Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

What if you could draw ANY image using real city streets? latest experiment: Upload any picture → the app detects its edges → then autonomous agent trace and fill the image using actual roads from OpenStreetMap. Agents draws the outlines and fills the interior in green. The city itself... show more

shadows

1,358 subscribers

17,097 views • 4 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Neural Cartography - a real-time city mapping engine powered by distributed rendering agents Agents work in parallel. City name gets drawn in the center. Urban fabric assembles around it. The idea behind Neural Cartography - a WebGL visualization where 7 specialized agents are dispatched simultaneously to reconstruct any city from raw geospatial data, tracing roads, waterways, railways, and city boundaries in real-time - right in your browser. #CreativeCoding #ThreeJS #ReactThreeFiber #DataVisualization #Geospatial #AgenticAI React-three-fiber Three.js #builders

Neural Cartography - a real-time city mapping engine powered by distributed rendering agents Agents work in parallel. City name gets drawn in the center. Urban fabric assembles around it. The idea behind Neural Cartography - a WebGL visualization where 7 specialized agents are dispatched simultaneously to reconstruct any city from raw geospatial data, tracing roads, waterways, railways, and city boundaries in real-time - right in your browser. #CreativeCoding #ThreeJS #ReactThreeFiber #DataVisualization #Geospatial #AgenticAI React-three-fiber Three.js #builders

shadows

10,331 views • 5 months ago

We just discovered the 🔥 COOLEST 🔥 trick in Flow that we have to share: Instead of wordsmithing the perfect prompt, you can just... draw it. Take the image of your scene, doodle what you'd like on it (through any editing app), and then briefly describe what needs to happen (e.g. "changes happen instantly"). Using Frames to Video, Flow will understand the drawings and incorporate them into the final video. Try it and show us what you find!

We just discovered the 🔥 COOLEST 🔥 trick in Flow that we have to share: Instead of wordsmithing the perfect prompt, you can just... draw it. Take the image of your scene, doodle what you'd like on it (through any editing app), and then briefly describe what needs to happen (e.g. "changes happen instantly"). Using Frames to Video, Flow will understand the drawings and incorporate them into the final video. Try it and show us what you find!

Google Labs

411,744 views • 1 year ago

Google Earth now lets you create AI images using real-world locations. With the new Nano Banana AI feature, you can pick any place in Google Earth, click “Create Image,” and describe what you want to see. The AI can turn that location into a historical scene, a futuristic city or a fantasy world The feature uses Google Earth’s satellite and 3D map data as the base, so the AI-generated images are built from real locations.

Google Earth now lets you create AI images using real-world locations. With the new Nano Banana AI feature, you can pick any place in Google Earth, click “Create Image,” and describe what you want to see. The AI can turn that location into a historical scene, a futuristic city or a fantasy world The feature uses Google Earth’s satellite and 3D map data as the base, so the AI-generated images are built from real locations.

Pirat_Nation 🔴

24,731 views • 1 month ago

If you're using match cuts in your video, the invideo editor + agent gives you the fastest, most seamless experience to do it. Here's what we did to create this in ~40 minutes: ~Picked an image with a circle in the centre. Used that image as a reference to generate other images with circular subjects (but you could always just use your own footage). ~Uploaded the audio track I wanted to use into the invideo timeline, and asked the agent to detect all beats and place markers there. ~Asked the agent to then place all my generated images against those markers. ~Used rulers in the editor to maintain clip/subject alignment.

If you're using match cuts in your video, the invideo editor + agent gives you the fastest, most seamless experience to do it. Here's what we did to create this in ~40 minutes: ~Picked an image with a circle in the centre. Used that image as a reference to generate other images with circular subjects (but you could always just use your own footage). ~Uploaded the audio track I wanted to use into the invideo timeline, and asked the agent to detect all beats and place markers there. ~Asked the agent to then place all my generated images against those markers. ~Used rulers in the editor to maintain clip/subject alignment.

Invideo

10,702 views • 7 days ago

Have you ever imagined your city turning into a Lego world? With Kling O1, that fantasy becomes real! Tools: Kling IMAGE O1, Kling Image to Video Use this image-generation prompt: Present a clear, 45° top-down isometric miniature Lego-style 3D cartoon scene of New York built entirely from plastic bricks. Recreate the city’s most iconic landmarks and architectural elements using distinctive Lego block geometry. Use clean, glossy brick textures with subtle PBR reflections and soft, playful lighting and shadows. Keep the composition minimalistic with a soft, solid-colored background. Feeling inspired? Just change the city name and watch a whole new Lego universe come to life!

Have you ever imagined your city turning into a Lego world? With Kling O1, that fantasy becomes real! Tools: Kling IMAGE O1, Kling Image to Video Use this image-generation prompt: Present a clear, 45° top-down isometric miniature Lego-style 3D cartoon scene of New York built entirely from plastic bricks. Recreate the city’s most iconic landmarks and architectural elements using distinctive Lego block geometry. Use clean, glossy brick textures with subtle PBR reflections and soft, playful lighting and shadows. Keep the composition minimalistic with a soft, solid-colored background. Feeling inspired? Just change the city name and watch a whole new Lego universe come to life!

Kling AI

38,391 views • 9 months ago

SOMEONE VIBE CODED AN APP THAT TURNS ANY PHOTO INTO A REAL PHYSICAL STAMP YOU CAN ORDER you snap a photo, it cuts it into a clean stamp design, and you can order the actual physical stamp to press onto anything. > take or upload any photo or image > it turns it into a proper stamp design automatically > all your designs are saved and sorted by date, so you can go back to any of them > order the real physical stamp right from the app and it ships to you > press it onto letters, packaging, cards, whatever you want so instead of paying a custom shop and waiting, you make your own stamp from a photo in a couple taps, then order it without ever leaving the app. the whole thing is dead simple and does one thing well, which is exactly why people love it

SOMEONE VIBE CODED AN APP THAT TURNS ANY PHOTO INTO A REAL PHYSICAL STAMP YOU CAN ORDER you snap a photo, it cuts it into a clean stamp design, and you can order the actual physical stamp to press onto anything. > take or upload any photo or image > it turns it into a proper stamp design automatically > all your designs are saved and sorted by date, so you can go back to any of them > order the real physical stamp right from the app and it ships to you > press it onto letters, packaging, cards, whatever you want so instead of paying a custom shop and waiting, you make your own stamp from a photo in a couple taps, then order it without ever leaving the app. the whole thing is dead simple and does one thing well, which is exactly why people love it

Om Patel

100,110 views • 2 months ago

MiniMax H3 Instead of sharing the prompts for each of these videos, I thought it would be more useful to share how I created that prompts. All of the videos were generated with text-to-video. First, find an image with the kind of scene, composition and mood you want to recreate. I used a few YouTube playlist thumbnails as references but Pinterest is also a great place to find inspiration. You can even use your own old or nostalgic photographs. Then upload the image to ChatGPT and ask it to describe the scene. The description it gives you can essentially become your text-to-video prompt. From there, you can generate completely new scenes with a similar composition, atmosphere and cinematic language. You can of course use the reference image directly with image-to-video or as a first frame. But if the original image isn't yours, I prefer using it only as visual inspiration and recreating the scene through text-to-video. This is the prompt I use with ChatGPT: "Describe the scene in this image in English, focusing primarily on what is happening, the characters, their actions and body language, the setting and the overall atmosphere. Also briefly describe the composition, framing, camera angle, approximate lens choice, lighting, color palette and cinematic aesthetic. Keep it concise and scene-focused rather than overly technical."

MiniMax H3 Instead of sharing the prompts for each of these videos, I thought it would be more useful to share how I created that prompts. All of the videos were generated with text-to-video. First, find an image with the kind of scene, composition and mood you want to recreate. I used a few YouTube playlist thumbnails as references but Pinterest is also a great place to find inspiration. You can even use your own old or nostalgic photographs. Then upload the image to ChatGPT and ask it to describe the scene. The description it gives you can essentially become your text-to-video prompt. From there, you can generate completely new scenes with a similar composition, atmosphere and cinematic language. You can of course use the reference image directly with image-to-video or as a first frame. But if the original image isn't yours, I prefer using it only as visual inspiration and recreating the scene through text-to-video. This is the prompt I use with ChatGPT: "Describe the scene in this image in English, focusing primarily on what is happening, the characters, their actions and body language, the setting and the overall atmosphere. Also briefly describe the composition, framing, camera angle, approximate lens choice, lighting, color palette and cinematic aesthetic. Keep it concise and scene-focused rather than overly technical."

Kōda

55,398 views • 1 month ago

Midjourney sref + Sora 2 Pro is the sauce. With one Midjourney style image, you can give a specific style for your entire project. I created two different 12-second clips and edited them together. Some details aren’t fully consistent, like the iPod or AirPods because the clips were made separately from a single image (Character in a specific style). It could be fixed in post-production, but that would take more time, and this was more of an experimental test. It would be great to add the actual product image with the current one to maintain product consistency. I feel like if there were a way to add 2–4 images into this workflow, it could open up a lot more possibilities and consistency. With an API, it could be possible. Or let’s see what Veo 3.1 has to offer.

Midjourney sref + Sora 2 Pro is the sauce. With one Midjourney style image, you can give a specific style for your entire project. I created two different 12-second clips and edited them together. Some details aren’t fully consistent, like the iPod or AirPods because the clips were made separately from a single image (Character in a specific style). It could be fixed in post-production, but that would take more time, and this was more of an experimental test. It would be great to add the actual product image with the current one to maintain product consistency. I feel like if there were a way to add 2–4 images into this workflow, it could open up a lot more possibilities and consistency. With an API, it could be possible. Or let’s see what Veo 3.1 has to offer.

Allar Haltsonen

10,141 views • 11 months ago

MiniMax H3 - Text to Video A city painted into existence. Change the city name and quote text and use it for any city. Prompt: [CITY_NAME] = EDINBURGH [QUOTE] = A city carved from stone and story. Create a fast, dense, cinematic 16:9 macro travel film where the entire identity of [CITY_NAME] is continuously painted into existence by living oil paint. Use a low grazing macro camera with extremely shallow depth of field. The world is a vast canvas covered in thick wet impasto paint, sculpted brushstroke ridges, carved grooves, glossy reflections and dense gold glitter. The paint must behave like an active force at all times. It flows like rivers, sweeps like brushwork, gathers like tides, curls at the edges, spills into new paths and physically constructs the city in real time. The film must feel fast, rich and uninterrupted. Use one continuous flowing camera move with no cuts. The camera races across the canvas, skimming over wet paint valleys, weaving between rising structures, accelerating through the city as new landmarks constantly appear ahead. Avoid slow drifting. Keep the visual progression energetic and tightly packed. Start with abstract moving pigment and rapidly transition into recognizable city formation. Show thick paint strokes being laid down, dragged, folded and pulled into shape by an invisible artistic force. Let streams of pigment split and merge like waterways, while dimensional brushstroke masses rise into streets, bridges, domes, towers, rooftops, plazas, canals and layered miniature architecture. Make the city feel as if it is being painted and built at the same time. Reveal many landmarks across the journey, not just one. Let the camera travel seamlessly through the whole city, with one landmark flowing directly into the next. As the camera advances, fresh paint forms arches, facades, bell towers, canal edges, stairways, statues, porticoes and skyline silhouettes associated with [CITY_NAME]. The transitions between landmarks should feel fluid and continuous, with brushstrokes extending forward to pull the viewer deeper into the city. Make the paint motion highly visible and expressive. Show pigment actively spreading across canvas, pouring into channels, stacking into forms, curving into structures and leaving wet textured trails behind. Gold glitter should move with the paint and collect along ridges and valleys, creating sparkling highlights that emphasize speed, direction and shape. Use warm golden key light from the lower left to ignite glossy paint and glitter. Add cool purple-blue ambient fill from the upper right to maintain a dreamy dusk atmosphere. Keep the distant background soft with haze and circular bokeh, but preserve strong clarity on the active foreground paint and newly formed landmarks. Toward the end, the camera rises and pulls back just enough to reveal a broader final view of the fully formed painted city, making it clear that the viewer has traveled through an entire living city built from moving paint. End on a striking travel-poster composition. Place elegant typography in the top left with generous breathing room. Show [CITY_NAME] in refined serif uppercase, with [QUOTE] beneath it in smaller delicate type. The overall feeling should be luxurious, poetic and visually intense, with continuous motion, dense landmark reveals and the clear impression that the whole city is being painted alive in real time.

MiniMax H3 - Text to Video A city painted into existence. Change the city name and quote text and use it for any city. Prompt: [CITY_NAME] = EDINBURGH [QUOTE] = A city carved from stone and story. Create a fast, dense, cinematic 16:9 macro travel film where the entire identity of [CITY_NAME] is continuously painted into existence by living oil paint. Use a low grazing macro camera with extremely shallow depth of field. The world is a vast canvas covered in thick wet impasto paint, sculpted brushstroke ridges, carved grooves, glossy reflections and dense gold glitter. The paint must behave like an active force at all times. It flows like rivers, sweeps like brushwork, gathers like tides, curls at the edges, spills into new paths and physically constructs the city in real time. The film must feel fast, rich and uninterrupted. Use one continuous flowing camera move with no cuts. The camera races across the canvas, skimming over wet paint valleys, weaving between rising structures, accelerating through the city as new landmarks constantly appear ahead. Avoid slow drifting. Keep the visual progression energetic and tightly packed. Start with abstract moving pigment and rapidly transition into recognizable city formation. Show thick paint strokes being laid down, dragged, folded and pulled into shape by an invisible artistic force. Let streams of pigment split and merge like waterways, while dimensional brushstroke masses rise into streets, bridges, domes, towers, rooftops, plazas, canals and layered miniature architecture. Make the city feel as if it is being painted and built at the same time. Reveal many landmarks across the journey, not just one. Let the camera travel seamlessly through the whole city, with one landmark flowing directly into the next. As the camera advances, fresh paint forms arches, facades, bell towers, canal edges, stairways, statues, porticoes and skyline silhouettes associated with [CITY_NAME]. The transitions between landmarks should feel fluid and continuous, with brushstrokes extending forward to pull the viewer deeper into the city. Make the paint motion highly visible and expressive. Show pigment actively spreading across canvas, pouring into channels, stacking into forms, curving into structures and leaving wet textured trails behind. Gold glitter should move with the paint and collect along ridges and valleys, creating sparkling highlights that emphasize speed, direction and shape. Use warm golden key light from the lower left to ignite glossy paint and glitter. Add cool purple-blue ambient fill from the upper right to maintain a dreamy dusk atmosphere. Keep the distant background soft with haze and circular bokeh, but preserve strong clarity on the active foreground paint and newly formed landmarks. Toward the end, the camera rises and pulls back just enough to reveal a broader final view of the fully formed painted city, making it clear that the viewer has traveled through an entire living city built from moving paint. End on a striking travel-poster composition. Place elegant typography in the top left with generous breathing room. Show [CITY_NAME] in refined serif uppercase, with [QUOTE] beneath it in smaller delicate type. The overall feeling should be luxurious, poetic and visually intense, with continuous motion, dense landmark reveals and the clear impression that the whole city is being painted alive in real time.

Kōda

26,703 views • 13 days ago

If you want to understand how far AI-assisted game development has moved in less than a year, IsoCity is one of the best examples. The original version took roughly 40–50 hours with Cursor Composer + cloud agents. Its assets were AI-generated, while the game itself grew into a surprisingly deep city simulation with traffic, pedestrians, trains, planes, zoning, resource management, saving, and mobile support. Under the hood: → Next.js 16 → TypeScript → Native HTML5 Canvas rendering → No external game engine → Custom isometric renderer and simulation systems And the best part: the whole project is open source under MIT, so you can study it, fork it, modify it, or use parts of the architecture in your own experiments. The visual jump from that 2025 build to what agents are producing in 2026 is pretty ridiculous. Built by Andrew Milich and contributors. Repo:

If you want to understand how far AI-assisted game development has moved in less than a year, IsoCity is one of the best examples. The original version took roughly 40–50 hours with Cursor Composer + cloud agents. Its assets were AI-generated, while the game itself grew into a surprisingly deep city simulation with traffic, pedestrians, trains, planes, zoning, resource management, saving, and mobile support. Under the hood: → Next.js 16 → TypeScript → Native HTML5 Canvas rendering → No external game engine → Custom isometric renderer and simulation systems And the best part: the whole project is open source under MIT, so you can study it, fork it, modify it, or use parts of the architecture in your own experiments. The visual jump from that 2025 build to what agents are producing in 2026 is pretty ridiculous. Built by Andrew Milich and contributors. Repo:

Token Gremlin

28,231 views • 29 days ago

OpenClaw, but built for normal people. Sim is an open-source platform that lets you build AI agent workflows on a drag-and-drop canvas. Connect them to channels like Telegram and WhatsApp and deploy without writing a single line of code. They also have a built-in Copilot that generates entire workflows from plain English, which you can then tweak and customize in the UI. Key features: - Free and open-source (Apache 2.0) - Vector store integration for RAG-grounded agents - Self-host with one command (`npx simstudio`) - Run fully local with Ollama, no API keys needed - Supports vLLM for production-grade self-hosted inference The thing I really like about Sim is the level of control you get. You can add conditional branching, parallel execution, human-in-the-loop approval gates, and even nest workflows inside other workflows. Everything is visible on the canvas, so you know exactly what your agent is doing at every step. And you can build a workflow in Sim, deploy it as an MCP server, and plug it into any agent, including OpenClaw. I've shared the link to Sim's GitHub repo in the next tweet.

OpenClaw, but built for normal people. Sim is an open-source platform that lets you build AI agent workflows on a drag-and-drop canvas. Connect them to channels like Telegram and WhatsApp and deploy without writing a single line of code. They also have a built-in Copilot that generates entire workflows from plain English, which you can then tweak and customize in the UI. Key features: - Free and open-source (Apache 2.0) - Vector store integration for RAG-grounded agents - Self-host with one command (`npx simstudio`) - Run fully local with Ollama, no API keys needed - Supports vLLM for production-grade self-hosted inference The thing I really like about Sim is the level of control you get. You can add conditional branching, parallel execution, human-in-the-loop approval gates, and even nest workflows inside other workflows. Everything is visible on the canvas, so you know exactly what your agent is doing at every step. And you can build a workflow in Sim, deploy it as an MCP server, and plug it into any agent, including OpenClaw. I've shared the link to Sim's GitHub repo in the next tweet.

Akshay 🚀

52,426 views • 6 months ago

Started using React Native two days ago and immediately fell down a tab-bar rabbit hole. I’d seen Instagram and Revolut collapse their tab bars on scroll while keeping every icon visible. I wanted that without giving up real iOS Liquid Glass. Turns out iOS 26’s public API can’t express that state. UITabBarMinimizeBehavior is an enum of when, not what. With onScrollDown, UIKit minimizes the bar to the active tab alone. There’s no parameter controlling what survives. So most implementations rebuild the visible bar as a custom component. Some use genuine glass materials, but the real UITabBar is gone and with it, the native selection capsule: that little blob that moves like a drop of water between tabs. You can reproduce it with separate springs on the leading and trailing edges. I didn’t want a reproduction. I wanted UIKit’s. Then I remembered a Flutter app i built some months back which uses cupertino_native. Flutter runs the app while a platform-view bridge renders a real UIKit UITabBar. Finding expo-glass-tabs clarified the compact geometry I wanted. The two ideas clicked: why not bridge a real UITabBar into React Native? Here’s the trick: a standalone UITabBar has no UITabBarController managing it, so Apple’s minimization rule never applies. That means I can control its frame and items myself. Expo Router still owns navigation and screen lifecycle. React Native detects scroll direction. Swift removes and restores the real item labels, recentres the icons and animates the native bar’s size. All five icons remain visible. The result keeps Apple’s Liquid Glass, water-drop capsule, hit testing and accessibility, while adding a compact state its public API doesn’t provide. One gotcha tho: detaching the bar means reimplementing everything the controller previously gave you for free. Active-tab reselect scrolling was one example

Started using React Native two days ago and immediately fell down a tab-bar rabbit hole. I’d seen Instagram and Revolut collapse their tab bars on scroll while keeping every icon visible. I wanted that without giving up real iOS Liquid Glass. Turns out iOS 26’s public API can’t express that state. UITabBarMinimizeBehavior is an enum of when, not what. With onScrollDown, UIKit minimizes the bar to the active tab alone. There’s no parameter controlling what survives. So most implementations rebuild the visible bar as a custom component. Some use genuine glass materials, but the real UITabBar is gone and with it, the native selection capsule: that little blob that moves like a drop of water between tabs. You can reproduce it with separate springs on the leading and trailing edges. I didn’t want a reproduction. I wanted UIKit’s. Then I remembered a Flutter app i built some months back which uses cupertino_native. Flutter runs the app while a platform-view bridge renders a real UIKit UITabBar. Finding expo-glass-tabs clarified the compact geometry I wanted. The two ideas clicked: why not bridge a real UITabBar into React Native? Here’s the trick: a standalone UITabBar has no UITabBarController managing it, so Apple’s minimization rule never applies. That means I can control its frame and items myself. Expo Router still owns navigation and screen lifecycle. React Native detects scroll direction. Swift removes and restores the real item labels, recentres the icons and animates the native bar’s size. All five icons remain visible. The result keeps Apple’s Liquid Glass, water-drop capsule, hit testing and accessibility, while adding a compact state its public API doesn’t provide. One gotcha tho: detaching the bar means reimplementing everything the controller previously gave you for free. Active-tab reselect scrolling was one example

kelvin.dart

67,945 views • 1 month ago

🧃 Introducing stereOS: a Linux based operating system hardened and purpose built for AI agents. It's clear that agents need an ACTUAL operating system (not what people are calling an "OS") to witness the full breadth and depth of their capabilities while mitigating the blast radius of autonomous, untrusted actors. But there are so many problems with AI sandboxes today: * Going out to the apple store and buying a mac mini will never scale and is way too expensive (obviously) * Running in Docker is too restrictive (agents can't stand up their own container infrastructure, no sub virtualization, docker-in-docker is very broken) * Firecracker strips all the hardware so GPU PCIe passthrough, secure boot, FIPs, etc. is out of the question. * Native VMs are too fat and the overhead of 1 agent per VM is too much. stereOS takes a different approach: it's a full NixOS system that you boot and then kick off agent sandboxes inside with gVisor + /nix/store namespace mounting. Each agent gets their own kernel and the /nix/store is read only by nature. Even if the agent was somehow able to escape the gVisor virtual kernel, they'd land on the NixOS system as the "agent" user! Not your actual hardware!! If you want to take a defense-in-depth approach, we support "native" agents that run at the system level kicked off by our `agentd` utility. These agents, on their own, can manage and kick off other sub agents using the internal sandboxing mechanisms. Today, we're open sourcing all of this: * stereOS: our purpose built Linux OS - * masterblaster: client utility to launch, manage, and orchestrate agents - * stereosd: the stereOS system control plane daemon - * agentd: the stereOS system agent management daemon - Give it a try, throw us a star, and let me know what you think 🧃⭐️

🧃 Introducing stereOS: a Linux based operating system hardened and purpose built for AI agents. It's clear that agents need an ACTUAL operating system (not what people are calling an "OS") to witness the full breadth and depth of their capabilities while mitigating the blast radius of autonomous, untrusted actors. But there are so many problems with AI sandboxes today: * Going out to the apple store and buying a mac mini will never scale and is way too expensive (obviously) * Running in Docker is too restrictive (agents can't stand up their own container infrastructure, no sub virtualization, docker-in-docker is very broken) * Firecracker strips all the hardware so GPU PCIe passthrough, secure boot, FIPs, etc. is out of the question. * Native VMs are too fat and the overhead of 1 agent per VM is too much. stereOS takes a different approach: it's a full NixOS system that you boot and then kick off agent sandboxes inside with gVisor + /nix/store namespace mounting. Each agent gets their own kernel and the /nix/store is read only by nature. Even if the agent was somehow able to escape the gVisor virtual kernel, they'd land on the NixOS system as the "agent" user! Not your actual hardware!! If you want to take a defense-in-depth approach, we support "native" agents that run at the system level kicked off by our `agentd` utility. These agents, on their own, can manage and kick off other sub agents using the internal sandboxing mechanisms. Today, we're open sourcing all of this: * stereOS: our purpose built Linux OS - * masterblaster: client utility to launch, manage, and orchestrate agents - * stereosd: the stereOS system control plane daemon - * agentd: the stereOS system agent management daemon - Give it a try, throw us a star, and let me know what you think 🧃⭐️

John McBride

150,844 views • 6 months ago

girl humanoids become the hands of your autonomous agents ngl “imagine if your agents ran a girl humanoid” is not sci-fi bait anymore it is the missing physical layer under every todo list that still dies in a chat window → what the stack actually is your autonomous agents already research compare book draft and click they live in tabs calendars inboxes and apis what they never had was meters a soft body that can walk the kitchen lift the bag set the product in frame and finish the last ugly centimeter girl humanoids become that layer cameras for eyes tendon hands for grasp a dock for overnight charge and a policy link so the agent’s plan becomes motion instead of another notification you ignore you do not “chat with the robot” as the main product you assign the agent the girl is the effector teleop stays for the weird fail the brief stays yours → what that unlocks under your tasks home ops as an agent job check inventory open delivery pick the brand meet the courier put it away the agent owns the logic she owns the walk ugc and brand days the agent writes the shot list watches her cameras calls the next pour you approve the take like a creative director not a joystick babysitter admin with legs forms research returns scheduling on the laptop side then a body that can grab the box tape the label and leave it by the door multi-agent theater that finally touches reality one agent shops one edits the caption one runs qa on the take one soft girl executes the physical beat they all needed → where this leads the house becomes an api with a face staff is no longer only humans on payroll or silent appliances it is agents with rented hands in a knit suit clicking forever gets embarrassing if the plan holds the body finishes it teleop becomes exception handling the dock becomes the real producer credit also the hard edge who is allowed to drive her what she can buy film unlock and say battery still ends the shift precision still breaks on the tiny cruel tasks a frontier agent plus a home body needs a short leash or your kitchen becomes an unsupervised checkout spree → my take girl humanoids become the hands of your autonomous agents which means the win is not a cuter gait it is closing the loop from intent → plan → meters → done imagine is over the punchline is the dock assign the agent let the soft hands finish the room so back

Luella

39,709 views • 5 days ago

Along with @levelsio, we’re looking for the best games you make with AI. More in his tweet below. Cursor 3 has a built-in browser, image generation, and cloud agents that can playtest, while Composer 2 is fast with Three.js. Great for building games! Even developers at Rockstar are using AI now. Games can be built faster, made more beautiful and complex, and created by more people. It's surprisingly easy if you have no experience. The games shown below were already made with Cursor by Startracker 🔺, Danny Limanseta, David Bui, and Chong-U. Show us what you can build! Can't wait to see your submissions.

Along with @levelsio, we’re looking for the best games you make with AI. More in his tweet below. Cursor 3 has a built-in browser, image generation, and cloud agents that can playtest, while Composer 2 is fast with Three.js. Great for building games! Even developers at Rockstar are using AI now. Games can be built faster, made more beautiful and complex, and created by more people. It's surprisingly easy if you have no experience. The games shown below were already made with Cursor by Startracker 🔺, Danny Limanseta, David Bui, and Chong-U. Show us what you can build! Can't wait to see your submissions.

edwin

78,789 views • 5 months ago

Everyone's sleeping on image-to-3D AI models. They can make your app look incredibly unique, with just a little effort. Here's how. This is my calorie tracker, built in a week with nothing but prompting. Just Claude Code + a couple APIs. The visuals are all AI-generated. I'll be sharing the full workflow + all the crazy technical stuff Claude and I did to make this work, so nobody has to struggle through it like me. Deep dive coming soon! Till then, this is the high-level idea: 1. Get a clean image of the food (or whatever your asset is) - In my app, the user describes foods via text, or attaches images (or both) - If text, an LLM extracts the food description and formats it into a specific prompt I tuned for this design, and we generate an image using Z-Image Turbo through fal - If image, we do the same thing but with FLUX.2 [dev] to edit the user image into our reference design - Originally, both used Google Nano Banana, but switching to open models cut costs and latency a ton 2. Gaussian splatting (2D image → 3D model) - I tried various 2D-to-3D options on fal and ended up with TripoSplat as my preferred balance of speed, cost, latency; this turns an image into a 3D model that looks super high quality (link below) - The app displays the 2D image while our backend generates the 3D splat - We "groom" the splat to reduce size and load time by culling low-opacity/scale points 3. Render efficiently on device Originally, it looked great but ran at 10 FPS. Getting to 120 FPS was a crazy journey. TL;DR: - SwiftUI had to go; it forced us to render each asset in independent MTKViews, which wasn't workable - Instead, we composite every dish into one full-bleed CAMetalLayer using MetalSplatter (link below) - We had to make some optimizations within MetalSplatter's code too, to reduce the overhead of sorting points per render Then I added some finishing touches like the subtle rotation and parallax as they move around. I think it turned out pretty cool :) Overall, this took some effort, but we still got it done in less than a day. Hopefully your agent can follow in the footsteps of mine and do it much faster. Keep an eye out for the bigger writeup, which'll give your agent everything it needs. If you have any questions, drop em below!

Everyone's sleeping on image-to-3D AI models. They can make your app look incredibly unique, with just a little effort. Here's how. This is my calorie tracker, built in a week with nothing but prompting. Just Claude Code + a couple APIs. The visuals are all AI-generated. I'll be sharing the full workflow + all the crazy technical stuff Claude and I did to make this work, so nobody has to struggle through it like me. Deep dive coming soon! Till then, this is the high-level idea: 1. Get a clean image of the food (or whatever your asset is) - In my app, the user describes foods via text, or attaches images (or both) - If text, an LLM extracts the food description and formats it into a specific prompt I tuned for this design, and we generate an image using Z-Image Turbo through fal - If image, we do the same thing but with FLUX.2 [dev] to edit the user image into our reference design - Originally, both used Google Nano Banana, but switching to open models cut costs and latency a ton 2. Gaussian splatting (2D image → 3D model) - I tried various 2D-to-3D options on fal and ended up with TripoSplat as my preferred balance of speed, cost, latency; this turns an image into a 3D model that looks super high quality (link below) - The app displays the 2D image while our backend generates the 3D splat - We "groom" the splat to reduce size and load time by culling low-opacity/scale points 3. Render efficiently on device Originally, it looked great but ran at 10 FPS. Getting to 120 FPS was a crazy journey. TL;DR: - SwiftUI had to go; it forced us to render each asset in independent MTKViews, which wasn't workable - Instead, we composite every dish into one full-bleed CAMetalLayer using MetalSplatter (link below) - We had to make some optimizations within MetalSplatter's code too, to reduce the overhead of sorting points per render Then I added some finishing touches like the subtle rotation and parallax as they move around. I think it turned out pretty cool :) Overall, this took some effort, but we still got it done in less than a day. Hopefully your agent can follow in the footsteps of mine and do it much faster. Keep an eye out for the bigger writeup, which'll give your agent everything it needs. If you have any questions, drop em below!

Anshu

29,342 views • 2 months ago

This is the easiest way to make $10k/month with organic affiliate and AI Arcads launched an ai ugc studio that lets you build an entire army of hyper-real AI actors Then you turn any static image into a high-quality video showcasing any product go to TikTok and make an account + warm it up using arcads you can run an entirely AI UGC account using the same character over and over, making it seem like an authentic TT page Mix the content up with slideshows and videos with the same character Here's the AI stack gameplan: - Claude to help you write scripts - Arcads to generate an image of an AI girlie that fits your product demographic Scroll tiktok and save + download every video / slideshow you see made by clippers promoting a product (there's literally loads) Your going to find an offer on whop for making money online or spirituality and target it towards girls feed all these videos you scraped into a custom google gemini gem trained to deconstruct hooks / angles for you for easy hook inspiration + ideas Deconstruct the hooks, put them into Claude and ask it to give you hooks for the same style of video put for your products your promoting For the videos do caption and reaction + showcase formats Generate the reactions using the character you made in arc ads then manually record the showcasing of the product or proof of the product working Also for caption generate a 8-10 second video you can put text over Include your CTA in the video for reaction style and captions for caption style Plus generate images with the same character and make slideshows directed to your product Now rinse and repeat this make multiple accounts with multiple different avatars and print

This is the easiest way to make $10k/month with organic affiliate and AI Arcads launched an ai ugc studio that lets you build an entire army of hyper-real AI actors Then you turn any static image into a high-quality video showcasing any product go to TikTok and make an account + warm it up using arcads you can run an entirely AI UGC account using the same character over and over, making it seem like an authentic TT page Mix the content up with slideshows and videos with the same character Here's the AI stack gameplan: - Claude to help you write scripts - Arcads to generate an image of an AI girlie that fits your product demographic Scroll tiktok and save + download every video / slideshow you see made by clippers promoting a product (there's literally loads) Your going to find an offer on whop for making money online or spirituality and target it towards girls feed all these videos you scraped into a custom google gemini gem trained to deconstruct hooks / angles for you for easy hook inspiration + ideas Deconstruct the hooks, put them into Claude and ask it to give you hooks for the same style of video put for your products your promoting For the videos do caption and reaction + showcase formats Generate the reactions using the character you made in arc ads then manually record the showcasing of the product or proof of the product working Also for caption generate a 8-10 second video you can put text over Include your CTA in the video for reaction style and captions for caption style Plus generate images with the same character and make slideshows directed to your product Now rinse and repeat this make multiple accounts with multiple different avatars and print

Pounds

32,407 views • 7 months ago

gemini omniflash is actually f*cking cracked. you can animate/edit any video with a text prompt. character swaps, object transforms, full environment changes without regenerating/rotoscoping. everyone using AI to to animate and edit videos right now hits the same wall. the clip comes out 90% right and you regenerate from scratch hoping the 10% fixes itself. it never does. the fix is using your video as the input. omniflash edits what's already there instead of rolling the dice again. here's what's in the system: > the two-layer premiere trick: generate the same shot twice (one with background removed), stack them, cut at one frame, instant scene change > character swap with a single reference image (plus the one line you need or the model keeps the original's features) > object transforms that leave the rest of the frame untouched: stone into glowing sphere, candles into flowers > style transfer from an image reference instead of text, way more accurate > why stacking edits in one prompt breaks everything and the exact step order that doesn't > the audio limitation nobody mentions and how to work around it i packaged every prompt, the edit sequence, and the premiere layering setup. RT + reply "OMNI" and i'll send it over.

gemini omniflash is actually f*cking cracked. you can animate/edit any video with a text prompt. character swaps, object transforms, full environment changes without regenerating/rotoscoping. everyone using AI to to animate and edit videos right now hits the same wall. the clip comes out 90% right and you regenerate from scratch hoping the 10% fixes itself. it never does. the fix is using your video as the input. omniflash edits what's already there instead of rolling the dice again. here's what's in the system: > the two-layer premiere trick: generate the same shot twice (one with background removed), stack them, cut at one frame, instant scene change > character swap with a single reference image (plus the one line you need or the model keeps the original's features) > object transforms that leave the rest of the frame untouched: stone into glowing sphere, candles into flowers > style transfer from an image reference instead of text, way more accurate > why stacking edits in one prompt breaks everything and the exact step order that doesn't > the audio limitation nobody mentions and how to work around it i packaged every prompt, the edit sequence, and the premiere layering setup. RT + reply "OMNI" and i'll send it over.

Sulfur

36,652 views • 2 months ago

GOOGLE MAPS SHOWS YOU ROADS. THIS WEBSITE SHOWS YOU EVERY TRAIN JOURNEY ON EARTH WORTH TAKING. it's called World Train Map → 1,470 routes. 120 countries. one map. click any line. see the distance, the time, the top speed, the year it opened. search any country. see every train in it worth riding. Moscow to Vladivostok. 9,289 km, seven days, eight time zones, one country. Xining to Lhasa, cresting at 5,072 m, oxygen pumped into sealed carriages. Lima to Huancayo, 4,781 m, on plain track with no rack rail to help it. the Jungfraubahn, ending in a station carved inside the Eiger since 1912. 117 night trains across 57 countries, 22 of them brought back from the dead since 2016. the best part is how fast your brain starts using it wrong. you open it to look up the Trans Siberian. then you check the night trains out of your nearest capital. then you're reading about a sleeper to a city you have never once planned to visit. built by one person in Norway as a hobby project. same person who built Movie Scene Map. just a website that shows you where the trains actually go. open tab. search your country. find the train you didn't know you could take.

GOOGLE MAPS SHOWS YOU ROADS. THIS WEBSITE SHOWS YOU EVERY TRAIN JOURNEY ON EARTH WORTH TAKING. it's called World Train Map → 1,470 routes. 120 countries. one map. click any line. see the distance, the time, the top speed, the year it opened. search any country. see every train in it worth riding. Moscow to Vladivostok. 9,289 km, seven days, eight time zones, one country. Xining to Lhasa, cresting at 5,072 m, oxygen pumped into sealed carriages. Lima to Huancayo, 4,781 m, on plain track with no rack rail to help it. the Jungfraubahn, ending in a station carved inside the Eiger since 1912. 117 night trains across 57 countries, 22 of them brought back from the dead since 2016. the best part is how fast your brain starts using it wrong. you open it to look up the Trans Siberian. then you check the night trains out of your nearest capital. then you're reading about a sleeper to a city you have never once planned to visit. built by one person in Norway as a hobby project. same person who built Movie Scene Map. just a website that shows you where the trains actually go. open tab. search your country. find the train you didn't know you could take.

Kyronis

31,036 views • 5 days ago

This is literally genius🤯 4.9 million views with this format And nobody even knows its a clanker they copied a viral format in the fashion space Easily automated it, this account alone could make $40,000/mo+ if they tie it to a fashion app And add a strong CTA anybody can replicate an AI account like this in 6 simple steps 1. Connect higgsfield MCP 2. Have nano banana create the base character 3. Have claude come up with a fashion line ( like Anime characters clothings ) 4. Have the higgs mcp generate 10 outfit variations images for claudes idea. 5. Generate all the clips using seedance 2.0 from the start image of each outfit and the same base prompt for walking. 6. add a CTA somewhere in there to your fashion app congratulations you automated a fashion app to $40k/mo

This is literally genius🤯 4.9 million views with this format And nobody even knows its a clanker they copied a viral format in the fashion space Easily automated it, this account alone could make $40,000/mo+ if they tie it to a fashion app And add a strong CTA anybody can replicate an AI account like this in 6 simple steps 1. Connect higgsfield MCP 2. Have nano banana create the base character 3. Have claude come up with a fashion line ( like Anime characters clothings ) 4. Have the higgs mcp generate 10 outfit variations images for claudes idea. 5. Generate all the clips using seedance 2.0 from the start image of each outfit and the same base prompt for walking. 6. add a CTA somewhere in there to your fashion app congratulations you automated a fashion app to $40k/mo

Ernesto Lopez

100,375 views • 3 months ago