Meng To - Codex superpowers for designers

[00:00] If you always chase the trends, you will become AI slop 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, it's AI slop, 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] Welcome to Dive Club, 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 to build his ideas with AI. 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. [01:00] I asked Mang to share more about why he's went all in on Codex since the last time we talked. I used to... [01:07] use cursor all the time. [01:09] But now Codex is shifting the mindset for [01:13] A lot of designers... [01:15] and a lot of people who've never done design before or coding before. [01:19] It's kind of like an evolution from... [01:21] Chachi Pitsi [01:23] into something far more powerful. [01:25] Your brain is on your computer. All the files are there. [01:29] 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.

[01:39] and it connects to all of the plugins and integrations such as Slack, [01:45] Telegram... [01:46] you know, Discord. Most recently... [01:50] you can now open... [01:51] and continue codecs on your computer, [01:54] using your phone [01:56] which I think is a huge deal. [01:58] The first time we met, [02:00] We did this podcast, which was about 16, 18 months ago. I built my very first app, Dreamcut. [02:07] It was using cursor, it was using Sonnet 3.5, [02:12] I never released that app. There was very key parts of the app that didn't pass the bar of quality. [02:20] So even though I thought in my mind that I would eventually solve those issues, [02:27] I never got to solve them. [02:29] because the technology was too young at the time. [02:32] It felt great to be able to wide code an app in a week or in a month. [02:38] But nowadays, with Codex, [02:40] We can do all of that [02:43] in a day, but you need the knowledge. [02:45] Recently, I watched Mr. Busi, and he was saying basically... [02:50] Because of knowledge, she's able to start a new YouTube channel [02:54] a faceless one and get-- - Oh, I saw that. - 60 million-- - You said 20 million. - 20 million, 20 million in six months. - 20 million subscribers in six months, [03:03] And he said he can totally do that. [03:07] with the knowledge that I hear. So I believe the same way.

[03:11] with Codex. [03:12] with you know any other tools such as the new cursor we cope composer 2.5 or the new clot or [03:19] But what I like about Codex is that [03:21] I believe they were the first one. They started in February and they were the first one to introduce this sort of [03:26] way of [03:28] building everything with threads. [03:30] And that completely changed the mindset because it was so powerful that if you look at cursor now, [03:36] That's exactly their UI nowadays. [03:38] You open cursor, it's like, [03:40] Sometimes I can't even tell between cursor and codex anymore because they're so familiar. [03:46] And the difference is just the model, but I think the maturity of Codex is just far greater at this point, even though I really love Codex. [03:55] Composer 2.5 I've been doing a lot of really really quick iterations in term of speed and [04:01] there's no equal. So this is one knowledge that everyone must know is [04:06] What model do you use? What app should you use? [04:09] And what is the difference between Composer 2.5 and GPT 5.5? [04:14] medium or extra high. If you're building apps, [04:18] 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. [04:32] But I don't open Figma anymore to... [04:35] build designs or to create design from scratch anymore. I do all of that work

[04:41] in codex. [04:43] All of my projects are here, including... [04:46] 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? [04:57] Or anytime that 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 video? [05:07] amazing library that [05:10] Someone just created or... [05:12] Can you create an article about the writing rules? I watched a really cool... [05:18] 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 [05:28] put all the main points about it? Can you also insert Paul Graham's essays at the same time? And can you also remember [05:35] like the philosophy of it and can you integrate that into the writing when we do it together with the agents real quick message and then we can jump back into it i've anticipated dessin'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 pre-loaded [06:05] or ideas. And then when you're ready, you can share your prototype in a single click. Dessin 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 slash 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 way

[06:35] easier to get started because you can now copy and paste from Figma directly into Papers Canvas. All of the layers and their properties, including images and SVGs, are imported in an instant. It's a pretty big deal and you can try it out today. Just head to dive.club slash paper to get started. 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. [07:03] Absolutely. And that is just step one, right? Step two is... [07:08] I think designers have to build their own tools. [07:12] Because the tools [07:13] that we have are never good enough. So let me give you an example. [07:18] So this is my own version of notion. [07:21] And so... [07:22] You know, getting this, yeah, my own version of Notion. I will tell you why I created this. So... [07:28] For example, on Notion, everything has to happen online. The AI is kind of like [07:34] It doesn't work locally. So... [07:37] What I'm doing here with Codex [07:39] is working with my files that are on my computer in Markdown, and every time we create a file here, it appears here. [07:46] So when I did the prep, [07:49] and I ask my AI, okay, for every title, I want you to generate [07:53] and image. [07:55] And then I also have a perfect prompt for the image [07:58] which I also create a UI for it in which... [08:01] I have a bunch of preset prompts [08:04] that I have gathered over the years.

[08:07] including, for example, [08:09] turning a design into a perspective mock-up because it looks just way better. So if you look at this one, the first version looks like this, which is like, as I mentioned before, AI slop. But then you turn it into a perspective mock-up and suddenly it looks so much better. So this is just one pro. 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. [08:38] 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, you know, I have my notes here, I have my version history here, and then... [08:50] I can see a history of the changes that I have made. [08:55] 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 and [09:06] I've almost built this so many times because I see the value in having all of my content locally. I don't want it trapped in some... [09:13] cloud-based product, [09:15] I don't love Obsidian. I've tried so many times to have it be sticky, and I just don't love it. [09:21] And I've only built it as a Mac app, but... [09:25] You building this [09:27] Locally in the web, I hadn't considered before, [09:31] And it's pretty compelling. What is cool when you build your own app is that you figure out like... [09:36] Okay. [09:36] I have all of this information here,

[09:39] What if [09:40] I can just ask AI... [09:43] to use each section as a context [09:46] to create my image. [09:47] So you can literally just [09:49] create like a new block like this [09:52] And then you can just... [09:53] generate an image without any prompt [09:56] and with a bunch of your presets, so for example I need a YouTube cover or an article cover, [10:01] and then I just generate it on the fly. I don't need any context because the context is here. So when I'm going to be generating this, [10:09] it's going to talk about what Codex actually did. That's the beauty of building your own tool, because you're not only doing that out of frustration because something is missing, [10:19] 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 [10:25] 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... [10:36] so many new ways to design, such as this, for example. I'm one of those designers who discover... [10:43] I work right I don't plan things I don't like have a giant blueprint where I just plan all the ideas in advance and [10:51] 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 it into a different version, so now I can turn this into perspective. [11:07] and [11:08] I can turn the video now, so this becomes a video.

[11:13] Wow. It's all part of the same workflow. It's all part of the tool that you're making, which again starts... [11:21] from Codex. I want to talk about the process of building the tools and actually writing code, because I totally forgot. Of course, you're using Sonnet 3.5 last time we talked, which now I have so much respect for. 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. [11:43] How does... [11:44] Codex [11:45] shape the way that you approach actually building software now? How has your workflow there changed as a result? Let's say you start from scratch. What do you want to do at this point? [11:57] is to go to the plugins, and then you want to find the tools... [12:03] That are part of your workflow because everyone is different every computer is different and [12:08] And so you want to download... [12:10] 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. [12:24] if you want to use video again you have hyper frame and then if you like to use [12:30] Voices, AI voices or AI avatars, that can be really, really powerful. Plugins integrations are like the same as plugins in Figma. It's 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.

[12:48] A skill is basically a prompt. [12:50] sometimes a large prompt. You can think about what is the best practice. It's more like a style guide. What is the best practice for taste? [12:58] Which font to use and you know, how do you got AI? [13:01] to not create AI slops. So the skill would be great for that. [13:05] The thing is that if you always chase the trends, [13:09] you will become a I-slop [13:11] Very soon. [13:12] So my suggestion to you is, [13:15] is [13:16] Always be a step ahead. It's like playing chess. You have to be always a step ahead. [13:22] of what is the baseline. [13:23] So right now, the baseline is... [13:27] Yeah, the AI slop, the interfons, the... [13:30] purple gradients and, uh, [13:32] That would have been amazing five years ago. If someone were using purple gradients, everyone was going nuts over that. But nowadays, it's AI's love, right? Very soon, it's going to be the serif fonts and the... [13:45] the same animations that AI use all the time. So you have to always be ahead. [13:50] And the only way you can be ahead is just to spend that last 10%. So the way... [13:55] that I like to do it [13:57] Especially as a designer or as someone who has [14:00] kind of like developed taste over so many years. [14:04] is that I use... [14:06] My memory is all of the things that exist on my computer that I have gathered. [14:13] over so many years of my career, the fonts that I know, the files that I have created, the Figma design that I have done,

[14:21] the code that I have done [14:23] 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 slots. [14:34] Because... [14:35] your starting point is you [14:37] and you are definitely not a I slot because you are unique as a human for those who [14:43] let's say are now designers just getting started [14:46] Take screenshots. [14:48] If you look at my codex, right... [14:51] Or or or cursor right because I've been doing a lot like really really a lot of iterations and [14:58] it always starts with a screenshot, screenshot, screenshot, screenshot. See? Every single time, I start with a screenshot. The reason why is very simple is because the screenshot... [15:09] is the fastest, easiest way to build. [15:13] without having to voice it, without having to type it. So for example, [15:17] Let's say I want to fix an issue here. [15:20] So what do I do? Well in codex we have a shortcut which is command command [15:25] Boom! It sends a screenshot right away to Codex. [15:28] just like that. And so it makes the whole thing so much easier. It took a screenshot of your browser [15:35] or whatever window that you have active, [15:37] And then from here, you can just start typing. You can just say, okay, I want to fix the top left part of this. [15:44] I want to fix the video timeline. So the question is, how knowledgeable are you

[15:51] 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 in one prompt. But I can guarantee you that nobody can make dream cut in one prompt. [16:07] just because I went through so many iterations, [16:10] and so many futures. [16:12] Here's another question. How many prompts do you think I use? [16:16] for every project, for any of these projects that I launched? I'm sure it is. [16:21] Thousands. [16:23] Yeah, at least 10,000 each. Yeah, I believe it. I totally believe it. Right. The one secret I use... [16:29] When I redid this video editor, I did it in a day, by the way. It was ugly, but I did it in a day. [16:36] And the secret was I searched the libraries that were video editors, and I wanted the ones that had... [16:43] video recording [16:45] Well, video editing, but also screen recording, zooms, and to be able to resize and all that stuff. And then you spend the last 10% to do all of these extra features that didn't exist before. So, for example, drag and drop or to be able to reposition it. [17:02] and these little dots that grow and bounce over. - I like those dots. Yeah, that's nice. - Right? And 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... [17:15] personality is [17:17] or that experience that you yourself have [17:20] 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.

[17:28] into existence. The only way... Quick question, because I know that 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... [17:43] everything for the finer details. Right, so remember at the time I was saying 95% of my code was written by me. Now [17:53] 0% of the data. 0%? 0%. Yeah. We have gone that far. And so, yeah, see, I just noticed like a little problem here. It's overlaying. [18:04] So I could just [18:05] Take a screenshot. [18:06] And then, you know, based on the resolution of my video editor... [18:11] 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 [18:23] so that AI understands me. So part of the... [18:26] skills nowadays is to be able to talk to AI in the most efficient way possible. [18:30] And one of the ways is just, yeah, take a screenshot, use your voice, because when you use your voice, you can explain things differently. [18:36] 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. There's one question that I can't stop asking myself. What if companies apply 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

[19:06] 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 hire, head to dive.club slash talent to join today. 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. [19:36] something that you said earlier where [19:39] 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 things [20:05] polish improvements simultaneously. [20:08] 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, [20:21] creating variables and [20:23] exporting code and doing everything manually. That skill is still super useful. [20:28] So let me give you an example. [20:29] Nowadays you can also annotate [20:31] So now you can just [20:33] point something that you want to fix and then you can say, you know, fix this, fix the padding, etc. Instead of

[20:41] taking a whole screenshot and explaining that, oh, this, the part that I want to fix is in feature templates, you annotate [20:48] And then boom, you can do that. The best people... [20:51] are the editors, right? I also think myself as more of an editor than as someone who likes to scratch from scratch. And also, you can totally say something like, okay, can you create a [21:03] A simple design generated... [21:06] in gpt image 2 nowadays right like for example [21:10] If you're creating like a 3D design, you would start with this, you would start with a screenshot, and then you turn it into a design. If you're creating a brand or a slide, [21:20] 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 into the final result. So generating... Quick question. Do you ever do that for interface design? Like are you ever exploring ideas? [21:39] Okay, so talk about that for a little bit because I'm doing a lot with spinning up quick HTML websites just to visualize ideas quickly. [21:46] but I'm not doing anything with GPT. But every time I play with it 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. [21:56] as this exploration mechanism yet. So I'd be curious how that fits in for you. 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...

[22:12] Most of these templates [22:13] are created from GPT-Image2 [22:16] screenshot to HTML. [22:18] No way. Yeah, yeah, yeah. This is insane. The same way that I'm doing that here. So I would start, let's say, [22:26] the content, I would start maybe the PRD or the article, and get the bullet points going, and then turning that into a... [22:35] 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. [22:44] 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... [22:53] landing page where i want to select maybe the the web design hero and i'm going to use the taste skill if 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 [23:08] But just go with this. I could have said, okay, my app is called... [23:13] Aura, and then it's a chat app, et cetera. And then it's just going to create a 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... [23:25] a 3D version of the Codex logo and I give the flat one and then I ask, "Hey, can you turn that into glass?" [23:32] Can you turn that into [23:34] you know, 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] Okay, I have another question. Because you've clicked on enough of these pop-ups now, we're like, the way that that pop-up enters is more drawn out and elegant than almost any I've ever seen. So talk to me a little bit about that. That's harder to do with just screenshots, right? How are you finessing that level of interaction and animation with AI? I'm going to give you another secret sauce that you can do today. This used to have you needing [24:16] team use, they use [24:18] a video [24:19] They give the AI a video and they ask the AI, [24:23] How should I prompt this animation? [24:26] Isn't that incredible? 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. 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. Maybe ask me some questions later. [24:49] But ultimately, I need you to write this prompt. I'm not going to be able to write this prompt. [24:53] And I love that tactic for something like interaction design. It makes a ton of sense. More than that, if you look at the way AI works, it's not getting any smarter. Let's take an example of Fable 5, right? [25:05] you use Fable 5 [25:07] 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

[25:16] Op. 4.8. [25:17] Or sun at 4.6 or 4.5. [25:21] 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 models is, [25:33] is by giving a giant [25:35] piece of prompt, literally. [25:38] So you would select all of these contexts, all of the sections that you want, all of these pre-promgs 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. Can we talk about the design.md piece for a second? [26:08] 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? But like how much strategy actually goes into making an effective design MD file? - 10 years ago, 20 years ago, all the designers [26:24] they have a style guide. [26:26] It's kind of like their guiding principle of their mastery of a designer. [26:32] You go to school, you work on 10,000 designs, [26:36] 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 [26:46] markdown file that the AI can read. So that's what design MD is. So why is it powerful? Like I mentioned before, if you're using a model like

[26:54] Mythos, Fable 5. [26:56] then you give something like DesignMD, it will understand it, and it will be able to take it to the next level. [27:02] If you use a base model, it won't understand it. So that's kind of like the difference. So design.amd is the design language, the design system that holds... [27:11] All of that beautiful information about the colors, the typography, the spacing guide, the corner radiuses, and... [27:20] Is it what surf is? And it goes into great details. And Google started this project [27:26] because it needed to standardize. [27:30] the language so that everyone follows accessibility and composition, and it needs to include all of these things. [27:38] segments. [27:40] And all of these things, [27:41] 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 yeah this is something that i think i could probably take more seriously in my own work honestly because i i think i rely on [28:00] Claude to almost piece it together. [28:03] each time I need it. If I'm working in paper, I do a lot of visualizing ideas in paper, and I'm always like, use the design system, use our typography, and I almost have to list things out. I'm like, I should probably just wrap this all into a skill. Say, use the design MD, [28:18] 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. 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

[28:32] colors and [28:33] the Figma files that I have done in the past, or the HTML and project, [28:37] I do exactly the same with Codex. [28:41] which is that I think I would say about 50% of my prom is me referencing another chat [28:47] or, [28:48] another page that I do. So I mentioned before that if I start a new project like a new iOS app, [28:55] I will reference [28:57] an entire folder, right? All of these, by the way, are folders. [29:01] in your computer. [29:03] When you start a new project, you reference an entire folder. [29:06] 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... [29:15] to reference [29:18] Another page so one thing that I love to say is if [29:22] 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 [29:50] 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, [29:59] And then you have multiple tasks within a thread.

[30:03] I'm not a person who likes to put too much stuff in agents.md. Therefore, the way that I work, [30:09] It's just taking a lot of screenshot. [30:11] 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 [30:27] having to [30:29] Feed a video every single time you prom. [30:31] 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, [30:38] remember [30:40] 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, [30:53] A runbook is more like a workflow. [30:55] 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... [31:12] new project [31:14] So instead what I do is I ask the AI to remember in memory about what we just did. [31:20] right so let's say we just created this this model and the design or this button i can say [31:26] I want you to remember [31:28] this and save it [31:30] 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...

[31:41] to do exactly in this style. [31:43] We've covered a lot of ground. [31:45] a ton of tactics. I want to make sure that we've, you're not missing anything basically. So like when you think about the, the little tools or tactics or workflows that designers can adopt to more effectively, um, [31:58] collaborate with and build with AIs or anything else that you want to make sure that we talk about before we move on? [32:07] 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 [32:15] You might want to start with medium because it's not too costly, it's not going to hit your limits. [32:20] not everyone's gonna have the $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, [32:32] 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, it's... [32:45] By the way, [32:46] To me, GPT 5.5 is probably the best model that I've used this year. [32:51] 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. [32:58] But I've been using Extra High and it's so, so good. [33:02] It's able to build anything you can dream of today, but most importantly, have an endless amount of curiosity about what's going on and how you can perfect your own workflow because it keeps evolving.

[33:17] And because it keeps evolving, [33:18] It always requires your attention. I've never worked so hard in my life. I've never put so many hours into the project. I've never built so many projects at the same time. I've never done... [33:30] anything [33:31] of this magnitude, Sala, who usually... [33:35] When I first started design code, I was traveling for two years, and I would spend all my time working on small projects. [33:43] 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 [33:54] and to save me time, but today, [33:58] You can do everything yourself because your editors are your agents. [34:03] 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 [34:15] is you opening to this world of apps and plugins and libraries [34:20] proms and design on MD. And if you have that, it's your greatest weapon. I can't think of a more inspiring way to wrap this up. And [34:28] Maybe even just something that I appreciate you scrolling through your Twitter feed. I mean, there's a lot of people who are obsessing over the workflow and... [34:37] then you kind of have this question about, like, well, okay, but what have you actually shipped, you know? [34:42] And man, you are the complete opposite where you're just a shipping machine. You're just putting really interesting and valuable things out left and right. And I have so much appreciation and respect for...

[34:53] 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 me. And I know that. [35:02] a lot of people listening feel the same way. So I appreciate you going 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. This is such an honor and I would love to come back next year and give you an update on what's going on with AI and sharing my new workflow at then because, you know, [35:29] 16 months ago we used Sonnet 3.5, now we're using GP5.5 in codex, but we don't know what's going to happen in 12 months.