I made seven small 3D worlds, each from a single image. One picture per world, one per character. @Viggle_PINOC by @ViggleAI, running on their new JST-2 world model, turned them into Gaussian splat worlds and rigged characters that run in the browser. Then Claude Code, connected to the PINOC MCP, walked Fern through every world and directed the camera. All of this is 3D. Imagine it as a landing page, a game or a demo people can explore.

I made a skill called HTML Reel that turns a post, a video or a landing page into a reel. It writes the script, builds every scene in HTML and cuts each move on a word. Once you record your take, it retimes everything to your voice.

Someone made a fully playable Le Petit Prince game, and the level of detail is mind-blowing. It feels cinematic the whole way through. You get to explore every planet from the story, and it's all interactive. Sac shared the full breakdown and prompts: GPT Image 2.5 for the concept art, Tripo for the 3D models, and Opus 5.5 driving Blender and Unity. He plans to open-source the full game too. Read it here:

I made these landing pages with MiniMax M3.1 Flash, at a fraction of the cost of frontier models. Three keyboard sites, a SaaS page, a rainy 3D Singapore at night and a little 3D lighthouse game. My favourite is the exploded keyboard one. I made one render of the keyboard in MiniMax first, and every painting, photo and film came from that render, so it's the same board in every room. $0.15 per 1M input tokens, $0.60 per 1M output. Here's the whole process, prompts included.

I made these landing pages with MiniMax M3.1 Flash, at a fraction of the cost of frontier models. Three keyboard sites, a SaaS page, a rainy 3D Singapore at night and a little 3D lighthouse game. My favourite is the exploded keyboard one. I made one render of the keyboard in MiniMax first, and every painting, photo and film came from that render, so it's the same board in every room. $0.15 per 1M input tokens, $0.60 per 1M output. Here's the whole process, prompts included.

You can pretty much turn all your Claude and Codex sites into Framer sites in one prompt: Create a copy of this site in Framer using the MCP: It's a cheat code for polishing the details, working with clients and creating templates.

I used the new Pika ChatGPT plugin to art direct this landing page. Has pretty much all the image and video gen models, plus really good editing tools. All inside Codex. Here's the full prompt: Create a landing page for the new roadster car, and we're going to recreate everything in 3D using Three.js. But first, I want you to use the Pika plugin to image-generate the website design for each section, and be creative about how we're going to present the car. For reference: Do it in the style of Tesla but dark mode. I need generations as references for each section of the site before generating in three.js. Make sure to get the 3D to be at least a score of 8 out of 10.

I used the new Pika ChatGPT plugin to art direct this landing page. Has pretty much all the image and video gen models, plus really good editing tools. All inside Codex. Here's the full prompt: Create a landing page for the new roadster car, and we're going to recreate everything in 3D using Three.js. But first, I want you to use the Pika plugin to image-generate the website design for each section, and be creative about how we're going to present the car. For reference: Do it in the style of Tesla but dark mode. I need generations as references for each section of the site before generating in three.js. Make sure to get the 3D to be at least a score of 8 out of 10.

Opus 5.5 sculpted every part of this ship in code, including the dragon, sails, and architecture. I can't say it has bad taste anymore. But it still needs steering, so I tried a new way of prompting. Live site: I asked Opus to score every part of the scene: the ship, water, landscapes, buildings, and their individual parts. Then I asked it to keep improving each part until it scored at least 8 out of 10, depending on my token and time budget. The key is to let it work as long as possible. The longer it works, the better it gets, until it reaches a point where I need to course correct. For me, Opus 5.5 reaches a level of detail and realism that no other model does.

Opus 5.5 is next level. I’m genuinely impressed by the three.js details. I generated a playable boat scene through Japanese landscapes with dynamic weather, day and night lighting, realistic textures and 3D characters. Live site: The water reflections, physics, scenery and architecture are insane. I could look at this all day.

This looks straight out of Blender, but it's all code in a single HTML file at about 186 KB. Astra can create these ultra-realistic 3D product demos for landing pages. A few three.js skills let you keep looping on the details, textures, lighting, and interactions until everything feels right. Live site: Our team has been adding five landing pages and dozens of components to every week. Reusing the same components and skills has improved the quality so much.

I've been using Hyper3D inside Codex to create 3D assets, especially ultra-detailed models for my landing pages. It's pretty crazy how fast the market is moving now that Astra, Opus 5, and Fable are getting so good at 3D. My current workflow is procedural three.js for environments, then Blender + Hyper3D for the more detailed models.

I recorded a 41-minute tutorial on how I use Astra to create insane three.js websites in Codex. I've been using DiffUI to brainstorm UIs before moving into code. It's fast and cheap, generates multiple variants and lets me branch ideas, sections, logos, and other components. Then I use "Copy for agent" and bring everything into Codex where I add transparent PNG layers, animations, and three.js skills. Live sites: 3D skills: Get $20 in credits on DiffUI:

GPT-6 Astra is amazing for motion design, especially when you're presenting a UI or an app. I asked it to create a Codex promo using PerspectiveUI from my ThreeUI library. Then I kept refining it: a midnight-blue nebula, stars forming a 6, progressive blur, 3D camera moves, close-ups of typing, and text particles. I finished by cutting it to 30 seconds, six distinct scenes, and three prompts from our conversation. Live site:

I open-sourced this scrolling virtual-tour landing page, along with 8 new three.js skills. They cover room-to-room tours controlled by scrolling, sky rays, sky backgrounds, falling leaves, four seasons, high-resolution textures, high-poly models, and retina rendering. Live site: Source: Skills:

This is a japanese house-tour landing page made in three.js with Fable 5.1 using the dream-loop skill. Live site: It's crazy how realistic it looks even though it's all code and under 1 MB (except images). You can tour every room, switch between seasons, see light rays through the house, and watch koi swim through realistic water. The secret sauce to ultra-realistic 3d in code is a loop like this: dream-loop gets the agent to generate a target image, compare the live 3d against it with a separate critic, and keep refining the result. Skill: Let me know if I should open-source the page.

I built a multiplayer Catan-inspired game entirely with Astra. It's free to play: It's mobile-friendly and has narration, guides, customizations, multiple expansions and a game lobby where anyone can join, chat, and use voice chat. It took 4 days to build and hundreds of dollars in tokens. Becoming a game dev in 2026 wasn't on my bingo card, but here we are. AI has advanced so much that you can finally make the game you've always dreamed of, even without a team.

I built a multiplayer Catan-inspired game entirely with Astra. It's free to play: It's mobile-friendly and has narration, guides, customizations, multiple expansions and a game lobby where anyone can join, chat, and use voice chat. It took 4 days to build and hundreds of dollars in tokens. Becoming a game dev in 2026 wasn't on my bingo card, but here we are. AI has advanced so much that you can finally make the game you've always dreamed of, even without a team.

I built StoryComet with Fable 5.1 in three days. 15 animated children's books in five languages, with translated voiceovers, covers and UI. Parents can track progress. Kids can take quizzes, collect pins and 3D souvenirs, and switch languages on the fly. Six books teach English, Spanish, French, Japanese or Chinese. My three-day workflow: - Day 1: prototype (and post on X) - Day 2: 9 more books, languages, progress, quizzes, pins and souvenirs - Day 3: polish, domain name, supabase, accounts, Stripe and optimization The first three books are 100% free so you can try the whole experience. Members unlocks the other 12 at early-bird pricing. The 3D models and tokens cost me hundreds of dollars, so your support means a lot.

So I'm adding learning books for math, science, and languages using the same concept. It's still early, but my kids loved the stories! For some reason, they don't like doing homework on paper. Hopefully, creating a world around it and making it interactive and rewarding will work better. I'm trying different themes like Harry Potter and origami. A lot of people want to create their own, so I'll make a specific course about this and include the source code. For now, you can take my Fable 5.1 game development course and join my webinars: