Video editor who got hooked on building fun 3D stuff with AI. Sharing it as I go, plus the workflow so you can build your own. @ Design+Code
Quebec
Joined February 2023
- Tweets588
- Following143
- Followers1.1K
- Likes1.2K
Samnang Aing retweeted
Major cheat code for life: Always having something on the calendar you're excited about. It can really be anything. Difficult physical challenge, big project, fun trip, ambitious goal, whatever. It creates energy. It promotes structure. It carries you through the lows. Life hack.
Samnang Aing retweeted
GPT-5.6 Sol just changed how I build websites with AI.
In this full 10-minute video, I test Sol and Terra inside Codex to build a cinematic landing page from a video reference.
I cover:
→ Which GPT-5.6 model to use
→ How I analyze a full website experience
→ How I recreate the layout, motion and interactions
→ Why better prompting matters more than one-shot results
→ How to avoid generic AI slop
The model matters—but the way you guide it matters even more.
Watch the full process below 👇
Want the free template and the exact prompt I used? They’re available exclusively in the description of the YouTube version: youtu.be/5o5PnTd5l_4
Samnang Aing retweeted
Emil has some of the best design engineering skills out there. Worth pairing with:
Engineering skills
github.com/mattpocock/skills
Agent orchestration skills
github.com/davidondrej/skill…
Together they cover design engineering, software engineering, and agent workflows.
All free and open source.
New skill: /apple-design
Apple’s WWDC videos are a goldmine of knowledge. I’ve combed through my favorite ones and came up with 17 design and motion principles.
Use them to review existing work or when working on something new to get it right.
github.com/emilkowalski/skil…
Samnang Aing retweeted
I made a Mac video editor that auto-zooms, cleans audio, adds captions and makes UGC videos with Images 2.0, Grok Imagine and Seedance 2.0.
I've been using this for all my latest videos.
dreamcut.ai
Samnang Aing retweeted
how to use Google's NEW open source Design.md + AI Skills to make your startup look like a $100 million company in 1 hour:
1. Design.md is an open source file from Google that captures the soul of a design. Typography, colors, spacing, all in one markdown file. You attach it to your prompt and your agent builds beautiful things every time.
2. Think of it this way. The HTML is the finished dish. The design.md is the recipe. The skills are the ingredients. Put them together and everything you build looks consistent and professional.
3. Don't create a design system from scratch. Find a brand you love. Linear, Stripe, Vercel, whatever resonates. Study it. Use ChatGPT or Claude to help you extract the design language into your own design.md file.
4. Build skills on top of your design.md. A landing page skill. A mobile app skill. A motion design skill. A slide deck skill. Each one references the same design.md so everything looks like it came from the same designer.
5. The biggest mistake people make: they nail one screen and then everything else looks generic. Design.md solves this. One file keeps every page, every format, every medium consistent.
6. Use it across everything. Your landing page. Your app. Your pitch deck. Your promo videos. Same DNA. Same taste. Same system. That's what separates a startup that looks real from one that looks vibe-coded.
7. Build a second brain for design inspiration. When you see something beautiful in the real world or online, capture it. Save it. When you're building something new, reference it. Taste is developed, not downloaded.
8. It's obvious but the difference between a product people trust and a product people bounce from is how it looks and feels. Design.md gives you that edge.
you can watch below
youtu.be/oLu32YpiIJw?si=1YoY…
shoutout to @mengto for coming on @startupideaspod and walking through his full workflow.
if you want to use AI to actually build gorgeous designs, you'll want to use see this.
watch
Samnang Aing retweeted
I made a tool that generates UIs with a design system that's copyable as prompts.
Everything is a prompt: font pairings, color system, spacing, icon sets, buttons and even webgl & threejs with full code samples.
This made explorations with Gemini 3.1 Pro so precise and fun.
Samnang Aing retweeted
🎁 GIVEAWAY ALERT (Limited Time)
After a long time, I’m giving away 6 high-converting hero sections, From aesthetic visuals to conversion-focused layouts.
All packed into one FREE Figma file 🚀
Perfect if you’re a designer, founder, or building your next landing page.
How to get it (super simple):
- Like this post
- Retweet (so others don’t miss it too)
- Comment “6 Combo”
- Follow me so I can DM you
That’s it.
I’ll send the FREE Figma file to your DMs in a few hours.
Don’t miss this one.
Samnang Aing retweeted
I tried mixing ChatGPT 5.1 and Gemini 3 in the same design… and the result surprised me 😱
I created this beautiful UI using ChatGPT 5.1 and Gemini 3. I started with ChatGPT 5.1 to build the full structure. Then I refined everything with my own style, updated the font, adjusted the colors, added depth with gradients, used the accent color carefully, and polished the whole layout so it feels clean, professional, and easy to read.
Visual hierarchy is always the most important part for me. I need a strong structure and clear information architecture before anything else.
After that, I used Gemini 3 to bring animation into the design. And the nice part is… I only needed a few simple keywords: CSS 3D transforms, orbit, scrolling, typing, and it understood what I wanted.
For the hero card, Gemini created a 3D transform using perspective(), rotateX(), and rotateY(), plus a smooth border-gradient hover effect.
It also generated:
Orbit rotation for the avatars, looping scroll for the logos, typewriter text, pulse animation for the icon, a progressive stroke-draw for the pie chart.
Normally, I don’t add a lot of animation. I like to focus on the UI itself, and animation is one of my weak points. With ChatGPT or Claude, I often spend too much time fixing the details.
But with Gemini 3, the animations were easier to produce and match my style.
So using both models together actually works really well.
And I’m excited to show you my next UI, fully created with Gemini 3.
Samnang Aing retweeted
Okay, as a designer, I'm over the moon with Gemini 3.
You can create far better results with the right prompting and references. Let's get into the details.
So I started underwhelmed. A non-descriptive "create a landing page" will give you generic purple results. Barely better than Claude 4.5 and def worse than GPT 5.1. Remember, it still likes purple by default.
BUT, when I started giving references to code and image-to-html. Holy sh*t, it's good. Like gpt-4-moment-good. It's like having midjourney but for web design. Hyper creative, excels at everything you throw at it: complex layouts, animations, card-flipping, 3D, visual accuracy, etc.
So, it's NOT good without handholding. It's only good if you are very descriptive, like giving images, font names, libraries, code, blueprints. It's like an unassuming anime main character. If you ask the most basic thing, it'll probably disappoint, but the moment you throw a well-written prompt and images, it'll go Saitama on you.
I know a lot of people love the idea of one-shotting crazy product ideas. But as someone who creates products and designs with AI every day, I can tell you that the beauty is in the details. AI shines when you iterate obsessively with it.
Gemini 3 absolutely nails the details.
Samnang Aing retweeted
GPT-5.1 is so good at UI. These were done with minor edits.
Let's look at the details.
First, the colors. No more purple everywhere. Less of those floating blurred balls of gradients. It seems to favor supabase green more now. Shadows and glows are handled with more taste. AI doesn't do advanced stuff like border gradients, so I added those with a few clicks in editor.
Then, the layout. It's much better at handling complex layouts like bento, adaptive layouts and overlays. While it's not as smart as Claude 4.5 for debugging animations or layout issues, it has far better taste. It does still struggle with elements that get squeezed, so gotta apply flex-none.
Typography looks more professional now. Less of those hugely bold generic fonts. Better hierarchy and use of sections/dividers. Still defaults too often to Inter, so I applied quick font pairings in Aura for Geist, Bricolage and Space Grotesk.
I used Iconify Solar duotone bold and MingCute fonts for the social icons. These can be included in the prompts.
Samnang Aing retweeted
Creating new components, but not stopping there.
I’m thinking about how they’ll move.
Animation = emotion ✨
#UIDesign #DesignProcess #WebDesign #AIDesign