Loading summary
Transcript56 lines
- [00:00]
Meng Tu
If you always chase the trends, you will become AI slob very soon. Right now, the baseline is the inter fonts, the purple gradients. That would have been amazing five years ago, like, if someone were using purple gradients. Everyone was going nuts over that. But nowadays, AI slob, right, very soon, you know, it's going to be the serif fonts and the, you know, the same animations that AI use all the time. You have to be always a step ahead of what is the baseline.
- [00:30]
Host 1
Welcome to Dive Club. My name.
- [00:32]
Host 2
My name is Rid. And this is where designers never stop learning. This week's episode is with Meng Tu, who's one of those people I like to keep tabs on to see how he's evolving his process as he continues
- [00:45]
Host 1
to build his ideas with AI.
- [00:47]
Host 2
So we're going to do a ton of screen sharing and go deep into all of his strategies for prompting design, MD files, and little tactics that he uses to get better outputs from the models. So, to start, I asked Meng to share more about why he's went all in on codecs since the last time we talked.
- [01:06]
Meng Tu
I used to use cursor all the time, but now Codex is shifting the mindset. For a lot of designers and a lot of people who've never done design before or coding before, it's kind of like an evolution from ChatGPT into something far more powerful. Your brain is on your computer. All the files are there. You can build apps, but you can also chat. You can also plan things. You can design. You can generate charts, create HTML, create markdown files, and it connects to all of the plugins and integrations such as Slack, Telegram, Discord, most recently. You can now open and continue codecs on your computer using your phone, which I think is a huge deal. The first time we met, we did this podcast, which was about 16, 18 months ago. I built my very first app, Dreamcut. It was using Cursor. It was using Sonnet 3.5. I never released that app. There was very key parts of the app that didn't pass the bar of quality. So even though I thought in my mind that I would eventually solve those issues, I never got to solve them because the technology was too young at the time. It felt great to be able to wipe code an app in a week or in a month. But nowadays with codecs, we can do all of that in a day. But you need the knowledge. And Recently I watched Mr. BC he was saying, basically because of knowledge, he's able to start a new YouTube channel, Faceless One, and get, oh, I saw
- [02:58]
Host 1
that he did 20 million. 20 million.
- [03:00]
Meng Tu
20 million, 20 million subscribers in six months. And he said he can totally do that with the knowledge that he has. So I believe the same way with codecs or with, you know, any other tools, such as the new Cursor with Composer 2.5 or the new Cloud. But what I like about Codex is that I believe they were the first one. They started in February, and they were the first one to introduce this sort of way of building everything with threads. And that completely changed the mindset because it was so powerful that if you look at Cursor now, that's exactly their UI nowadays, right? You open cursor. It's like, I can't. Sometimes I can't even tell between cursor and codecs anymore because they're so familiar. And the difference is just the model. But I think the maturity of codecs is just far greater at this point. Even though I really love composite 2.5, I've been doing a lot of really, really quick iterations. In terms of speed, there's no equal. So this is one knowledge that everyone must know is what model do you use, what app should you use, and what is the difference between composer 2.5 and GPT 5.5, medium or extra high? If you're building apps, you need to know what the tools are, right? It used to be Figma, which, by the way, I don't open Figma anymore. Yeah, sure, I sometimes open it for a history of the work that I've done in the past, like the logo and all that stuff, but I don't open Figma anymore to build designs or to create design from scratch anymore. I do all of that work in Codex. All of my projects are here, including, you know, the preparation for a podcast. I would just go to my agents, like, hey, I have a new podcast coming. These are my talking points that I want to talk about. Can you generate the images? Or anytime that I. I find an article that is super cool or a video on YouTube that is amazing, I would go and, you know, okay, can you create an article on this amazing library that, you know, someone just created? Or, you know, can you create an article about the writing rules? Like, I watched a really cool podcast video on YouTube about the simplicity of writing and, you know, copywriting and stuff like that. I was like, can you watch the video? And then can you create and put all the main points about it? Can you also insert Paul Graham's essays at the same time? And can you also remember, like, the philosophy of it and can you integrate that into the writing? When we do it together with the
- [05:42]
Host 2
agents, Real quick message.
- [05:43]
Host 1
And then we can jump back into it.
- [05:44]
Host 2
I've anticipated Desen's recent release for a full year. It's called Surfaces, and it enables you to design and prototype directly on top of an existing production interface. All of the pages and flows that you need are preloaded inside of Destin as starting points, so you can easily make changes, explore ideas, and then when you're ready, ready, you can share your
- [06:09]
Host 1
prototype in a single click.
- [06:11]
Host 2
Destin is the only design tool that allows you to design on existing pages and flows pulled directly from Prod, which is a pretty big deal for teams. And you can get started today. Just head to Dive Club Dessin. That's D E S S N. If you still haven't tried Paper, even though it kind of feels like everybody on this podcast is talking about it lately, they just made it work. Way easier to get started. Because you can now copy and paste from Figma directly into Paper's canvas. All of the layers and their properties, including images and SVGs, are imported in an instant. It's pretty big deal. And you can try it out today. Just head to Dive Club Slash Paper to get started.
- [06:55]
Host 1
Now, on to the episode. So you're not even just using it just to create. It's actually like where you are storing resources almost too.
- [07:04]
Meng Tu
Absolutely. And that is just step one. Step two is, I think designers have to build their own tools, because the tools that we have are never good enough. Let me give you an example. This is my own version of Notion, and so getting this. Yeah. My own version of Notion. I will tell you why I created this. So, for example, on Notion, everything has to happen online. The AI is kind of like, it doesn't work locally. So what I'm doing here with Codex is working with my files that are on my computer in Markdown. And every time we create a file here, it appears here. So when I did the prep and I asked my AI, okay, for every title, I want you to generate an image. And then I also have a perfect prompt for the image, which I also create a UI for it, in which I have a bunch of preset prompts that I have gathered over the years, including, for example, turning a design into a perspective mockup, because it looks just way better. So if you look at this one, if you look at this one, the first version looks like this, which is like, as I mentioned before, AI slob. But then you turn into a perspective mockup, and suddenly it looks so much Better. So this is just one problem. This is just one example of what you can do with AI. And on top of that having tools like, okay, you're doing a presentation now, you can draw on it. Okay, cool. You can also watch the notes because this is all part of your file. So you can just like, if I'm doing a talk, I have my notes here, I have my version history here, and then, you know, I can see a history of the changes that I have made, you know, a history of the design if I started from scratch or not. And then all of this is created locally using my agents, which started from Codex.
- [09:06]
Host 1
I've almost built this so many times because I see the value in having all of my content locally. Like, I don't want it trapped in some cloud based product. I don't love Obsidian, I've tried so many times to have it be sticky and I just don't love it. And I've only built it as a Mac app. But you building this locally in the web, I hadn't considered before and it's pretty compelling.
- [09:33]
Meng Tu
What is cool when you build your own app is that you figure out like, okay, I have all of this information here. What if I can just ask AI to use each section as a context to create my image? So you can literally just create a new block like this and then you can just generate an image without any prompt and with a bunch of your presets. So for example, I need a YouTube cover or an article cover and then I just generate on the fly. I don't need any context because the context is here. So when I'm going to be generating this, it's going to talk about what codecs actually did. That's the beauty of building your own tool is because you're not only doing that out of frustration because something is missing, you're not only doing that because it's the only way to do it locally. Because Codex works really well locally and agents can do it far more powerful than any private walled garden that exists out there in the cloud. But also as you create those tools, you suddenly discover so many new ways to design, such as this, for example. I'm one of those designers who discover, as I work, right, I don't plan things, I don't have a giant blueprint where I just plan all the ideas in advance. Because when you work solo, this is your superpower, this is how you move way faster than anyone else. And so when you generate like this and then you can turn into a different version. So now I can turn this into perspective. And you know, I can turn the video now so this becomes a video.
- [11:14]
Host 1
Wow.
- [11:14]
Meng Tu
It's all part of the same workflow. It's all part of the tool that you're making, which again starts from codecs.
- [11:22]
Host 1
I want to talk about the process of building the tools and actually writing code because I totally forgot, like, of course you were using Sonnet 3.5 last time we talked, which now I have so much respect for it. Like at the time that felt like magic. And now you look back and you're like, oh my gosh, it's so rudimentary. So I salute thee for getting as far as you did with sonnet 3.5. My question then is, how does Codex shape the way that you approach actually building software now? How has your workflow there changed as a result?
- [11:53]
Meng Tu
Let's say you, you start from scratch. What do you want to do at this point is to go to the plugins and then you want to find the tools that are part of your workflow. Because everyone is different, every computer is different. And so you want to download, of course the main one, like computer use. But then you have a lot of things like I'm sure you know, granola if you work with that, or Canva or figma that you can install. If you want to make videos, you want to use Remotion. If you want to use video again you have Hyperframe. And then if you like to use voices, AI voices or AI avatars that can be really, really powerful. Plugins integrations are like the same as plugins in Figma is the powerful ones created by startups or individuals that have spent a lot of time integrating IT Skills on the other hand are the ones that are kind of like prompts. A skill is basically a prompt, sometimes a large prompt you can think about what is the best, like what is the best practice. It's more like a style guide. What is the best practice for taste, which font to use? How do you guide AI to not create AI slob? So the skill would be great for that. The thing is that if you always chase the trends, you will become AI slob very soon. So my suggestion to you is, is always be a step ahead. It's like playing chess. You have to be always a step ahead of what is the baseline. So right now the baseline is, yeah, the AI slop, the inter fonts, the purple gradients. And you know, that would, would have been amazing five years ago, like if someone were using purple gradients, everyone was going nuts over that. But nowadays AI slob Right. Very soon, you know, it's going to be the serif fonts and the, you know, the same animations that AI use all the time. So you have to always be ahead. And the only way you can be ahead is just to spend that last 10%. So the way that I like to do it, especially as a designer or as someone who has kind of like developed taste over so many years, is that I use my memory. My memory is all of the things that exist on my computer that I have gathered over so many years of my career. The fonts that I know, the files that I have created, the figma designs that I have done, the code that I have done. And because it exists on my computer, I can just reference it and give it to AI as a starting point. So when you have a starting point, your AI will stop making AI slop, because your starting point is you, and you are definitely not AI slob, because you are unique as a human. For those who, let's say, are not designers, just getting started, take screenshots. If you look at my codecs or cursor, right, because I've been doing a lot of iterations, it always starts with a screenshot. Screenshot, screenshots, screenshots. Every single time I start with a screenshot, the reason why is very simple, is because the screenshot is the fastest, easiest way to build without having to voice it, without having to type it. So, for example, let's say I want to fix an issue here. So what I do well, in codecs, we have a shortcut, which is command, command, boom. It sends a screenshot right away to codecs, just like that. And so it makes the whole thing so much easier. It it took a screenshot of your browser or whatever window that you have active, and then from here you can just start typing. You can just say, okay, I want to fix the top left part of this. I want to fix the video timeline. So the question is, how knowledgeable are you of your product? Because if you're not knowledgeable about your product, forget it. You're not going to do anything meaningful, and someone else in three months time will do exactly what you're doing and in one prompt. But I can guarantee you that nobody can make Dreamcut in one prompt just because I went through so many iterations and so many features. And here's another question. How many prompts do you think I use for every project for any of these projects that I. That I launched?
- [16:20]
Host 1
I'm sure it is thousands.
- [16:23]
Meng Tu
Yeah, at least ten thousands each.
- [16:26]
Host 1
Yeah, I believe It, I totally believe it.
- [16:27]
Meng Tu
Right. The one secret I use when I redid this video editor, I did it in the day by the way. It was ugly, but I did it in a day. And the secret was I searched the libraries that were video editors and I wanted the ones that I that had video recording that, well, video editing, but also screen recording, zooms and to be able to resize and all that stuff. And then you, you spend the last 10% to do all of these extra features that didn't exist before. So for example drag and drop or you know, to be able to re reposition it, you know, and these little dots that grows.
- [17:06]
Host 1
Dots. Yeah, that's right.
- [17:08]
Meng Tu
And this is inspired, this is inspired by Apple. But you will never find something like this in an existing library. Why? Because it's not part of that personality or that experience that you yourself have by watching Apple work or by watching your best friend designer work and then giving you that idea and then knowing how to prompt it into existence.
- [17:31]
Host 2
The only way, because I know that
- [17:32]
Host 1
you have an engineering background, right? Like you're not intimidated by code. So if you're working on the web app version within that 10%, are you writing any code at all or are we prompting everything for the finer details?
- [17:45]
Meng Tu
Right. So remember at the time I was saying 95% of of my code was written by me. Now 0% of it was written by 0%. Yeah, we have gone that far. And so yeah, see I just noticed like a little problem here, it's overlaying. So I could just take a screenshot and then, you know, based on the resolution of my video editor we have these edge cases that AI will never be able to fix. I spent so much of my time testing everything and just reporting bugs, but not just reporting bugs, but saying exactly the right thing so that AI understands me. So part of the skills nowadays is to be able to talk to AI in the most efficient way possible. And one of the ways is just yeah, take screenshot, use your voice. Because when you use your voice you can explain things much clearer. Instead of saying go here and because you're lazy to type all of that stuff, you don't add all of those details that you can speak like three or five times faster.
- [18:48]
Host 2
There's one question that I can't stop, stop asking myself. What if companies applied to talk to you rather than the other way around? And that question is the foundation for the all new dive talent network. And it's working like right now I'm helping many of the most exciting startups that I know to hire the designers and builders who listen to this show. So if you're curious what might be out there, and maybe you want to get on my list, or maybe you're even looking for your next design. Higher head to dive club slash talent to join today.
- [19:22]
Host 1
I'm encouraged by your 0% answer, because I do think there's like a whole group of people that I have on the show actually, where, you know, it's slower to describe that you should change the padding on something than to just go in and change it. And I'm like, yes, I totally agree. But I think it goes back to something that you said earlier, where the big shift with these tools for me too is I'm just doing way more things in parallel. Like, I don't care if it takes more time for AI to change the padding than if I wrote it manually, because I'm not sitting there waiting for a loading state. Like, I'm allergic to loading states. Now, if I'm looking at a loading state, it means that I need to spin up another agent, you know, and so I'm okay with kind of doing a similar workflow as long as I'm able to be making many different polish improvements simultaneously.
- [20:08]
Meng Tu
Yes, exactly. It's how precise you are, you know, back in the day, you know, when I say back in the day, I mean, a lot of people still do it, you know, using figma and moving rectangles and sort of like creating components, you know, creating variables and exporting code and doing everything manually. That skill is still super useful. So let me give you an example. Nowadays you can also annotate. So now you can just point something that you want to fix, and then you can say, you know, fix this, fix the padding, et cetera. Instead of taking a whole screenshot and explaining that, oh, this. The part that I want to fix is in feature templates. You annotate, and then, boom, you can do that. The best people are the editors, right? I also think myself as more of an editor than someone who likes to start from scratch. And also, you can totally say something like, okay, can you create a simple Design generated in GPT Image 2 nowadays, right? Like, for example, if you're creating, like a 3D design, you would start with this. You would start with a screenshot, and then you. You turn that into a design. If you're creating a brand or a slide, then you start with that, and then you sort of like, slowly and surely walk into the things that you need, the inspiration that you need to gather and eventually get in, get into the final results. So generating.
- [21:35]
Host 2
Do you ever do that for interface design?
- [21:37]
Host 1
Like, are you ever exploring ideas? Okay, so talk about that for a little bit because I'm. I'm doing a lot with like, spinning up quick HTML websites just to visualize ideas quickly. But I'm not doing anything with GPT.
- [21:49]
Host 2
But every time I play with it
- [21:50]
Host 1
to create an interface, even if it's just as like a mock asset for a website, I'm always really impressed. But I haven't used it as like this exploration mechanism yet, so I'd be curious how that fits in for you.
- [22:01]
Meng Tu
GPT Image 2 has become so good. If you look at the templates that we make, by the way, we're probably the largest library of templates. We have 5,000 templates. But, you know, nowadays most of these templates are created from GPT image 2 screenshot to HTML. Yeah, yeah, yeah. This is insane. The same way that I'm doing that here. So I would start, let's say the content. I would start maybe the PRD or the article and get the bullet points going and then turning that into a landing page or a HERO section. So, for example, so let's say I have this one I don't have. Let's assume that this is an app. So I would go insert an image and I would be like, okay, because I already have the context of, let's say, the app that I want to build. So I'm going to go here and I'm going to select landing page, or I want to select maybe the web design Hero. And I'm going to use the taste skill. For those who don't know, taste skill is what allows the AI to sort of pick the right fonts, the right colors, design system and so on. I don't need the reference here, but just go with this. I could have said, okay, my app is called Aura. And then, you know, it's a chat app, et cetera. And then it's just going to create the design for you. You can say, oh, I want the testimonial section, I want the HERO section. So there's so many ways to generate. So, for example, I need a 3D version of the Codex logo and I give the flat one and then I ask, hey, can you turn that into glass? Can you turn that into, you know, a 3D perspective and so on so you can explore a lot of things. Illustration. So, so good. Slides, interior design. Wireframe. I love wireframe.
- [23:46]
Host 1
Okay, I have another question. Because you've clicked on enough of These pop ups now where like the way
- [23:51]
Host 2
that that pop up enters is more
- [23:54]
Host 1
drawn out and elegant than almost any I've ever seen.
- [23:56]
Host 2
So talk to me a little bit
- [23:57]
Host 1
about how do you. That's harder to do with just screenshots, right? Like, how are you finessing that level of interaction and animation with AI?
- [24:06]
Meng Tu
I'm going to give you another secret sauce that you can do today. This used to have you needing to learn all about these libraries, these animation terms. Now you know what our team use? They use a video, they give the AI a video and they ask the AI, how should I prompt this animation? Isn't it incredible?
- [24:29]
Host 1
It's such an important tactic because it's like everything comes down to language at the end of the day. I was working on that with shaders recently. I don't have any of the language for shaders. It's like I almost had to use Claude as an intermediary to be like, give me some. I'm trying to achieve X, I have no words for it. Like maybe ask me some questions. But ultimately I need you to write this prompt. Like I'm not going to be able to write this prompt. And I love that tactic for something like interaction design, it makes a ton of sense.
- [24:58]
Meng Tu
More than that, if you look at the way AI works, it's not getting any smarter. Like let's take an example of Fable 5, right? You use Fable 5 right here and you ask it, can you create a beautiful landing page? There is zero difference between that landing page and one Created by Opus 4.8 or Sonnet 4.6 or 4.5. The reason why is because it's like you're using someone far too powerful for a simple task. The only way you can utilize these super intelligent model is by giving a giant piece of prompt, literally. So you would select all of these contexts, all of the, you know, the sections that you want, all of these pre prompts that I already have in my template. And then you put all of these giant prompts with the design system, design MD and the preview of the HTML of the reference or the screenshot, or you can import the URL and then you can fully utilize a model like Fable 5. Otherwise there's no point. You're paying for nothing.
- [26:05]
Host 1
Can we talk about the DesignMD piece for a second? I think it's interesting that you've fully productized that in aura. For people who hear it, maybe they see it on Twitter, you can intuit what it is. Right? Right. But like how much strategy actually goes into making an effective design MD file
- [26:21]
Meng Tu
10 years ago, 20 years ago, all the designers, they have a style guide. It's kind of like their guiding principle of their mastery of a designer. Right. You go to school, you. You work on 10,000 designs. You have embedded in your blood that design language, that style guide, the design MD is basically all of that sweat, tears and blood into one markdown file that the AI can read. So that's what DesignMD is. So why is it powerful? Like I mentioned before, if you're using a model like mythos fable 5, then you give something like designermd, it will understand it, and it will be able to take it to the next level. If you use a base model, it won't understand it. So that's kind of like the difference. So design MD is the design language, the design system that holds all of that beautiful information about the colors, the typography, the spacing guide, the corner radiuses, and is it what surface? And it goes into great details. And Google started this thing because it needed to standardize the language so that everyone follows accessibility and composition. And it needs to include all of these, you know, segments and all of these tokens that we designers have kind of learned over the years. But if you're a new designer, you kind of lost all of that context. So the design MD holds all of that information so that you don't have to.
- [27:54]
Host 1
Yeah. This is something that I think I could probably take more seriously in my own work, honestly, because I think I rely on Claude to almost piece it together each time I need it. Like, if I'm like working in paper, like, I do a lot of visualizing ideas in paper, and I'm always like, you know, use the design system, use our typography, and I almost have to kind of list things out. I'm like, I should probably just wrap this all into a skill, say, use the design MD and then do the thing that I've asked. This is my to do list that I'm adding for myself after we hang up here.
- [28:24]
Meng Tu
I mentioned, as a designer, I always work with a previous work that I've done in the past. So whether it's the fonts that I've gathered, whether it's the colors and the figma files that I have done in the past or the HTML and project I do exactly the same with, you know, with codecs, which is that I think I would. I would say about 50% of my prom is me referencing another chat or another page that I do. So I mentioned before that if I start a new project, like a new iOS app, I will reference an entire folder, right? All of these, by the way, are folders in your computer. When you start a new project, you reference an entire folder. You can say something like, okay, I want an iOS app based on my Mac app that I already done this in this folder. But when you do iterations, this is where you start to reference another page. So one thing that I love to say is create this page or this modal or this button in the style of another button that I created in this page. And so it will do exactly that. Or you can also bring the Design md. But then again, Design MD is powerful at the beginning, but when you're doing a lot of iterations really quickly, you don't want to always reference that. You can totally save that into your Agents md. For those who don't know, Agents MD is the file that is always read by the AI for every single prompt or any time that you create a new thread or a new task. So this is a project, this is a thread. And then you have like, multiple tasks within a thread. I'm not a person who likes to put too much stuff in Agents md. Therefore, the way that I work is just taking a lot of screenshots and then referencing a lot of files. You know, like, this is where my file is. This is where the file the page is. This is the button that I created. And then just remembering the most important terms, design terms and details. You know, you ask about the modal. Eventually, if you want to stop having to feed a video every single time you prompt, you have to remember that. Or another thing that I love to do is like, I can say something like, from now on, I want you to remember this workflow in memory or this design system in memory. They could have a Agents MD inside a project, which is kind of cool. Sometimes I call it a runbook md. A runbook is more like a workflow. Sometimes I call it workflow md, but generally speaking, it's Agent md. You have a main agent MD for all of the things. So you can totally go to Settings and go to your configuration and then put that into that. It's a bit dangerous because it's read for every single prompt or every single new project. So instead what I do is I ask the AI to remember in memory about what we just did, right? So let's say we just created this model and the design or this button. I can say, I want you to remember this and save it to your memory. And then usually what it would do is it would save that in the Agents MD for this specific project, so that the next time that it's creating a model, it will remember to do exactly in this style.
- [31:44]
Host 1
We've covered a lot of ground, a ton of tactics. I want to make sure that we're. You're not missing anything, basically. So, like, when you think about the little tools or tactics or workflows that designers can adopt to more effectively collaborate with and build with AI, is there anything else that you want to make sure that we talk about before we move on?
- [32:06]
Meng Tu
I'm using GPT 5.5 extra high, so we haven't talked about this too much. Like, what is the difference between the model? So obviously, when you first start, you might want to start with Medium because it's not too costly, it's not going to hit your limits. Not everyone's going to have like, the sort of $200 or $100 plan. So what I would do is I would start with Medium because it doesn't eat a lot and it's reasonably good. It's going to be able to do most of the things, but much faster as well. Another thing you can do is to go to Cursor and use Composer 2.5, which is super fast. And because it's so fast, I can just focus on one project at a time. But when I use Extra High is, by the way, to me, GPT 5.5 is, like, probably the best model that I've used this year without counting the new Mythos and all that stuff. But they're very expensive anyway, so I would probably not use them at this time. But I've been using Extra High, and it's so, so good. It's able to build anything you can dream of today. But most importantly, have a. An endless amount of curiosity about what's going on and how you can perfect your own workflow. Because it keeps evolving, and because it keeps evolving, it always requires your attention. I've never worked so hard in my life. I've never put so many hours into the projects. I've never built so many projects at the same time. I've never done anything of this magnitude solo, usually. You know, when I first started design code, right, I was traveling for two years and, you know, I would spend all my time sort of like, working on, like, small pockets of the content, creating my first video. And I remember it took so long, eventually it made enough money. I built a team. We had a team of editors, video editors, and, you know, to save me time. But today you can do everything yourself because your editors are your agents. Your designer is your agent, your coder is your agent, your personal assistant, of course. But anything that you can think of, your agent can do it. And the only thing that's stopping you is you opening to this world of apps and plugins and libraries and proms and design md and if you have that, it's your greatest weapon.
- [34:25]
Host 1
I can't think of a more inspiring way to wrap this up and mang even just something that I appreciate you like scrolling through your Twitter feed.
- [34:33]
Host 2
I mean, there's a lot of people
- [34:33]
Host 1
who are obsessing over the workflow, and then you kind of have this question about like, well, okay, but what if you actually shipped? You know, and, man, you are the complete opposite, where you're just a shipping machine. You know, you're just putting really interesting and valuable things out left and right. And I have so much appreciation and respect for what you're doing. As somebody who's not only curious, but just goes and runs through walls and makes things happen, you're super inspiring to. And I know that a lot of people listening feel the same way. So I appreciate you coming on and just sharing a little bit about how you're thinking about things, how your workflow is evolving, what you're working on. I think we should make it maybe like an annual checkpoint because there's always so much to learn from you.
- [35:18]
Meng Tu
This is such an honor, and I would love to come back, like, next year and give you an update on what's going on with AI and sharing my new workflow at at then. Because, you know, 16 months ago, we used Kusane 3.5. Now we're using GPT 5.5 in Codex, but we don't know what's going to happen in 12 months.