Can AI Make Good Design?

Welcome to Syntax. We lost the first like 20 seconds of this episode on Riverside. So, I'm here recording it again. I went to find the shirt that I was wearing. I spilled schwarma of poutine on it, so it's dirty. So, listen up. We're going to get the editor to try cut it in perfectly and I'm just going to start saying what I was saying at the beginning of it. We have a show on AI design. And don't turn it off just yet because this isn't the AI design show where guys are like, "Oh, I one-shoted this and it looks amazing to me and I think designers are toast." No, that's not what this show is about. This show is about uh we know that AI can write pretty good code and and that's great cuz it's very deterministic. It's it can be tested, things like that. But design like can a model create something that is good, that is functionally useful, that converts well for the business, that helps the actual end user. Um, we're in this like weird space right now where it seems like everybody is just ripping each other off. Every app looks exactly the same and there's tons of new tools to help you. So, in order to get to the bottom of this, we're going to attempt to answer some of the following questions. Can AI be creative? Can it make you creative? Can good design be extrapolated? Um, what about user experience? Can AI make a good user experience? You know, does it know about all of the complexities of your UI of what people are trying to get done? Uh, can you make good design programmatic? We've talked about this in in the previous many episodes of like can you programmatically pick good colors like with math those things are are kind of hard to get to. So we'll answer that question. Can I AI make design that influences the end goal? So buying something, you know, or or helping somebody get to the the end use, why are they using your application at the end of the day? Can you help them with that? Um, and then we're going to end it off with just like tools and thoughts of if you want to design something, whether you're designer or not, what tools should you be looking at and and how should you be thinking about using these things? My name is Wes. With me as always is Mr. Scott Tinsky. You're ready to get into it, Scott? Oh, I'm so ready to get into it. I this is a topic that I I think a lot about especially given just how many how many vibecoded designs you see and it's such a tell. There's so many tells these days uh of once you've worked with AI I can I feel like I could even tell Wes which model design something at this point which like there are specific tells for for GPT verse anthropic etc. So, I I'm really interested to hear your thoughts on this, but also in general, man, design is something that I'm constantly looking to get better at and feel like I'm constantly not good enough at. So, uh let's get into it. I know sort of an aside from that, but I know that there are many architects which which can look at a building and say, I know which software this building was designed in due to the way that the the curves fit together. you know, as soon as they add a new fillet tool and then all of the buildings have that, which is absolutely crazy. And I feel like I'm going to be on Antiques Road Show when I'm older being like, "Well, yes, that was uh that was done with SONNET 45, NOT 46." You might be a little bit confused, you know? I'm be able to pick it out. So stay tuned for that. But let's talk about like Yes, the border left here is indicative of the era. So, I got onto this whole thing because I get these emails every single day from these like slopcoded startups and they say like here check it out like let me know if you if you want to use it and I always click through to the website and see what it is and it's it's the same thing of everything, right? where someone just logged into VZero or Lovable or Claude or whatever and typed like make me a business, make no mistakes, and it shhat out some uh business out the other end. And what's interesting is that on all of these I see the same name over and over again. I see Sarah Chen on there and I was like, where is Sarah Chen coming from? And I I was like, I got to get to the bottom of this. So, first of all, I thought like maybe this is just the same person doing this over and over again. And and it turns out that wasn't the case. It was many websites. So I was like, where is Sarah Chen coming from? Like maybe it's coming from like one of these like site builders, you know, maybe they have like seated it with a template that has Sarah Chen as a testimonial and just uses that. And I looked into it and it didn't seem to be the case because all of the examples that I had found I looked on GitHub and the use of Sarah Chen in the last year has just skyrocketed and and they were all from like different generators you know some of it was in like PHP code some of it was in like markdown documents and and PowerPoint slides and there there didn't seem to be any commonality between them all. So finally I went into chat GBT and I said give me a list of like five random testimonials or not random five testimonials and Sarah Chen bam first one and I went into every other model and every single one had either I think four out of five had Sarah Chen as the first and then somewhere in there it had a variation of Sarah Chen in there which was absolutely wild. So every single model is using Sarah Chen as it and and I I thought like hm if you think AI is is making you creative it's it's not. That's making you like what programmatically what what what did I what was I saying it was called? Hold on. Yeah, you're it's making you probable or likely. I got to ask how how did you notice Sarah Chen for because for me my brain just glosses over that stuff. You know the times that I don't or when I see my good buddy Wes up there, I'm like, "Hey, that's Wes. He's got a little Wes." But I don't think I would have noticed any rainbow. Like this guy emailed me and says like, "Hey, we are a business." And then I like go to his website and it says Sarah Chen and then there's like a obviously an AI photo and I was like that's not Sarah Chen. And so I Googled it. There was another one like Marcus Rodriguez was the one the other one um that kept showing up. So I I Googled Marcus Rodriguez and testimonial and I found I'm not kidding. I probably found two or 300 like startups.coms that had him as a thing and in in many cases his like attribution of the um well company he's associated with was also the same it was like info tech or something like that. Uh so I like just by googling it I found like man this Marcus Rodriguez and then beside it was always Sarah Chen was used over and over and over again. So it's just deterministic right. Did you did you respond to uh the uh people who emailed you asking you Sarah? So I first thought like oh I'm on to some like slo ring you know and I'm going to I'm going to infiltrate the slo ring. So I emailed him and I was like hey can we can we jump on a call? I would love to do a a syntax episode on this. And he's like yeah absolutely let's talk right now. And then I realized like no it's not a slobbering it's just that everybody's using the same Sarah Chen testimonial. So I feel like I feel I feel like that is fraud. That is fraud. Yes. Oh, absolutely. I would say that is fraud. Yes. Yeah. That's crazy. So all of that to say like can AI make you creative? I I think like if you are expecting it to do all of the work of making you something beautiful, something creative, something that goes into whatever, it's not going to happen, right? I think that it can certainly help you explore ideas with the Mad CSS website, right? We we had these like super silly like '9s basketball photos, which one person asked if we like took those, which was like, of course not. We those are we didn't travel back to the '9s and take like NCAA photos. And and me at my my you know massive height of 5 foot seven I I can certainly dunk like that. You best believe uh I am good on the trampoline but not that good. But when I was designing that thing I went through I don't know probably like 20 or 30 different like iterations of what we could do. And it it certainly helped me explore different areas. And I think that AI can help you do that. But at the end of the day, it's not coming up with with new ideas. It's all been trained on stuff that has been done before, which is maybe not necessarily a bad thing, but I I don't think it's actually making you creative, and it's just making everything some disgusting warm stew that is just all of the ideas that have been done before, all of the stuff that's been trained on, and it's all sort of just this mediocre sort of watered down version of that. But what about these design tools that create really good design? Well, we'll talk about that because like you you see a lot of these design tools that put out seemingly decent looking websites. We'll talk about that in just a sec, but let's talk about YouTube thumbnails for a second. The latest Gemini can crank out like a Mr. Beast style thumbnail, which is like super high um high HDR. It widens eyes. does all the like stupid YouTube thumbnail stuff that like we do it as well, right? Because why? Because it works, right? But now that it they're able to just simply you can just type type and it cranks out what you used to pay hundreds of dollars for to a designer for this type of thumbnail. Now, everybody every single thumbnail is like that on YouTube, right? It's the the wow face, all of that. It's the the the blue versus red, the thing down the middle, big letters on top. That is now table stakes. And I think that now that is table stakes, it's going to stop working in the next two or 3 weeks. I guarantee you because everyone has figured out, oh, I don't need to like previously it was somebody like Mr. Beast. They had somebody on staff figuring out these and then other people started to copy those and now it's simply just like a prompt away and every single thumbnail looks like that. Now it's going to stop working because it's table stakes. Everybody can do it, right? And now we're going to have to guarantee we're going to see like a shifting of YouTube thumbnails to something else. And I don't know what that something else is, but we will see. Yeah, I know. It's a YouTube thumbnails are a whole thing in general. Even like thinking about that wow face. I hate the wow face, but it works. And I'll tell you why it works. It's psychology. People recognize faces and expressions better than they recognize text or images like that. So, uh, the faces work even though I hate them and they're ugly, but we got to do it. The next question here is, can good design be extrapolated? Meaning that if you were to provide it with a list of examples, a list of rules, colors, spacing, type, all of that stuff, if you sort of make a good base of design, can it then be extrapolated into to something larger? Um, and I I think partially yes. That's what we're seeing now with tools like Google Stitch where you go into it and you you tell it what you want. And in my case, I found what was helpful is I asked Claude to summarize all of the features and all of the the layouts and whatever that needs to happen without describing what it looks like. And then I took that copy pasted that into Google Stitch and it cranked out like a decent looking design. But after using it three or four times, you can clearly tell that they have have seated it with some good stuff, right? They have a whole bunch of templates. They have a whole bunch of good fonts. They have a whole bunch of rules about what colors work well with each other. They probably have a massive prompt of like these are the things that look good. And then out the other end, you you the user can say, "All right, well, I want it to to do this, right? I need form inputs or sliders, all that stuff. Then I want to use these colors." And then it can it can take those things and sort of extrapolate that into something that is looking halfdeent. But even after it's been out for what, like a month or two, I can now eyeball one of these Google Stitch designs no problem because they all start to look the same after after a while. I think that goes along very nicely and and nicely in a a sense where like even with development I a lot of people feel like AI is really helpful in green field in general but the times where I find it to be the most helpful are with established patterns taking care of tasks that you uh is like mostly just regurgitating either patterns that you've already done or re-implementing those same patterns but without those established patterns left to its own devices, it's way less effective. So I think extrapolating good design to me falls under that same category of established patterns and extrapolating on those established patterns with hard rules about how to extrapolate on those patterns. I you know especially when you get into CSS stuff whether that is like not adding new new CSS varss without approval etc. And there's probably people screaming at the the radio right now being like, "That's what a design system is, you dummy." And like we've had this before we've had AI and that is a system of rules and pieces that you can sort of put together, but there there is a limit to it as well, right? Because like we had Bootstrap, we had have set Shad CN and those things look really good out of the box, but at a certain point you can't just click them together like they're Lego. You have to have a little something that is a little bit higher. Uh you have to be able to figure it out. And that's what my next point is is can AI make a good UX? But before we get into that, let's talk real quick about this like design. MD. So this is a Do you want to give a quick explanation of what it is? Yeah. So uh what is it like a couple weeks ago? Google came out with their design.mdspec which the idea for the design.mdspec is that you are putting it it's kind of like your agents.md or any of these uh steering documents that you have inside of your codebase but only for design patterns and when I first saw design I was looking at it and it's basically what it's a markdown file with front matter uh about your design tokens, your properties. It's a parser as well and like a llinter. So, it is a lot more structured than just a markdown file, but it you're right, it is a steering document, right? And and so there are those aspects of it too, right? Where where there is validation involved in this document, but it is really and my my initial reaction was like this this looks like just a root CSS declaration. Yeah. There are more things in here, but it feels like prime territory for drift for kind of it's like duplication of ideas that are expressed in code already. Uh but the idea is is that your AI uses this as essentially a design document. This is the rules of this library. If you're adding uh design to this, it's following these dang rules. Whether that is the colors, fonts, all that stuff, the naming of things, uh what belongs to what, with the spacing, rounded corner spacing. Again, yeah, I still don't necessarily get it get the need for it. But I I think the big play here is that like it's a standard that can be translated between things. So like if you have a Figma that can output this and then like you have like a like a tailwind it can be converted from one to another. Um but first of all I wonder like do we do we need this rigidness and second of all I say if there is rigidity I feel like I would rather do this in like a CSS file with comments maybe I would love I know this is not going to happen. And I would love a standard way of just defining CSS variables because that's really kind of what this is cuz like spacing, rounded, all that stuff. Just just come up with a standardized name for all this stuff in your root CSS declaration. Point it there. Add some comments about the overview or whatever. Bingo bingo. Now you're not having a AI document and a code document that could get out of sync. The drift kills me. I think there's there's a different world for this as well where the whole design tokens folks, you know, where you you're Salesforce and you have 40 different implementations of your design. But I'm curious to see if there's any any uptake. I certainly don't want another file in my my root of my repo. Oh, yeah. Right. Another another root in my repo. Yeah. The next one is, can AI make good UX? Um, so much of design is is not just making it look good. It's it's about making an interface that is consistent. It's something that has clear purpose, low friction to the user, right? And quite honestly, I don't think AI is very good at this. I think it's great at throwing buttons on there. I think it's good at um having cards and putting cards inside of cards, but when it comes down to this is our specific app and we are doing this one thing, right? Like we are booking trailers, you know, we are U-Haul. That maybe that's a good example. I freaking hate U-Haul. U-Haul's app is absolutely awful. The UX is I makes me want to kill myself and it just the worst. You could say that. You could say I think the UX makes me want to die and it just it drives me nuts. Right. And what needs to happen there is that a designer that understands UX needs to come in and understand what is actually getting done here and figure out both the interface as well as the flow for for actually booking a trailer on U-Haul, right? And I don't know that if you were to give AI these problems, it that it would make a good thing because it it just really doesn't understand. Maybe you could, I don't know, take a whole bunch of user feedback and like and pipe that in and summarize it and stuff, but I think at a certain point you still need somebody who understands the stuff and has a good UX because it's just you're going to get these awful interfaces at the end of the day. Yeah, I find most the the UX work that AI does even with strict rules and you can download a UX skill from skills whatever that malware and throw it on your system and and prompt away make this UX more user friendly and like it just flat out is bad at that there like I have such strict UX rules in mind and it still just like falters with that. I I always I find I find myself saying move move out of the way let me do it like way more than ever these days. I even think just like so much of that is just subjective, you know, like, oh, I'm taste. I hate that like taste thing so much, but yeah, it makes sense. It's just like somebody needs to taste use this thing and go, oh, you know what? when I selected my location and then the trailer wasn't available, there should be a very good UX for being able to realize, oh, there is a similar trailer at a different place nearby or there are this is a trailer that I could get that is similar at this location and yeah, there's just there's so much to it. So, not good at UXMO. So, if you have AI designing your app, you're going to want to make sure that you have Sentry because why? They have rage click detection. Because when AI designs your crappy user experience, users are going to be clicking on stuff and being like, why doesn't this work right? Or, uh, why isn't this doing what I'm expecting it to? And then you're going to get those reports in your dashboard in Sentry, and you're going to be able to see exactly who's having issues. You can also collect user feedback for when users feel like this thing might suck. Uh there's a lot of great stuff here too, like outages and being able to track errors from your slopcoded mess. So check it out at century.io/sintax. Sign up, get two months for free using the coupon code tasty treat. Trust me, this is a tool that is going to help you at every single rage clicks and dead clicks as well. That's if you're interested in the difference between the two. A rage click is where someone clicks multiple times and is is raging out. And a dead click is where somebody clicks on something that is seemingly interactive like a button or a link. And then after a threshold, I think it's like 200 milliseconds or something, nothing happens, right? And uh if nothing happens, that's a dead click. I have a sick shirt from Sentry that says dead click on it. So, take your dead clicks, pipe them back into your AI, and uh get Sentry to fix it. Can good design be programmatic? This is kind of an interesting one. And we've asked this many times to many of our guests over the years of can you programmatically pick good colors? And and I think the answer to that is is no. So, like I think like Warp Terminal is a good example of this. They have this concept of themes and you give them I don't know three or four colors of of what you want it to do and then it tries to to skin the entire terminal based on those programmatically lighter darker contrast you know all that stuff and it just it doesn't it's not a good-look terminal I don't think so it just doesn't look very good whereas if you look at something like like a VS Code terminal where you can control absolutely every little thing looks a lot better Right. I don't think you can programmatically pick good design. And then also you have this this aspect of colors are trendy. What what comes and goes is is very trendy. And now as everybody's ripping each other off, those trends move so much faster than they previously were. So I don't think it can be programmatic in that regard. But I do think it can be programmatic in other ways. Like text wrap balance, right? text wrap balance in the browser makes if you have two lines of of like an H2 and it will figure out how to balance those things. That is an algorithm, right? The the browsers implement those and they figure out how wide the letters are and whatnot. So, I think like that can be programmatically done. A lot of design can be programmatically done, but a lot of it can't be as well. Yeah, I I agree on on most accounts and I'm the type of person like I we've talked about this before where my design inclination is to make a system and follow that system. Like I that is just how my brain works and then you come in with your paintbrush and you're like f your system and it always looks better. So I I tend to agree with you on this. But for my ego, I'm gonna say that it can be programmatic just because otherwise I can't design for programmatic and maintainable are different things here, Scott, because often the like just tweaking it here and there and and adding your own little flare to things to look good. It it looks good initially, but then all of a sudden your your spacing is inconsistent. your font sizes are are not the same across the board and then it becomes a little bit harder to maintain over time because everything has been tweaked a little bit. That's why people are so strict about their design systems because you're not going to like let somebody add their little bit of flare or change the blue or add a gradient here or there because then it just becomes a mess over time and things drift. Yeah. Yeah. I I like my design systems because once I have a plan in place, I do not like that plan to change. I like this. This was my plan. Uh, can AI make a design that influences an end goal? For example, buying something or trying to book a flight or like whatever the end goal of your application is. And that's kind of an interesting question to me because I think with enough data, yes, the reason why like Tik Tok, Twitter, all these things are are so addicting is because they have these algorithms that are able to figure out like what you actually like and then like with enough AB testing um you can figure out what all the dark patterns are or what are all the best patterns, you know, like we had Travis on who works at Google and he he does exactly that is like He does design for what happens when there's a tornado and someone Googles tornado, what should pop up on Google? And like that's kind of timesensitive, right? So, I'm sure they're they're very data heavy on that type of thing. And I don't I don't necessarily know if that that pushes itself into AI, but certainly you could you can start pushing that into algorithms. So, I think yes, but then I think about like like marketing. I saw this tweet the other day where someone's like, "I replaced a social media person that was $500 an hour with this one skill." And it's like, "No, you didn't. No, you didn't. You're not." Yeah. No, you didn't. Again, we're talking about table stakes. As soon as people figure out what works in marketing, that changes, right? And it's just this constantly evolving thing. Like and now we're starting to see I don't know if you saw this or not but Grock's like imagine where they can make video of somebody like sitting in front of a camera talking and it is almost indistinguishable so good. And I I asked myself like why do we need this? But I also was thinking about that. And I'm like, man, we're going to have to get rid of our like nice cameras and lights because as soon as everyone starts using these like AI generated influencers, I'm just going to scroll past as soon as I my brain detects nice lighting, nice camera, good microphone. It's too good. Swipe past, you know. Yeah. So, we got to get here. Please, I think that's a a good point. I mean, as we uh when I interviewed Sarah Bird at Microsoft, she said that the things that she's most interested in now are like the things that are like the most human and imperfect, like Japanese pottery and stuff like that because she's been working in machine learning for so long. And I do think that that is going to be an aesthetic push back to this glossy fake looking everything. Yeah. So, I'm sorry folks that I look too good that you might think I'm AI. He's not. say that. I'm not sorry. Comment down below who is more AI looking, Scott or I or me. I I can't even. Somebody did think I look like AI in one of my videos and they were being serious. Why is this video so weird? Are you AI? But it was an audio desync issue that caused it to be I think. Yeah. Well, even like my little uncanny valley. Every time someone is either on a green screen or something is too produced, they start saying that's AI, you know, and we're like, no. Like we were watching a baseball game and they had like the they had the interviewer and the the player so well lit that like like it was dark outside and he was so well lit and my my kids immediately were like, "That's AI." And we're like, "No, it's it's not. He's just well lit. It's just good photography." you know, little bouquet in the background of the thing and they immediately were just like, "No, it's too good." So, with all this said, design and AI should and can designers actually use AI and have it enhance your abilities rather than turn you into a mindless kind of slot factory of the same stuff. I think there is a range, right? There's like a tool aspect to it which is like I am simply just using these as tools to help me get my work done more productively, help me be able to research it. Just whatever your end game is, these tools can certainly help you. Like on one end of the spectrum, there is background removal in Photoshop. And I don't think there's anybody out there that like as as much as many of the designers hate AI, I don't think there's anyone be like, you know what, we should be using the like pen tool or the little transform selection tool and like cut out around like I'd spent my time doing that and cutting backgrounds out. I'll take the AI background removal any day, you know? That's so important for me. Yeah. Yeah. I mean, those types of algorithm people act like that's just completely unrelated, but it's not. Yeah. Well, I think like that one seems relatively harmless, whereas some of the like on the other side like there's a the complete brand design, you know, like I'm starting to spot like I always think about plumbers like you see a truck driving around your neighborhood which is a plumber and you can again get you can almost eyeball which model they use to create their plumbing logo, you know, like you can you can start seeing the ones that are like 2 years old and you can just tell what it is. And now you're starting to see them and they have that like sort of like um that orange yellow haze to it um that all these like chat GBT images that get kicked out are. And I I think there there certainly is a space for it. I think the best designers are going to figure out how to use this to create good experience to create beautiful things but not just actually do the dumb brain stuff for you. And like we've seen this over the years, right? We had clip art and then you had these like corporate blobby people on all these websites and then we had these like pre purchased packs. Something you may not see but you'll probably notice it now is if you ever see if you ever see like an an inanimate object, you know, like a heart or a burger and then they put fried they put legs on it and it's like it's like a burger that walks. Like the mascot for my new burger shop is a burger that walks or like the mascot for my new coffee shop is a coffee cup with legs and a little eyeballs and it's just walking. You know, like I've I have stickers that do exactly that. And that has become such like a trope that like you can just go online and purchase like 100 eyeballs and legs and then you can just add them to whatever it is that you want. You know, I'm a lawyer. I'm going to take the gavvel and put put legs on it. But then everybody started doing that and now I I can't unsee it every time I see that we have Canva, you know, Canva brought decent design to absolutely everyone. Before we had Canva, it was just word art, clip art, bad stuff that people could sort of just put together and then Canva came out with like halfdeent looking stuff. You can still spot it, but is that bad? You can spot it a mile away. Yeah, you can spot it in a mile away. I mean, I think with any of this stuff that like your in and that same line that you're drawing, your AI logo and a lot of that stuff is word art. It's clip art. It is that. It's just the 2026 version of that. And and if it's not, then it's probably derivative or it's just a copy paste of some other basic logo. Ben, that's a that's a genre of Twitter that drives me nuts is people being like, "AI is changing everything. I made this incredible logo." And it's like, "Brother, this logo sucks." That's the most frustrating thing. And and also like, do regular people care. They probably don't. I'm going to be honest. Yeah, they probably One thing that drives me baddy is that I get all these Tik Toks for Msuno metal core, you know, like like AI music and all the comments are just like, I don't care that it's AI. It's a it's a banger. And like the country music has had this for a long time. Like they know people know programmatically what makes a good catchy riff and like what will people sing out and what will be a good bar song and people don't necessarily care because it's just I don't know. I I I I find myself slop for the masses. Slop for the masses. So that's that's another that's another aspect of it as well. Like I I hate to be the guy who's like, "No, uh you won't do that." Cuz like we had those people with with Dreamweaver, right? Don't use Dreamweaver. It kicks out crappy code. You know, I did use Dreamweaver. Yes, I know. Yeah, that's a a kind of a interesting part. But here we are. Before we get into our final thoughts here, let's talk real quick about like just like tools that that people are using. Figma, MCP, Paper, Pencil, Claude is surprisingly a very good design tool. Like the other day I had a grid of I think 12 icons, right? And it was on a white background and I needed to programmatically I needed to like remove the background. I needed to slice them up into their own. I needed to trim them. And normally I would go into Photoshop and I would slice and dice and remove the background and then put everything in in a layer and then export them. And that would probably take me, I don't know, 20 22 minutes or so. Um, but in my case, I just told Claude, "Hey, slice and dice, remove the background, trim transparent pixels, and rename each of the icons to what they actually are." And it just looked at the thing and put gave a perfect name for it. just beautiful icons out the other end. All nicely in a folder, all exactly the same size. And that was just such a good use case of using these tools rather than having to like spend time clicking buttons cuz like being a designer is not about knowing which buttons to click, you know? It's not about the medium, not about the tools. It's it's about the endgame of what you're trying to actually get done. I think that's such a good because it's what you just said there is you outsourced the busy work to AI. The stuff that is obnoxious, the stuff that takes forever. You're clicking around. You're I love that take in terms of like that's the stuff that AI is the best at. Again, established patterns or established workflows, moving through it. the creative stuff. Maybe it's good for people who don't have any design creativity at all, but you're not going to get anything unique out of it or genuine unless you're really really top tier maybe. I don't even know. Yeah, let us know down below. We'll we'll end it with this is let us know down below what you think. Can AI make good design? And if so, how do you make AI give you good design? Peace. Peace.