Tips for anyone who vibecodes.All images in this post are my original work.As AI slop continues to inundate our everyday lives, I have come to the following conclusions —People can identify slop.People dislike slop.People don’t know how to de-slopify their slop.Put another way, it is relatively easy to recognize bad design, but it is another thing entirely to fix it.Of course, this dilemma predates AI. Every designer is used to receiving opinionated yet inactionable feedback from virtually every other discipline, and many of us spend far too much time translating platitudes like “we need this to have more wow-factor” into tangible design changes.But even for seasoned designers, the uncanny-valley-esque aesthetic of slop can be a tricky one to break down and redesign. I think this is because AI leverages real components and patterns that do make sense in certain contexts, but when surfaced in irrational, formulaic combinations just feel off in a way that’s hard to articulate.So today, I thought I would spend some time diving into exactly what the telltale signs of AI slop are, and how we as vibecoders can learn to de-slopify our designs.But before I do that, let’s address one question —Are all AI-generated artifacts “slop”?I don’t think so. Pretty much all user interfaces are at least partially vibecoded these days, including my own designs. If anything, AI has led to some of the most exciting, expressive digital design of all time.On the other hand, Slop is what happens when AI artifacts are generated without thought, effort or quality — often in high quantities. Slop strips out considered decisions, adds unnecessary fluff and ends up telling every story the exact same way.This is fine as a foundation for real design iteration, but should not be considered (or as I have sadly seen, celebrated) as a thoughtfully designed final output.Even taking one extra moment to “de-slopify” your AI artifacts forces you to actually reflect on the content you’re generating, and that’s the most important takeaway here.So, let’s break it down.Observe the two dashboards below. Can you tell which one is slop?Dashboard ADashboard BNow, can you express exactly why you think it’s sloppy? Not just a vague description like “it just looks janky” or “the UI isn’t modern”. Really try to identify the individual components that make it look like that.Learning to really analyze AI-generated UI is the first step in de-slopifying it. Once you have made your own observations, take a look at the cheatsheet I put together below and really take some time to digest it. How many of these patterns can you spot in Dashboard A?A breakdown of Slop Tells in vibecoded UI.Now that we have looked at the anatomy of slop, let’s discuss how exactly you de-slopify a design.I think there are a few different levels of “de-slopification” you can apply, depending on what you are designing. For the sake of this guide, I will illustrate each level with a Y2K-themed trivia deck that I made for my sister’s birthday.Level 0: the one shot prompt.Let’s start by taking a look at what AI-generates with a simple, single line prompt: Make a fun y2k slide deck for trivia night.Prompt: Make a fun y2k slide deck for trivia night.As you can see, the generated slide above has all the telltale signs of AI slop. This is to be expected when using a very basic prompt, no follow-ups and zero styles for the AI to reference.But what if I just tell the AI not to be sloppy?You might be wondering if you can just ask your agent to de-slopify its own work. But as you can see from the image below, that’s not super effective. You’ll need to be a lot more precise if you want to get a good result from AI.Prompt: Make it look less vibecoded.Level 1: clean up the slop.Once you learn how to recognize the individual components of slop, you can pretty easily guide the AI to fix each one. The result might not be the most beautiful design in the world, but it won’t feel like AI slop anymore.This is a great option if your artifact looks pretty good already, and you just want a quick way to add a little human polish or personality.Prompt: I want this slide to feel more fun and playful. Use the font Londrina Shadow. Use the color palette #CAD2FS [see full prompt below].Just removing all the unnecessary elements AI adds into every design can make a huge difference. Visual density is one of my pet peeves when it comes to slop and bad design in general (if you want to learn more about UI density, I highly recommend checking out Matthew Ström-Awn’s awesome Config talk on the subject).Once you have removed all the fluff, get specific with your changes. In particular, when it comes to colors, fonts and graphics.De-slop Prompt ExampleOften, choosing a nice color palette (I use Coolors.co), a unique font (I use Google Fonts since they’re free) and some open-source icons (I like Lucide icons for most UI mockups) is enough to make a vibecoded interface feel premium.Uploading some photos (check out Unsplash) or graphics is another easy way to create an “analog” look and feel.Using a photos to add a “human” feel to the design.AI will default to the same styles without guidance, but if you point it in the right direction it can actually pull from a lot of cool resources.Level 2: define the aesthetic.One of the easiest ways to visually guide AI is to provide some reference material.This is my go-to option for most of the one-off artifacts I create, whether it’s fun side projects like this or quick prototypes to share a design idea.Prompt: Restyle this with a video game, pixel-art aesthetic, reference the imageFor this path, you can either paste in an image or verbally describe a specific style in your prompt for your AI to reference.For something playful like this trivia deck, a retro video game look is a fun yet achievable aesthetic for AI. When I’m working on something more professional, I tend to ask for a sleek, AI-native feel instead. This, combined with the component tweaks from Level 1, can get you a pretty polished final result.Quick Tip: As general rule, AI struggles with more organic, expressive aesthetics. The more “digital” and less “organic” a style feels, the easier it will be for a machine to recreate it.Digital to Organic SpectrumA note on references and AII just want to clarify here that by “reference styles”, I don’t mean “steal from other designers”.Of course, designers have always drawn inspiration from each other, and admittedly these models are already trained on existing work. But, directly feeding another human’s creative output into a machine for replication without their permission isn’t right— especially if you are going to be publishing or shipping said artifact.There are plenty of open-source libraries like Unsplash to pull from for general guidance. And if you really want great, unique design, you can always just work with a real designer!Level 3: design it for real.The two levels above are great for de-slopifying smaller, standard artifacts. However if you want to vibecode something more substantial like a full website, you need to go one level deeper.You have to design it from scratch.Prompt: recreate this figma file exactly.What do I mean by designing from scratch? I mean finding inspiration on Dribbble and Mobbin, drawing out messy wireframes by hand, opening up Figma and handcrafting a design frame-by-frame. And finally, using that design as a reference for your AI to build.If you’re looking for some inspo, checkout how Interfere just rebuilt their website, starting from Figma explorations all the way through to code.Designing in Figma like the good old days.If you’re a designer, this probably sounds like a relief. “Real Design” is still alive and well! If you’re not a designer, then you have two options: hire one, or learn how to become one yourself. There are many incredible resources out there to get you started, and if vibecoding is something you are starting to do a lot, I highly recommend diving into design more seriously too. Trust me, it’s a lot of fun!In conclusionIt’s worth noting that the levels above are really intended for de-slopifying one-off designs: your vibecoded dashboards, your LinkedIn post visuals, your hyperpersonalized software, your little sister’s birthday trivia games — you get the picture.However, if you’re looking to de-slopify an entire product or brand, then that’s a whole other level — one that dives into agentic workflows and design systems and design skills — and could honestly fill up a whole other article.If you would like to learn more about that process, let me know in the comments and I’ll do a deep dive into setting up a solid AI Design Foundation at some point.In the meantime, I hope you found these tips and tricks helpful! Go forth and de-slopify the world.Merriam-Webster — “Slop” definitionhttps://www.merriam-webster.com/dictionary/slopMatthew Ström-Awn — Config talk on UI densityhttps://www.youtube.com/watch?v=notTKhz8C2cCoolors — Trending color paletteshttps://coolors.co/palettes/trendingInterfere — How We Built Interfere’s New Websitehttps://interfere.com/blog/how-we-built-interferes-new-websiteFigma — Getting Started in Designhttps://www.figma.com/resource-library/getting-started-in-design/Julie Zhuo — “I Never Want to Use Third-Party Software”https://lg.substack.com/p/i-never-want-to-use-third-party-softwareHow to de-slopify your designs was originally published in UX Collective on Medium, where people are continuing the conversation by highlighting and responding to this story.

How to de-slopify your designs

What the Bible got wrong about AI

LAS Art Foundation in Berlin and beyond LAS Art Foundation, formerly Light Art Space, is the Berlin-based organization that looks to create works of art that are born from the bleeding edge. Some of its most famous shows, born from a synergy between art and technology, have occupied Berlin’s Halle am Berghain and Kraftwerk. These club and event venues are fitting environments for the typical LAS show, where monumental use of sound, lights, and moving digital images transforms the spaces into a pulsating, immersive experience that couldn’t be contained in the traditional white cube. In conversation with designboom, LAS CEO and co-founder Bettina Kames talks about their first exhibition with artist Refik Anadol, their mission for new media, and their approach to AI and quantum computing. Ian Cheng: Life After BOB 9 september &#8211; 6 november 2022 at Halle am Berghain, Berlin © 2022 Ian Cheng, presented by LAS Art Foundation | image © Andrea Rossetti a technology forward approach to art Although LAS is often associated with the German scene, it’s fundamentally a nomadic organization. It has been able to fill infamous Berlin clubs with sprawling works by artists like Ian Cheng, Laure Prouvost, and Jakob Kudsk Steensen. Now, they’ve gone on to occupy spaces in Venice, the home of the contemporary art biennale, with exhibitions like Josèfa Ntjam’s swell of spæc(i)es and Natasha Tontey: The Phantom Combatants, alongside hosting an online residency that is supporting the works of Xin Liu & Eunjo Lee. But no matter the URL or IRL, a LAS show is easy to recognize for its forward-thinking approach to applied technologies. Reflecting on this identity, Kames looks back to its founding days in 2016, when she and co-founder Jan Fischer were asking themselves, ‘why another art foundation?’ ‘it really needs to be an art foundation about the future,’ says Kames, recounting the conversations and ideas shared between her, Fischer, and the people around them. ‘That&#8217;s why LAS is at the intersection of art, the latest technologies, the latest breakthroughs in science.’ One such example of this is Laure Prouvost’s 2025 exhibition, WE FELT A STAR DYING, which uses a multisensory experience to untangle the complexities of quantum computing. In their online explanation of the exhibition, LAS even includes a short pop-up window that explains what a quantum computer is for those who come from a non-technical background. Holly Herndon, PROTO (restaged), Kraftwerk Berlin, 06.12.2019 | image © Camille Blake The intersection between art and technology ‘Often when we talk about the present, but also the future, it&#8217;s related to massive changes, rapid developments and technology,’ remarks Kames on this didactic approach to exhibition making. ‘It&#8217;s linked to something like AI. For example, we did this exhibition about quantum computing [Laure Prouvost’s] and often these are topics that are quite complex and sometimes hard to understand, sometimes even frightening. So we said it&#8217;s important to build bridges into society, to take society along. And art can be this kind of door opener’ Laure Prouvost, WE FELT A STAR DYING 2025. Installation view at Kraftwerk Berlin, commissioned by LAS Art Foundation and co-commissioned by OGR Torino, © 2025 Laure Prouvost | image by Andrea Rossetti © VG Bild-Kunst, Bonn 2025 forms of accessibility in art Kames goes on to talk about the different modalities they’ve used to make the exhibitions more accessible, which have included guided tours and inviting high school students to get involved. Seeing as their events are often very bright and involve sound elements, they’ll also have lower-impact versions of the show, where the lights and sounds are more muted, to accommodate these needs. And perhaps the most particular of these moves toward accessibility is its choice of venue. ‘It’s very important that we always activate different spaces like Berghain or like Kraftwerk. And it&#8217;s often spaces that don&#8217;t have the same barrier like a museum space. It&#8217;s easier to come to Berghain. It&#8217;s easier to come to Kraftwerk if you&#8217;re not part of the art scene or cultural scene,’ says Kames on how these spaces don’t have the same perhaps intimidating presence that traditional art spaces might have. Additionally, being in these new contexts encourages both artist and audience to consider what the boundaries of ‘art’ can be. Natasha Tontey, The Phantom Combatants and the Metabolism of Disobedient Organs, 2026. Installation view at Ateneo Veneto, Venice, Italy, commissioned by LAS Art Foundation and Amos Rex, © 2026 Natasha Tontey | photo by Jacopo La Forgia Natasha Tontey, The Phantom Combatants and the Metabolism of Disobedient Organs, 2026. Installation view at Ateneo Veneto, Venice, Italy, commissioned by LAS Art Foundation and Amos Rex, © 2026 Natasha Tontey | photo by Jacopo La Forgia Engaging the senses beyond the screen One of the first things audiences gather from an LAS show like Anadol’s or Cheng’s is that it’s incredibly engaging, looking more like a nightclub than anything seen at a typical museum. But Kames points out that the lights and sound don’t detract from the theory and artistic rigor. ‘It&#8217;s really an exhibition by the leading artists of our times on the highest curatorial level. And with all your senses doesn&#8217;t always mean a flashy LED screen. It could be a smell or these beautiful sculptures. It can mean many things even though obviously some of our content is digital.’ Jakob Kudsk Steensen, Berl-Berl, installation view, Halle am Berghain, Berlin, 2021 | image © Timo Ohler Refik Anadol, Latent Being, 2019, Kraftwerk Berlin | image © Marcelina Wellmer Evaluating and re-evaluating the cutting edge Although their programs reach into different mediums, LAS is, at its core, a space for technological collaboration. On this, Kames remarks, ‘one of the reasons to launch the quantum sensing program,’ with Prouvost’s exhibition, ‘was really to embrace a new ecosystem, a new territory of technologies related to quantum computing, and experiment with them and to develop new artistic media with them. So Laure’s exhibition, for example, which was a collaboration with Google AI quantum and their lead scientist, we developed our own quantum AI diffusion model, because there wasn&#8217;t one in the world for moving image.’ She goes on to address some of the controversy that arises in regard to the use of AI in the art space, saying, ‘what we&#8217;re trying to achieve with LAS is a neutral platform to have discourse, for experimentation, for debate. That applies to AI, same applies for quantum technologies, same applies for whatever. We see this polarization in the world and I think it&#8217;s important to create spaces that are not feeding into that and do quite the opposite.’ Kames refers back to Refik Anadol’s exhibition in 2019, Latent Being, reflecting ‘back then, like we did that first exhibition on machine learning already arguing [a technology that’s] at the center of what we&#8217;re facing now. And we debated then, ‘what is our position on that? What is important for LAS? or what is maybe also missing that we can contribute?’ LAS Art Foundation | UNA / UNLESS Temporary Pavilion at the Accademia di Belle Arti, Venice, 2024, commissioned by LAS Art Foundation, © 2024 UNA / UNLESS | image by Andrea Rossetti / Héctor Chico project info: organization: LAS Art Foundation, formerly Light Art Space | @las_artfoundation CEO & co-founder: Bettina Kames This interview is part of designboom’s SPECTATOR AND SPECTACLE chapter, asking how wonder gets built, presented in partnership with SolidNature, and how it might return some mystery to a world that has measured most of it away. Discover more stories that turn onlookers into participants, alter perception and disrupt the everyday here. The post how LAS art foundation transforms quantum computing and clubs into art appeared first on designboom | architecture & design magazine.

Creative AI

Get Creative AI signals in your inbox

Deploy Autonomous AI Capabilities & Skills Runtimes

Related desks