时代有真实人类经验的人——让他们不仅能获得大量价值，还能感受到真实性，以及一个能产生共鸣的视角。所以，拥有一个 AI 数字人（avatar）能让你摆脱'哎，今天还得做头发、还得穿件像样的衬衫'的负担——有时候你就是不想收拾自己。有了 AI avatar——顺便说，Canva 在这块做得很好，HeyGen 也是非常出色的 AI 工具——它们可以生成一个你自己的克隆，包括你的声音，然后你只要把想让 AI avatar 说的话打出来，同时自己做屏幕分享——顺便说，这正是我在做的这个应用要解决的事——把两者合在一起，你的演示就完成了。因为一切的本质都是'呈现'（presentation）。UGC 也是一种呈现，只不过是以你会发在 Instagram、TikTok 或 Twitter 上的形式。而如果你是一个 PM，你要向团队传达信息，最好的方式就是录一段自己的屏幕录像，边讲边展示 slides，这样会人性化得多。

[15:30] Aakash

Nice. Amazing. Yeah. I think I've seen like some creators create like almost like photo realistic avatars. So, I'm excited for that demo coming up.

很棒。是的，我见过一些创作者做出了几乎照片级真实感的数字人，所以我很期待接下来的演示。

[15:38] Meng

Yes. And with image 2.0, um, everyone starts with image 2.0. I'm going to get more into the details of it, but for now, let's get into how to get started with codecs. So, uh, the first thing you want to do is to get into the plugins and the skills, right? The difference between a plug-in and a skill is just how deeply integrated it is. Usually a plug-in is more like it has uh you know the whole backend stuff and the whole integration uh more like a Figma plugin or Photoshop plugin where you know there's a whole team behind it whether it's OpenAI or Slack or Chrome or linear. So you want to definitely use this is one of the most amazing thing is computer use and we are I would say we are in the middle of that journey but eventually it's going to get so much better but right now it's so good it it's able to work on your computer like it can it can open Figma and start designing something on its own by using your own brow your own mouse right and that's so good because you know you've heard of MCP you've heard of like CLI for those who don't know CLI is when it goes to your command line it starts communicating a with APIs and MCP is when uh Figma for example introduce some sort of like a plugin and then uh you know again you it's connecting to the AI agents and it does all of these task but then you have computer use which works on everything right it doesn't require someone to build something it's going to just use your computer as a human would so I would imagine eventually you're going to be able to do computer use and you have an AI agent that records on your computer and creates videos and presentation using your AI avatar. So that's just how powerful it is. But for now I'm using uh computer use a ton for testing. So for example uh you know a user has a problem you're going to go through that flow and you're going to use computer use for that. It's going to click here goes to this website's already log in and then you know go through that flow. Oh, we have this bug and then it fix it and so it it reaches those pages and then it fix the bug. So computer use super super important spreadsheets presentation Chrome similarly to computer use but I would say that nowadays CEX has its own browser and so the AI is able to do everything by itself and oh Gmail super important as well. So, it's going to be able to to go to your Gmail and it's going to be able to reply to your emails and it's going to be able to do a lot of cold reach, uh, which I know a lot of people do that. Now, one side note about this is that I want to talk about trust because, you know, for a, you know, at

对。而且有了 Image 2.0——大家都是从 Image 2.0 开始上手的，细节我后面会展开讲，现在我们先进入 Codex 的上手环节。第一件要做的事，就是去看插件（plugins）和技能（skills）。插件和技能的区别只在于集成的深度：插件通常是带完整后端和整套集成的，更像 Figma 插件或 Photoshop 插件那种，背后有一整个团队在做，不管是 OpenAI、Slack、Chrome 还是 Linear。你一定要用的、也是最惊艳的功能之一，就是 computer use（计算机操作）。我觉得我们现在处在这段旅程的中途，它最终会变得好得多，但即便是现在也已经非常强了——它能直接在你的电脑上干活，比如自己打开 Figma，用你的浏览器、你的鼠标开始设计东西。这太厉害了。你们应该听说过 MCP，也听说过 CLI——给不了解的人解释一下：CLI 就是它进到你的命令行里，开始跟各种 API 通信；MCP 则是比如 Figma 提供了某种插件，连接到 AI agent，让它去完成这些任务。而 computer use 是对一切都适用的——它不需要任何人先去开发对接，它就像人类一样直接使用你的电脑。所以我可以想象，最终你可以用 computer use 加上一个 AI agent，让它在你的电脑上录屏、用你的 AI avatar 生成视频和演示，这就是它的威力。目前我主要用 computer use 来做测试。比如某个用户遇到了问题，你要走一遍那个流程，就可以用 computer use：它会点这里、进入网站（已经登录好了）、走完那个流程——哦，发现这个 bug 了——然后去修复它，它能到达那些页面然后把 bug 修掉。所以 computer use 超级重要。还有电子表格、演示文稿、Chrome——Chrome 和 computer use 类似，不过我得说现在 Codex 有自己的浏览器了，AI 自己就能搞定一切。哦对，Gmail 也超级重要：它能进你的 Gmail、帮你回邮件，还能做大量的 cold outreach（陌生触达），我知道很多人都在干这个。关于这一点我要插一句，聊聊'信任'这个话题，因为……

[18:31] Meng

the beginning of the year, we had Open Claw and then Open Claw took over the wolf by storm. Now the the biggest problem with open claw at the time and I was a you know I wouldn't say a big but I I I did it for like a month until I got into codeex but the biggest problem with open claw was security a lot of people were worried including myself that if it reads my email someone can inject a prom and then start you know hacking my computer and getting all my you know open AI keys and stuff like that and so you know there were no guard rails at the time but now it's it's a lot better and thanks to think like Codex, you you have something that is within a trusted channel which is codeex or an open AI and since they have a lot of accountability versus just an open-source project um they can put all of these guard rails you can it's going to ask you for permissions and all that stuff. So which is why I trust you know installing a Gmail plugin. I know it sounds, you know, and nowadays I actually use it to send emails. For example, when there's a failed payment, I would sometimes send an email saying, "Hey, you know, is there something wrong?" But I, you know, for a lot of PMs could be like, "Oh, you know, someone reported an issue on Linear or something and you receive an email, you can reply right away with, you know, an auto reply, but using an AI instead, like an agent instead, which which is a lot more smarter and stuff like that. So, this could be super useful. Obviously, Google calendar would be really good. I'm not a super calendar user at the moment. I'm also not a linear user, by the way. And for me, I actually use Discord. Um, and you know, Discord because I'm I'm very customerf facing. So, I use Discord for everything, team chats and all that stuff. And AI can do pretty much everything. Now, we're going to get into the skills. So skills is more like uh anyone can create a skill including you.

……今年年初的时候，OpenClaw 横空出世，席卷了整个圈子。当时 OpenClaw 最大的问题——我算不上重度用户，但也用了差不多一个月，直到我转向 Codex——最大的问题就是安全。很多人都担心，包括我自己：如果它读我的邮件，有人就可以注入一段 prompt，然后开始黑我的电脑，把我的 OpenAI 密钥之类的东西全偷走。当时是没有任何防护栏（guardrails）的。但现在好多了，多亏了 Codex 这样的产品——你用的是一个可信渠道，也就是 Codex 或者说 OpenAI。因为他们背负着很强的问责压力，不像一个纯开源项目，所以他们能把这些防护栏都做上，它会向你请求权限等等。这就是为什么我敢装 Gmail 插件。我知道这听起来有点吓人，但现在我真的在用它发邮件。比如出现支付失败时，我有时会发一封邮件问：'嘿，是遇到什么问题了吗？'对很多 PM 来说，场景可能是：有人在 Linear 上报了一个 issue，你收到邮件，你可以立刻回复——不是用那种呆板的自动回复，而是用 AI、用一个 agent 来回，它聪明得多。这会非常有用。当然，Google Calendar 也会很好用，只是我目前不算重度日历用户。顺便说，我也不用 Linear。我自己实际用的是 Discord——因为我是非常面向客户的，所以我什么都用 Discord：团队沟通等等全在上面，AI 几乎什么都能干。接下来我们讲技能（skills）。技能更像是任何人都可以创建的东西，包括你自己。

[20:25] Meng

You should be a creating your own skill. So, it's a lot more hands-on and it it's it's a variety of stuff and small stuff such as, you know, prompting and uh image generation or what what model to use for image or video generation or uh you know, if if you're talking about design for example, what are the design MDs that you should be uh always considering or what are the taste skills that you should always use whenever you design a landing page or a slide to make it 10x better looking. Um, and then you know you have yeah front end stuff. For example, I I'm building u um a Mac app and also an iOS app which is what Dream Cut is is on. So I use Swift UI skills. Um, Playright is really good for taking screenshots. Netlifi is really good for deploying your website because you're going to create all of these HTMLs and React project, but they need to be hosted somewhere. So something like Versel or Netifi, you just drag and drop your HTML or your React project and it's going to turn it into a URL and it's going to be hosted on an internet and then you connect it to a custom domain name and then voila, you have your SAS product or your landing page. So these are kind of like the skills that I have and I would highly recommend you know most of them all at least the ones that I just mentioned. Copywriting is super good as well. So helps you write better for your uh you know your your landing page but also your documents and then we're going to get into the projects. Uh but first of all do you have any questions about where we are?

你就应该创建你自己的技能。它更偏动手实操，涵盖各种各样的小东西：比如 prompt 写法、图像生成、生成图片或视频该用什么模型；再比如聊到设计，你应该始终参考哪些 design MD 文档，或者你在设计落地页、设计 slide 的时候应该用哪些'品味技能'（taste skills），让它的颜值提升 10 倍。然后还有前端相关的。比如我在做一个 Mac 应用和一个 iOS 应用——DreamCut 就跑在这两个平台上——所以我用 SwiftUI 技能。Playwright 非常适合截图。Netlify 非常适合部署网站——因为你会生成一堆 HTML 和 React 项目，它们总得托管在什么地方。像 Vercel 或 Netlify 这种，你把 HTML 或 React 项目拖进去，它就变成一个 URL，托管在互联网上，然后你绑一个自定义域名，瞧，你的 SaaS 产品或落地页就上线了。这些就是我在用的技能，我强烈推荐其中大部分——至少是我刚才提到的这些。Copywriting（文案）技能也非常好，能帮你把落地页和各种文档写得更好。接下来我们要进入项目（projects）环节。不过在此之前，你对目前讲到的内容有什么问题吗？

[22:07]

How often are you updating your skills? I update them when I noticed that there's a lack of understanding that my my AI agents have. So for example, no, you know, when I was building my Swift SUI apps, I was noticing, oh, it's missing some some knowledge about performance and stuff like that. So I would go on the web and I would look for skill around performance, about Mac development or iOS development. Uh, which by the way is super fun. If if you're like a PM or a founder, you want to build something, start building apps. There's so many needs and there's so many ways to create an app around something and you have so much power when you build an app for let's say iOS or Android because you have access to all of these technologies that nobody are using on a app level. So that's why I think it's so fun. Uh but obviously everyone knows how to build a website. So I would download the skills for building a website but also like the taste skill for like front end development and design skills and CSS and Tailwind skills. So, uh, other skills that I would recommend if you're building landing pages is for like you look at libraries like for animations or, um, Lennis or locomotive or, you know, Barber like there's just so many of these, you know, I know I'm dropping a lot of names. I cannot cover them all, but, you know, there's category of skills, there's categories of like uh, you know, things you should be using depending on what you're building, what you're generating. Uh and then you have to study the AI models that are doing images, videos, uh you know, just AI agentic stuff, coding. Uh it's it's it's a world of stuff and there's just so much to learn which I hope just by dropping the name, you're going to be doing some research on them and then you're going to be integrating them into your workflow.

【Aakash】你多久更新一次你的技能？【Meng】当我注意到我的 AI agent 存在理解上的欠缺时，我就会更新。举个例子，我在做 SwiftUI 应用的时候，发现它缺少一些关于性能优化之类的知识，我就会上网找关于性能、关于 Mac 开发或 iOS 开发的技能。顺便说，这事特别有意思——如果你是 PM 或者创始人，想做点东西，那就开始做应用吧。世界上有太多需求没被满足，围绕任何一个点都有很多种做应用的方式。而且当你为 iOS 或 Android 做应用时，你手里的能力非常大，因为你能调用那些几乎没人在应用层面使用的技术。这就是我觉得它有趣的原因。当然，做网站人人都会，所以我会下载建站相关的技能，还有前端开发的'品味技能'、设计技能、CSS 和 Tailwind 技能。另外，如果你在做落地页，我还推荐去看一些库，比如动画相关的 Lenis、Locomotive，还有 Barba 之类——这类库太多了。我知道我在抛一大堆名字，没法一一展开，但技能是分门类的：取决于你在做什么、在生成什么，你应该用不同类别的东西。然后你还得去研究那些做图像、做视频、做 agent 类工作、做编程的 AI 模型。这是一整个世界，要学的东西太多了。我希望光是听到这些名字，你就会去做点功课，然后把它们整合进你的工作流。

[24:03] Aakash

Awesome.

太棒了。

[24:04] Meng

Okay, so now we're going to get into the projects. So I want you to think about codeex like a chat GPT but on steroids. That's basically what it is. Everyone knows how to use chat GPT. The first time that OpenAI introduced CHP everyone was like wow the future of a the future of UI is is basically a chat and uh I fully disagree with that by the way. Um, there's a ton of detentations, but there's also a ton of stuff that we're unlocking. And we've never seen more UI nowadays than we've ever seen in the past. But at the center of it all is the chat. So, like I mentioned before, I was a huge cursor user. I was also into the nitty-gritty of like using Figma for design and using uh something like VS Code for coding. And you know we have a whole new generation of people especially PMs and people who've never done coding before who are getting more and more technical because of AI right and for for us the technical people who have done this for like a decade we are 10x the workflow basically what the stuff that we've always dreamed of building before now we can do it like for example never in a million years I would think of building my own video editor yet here I am. So the PM who's never done technical stuff is now doing technical stuff. The one who's never done like the teenagers who's never done an iOS app now suddenly gets into coding and you know use swift to build his app in in a matter of days and so yeah this is where we are and we started all of this with chat. So while we nobody want like all of these people including myself nowadays I I haven't written a single line of code in the past 6 months and and I've heard a lot of engineers do that as well. Um so where where are we right now if nobody's writing code right so we're moving from VS Code and Figma into the chat box. Okay, so basically cursor is also like VS code but with AI agents and even cursor they're moving away from the sort of like GitHub ccentric files and folder centric into the chatbased project and the same way with cloud code as well. They're moving away from cloud code in the terminal which is highly technical into something like cloud co-work and cloud design. So you're seeing this shift into a more projectbased chat and this is where we are right now with Codex and Codex has started this movement and then you also had you know uh uh like also like the the local base generation. So with all of this you have the projects and a project is basically just a folder. So now if you want to start a new project, you're going to click here. You can either start from scratch or use an existing folder. Now

好，现在我们进入项目（projects）环节。我希望你把 Codex 想象成一个'打了激素的 ChatGPT'，它本质上就是这么回事。人人都会用 ChatGPT。当年 OpenAI 刚推出 ChatGPT 时，所有人都在说'哇，UI 的未来就是一个聊天框'——顺便说，我完全不同意这个说法。聊天有一大堆局限，但它也解锁了一大堆东西——事实上，我们现在看到的 UI 比历史上任何时候都多。但这一切的中心，确实是聊天。就像我之前说的，我曾经是 Cursor 的重度用户，也曾深陷在'用 Figma 做设计、用 VS Code 写代码'的细节里。而现在有一整代新人——尤其是 PM 和从没写过代码的人——因为 AI 变得越来越技术化。对我们这些做了十年技术的人来说，工作流被放大了 10 倍：那些我们过去只敢想想的东西，现在真的能做出来了。比如我这辈子都没想过要自己做一个视频编辑器，可我现在就在做。从没碰过技术的 PM 现在在做技术活儿；从没做过 iOS 应用的青少年突然开始写代码，用 Swift 几天就把应用做出来了。这就是我们所处的时代，而这一切都始于聊天。现在——包括我自己在内——过去 6 个月我一行代码都没写过，我听说很多工程师也是这样。那么问题来了：如果没人写代码了，我们现在处在什么位置？我们正在从 VS Code 和 Figma 迁移到聊天框里。Cursor 本质上也是带 AI agent 的 VS Code，但即便是 Cursor，也在从那种以 GitHub、以文件和文件夹为中心的模式，转向以聊天为基础的项目模式。Claude Code 也一样：他们正在从高度技术化的终端里的 Claude Code，转向 Claude Cowork 和 Claude Design 这样的东西。你能看到这个趋势——转向更加以项目为中心的聊天模式。这正是 Codex 现在所在的位置，Codex 开启了这场运动，同时还有本地化生成这条线。基于这一切，你就有了'项目'的概念，而一个项目本质上就是一个文件夹。想开一个新项目的话，点这里，你可以从零开始，也可以使用一个已有的文件夹。

[27:17] Meng

the folder can be anywhere on your computer. Okay? And keeping in mind that your AI nowadays can have full permission on anything on your computer. And in fact, I have this little thing here, full access 247 because I trust it because it has guard rails. So, what you want to do is you you're going to start this project and you're going to go to your downloads folder, right? Everyone knows what their downloads folders are. And then you from the downloads folder, you're going to create a project uh a folder called projects. And then in the in in the projects folder, you're going to create a product a project a folder for every single project that you you're doing right now. And let me give you some example. So these are the apps that I'm building. But I also have content which is for all the MD files and all the you know uh the text the preparations the the video scripts if you're a YouTube channel for example or if you're making presentations you would create these markdown files. Okay. And then we also have a folder that you can put all your customer support stuff or the issue stuff like you know anything that the customer might have and you want to follow up. You also want to have something for your company. So if you have like if you start your own company or you you you know you have accounting you want to create a folder for that. So, you're going to put all of your invoices, all of your, you know, uh, registry and documents and receipts, uh, but also all your company files, you know, all the context of your, uh, the team that you work with and so on and so forth. And then you, uh, you might have a folder for skills that you're going to put all your skills into it so that you can use it for the next stuff. If you have kids, you might have a folder for school uh where you're going to put all of their the kids assignments and their homeworks and you know so that the AI has context because you don't want to give AI too much context otherwise it's going to cost too much tokens. That's why you want to have something like this. So I'm not going to get into the coding aspect even though I think this is a hugely beneficial thing to do. you know you you create a new folder you know let's say you want to create an an iOS app then you start you know a new chat for example and you can use whisper flow and you can start with the context usually you you can ask questions right um the first thing you want to do is the plan mode so you're going to start with I want to plan this so you know obviously it it also took what I said, um, but you always want to start with I

这个文件夹可以在你电脑上的任何位置。要记住，现在你的 AI 可以对你电脑上的任何东西拥有完整权限——事实上我这里就开着这个小开关：全天候完全访问（full access 24/7），因为我信任它，它有防护栏。那么你要做的是：开一个项目，然后去你的'下载'文件夹——每个人都知道自己的下载文件夹在哪——在下载文件夹里创建一个叫 projects 的文件夹，然后在 projects 里面，给你手头的每一个项目各建一个文件夹。举几个例子：这些是我正在做的应用；我还有一个 content 文件夹，放所有的 MD 文件——各种文字材料、准备稿、视频脚本（如果你做 YouTube 频道的话），或者做演示时创建的这些 markdown 文件。然后还有一个文件夹放客户支持相关的东西——各种 issue、客户可能遇到的问题、需要跟进的事项。你还应该有一个公司文件夹：如果你开了自己的公司，或者要做记账，就建一个文件夹，把所有发票、注册文件、单据收据都放进去，还有公司的各种文件——你合作团队的背景信息等等。然后你可能还有一个 skills 文件夹，把你的技能都放进去，方便后续使用。如果你有孩子，还可以建一个 school 文件夹，放孩子的作业和功课，让 AI 有上下文——因为你不想给 AI 塞太多上下文，不然 token 花销太大，这正是需要这样组织文件夹的原因。我就不深入讲编程的部分了，虽然我认为那非常有价值。比如你建一个新文件夹，想做一个 iOS 应用，那就开一个新对话——你可以用 Wispr Flow 语音输入——先从上下文开始，通常你可以先问问题。第一件要做的事是计划模式（plan mode）：你要用'我想规划这个'来开头——你看，它把我刚才说的话也收进去了——总之永远要以'我想规划这个'开始。

[30:09] Meng

want to plan this. And the reason why is because you you don't want to get into the coding yet because you want to approve every single thing that you want to build first. And then you're going to be like, I want to build an app that scans QR code and sends automatically uh the content of that QR QR code to my email, for example. So then you have an app idea, right? And you want to plan it first. And by the way, uh I shouldn't put this in an existing folder, but I could just create one. Start from scratch. And let's say QR project. And I'm going to save this. And then I'm going to do this. So let's talk a little bit about the permissions. Okay. So you have the default permission. I think most people are going to start with this. Now, this is when you're a new user. you don't trust the AI yet. You know, your level of trust is like zero to 100. At the beginning is more like zero and then eventually you learn to trust. So default permission and again this depends on you whether you value speed and the co the token cost and all that stuff. You can start with standard and you can start with medium. Now because and this depends on the level of difficulty that you think this project is going to take. So, for example, if you don't have a ton of tokens, you have like a $20 a month plan uh and and you you just want to experiment, you want to go with medium or low, right? But me, I'm a $200 plan because I I use this every day. And one of the key reason that I'm actually using uh OpenAI is because they're far more generous in term of tokens. I'm sure some of you of you already experienced it. Oh, you know, I'm already at my limits after five prompts on cloud design, for example. Well, that's that's the reason is because like first their their models are super costly and I'm last thing I checked I don't think they have like a low, medium, high and extra high setting and these are related to the token cost.

为什么呢？因为你还不想直接进入写代码的阶段——你希望先逐条审批你要构建的每一样东西。然后你会说，比如：'我想做一个应用，扫描二维码，并自动把二维码的内容发送到我的邮箱。'这样你就有了一个应用的想法，对吧？你要先做规划。顺便说，我不该把它放进一个已有文件夹，我可以直接新建一个：从零开始，就叫 QR project 吧，保存，然后这样操作。接下来我们稍微聊聊权限（permissions）。首先是默认权限，我想大多数人都会从这里开始。这是你还是新用户的阶段——你还不信任 AI。你的信任度是从 0 到 100 的：一开始基本是 0，然后慢慢学会信任。所以先用默认权限。另外，这也取决于你怎么权衡速度和 token 成本。你可以从 standard 档开始，也可以从 medium 档开始——这取决于你判断这个项目的难度有多大。比如说，如果你 token 不多，用的是每月 20 美元的套餐，只是想做做实验，那就选 medium 或 low。而我用的是 200 美元的套餐，因为我每天都在用。我选择 OpenAI 的一个关键原因，就是他们在 token 上慷慨得多。我相信你们有些人已经体验过了：'哎，我在 Claude Design 上才发了五条 prompt 就到限额了。'原因就在这：第一，他们的模型非常贵；第二，我上次看的时候，他们好像还没有 low、medium、high、extra high 这样的档位设置——而这些档位是和 token 成本直接挂钩的。

[32:11] Meng

So like I said if you have like a $20 a month you might want to use low. If you have like a $200 and you want you value accuracy over everything everything everything else and you do a lot of like you do a fleet of agent. I like to do like 20 agents running at once. then you go with extra high because you can afford to wait on them. So this is a high difficulty one. So I'm going to do this right here and I I will set it to full access because I already trust it. And you can see everything is uh is is happening locally. So I'm going to start with that. And uh and then it's going to start uh thinking and it's going to come up with a plan. And while I'm doing this, I can also go to I think a lot of people are going to do this content which is for example I want to create a slide for the stats that I have like new users how many news users have what are the revenues that I'm doing every day for my projects Dreamcut aura new form and I want you to look into my downloads folder and in the download folder there's a projects folder and you're going to find those projects folder folders right there. I want you to read those folders and I want you to look for the revenue stats and the new user stats, um the the conversion rate, etc. And then I want you to create a slide. So again, this is why I'm using Whisper Flow because when I'm using Whisper Flow, I can give a ton of context and it also formats everything that I say in a super nice thing. Yeah, like a really nice format. And you can see here while I'm doing this, it's already done. So now I have my bill plan for my iOS app. Okay. So now I just need to read through this and kind of make sense of it. If I have any question about it, I will ask a question. It's super important to ask the question. And when I'm done, I would say, okay, let's do it. But for now, I'm going to say, okay, so architecture, we're going to need the QR scanner technology. We're going to need a backend secure. So the AI is really smart and 5.5 is considered the gold standard nowadays. So you have two uh of the best AI right now, which is one Opus 4.7 and two uh you know, GPT 5.5 at extra high. And so it's super good and you know give it a try. Honestly, give it a try. I know you're going to get you're you're going to build your your dream app just from listening to this.

所以就像我说的，如果你用的是每月 20 美元的档位，可能就选 low（低推理强度）。如果你用的是 200 美元的档位，而且你把准确性看得比什么都重要，同时你会跑一整支 agent 舰队——我喜欢同时跑 20 个 agent——那你就选 extra high（超高强度），因为你等得起。眼前这个任务难度比较高，所以我就在这里用高强度来跑，而且我会把权限设成 full access（完全访问），因为我已经信任它了。你可以看到所有东西都是在本地运行的。我就从这个开始。然后它会开始思考，给出一个方案。在它跑的同时，我还可以去做另一件事——我觉得很多人都会拿它来做内容，比如：我想为我的数据做一页幻灯片，像新增用户有多少、我各个项目（Dreamcut、Aura、New Form）每天的收入是多少。我让它去看我的 Downloads 文件夹，里面有个 projects 文件夹，它会在那里找到那些项目的文件夹。我要它读这些文件夹，找出收入数据、新增用户数据、转化率等等，然后做成一页幻灯片。这也是我为什么用 Wispr Flow（语音输入）——用它我可以一口气给出大量上下文，而且它还会把我说的话整理成非常漂亮的格式。你看，就在我说话的这会儿，那边已经跑完了。现在我的 iOS App 的构建方案已经出来了。接下来我只需要通读一遍，把它消化清楚。如果有疑问，我就提问——提问这一步超级重要。等我确认没问题了，我才会说'好，开干'。现在我先看：架构上，我们需要 QR 扫码技术，需要一个安全的后端。这个 AI 真的很聪明，5.5 现在被视为黄金标准。所以你手上有当下最强的两个 AI：一个是 Opus 4.7，另一个是开到 extra high 的 GPT 5.5。真的非常好用，说真的，你去试试。我敢说，光是听完这期节目，你就能把你梦想中的 App 做出来。

[34:51] Meng

And so yeah, you know, it it's giving me the plan. It gives me the MVP features. It gives me like uh okay, what this is the format that I'm going to get and this is the scan and this is the the content. It's going to give me the URL. I receive the email safety features and so on and so forth. Okay, so this is great and then I can start building or if I have a new question for example I can say um can we expand on the email um and can we actually have an image like maybe a screenshot of the QR code so let's say the QR code goes to a website and uh let's say you know I want to use a technology that takes a screenshot of that website what it looks like and then send it to as part of the email So obviously you want to start with a question otherwise the AI might think that it's time to get into the coding

所以你看，它把方案给我了：给出了 MVP 功能清单，告诉我最终会拿到什么样的格式、扫码是怎么回事、内容长什么样，还会给我 URL、邮件接收、安全特性等等。这就很好了，接下来我可以直接开始构建；或者如果我有新问题，比如我可以说：'我们能不能在邮件这块展开讲讲？能不能在邮件里加一张图片——比如 QR 码的截图？假设这个 QR 码指向一个网站，我想用某种技术给那个网站截个图，看看它长什么样，然后把截图作为邮件的一部分发出去。'注意，你要以提问的方式开头，否则 AI 可能会以为该开始写代码了。

[35:44] Meng

and like I said you know I'm just going you through like an exercise of a random app that just came came up like that. Um but this is what it looks like to build an app. Let's say you're a PM or um you know someone who's never done coding before. This is how I would start.

就像我说的，我只是带你做一个练习，用的是一个随手想出来的 App。但做一个 App 就是这个样子。假如你是个 PM，或者一个从没写过代码的人，我就会这样起步。

[35:59] Meng

And then you know for content super important again it's exploring all the files. superpower running like it understands everything that I'm talking about. It understands that I have a downloads folder. It have a projects folder. I have dream cut new form and it even understands all the sort of the names that I have that are not you know normal names right they're like uh specific names and the same with generating your avatar or generating a slides you know for example I can say uh can you create a slides presentation in a you know um keynote format so it can even create like specific format. I should probably really uh you know I was talking during this uh for all of the stats around my last meeting with a cache and uh you should also look into uh the document that I have in my content folder where I prepared the prep for the podcast. I want you to look at the content and basically from all of that content I want you to create a slides presentation in a keynote format. Let's plan this.

然后你看，做内容这块也超级重要——它又在探索我的所有文件了，简直像开了超能力一样在跑。它理解我在说的一切：它知道我有个 Downloads 文件夹，里面有个 projects 文件夹，我有 Dreamcut、New Form 这些项目，它甚至能认出我那些不太'正常'的名字——都是些很特殊的命名。生成头像或生成幻灯片也是一样。比如我可以说：'你能不能做一份 Keynote 格式的幻灯片演示？'它连特定格式都能生成。我应该趁着刚才说话的工夫，把上次和 Aakash 开会的所有数据都用上——'你还应该去看我 content 文件夹里的那份文档，我在里面为这期播客做了准备。我要你把这些内容都看一遍，然后基于所有这些内容，做一份 Keynote 格式的幻灯片演示。我们先做规划。'

[37:19] Aakash

So even for a slide planning is worthwhile.

所以说，连做幻灯片都值得先做规划。

[37:22] Meng

Yes, exactly. And this is cool with whisper flow as well. You have a dictionary now. So it it understood that your name was written this way even though it's not like a you know I don't want to I don't want to you know obviously you know best but it's not a conventional name in term of the way it's written right

对，正是这样。Wispr Flow 还有个很酷的地方——它现在有词典功能了。所以它知道你的名字是这样拼写的，虽然它——我不是说不好，你的名字当然很棒——只是从拼写方式上讲，它不算一个常规的名字，对吧？

[37:40] Aakash

yeah exactly

哈哈，没错。

[37:42] Meng

so it it was able to figure it out why because when I use whispers flow it kind of um you know I correct it and then the whisper flow understood that I corrected your name and then it remembered afterwards and you know that's is the power of AI. It understands context and it's more proactive rather than always waiting for you to to ask for something. So again, you know, here I'm asking for a very specific thing and because I'm asking for like a keynote file, right? Now the question is is AI able to to create a keynote file? Yes or no? And then you can ask that you can explore those things. Um but most importantly if the AI is not able to do that then you can always say are you able to create a keynote file if not what if you use computer use to open keynote and then go step by step into creating that presentation in Keynote right and then while it's working you have also the ability to cue new commands okay and um you know Uh so here it gave it gave me the plan because that's what I asked for but also I can steer it and I can cue new uh new task that I want to give. So uh you can see here you know uh let's see if it's able to. So deliverable uh key is required. I can try converting keynote afterward. The reliable format is PBT which is kind of like I think it's a PowerPoint presentation. uh that keynote is able to open cleanly um and then you know it's kind of looking into this uh and also you can sort of steer the the conversation so for example I can say something like let me just restart this what if we generate the image first as a slide in GPT 2.0 O image first. Let's create five of them. Uh let's use this taste skill and let me make sure that it looks good before we actually build the actual slides with layers. So um here it did a problem with GPT2, but that's my fault. So I can always stop it. I can edit it and I can say um image and then it inserts nicely into um into the text. It understands the context of the text. So obvious obviously if if I didn't correct it, it would just say GPT 2.0 which doesn't make any sense. It could be like an AI model. So understand these keywords is really key to knowing what to build and how to say it right so that the AI doesn't make mistake on top of the fact that you're using the planning mode and you're also asking a question. So those are the three factors before you actually get into building and generating the images and you know if you're blocked by something the AI is going to ask you so for example maybe uh image 2.0 is not installed as a skill.

它能自己搞明白，为什么？因为我用 Wispr Flow 的时候纠正过一次，它就理解了我纠正的是你的名字，之后就一直记住了。这就是 AI 的力量——它理解上下文，而且更主动，不会总是干等着你去要求什么。回到刚才：我在这里要的是一个非常具体的东西，因为我要的是一个 Keynote 文件，对吧？那么问题来了：AI 到底能不能生成 Keynote 文件？能还是不能？你可以就这个去提问、去探索。更重要的是，如果 AI 做不到，你随时可以说：'你能生成 Keynote 文件吗？如果不能，那用 computer use 打开 Keynote，然后一步一步在 Keynote 里把这份演示做出来，怎么样？'而且在它干活的时候，你还可以往队列里排入新的指令。你看这里，它把方案给我了，因为我要的就是方案；但我也可以随时给它调方向，把我想布置的新任务排进队列。你看这里——我们看看它行不行。交付物那里写着：需要 .key 文件，可以事后尝试转换成 Keynote；可靠的格式是 PPT，差不多就是 PowerPoint 演示文稿，Keynote 能干净地打开。它在研究这个的同时，你还可以引导对话方向。比如我可以说——我重新来一遍——'我们要不要先用 GPT Image 2.0 把每页幻灯片生成图片？先做五张。用上这个 taste skill，让我先确认视觉效果没问题，再去做真正带图层的幻灯片。'这里它把 GPT 2 理解错了，不过那是我的锅。我随时可以叫停它、编辑指令，我说'image'，它就漂亮地插进文本里了——它理解文本的上下文。显然，如果我不纠正，它就会写成'GPT 2.0'，那就完全说不通了，会被当成某个 AI 模型。所以，掌握这些关键词是重中之重——知道要构建什么、该怎么表述，AI 才不会犯错。再加上你用了规划模式、你也在主动提问——这就是真正动手构建和生成图片之前的三个关键要素。而且如果你被什么东西卡住了，AI 会来问你。比如，也许 Image 2.0 并没有作为一个 skill 装上。

[40:51] Meng

But in this case, since we're using codecs, it should be fine. Uh so let's look into the QR project. Uh here it says okay notes screenshot captured automatically by this using the scan. Let me see if um I can ask for example what technology are you using for for taking a screenshot and uh okay so here it says screenshot service like brow browserless and screenshot one do you think that playright would be a better technology for taking screenshots right so this depends on your knowledge I know that playright is one of the best ways because I've been using it for for aura my my other projects. So again this is kind of like the gist of it and um uh how I would do things. The last thing the the last bit of knowledge that I want to give you that I do like 90% of the time is especially when you get into the nitty-gritty when you're building a website is you want to take screenshots of everything. Okay? Because the AI like an image is worth a thousand words. You can use of course whisper flow to talk and give a ton of context because the more context the better and you don't want to type all of that context because you get lazy as human. You're limited by your speed and your thinking is way faster than your typing if you think about it. So the second best thing is um using your voice. So you can talk way faster than your typing. And the third best the the the even better than that is taking a screenshot because taking a screenshot you have this new uh you know you select for example the browser and then you have this new shortcut which is like command command and then it takes the screenshot automatically of that browser that you had focus and look at that

不过这次因为我们用的是 Codex，应该没问题。我们来看 QR 这个项目。这里它写着：'截图由扫描服务自动捕获'。我可以问它，比如：'你截图用的是什么技术？'它回答：用的是截图服务，比如 Browserless 和 ScreenshotOne。那我再问：'你觉得 Playwright 会不会是更好的截图技术？'——这就取决于你自己的知识储备了。我知道 Playwright 是最好的方案之一，因为我在 Aura（我的另一个项目）里一直在用它。所以，这大概就是整套做法的精髓了。最后一条我想送给你的经验——我 90% 的时间都在这么干——尤其是当你深入到细节、正在做一个网站的时候：你要给所有东西截图。为什么？因为对 AI 来说，一图胜千言。你当然可以用 Wispr Flow 说话来提供大量上下文——上下文越多越好，而你又不想全靠打字，因为人是会犯懒的。你受限于打字速度，而如果你仔细想想，你的思维远比你的打字快。所以第二好的方式是用语音——说话比打字快得多。而第三种、比语音还要好的方式，是截图。截图现在有个新玩法：比如你选中浏览器，然后按一个新快捷键——Command Command 连按两下——它就自动把你当前聚焦的那个浏览器窗口截下来了。你看，就这样。

[42:54] Meng

it it's really amazing and this is just a new feature that that was launched last week and another new feature that was launched last week is the mobile. This is incredible. Okay, just to give you an idea of how incredible this is. when I go outside or I go commuting or you know I take a taxi or I'm waiting for my food to be deliver to be served at the restaurant I can open my codeex which is connected to my computer and I can go to each of these tasks that are being worked on okay and and just keep working on my project by just chatting. So the mobile, the Codex mobile sits in your chat GPT app. Okay. All you need is your chat GPT app and there's a little button that says codeex. You click on it, you connect it to your to your codeex on your computer and then you have access to all of these projects. Isn't that beautiful? because then you can follow up with all of these chats and everything that you do and ask is being worked on your computer and not on your phone. And that's the magic. The magic.

这真的太棒了，而且这只是上周刚发布的新功能。上周发布的另一个新功能是移动端，这个简直不可思议。给你举个例子感受一下它有多离谱：我出门在外、通勤路上、坐出租车，或者在餐厅等上菜的时候，我可以打开我的 Codex——它连着我家里的电脑——然后逐个查看那些正在被处理的任务，光靠聊天就能继续推进我的项目。移动端的 Codex 就藏在你的 ChatGPT App 里。你只需要 ChatGPT App，里面有个小按钮写着 Codex，点一下，把它连接到你电脑上的 Codex，然后你就能访问所有这些项目了。是不是很美妙？因为你可以跟进所有这些对话，而你做的、你要求的每一件事，都是在你的电脑上执行的，不是在手机上。这就是魔法所在。真正的魔法。

[44:17] Aakash

Does your computer need to be on for that?

那你的电脑得一直开着吗？

[44:19] Meng

Yes. So, there's a few options that you you have to do in your settings. I'm not going to go into my settings just because I want don't want to share the sensitive stuff, but you're going to go through like a workflow where you're giving permissions to, for example, uh, you know, keep my codeex on even though my screen is locked um, and work on these things. So, as you can see, you know, I'm working on slides, okay? And it's taking it understood that I have a folder for content and in my folder for content I have a prep file around the um you know around your podcast and you know we have uh stats we have these beautiful slides I'm also using uh the taste skill that gives me better design skills and better fonts and typography that looks like it was done by a senior designer. Now, that being said, of course, it's going to make mistakes. So, for example, sometimes it likes to cram a lot of information, a lot of lines, and it doesn't it's not smart enough to know that it's not able to cram all of this stuff in a way that makes sense. So, for example, you can see it's trying to put like so many futures in in in a space that doesn't allow it to do, and that's where it struggles. So you over time you kind of understand how to deal with these things with these uh pitfalls and then you overcome it and this is where you as a human you become better at uh at kind of like making these micro decisions in a split second and then you say oh this is wrong right fix this and uh you take screenshot for the context again beautiful animation right boom and it just you know it does this beautiful animation, gives me the context, gives the screenshot of the image that you're talking about. You go to a website, you go to a slide, boom, you do the you do that that you know that shortcut and it gives you the context and so on so forth. So the beauty of all of this I want you to understand is that all of this is happening all at once. when usually traditionally if you think about 10 years ago using Figma or using uh VS code you're limited by one task you do one thing at a time you do one project at a time you have one cursor what you need to understand nowadays is that you don't have to do that anymore you have an army of agents so when I say an an agent like this is an agent this is an agent this is an agent and they all working sim simultaneously.

是的。设置里有几个选项需要你配置。我就不打开我的设置了，因为里面有些敏感信息不方便展示，但你会走一个授权流程，比如允许'即使屏幕锁定也让我的 Codex 保持运行'并继续处理任务。你看，我现在正在做幻灯片，它已经理解了我有个放内容的文件夹，里面有一份围绕你这期播客的准备文件。我们有数据，有这些漂亮的幻灯片。我还用了 taste skill——它能带来更好的设计品味、更好的字体和排版，看起来就像出自一位资深设计师之手。当然，话说回来，它肯定会犯错。比如，它有时候喜欢把一大堆信息、一大堆文字硬塞进一页里，它没有聪明到意识到自己塞不下、塞了也不合理。你看这里，它想把这么多功能点挤进一个根本放不下的空间里——这就是它吃力的地方。时间久了，你就慢慢懂得怎么应对这些坑，然后跨过去。这也正是你作为人类变得更强的地方：你要在一瞬间做出这些微决策，然后说'哦，这里不对，改一下'，再截个图给它补上下文。看，又是那个漂亮的动画，啪的一下，它就把上下文和你正在说的那张图的截图都带上了。你打开一个网站、翻到一页幻灯片，啪，按一下那个快捷键，上下文就有了，如此往复。这一切的美妙之处，我希望你真正理解的是：所有这些是同时发生的。传统上，回想十年前，你用 Figma 或者 VS Code，你被限制在一个任务里：一次做一件事，一次做一个项目，你只有一个光标。而如今你要明白的是，你不用再这样了——你拥有一支 agent 大军。我说 agent 的意思是：这是一个 agent，这是一个 agent，这也是一个 agent，它们全部在同时工作。

[47:06] Meng

And on top of that, each of those agents can generate multiple designs at once or multiple documents at once. And then you're kind of cloning yourself, if you will. And your the only task left is you as a product manager who is managing this fleet of agents to create your your dream projects.

更进一步，这些 agent 里的每一个都能同时生成多套设计，或者同时产出多份文档。这相当于你在克隆你自己。而你剩下的唯一工作，就是以产品经理的身份，管理这支 agent 舰队，去打造你梦想中的项目。

[47:31] Aakash

Amazing. for that taste skill. Is that one of the skills that OpenAI provides or did you create it? What does that look like in order to generate slides of this quality?

太棒了。关于那个 taste skill——它是 OpenAI 官方提供的 skill 之一，还是你自己写的？要生成这种质量的幻灯片，它里面到底长什么样？

[47:40] Meng

Sure. So, I'm going to ask you a question because I don't want to switch between the browser and and and this window. So, um the taste skill I want you to go find on GitHub. There's a T skill. Um you can also give me the list on the T skill from a website. Maybe go on Google and also go on GitHub, find the taste skill. So, I'm gonna do it super fast. Speed uh fast and I'm going to go maybe medium. This is not a high difficulty. Should be faster. Um there's also Google. No, sorry. OpenAI Spark. I'm not sure if they still have that. Yeah, I think this codec spark 5.3. They have they don't have the but this apparently is like almost instant. I can Let me try that one actually. Let me try it. just to compare it. I'm I'm curious. I'm so used to using just like uh the other one. So, let's just compare how fast it is. So, find the taste skill. Okay, this one is obviously this this did had like a little Okay, it's it's looking it's fast, but there you go. Uh taste skill. It's from the design taste front end. You have ver different versions. It's uh and then you have redesign skill, soft skill, output skill, uh brutalist skill and so on. There's also one for image gen which is for image generation. So the one that I'm using right now is uh GPT and look at this one is already done and it did it in 25 seconds versus this one it did it in 18 seconds. That's interesting. Maybe it's a GPT 5.5 thing. So GPT 5.5 is also faster than 5.3. So that's that's an interesting te test. Uh I did this at medium and it was faster than spark. But again it could be also uh you know depending on what you're asking for. But again it links to the to the GitHub project and it gives me all the skills. It's basically just a file. So you just picked up on this known file. You didn't have to modify it much and we already get a pretty good slide output.

好，那我直接把这个问题丢给 AI，因为我不想在浏览器和这个窗口之间切来切去。我说：'taste skill，你去 GitHub 上找一下，有一个 taste skill。你也可以从网站上把清单列给我，去 Google 搜一下，也去 GitHub 上找这个 taste skill。'这次我要跑得超快，速度优先，推理强度选 medium 就行——这不是高难度任务，应该更快。另外还有——不是 Google，抱歉，是 OpenAI 的 Spark，我不确定他们是不是还保留着这个。对，应该是 Codex Spark 5.3。据说这个几乎是即时响应的。我来试试这个，就为了对比一下——我很好奇，我平时用惯了另一个。那我们就比比看谁更快。'去找 taste skill。'好，这边这个明显……好，它在查了，确实快。出来了：taste skill，来自 design taste 前端那个仓库，有好几个不同版本，然后还有 redesign skill、soft skill、output skill、brutalist skill 等等，还有一个 image gen 的，是做图像生成的。我现在用的是 GPT 那个——你看，这边已经跑完了，它用了 25 秒，而另一个用了 18 秒。有意思，可能是 GPT 5.5 的缘故——GPT 5.5 居然还比 5.3 快，这是个挺有意思的对比测试。我用 medium 跑的这次比 Spark 还快。当然，这也可能取决于你具体问的是什么。总之，它给我链接到了那个 GitHub 项目，把所有 skill 都列出来了。它本质上就是一个文件。所以你只是捡了一个现成的公开文件，几乎没怎么改，就已经能拿到相当不错的幻灯片产出了。

[49:44] Aakash

Sounds like you'd give that slide output a couple iterations. Would you then ask it once it's done the image genen one to create a PPTX or what's what's how do we close the loop on this presentation?

听起来你会让这个幻灯片的产出迭代个几轮。那等图像生成那一版做完之后，你会接着让它生成一个 PPTX 吗？还是说，我们要怎么把这个演示文稿的流程闭环起来？

[49:55] Meng

Sure. So let's say um you could like again it depends on your workflow and what tool you want and what is the last format that you want. So for example I can say something like uh I really like the first slide. Can you do that in HTML? Uh, and I want you to use the best image to HTML generation vision possible. And I know you can do it because I know GPD 5.5 is one of the best. So this is one way to go about it. I really like the fourth slide and I want you to recreate it in Figma. Maybe we can use computer use to open Figma and then try to recreate it. So that's another another way. And can you use the Figma MCP to to um uh to create the slide the let's say slide number four. So again these are for experimentation but this is how I would close the loop. You have multiple options. I would definitely go with the HTML route um just because the AI has really really good code generation nowadays. If you're asking it to recreate something in Figma, it's going to take way longer and uh you might need to know Figma and you might need to install the MCP or you might even need to do it directly in Figma. So you would maybe like download this as an image and then in Figma they already kind of figure out the workflow and you just drop the image and you ask the AI in Figma to recreate this in Figma. Uh but if you want to stay in codeex which I think a lot of people would want to do that just because you don't want to have like 10 20 subscriptions all at once like Figma subscription you know all of these like so you want to keep sort of like the uh the blast radius as low as possible and yeah that's what I would do. So it's going to generate the HTML and it's going to open it in a browser so when it's done but right now it's not done yet. So uh again there's a number of ways again I can can you also recreate it in uh PowerPoint uh using Keynote the app. So it depends on your workflow. It depends what is the the app that you use but this is how I would do things.

好的。比方说——这还是取决于你的工作流、你想用什么工具、你最终想要什么格式。举个例子，我可以这样说：「我非常喜欢第一张幻灯片，你能把它做成 HTML 吗？我希望你用现在最强的『图像转 HTML』视觉能力来做。我知道你做得到，因为 GPT-5.5 就是这方面最强的之一。」这是一条路。另一条路是：「我很喜欢第四张幻灯片，我想让你在 Figma 里重建它。」也许我们可以用 computer use 打开 Figma，然后尝试重建；或者「你能不能用 Figma MCP 来创建第四张幻灯片？」这些都还偏实验性质，但闭环就是这么做的，你有很多选项。我个人肯定会走 HTML 这条路，因为现在 AI 的代码生成能力真的非常强。如果你让它在 Figma 里重建，会花长得多的时间，而且你可能得懂 Figma、得装 MCP，甚至得直接在 Figma 里操作——比如把这张图下载下来，然后在 Figma 里（他们其实已经把这个工作流打磨得差不多了）直接把图拖进去，让 Figma 里的 AI 把它重建出来。但如果你想一直待在 Codex 里——我觉得很多人会想这么做，因为你不想同时养着一二十个订阅，什么 Figma 订阅之类的——你会想把「爆炸半径」控制得越小越好。是的，我就会这么干。它会生成 HTML，做完之后会在浏览器里打开，不过现在它还没跑完。再说一次，路子有很多种，我还可以说：「你能不能也用 Keynote 这个应用把它重建成 PowerPoint？」这取决于你的工作流、你平时用什么应用，但我就是这样做事的。

[52:12] Aakash

Okay. So Imagen is almost like a first draft which you can give it feedback. Then you can export it using any of these four different prompts of which it sounds like HTML is going to be the fastest. HTML is going to be the most controlled, the fastest, and it's all going to happen in codecs.

好，所以图像生成的版本差不多相当于一个初稿，你可以对它提反馈。然后你可以用这四种不同的 prompt 里的任意一种把它导出，其中听起来 HTML 会是最快的——HTML 可控性最强、速度最快，而且整个过程都发生在 Codex 里。

[52:33] Aakash

Probably probably the least tokens then too.

而且大概也是最省 token 的。

[52:36] Meng

Absolutely. So you have to understand also you can take that and turn that into a video. So for example, you can say something like, oh, I have a new idea. I want to turn those four slides into a video. Maybe you can use something like um what was the name? Well, uh hyperframes and I believe there's a new one. Maybe you can look into those. Let's plan this first. And uh basically the goal and this is good that you give the goal al also is that the goal is that I want these four slides into a video that shows the slide one by one with maybe a fade transition and each slide have a a 5second and maybe in that video we can we can sort of like do a transition of each bullet point like one second each. So that's kind of how I would do it. But um you know there's just so many so many ways and this is the beauty of where we are today with agents is that you're not limited to one tool. Like before my whole life revolved around using Figma and you know of course now I could say the same about Codeex but in this case we're actually using agent and the agent is not using only Figma right and the agent has access to the whole world of tools to create the goal that you want it to to do right and that's I think that's really beautiful

完全正确。你还要明白一点：你可以拿这个东西再把它变成视频。比如你可以说：「哦，我有个新想法，我想把这四张幻灯片做成一个视频。也许你可以用 Hyperframes 之类的工具——我记得还有个新出的，你可以去调研一下。我们先做个规划。」然后——把目标讲清楚这一点很好——目标是：我要把这四张幻灯片做成一个视频，一张一张地展示，也许带个淡入淡出的转场，每张停留 5 秒；也许在视频里每个要点还可以做个逐条出现的过渡，每条一秒。我大概就会这么做。但你知道，方法实在太多了，这正是我们今天有了 agent 之后最美妙的地方：你不再被限制在一个工具里。以前我的整个职业生涯都围着 Figma 转——当然现在你可以说我围着 Codex 转，但这里我们实际用的是 agent，而 agent 用的不只是 Figma，它可以调用全世界的工具来实现你给它设定的目标。我觉得这真的很美妙。

[54:13] Aakash

100%. I think that people who are stuck in chat GBT haven't realized that this can connect to all of your existing apps if you're using it in codeex.

百分之百同意。我觉得那些还困在 ChatGPT 里的人，没有意识到如果你在 Codex 里用它，它可以连接你现有的所有应用。

[54:23] Meng

Absolutely. Everything you can think of you can imagine. Anything that fits your workflow can be done in codeex and you can now use computer use. You can also do uh these screenshots that I highly recommend and you can also do that on a go by using the codeex mobile. What's next after presentations?

完全正确。你能想到的、能想象到的一切，只要契合你的工作流，都可以在 Codex 里完成。现在你还可以用 computer use，也可以用我强烈推荐的截图功能，甚至可以在路上通过 Codex 移动端来做这些。（Aakash：）演示文稿之后，我们接下来聊什么？

[54:43] Meng

Yeah. Um, I I think we already had one hour, so I'm not sure how how long you want to stretch it.

嗯……我们已经聊了一个小时了，我不确定你还想拉多长。

[54:49] Aakash

Um, not too much. Just in case you had some stuff planned. I think you had like the avatars we talked a little bit about. If you want to talk about that, we can quickly go over it. It's up to you.

不用太久。只是想着你可能还准备了些东西——我记得你提过 avatar（数字分身）那个话题，我们之前简单聊过。如果你愿意讲，我们可以快速过一下，看你。

[54:58] Meng

Um, sure. So, but avatar is more like a personal thing. Okay. So, you know, just because I kind of tease everyone about the avatar thing and you had a question about it. So, let's talk about it. Um, so nowadays UGC content is a big deal. And I think that one of the thing that you have to create the most is to creating like a a digital twin of yourself. So in order to create a digital twin, what you would do is that you would take the best head shot of yourself and you would drag and drop into this. Okay? But in my case, uh, since it's kind of personal, I don't want start dragging and dropping my portraits. Um, I'm just going to ask Yeah. Okay. I want you to go into the content folder and I want you to look for the best pictures of me. And then from those best pictures, I want you to create an avatar, a digital twin of myself using GPT image 2.0. And I want different angles, different lighting, uh, in a studio setting, in an outside setting, me using my camera phone, uh, you know, recording myself or me in my studio, uh, or as a YouTuber or as a content creator or me at the office working on at on my at my desk. So, I want you to generate 10 images of me um, using GPT image 2. So this is how I would do it. But normally you would just drag and drop uh the image right here just the same way that you go to like um you know here and then you do the this sort of uh the shortcut. Uh so and then what I would do next once you have your avatar I would say something like okay so I have these screen recordings that I did uh using either screen studio or dream cut and then I want you to take those screen recording and put my avatar and I want you to create a video script using a markdown file and I want you to say those things using my my digital twin to say those things that I have in my video script and next to the to the video presentations that I did or the image presentations that I did. And then I wanted you to use hyperframes to uh do all of that stuff into a one minute video. And I want the 16x9 content for YouTube. I want the 4x3 content with captions uh for X and I want the 9 by6 content uh with uh my avatar at the bottom and then the screen recording at the top with a hook and uh uh that's going to be 9 by6 uh finalized at the end with a call to action that says something like drop a comment. I'm going to send you the whole workflow.

好啊。不过 avatar 更像是个比较私人的东西。行，既然我一直跟大家卖这个关子，你也正好问到了，那我们就聊聊。如今 UGC 内容是个大事，我觉得你最需要创建的东西之一，就是给自己做一个数字分身（digital twin）。要做数字分身，通常你会拿一张自己最好的头像照片，直接拖进这里。但在我的情况下，因为这有点私人，我不想真的把自己的肖像照拖来拖去，所以我直接这样下指令：「我要你进入 content 文件夹，找出我最好看的几张照片。然后基于这些照片，用 GPT Image 2.0 给我创建一个 avatar、一个我的数字分身。我要不同的角度、不同的光线：摄影棚场景、户外场景、我拿手机自拍录像的样子、我在工作室里的样子、作为 YouTuber 或内容创作者的样子、我在办公室伏案工作的样子。总之用 GPT Image 2 生成 10 张我的图。」我是这么做的，但正常情况下你直接把照片拖到这里就行，就像你平时在这里用那个快捷方式一样。接下来，等你有了自己的 avatar，我会说：「我有几段用 Screen Studio 或 DreamCut 录的屏幕录像。我要你拿这些录屏，配上我的 avatar；先用一个 markdown 文件写一份视频脚本，让我的数字分身把脚本里的内容讲出来，放在我做的那些视频演示或图像演示旁边。然后用 Hyperframes 把这些全部合成为一条一分钟的视频。我要一版 16:9 的给 YouTube；一版 4:3 带字幕的给 X；还要一版 9:16 的，我的 avatar 在下方、录屏在上方，开头有 hook，结尾收在一个行动号召上，比如『来评论区留言，我把完整工作流发给你』。」

[57:58] Meng

That's how I would do it. And by the way, I I cram I put a lot of knowledge that I I've been doing a lot recently. So this this prompt is going to be so good for you guys. Uh but yeah, this is how how I would do it. And obviously it's not guaranteed that it's going to work. By the way, there's a lot of stuff. But if I have to imagine myself in 6 months time in uh in a year's time I would imagine that the AI will be able to do this perfectly which is which comes back to the the point where creating you a digital twin is going to be amazing. Uh do I do want to drop like a little FYI there a there's going to be a push back on AI video generation and image image generation where you don't want to deceive consumers. So doing a digital twin is fine as long as you're not creating yourself using a fake product or doing stuff that are not real. But you know I would imagine that creating presentations is fine and you know you as a human has to validate the content to make sure that you're not deceiving anyone. Uh but there will be a huge push back because I'm starting to see a lot of these video generation using cens that are creating like fake products. uh and a lot of people are going to complain uh to the FCC and and and there's going to be like, you know, a lot of bad stuff going on. But, you know, there's also the good side of it, which is what I'm showing you guys right now, is like, okay, I want to create a a video presentation that I'm going to send to my team, and uh these are the talking points. This is my AI avatar because I don't want to do my hair. I don't want to, you know, uh, you know, maybe it's it's at night time, the lighting is horrible. So, this is the best way to do it.

我就会这么做。顺便说一句，我把自己最近实践的大量心得都塞进去了，所以这个 prompt 对你们来说会非常有用。当然，这不保证一定能跑通——里面环节确实很多。但如果让我想象六个月后、一年后的自己，我相信到时候 AI 能把这件事做得完美，这又回到那个观点：给自己做一个数字分身会是件很棒的事。不过我想在这里提个醒（FYI）：AI 视频生成和图像生成会迎来一波反弹（push back），核心是你不能欺骗消费者。做数字分身本身没问题，前提是你不能用它去演示假产品、去做不真实的事情。做演示文稿这种用途我认为是没问题的，而且作为人类，你必须亲自校验内容，确保没有误导任何人。但反弹一定会很猛烈，因为我已经开始看到很多用 Seedance 这类工具生成的视频在制造假产品，很多人会去 FCC 投诉，接下来会有不少乱象。但它也有好的一面，就是我现在给大家展示的这种：比如「我要做一条发给团队的视频演示，这些是要点（talking points），出镜的是我的 AI avatar——因为我不想弄头发，或者现在是深夜、光线很糟」。这种时候，这就是最好的做法。

[59:48] Aakash

Should people be using Seed Dance for that video or is Chad image fine?

那做这种视频，大家应该用 Seedance 吗？还是用 ChatGPT 的图像功能就够了？

[59:53] Meng

So, Chad doesn't have a video generation. They already discontinued like their video generation stuff.

ChatGPT 没有视频生成功能，他们已经把视频生成那块下线了。

[1:00:01] Meng

I would probably use Google V or Google Omni. But the number one thing that I would use if if you're focusing on presentation, I would use hijen. And hunen has a plethora of tools uh for lip syncing for creating your avatar, creating your digital twin uh specifically for the need of presentations. Now, Cedans is the best AI model for everything including like film making or it has the best understanding of like let's say you you want to ask for like a cat who does a vacuum in Tokyo. Well, Cance is definitely going to do uh the best job at that.

我可能会用 Google Veo 或者 Google Omni。但如果你专注做演示文稿，我的首选是 HeyGen。HeyGen 有一整套工具，涵盖口型同步（lip sync）、创建你的 avatar、创建你的数字分身，专门针对做演示的需求。而 Seedance 则是全能型里最强的 AI 模型，包括电影制作之类的场景，它的理解力也最好——比如你想要「一只猫在东京用吸尘器打扫」，Seedance 肯定能做得最出色。

[1:00:43] Meng

Okay, amazing. Last point I just wanted to cover off on in codeex is when how do you generate like divergent ideas for app design like we were talking about that QR email scanner? What's your workflow or the recommended workflow for PMs when they want to really investigate the design space of a product feature? Sure. So the first thing I would do so I'm going to I'm going to prompt. I I think prompts is very useful to a lot of people. Okay. Okay. So, I want you to open the app. I want you to open Xcode and I want you to run the app and then you know let me know if there are any permission issues. Let me know if I have to create an Apple account, developer account. Let me know if I have to log in. But, you know, at the end of the goal should be to open the app and to run the app on either my phone or on iOS simulator so I can test the app. And then once you run the app, I want you to take a screenshot of every single part of the flow. So to give some example, we have the sign in, we have the payment flow, we have the editor flow and so on. So um okay, so my codeex was opening Figma, so I had to focus back. Um and yeah and there you go. So this is how I I would prompt it. And you know at every step of the way you can ask for you know for codecs to take a screenshot of the app and to make you validate things and to kind of like ask you if the pixels are right or the designs are right. Now, it's kind of hard for me to show you without getting into like the nitty-gritty of all of these uh uh projects that I'm working on, uh which can be a bit sensitive, but you know, in this case, if I was in like if the app was already built, right? So, for example, I don't know. Oh, PowerPoint presentation. Let me see if Oh, okay. See, I'm I'm constantly surprised by AI, right? It's able to to open the PowerPoint presentation, okay? And it create the PowerPoint presentation. So, if you're already familiar with PowerPoint or Keynote, you already have a basic slide that looks better than what most PMs can do in term of design, right? I'm not saying, you know, like it's better than the the senior designer, but it's still better. But if you're only f if you forget about the design right and you can always upgrade this with the taste skill this is what you have and I open it in codeex and I can like it's a PowerPoint file I can also open it in keynote and edit things. So this is one example let me see if I have um the HTML if it's ready. Yeah it is ready. So let's review this.

（Aakash：）好，太棒了。关于 Codex 我想聊的最后一点是：你是怎么为 App 设计生成发散性创意的？就像我们之前聊过的那个二维码邮件扫描器。当 PM 想要真正探索一个产品功能的设计空间时，你的工作流或者你推荐的工作流是什么？（Meng：）好。我要做的第一件事——我直接来写 prompt，我觉得 prompt 对很多人都很有用。好，开始：「我要你打开这个 App。打开 Xcode，把 App 跑起来，然后告诉我有没有权限问题，要不要创建 Apple 账号、开发者账号，要不要登录。最终目标是把 App 打开并跑在我的手机或 iOS 模拟器上，让我能测试它。App 跑起来之后，我要你给整个流程的每一个环节都截图——举例来说，我们有登录流程、支付流程、编辑器流程等等。」——哦，我的 Codex 刚才把 Figma 打开了，我得把焦点切回来。好，就是这样，这就是我下 prompt 的方式。在每一步你都可以让 Codex 给 App 截图，让它请你来校验，比如像素对不对、设计对不对。现在我很难在不深入细节的情况下给你演示，因为我手头这些项目有点敏感。但假设 App 已经做好了——比如，我看看……哦，PowerPoint 演示文稿！你看，我总是不断被 AI 惊到：它居然能打开 PowerPoint，而且真的生成了 PowerPoint 文件。所以如果你本来就熟悉 PowerPoint 或 Keynote，你现在拿到的这个基础版幻灯片，在设计上已经比大多数 PM 自己做的要好了。我不是说它比资深设计师强，但确实更好。就算先不管设计——而且你随时可以用 taste skill（品味技能）来升级它——你拿到的就是这个成果。我在 Codex 里打开它，因为是 PowerPoint 文件，我也可以在 Keynote 里打开并编辑。这是一个例子。再让我看看 HTML 那版好了没……好，好了，我们来看看这个。

[1:03:52] Meng

Okay this is for review. I'm going to open it in the browser. Oh, this is HTML review. I'm not sure where it doesn't have the ability to open in a browser, but I can always ask it if I'm not sure where. Um, there you go. Right. No, this is the image. Well, I can always go to the folder, but uh so let me take a screenshot. I'm not sure why. So, this is where I'm like, you know, can you open this HTML file for me and open it in codeex? And uh I'm going to press enter. I'm going to ste it right now because this is this takes priority and hopefully

好，这个是用来 review 的。我要在浏览器里打开它。哦，这是个 HTML 的 review 文件。我不太确定它有没有直接在浏览器里打开的能力，但不确定的时候我随时可以问它。你看，出来了。不对，这是那张图片。当然我也可以直接去文件夹里找，不过——让我截个屏。不知道为什么没出来。所以这种时候我就会直接说："你能帮我打开这个 HTML 文件吗，在 Codex 里打开。"然后我按下回车。我现在就让它执行，因为这件事优先级最高，希望能成。

[1:04:37] Aakash

Oh, nice.

哦，漂亮。

[1:04:38] Meng

So, it's really cool. So, it's going to open it. And while we're doing that, so let's see. Yeah, you know, it's it's really amazing. And you guys don't see it, but it's opening my Xcode. It's building, you know, it's doing a lot of things that I don't want it to do because, you know, these are not real projects. So, I'm just going to stop it here.

所以这真的很酷，它就要把文件打开了。趁它在跑，我们再看看——是的，真的很神奇。你们屏幕上看不到，但它正在打开我的 Xcode，在做构建，做了一大堆我其实并不想让它做的事，因为这些都不是真正的项目。所以我就在这里把它停掉。

[1:05:00] Aakash

Amazing, guys. So, we just walked through some of the most important PM use cases for you in design, right? Building app designs, using real screenshots to iterate and improve on those app designs, building slides and charts with your real data, and as you saw, minimally directing where to even pull that data from. It has full permissions because you toggled on for permissions and this is how you really increase your leverage as a product manager. Another question I had for you Mang and we were talking about this pre-all was around this topic of PMS potentially shifting out of product management right now. Last week we saw 10% of MEA get laid off. A couple weeks before we saw similar numbers at Oracle. the market is starting to get flooded with PMs and a lot of these people, they're being forced out of a job. They're looking at the world and they're saying, "Whoa, maybe I should be building an AI app of my own." What are the things that a PM needs to know if they're going to go from PM to founder uh to really succeed? Right? So, I just want to clarify something. And when we say that P PMs are getting fired, I think it's important to clarify that it's the the non-technical PMs that are getting fired, the technical PMs are actually staying at those companies. Uh and and this gives us a very important message, which is that as a as a PM, you need to get more technical. And when we say technical, it doesn't mean that you're going to write the line of code. Like I mentioned before, I I haven't written a single line of code in the in the past six months. Technical is this. This is what I mean by technical. You're no longer the the bureaucracy player, the politics player in the company. Nobody needs that anymore because AI can kind of juggle around that. Um your job is basically to understand all of these jargon. So what is the best AI model? You know when someone who's more technical than you who's working on those project when they talk about uh GPD2 image 2.0, you know what it is. So those PM who have these superpowers and who have all of these knowledge base and who has all of these workflow they um they will be the one who will be staying and they will be the one that will be um transitioning to a new role. And for those who who got fired by the way I'm sorry but you will probably transition into a new role that is more technical and then your job will be safe. Um but beyond that, right, let's say you transition to that new role. You also have a window to for me a far better role than any of those working at the big company because these big companies, they don't have feelings

太棒了，各位。我们刚刚把 PM 在设计上最重要的几个用例都走了一遍，对吧：做 App 设计稿、用真实截图去迭代和改进这些设计、用你的真实数据做幻灯片和图表——而且你们也看到了，连数据从哪里拉取都只需要最少的指示。它拥有完整权限，因为你打开了权限开关，这就是作为产品经理真正放大自己杠杆的方式。Meng，我还有一个问题想问你，我们开播前也聊到过——就是现在 PM 可能正在被迫离开产品管理这个话题。上周我们看到 Meta 裁掉了 10% 的人，几周前 Oracle 也是类似的数字。市场上开始涌入大量 PM，很多人是被迫失业的。他们看着这个世界，心想："哇，也许我该自己做一个 AI 应用。"如果一个 PM 要从 PM 转型成 founder，想真正成功，需要知道哪些东西？（Meng：）好，我想先澄清一件事。当我们说 PM 正在被裁的时候，很重要的一点是要说清楚：被裁的是非技术型 PM，技术型 PM 其实都留在了那些公司。这给了我们一个非常重要的信号——作为 PM，你需要变得更懂技术。而当我们说"技术"的时候，并不是说你要亲手写代码。就像我之前提到的，过去六个月我一行代码都没写过。"技术"指的是这个：你不再是公司里玩官僚、玩政治的那个角色，没人再需要那些了，因为 AI 基本能把那一套绕过去。你的工作本质上是要搞懂所有这些行话。比如最好的 AI 模型是什么？当一个比你更懂技术、正在做那些项目的人跟你聊起 GPT Image 2.0 的时候，你知道那是什么。所以那些拥有这种超能力、拥有这些知识储备、拥有这些 workflow 的 PM，他们才会留下来，他们才是能转型到新角色的人。至于那些已经被裁的朋友——顺便说一句，我很遗憾——但你大概率会转型到一个更偏技术的新角色，然后你的工作就安全了。不过除此之外，假设你转型到了那个新角色，你其实还有一个窗口期，去争取一个在我看来远比在大公司打工更好的角色——因为这些大公司对你是没有感情的。

[1:07:55] Meng

for you, right? When they need you, they hire you. When they don't need you, they fire you. But what if you're your own boss, right? So I think you know for now this is what I do and I manage a team of uh six people and basically I have build these products. They're making well over a million a year and I can afford a team. I can afford to pay my tokens which is amazing because I love doing what I'm doing and I want I want to keep doing that. So um you will pro the end goal the endg game is probably that you starting your own company because AI you don't need to be scared of starting a company anymore because AI can take care of all the paperwork for you all the accounting for you all the the boring stuff the janitor stuff the stuff that you were always scared of doing and even the marketing stuff it can do a lot of that stuff for you so at the end of the day the last 10% or the last 8% is you kind of being um you know orchestrating everything. So you're the one who does the quality assurance. You're the one who uh you know make sure that the plan that you give to AI makes sense. You're the one who has the moat. So you know best because like any business rule is that you have to be the one who knows this topic the best otherwise you don't have any leverage. So when you have this knowledge whether it's around coffee design PM you know uh lawyer stuff you should utilize that and then let AI be your amplifier magnifier so that you can quickly make these micro decisions and you can deploy a fleet of agents. Uh, I think that's the end game. But I think for now, right, you are probably, let's say, either you got fired and you have to transition to a more technical role or you're already technical and you didn't get fired, which is amazing and then but eventually you will get fired because AI will replace everyone at some point or you we will find new ways to to do our job in which AI cannot fire us. uh but it's you know it's a cat and mouse uh chase but eventually if you know if you if you solve that sort of a formula and there's by the way a formula for everything there's a recipe for everything this is what I kind of learned nowadays like for everything there's a formula so whether it's like a YouTube channel there's a formula to go viral or whether it's like a an expose there's a formula to go viral you know Instagram Tik Tok and you know you can look at my Instagram you can look at my uh at my uh LinkedIn and all that stuff. I have viral post and all those things. So, I have kind of everyone's still learning. I'm not saying I'm like, you know, uh I know everything. I'm not saying that at all.

对吧？需要你的时候就雇你，不需要你的时候就裁掉你。但如果你自己当自己的老板呢？我现在做的就是这个：我管着一个六个人的团队，做出了这些产品，它们一年收入远超一百万美元，我养得起团队，也付得起我的 token 费用——这太棒了，因为我热爱我正在做的事，而且想一直做下去。所以终局大概率是你去开自己的公司。因为有了 AI，你不需要再害怕创业了：AI 能帮你搞定所有文书工作、所有记账、所有无聊的杂活、那些你一直害怕做的"清洁工"式的事情，甚至连营销的很多活它都能干。所以到最后，剩下的那 10% 或者 8%，就是你来做统筹编排：你负责质量把关，你负责确保交给 AI 的计划是合理的，你是那个拥有护城河的人。你必须最懂这个领域——任何生意的规则都是，你得是最懂这个话题的那个人，否则你就没有任何杠杆。所以当你拥有这种知识，不管是咖啡、设计、PM，还是法律相关的东西，你都应该利用它，然后让 AI 成为你的放大器、扩音器，这样你就能快速做出这些微决策，部署一整支 agent 舰队。我认为那才是终局。但眼下呢，你要么是被裁了、必须转向一个更技术的角色，要么你本来就够技术、没被裁——那很好，但最终你还是会被裁，因为 AI 迟早会取代所有人；或者我们会找到新的工作方式，让 AI 没法"炒"我们。这是一场猫鼠游戏。但归根结底，如果你能解开这个公式——顺便说，万事皆有公式，万事皆有配方，这是我最近悟出来的：任何事情都有公式。不管是做 YouTube 频道，有一套爆款公式；还是做长文爆料，也有一套走红公式；Instagram、TikTok 都一样。你可以去看我的 Instagram，看我的 LinkedIn，我在这些平台上都有过爆款帖子。当然大家都还在学习，我不是说我什么都懂，完全不是这个意思。

[1:11:12] Meng

I'm just saying that I have done, you know, a viral post on each of them. And my point is that there is a formula for all of those things. And there's also a formula which is for the endgame to start a business. And that formula is you being the best at your job and you deploying your fleet of agents and you uh you utilizing that last 8% of a human taste uh to orchestrate uh all the task and make sure that it's it's like the quality is always higher than the baseline but to understand you have to understand that baseline is getting higher because of AI but also the ceiling of quality quality is also getting higher. So your job is always to get to if this is a fivestar which is by the way is a podcast I listened from the the co Airbnb you want to get to 11 star uh but at the minimum should be the five star and then you have to imagine what is six star, seven star, eight star, nine star, 10 11 and then your job is to always be above the five star uh six star, seven star and uh to to think about the future which is the 11 star. Wow, what a persuasive argument for tripling down on your product management skill set, product strategy, vision, delivering a six, sevenstar, 11star eventually experience. That is pretty much the future for all of our roles. Mang, you have brought it down for us in an amazing way. If people want to learn more from you or connect with you online, where should they go?

我只是说，我在每个平台上都做出过爆款。我想表达的是：所有这些事情都有公式。而通往终局——创业——也有一个公式：那就是你在自己的专业上做到最强，部署你的 agent 舰队，然后用人类品味那最后的 8% 去统筹所有任务，确保质量永远高于基准线。但你要明白，因为 AI 的存在，这条基准线在不断抬高，同时质量的天花板也在抬高。所以你的工作永远是——如果五星是标准（顺便说，这是我从 Airbnb 联合创始人的一期播客里听来的），你要奔着十一星去，但至少要做到五星，然后去想象六星、七星、八星、九星、十星、十一星长什么样，你的工作就是永远做到五星之上——六星、七星——并且去思考那个代表未来的十一星。（Aakash：）哇，这真是一个极有说服力的论证：加倍押注你的产品管理技能——产品策略、愿景、交付六星七星、最终十一星的体验。这几乎就是我们所有角色的未来。Meng，你今天讲得太精彩了。如果大家想向你学习、想在网上联系你，应该去哪里找你？

[1:12:47] Meng

Sure. You can go to X um Mangto. You can also LinkedIn, Instagram, uh I'm starting my Tik Tok channel, so it's also Mento. I believe you can also find the uh the products that I build and um you know, just check like these are the stuff that I vibe coded. Um and I'm using AI to create all of these things. You can check for yourself the level of quality that it is. And uh keeping in mind that each of these products have way over 10,000 prompts each. So, do not give up on the first prompt. But yeah, you know, Aura, New Form, Dream Cut. I'm going to keep building products. I'm going to keep uh learning these formula, and I hope you will, too.

当然。你可以上 X 找我，账号是 MengTo。LinkedIn、Instagram 上也有，我还刚开了 TikTok 频道，同样是 MengTo。你们应该也能找到我做的那些产品——去看看吧，这些都是我 vibe coding 做出来的东西，全都是用 AI 创造的。你可以亲自去检验它们的质量水准。记住一点：这些产品每一个都用了远超一万条 prompt。所以，不要在第一条 prompt 上就放弃。总之，Aura、New Form、Dream Cut——我会继续做产品，继续学习这些公式，希望你们也一样。

[1:13:31] Aakash

All right, we're going to link all his socials, Aura, New Form, and Dream Cut down below. Subscribe to his YouTube channel. Follow him on all platforms. Ming, thank you very much.

好的，我们会把他所有的社交账号，还有 Aura、New Form 和 Dream Cut 的链接都放在下方。订阅他的 YouTube 频道，在各个平台关注他。Meng，非常感谢你。

[1:13:40] Meng

Thank you so much for listening and uh thank you for inviting me to this podcast. It's honor.

非常感谢大家的收听，也谢谢你邀请我来这期播客，深感荣幸。

[1:13:45] Aakash

My pleasure. Bye, everyone. I hope you enjoyed that episode. If you could take a moment to double check that you have followed on Apple and Spotify podcasts, subscribed on YouTube, left a rating or review on Apple or Spotify, and commented on YouTube, all these things will help the algorithm distribute the show to more and more people. As we distribute the show to more people, we can grow the show, improve the quality of the content and the production to get you better insights to stay ahead in your career. Finally, do check out my bundle at bundle.ashg.com akashg.com to get access to nine AI products for an entire year for free. This includes Dovetail, Mobin, Linear, Reforge, Build, Descript, and many other amazing tools that will help you as an AI product manager or builder succeed. I'll see you in the next episode.

我的荣幸。各位再见。希望你们喜欢这一期节目。请花一点时间确认一下：你已经在 Apple 和 Spotify 播客上关注了我们、在 YouTube 上订阅了、在 Apple 或 Spotify 上留下了评分或评论、并在 YouTube 上留了言——所有这些都能帮助算法把节目分发给更多人。当节目触达更多人，我们就能把它做大，提升内容和制作的质量，为你带来更好的洞见，帮你在职业生涯中保持领先。最后，记得去 bundle.aakashg.com 看看我的大礼包，可以免费获得九款 AI 产品整整一年的使用权，包括 Dovetail、Mobbin、Linear、Reforge、Build、Descript 等许多出色的工具，帮助你作为 AI 产品经理或 builder 取得成功。我们下期节目见。