Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Marco Amati, an Unreal Engine VFX Compositor, shares a powerful R&D project focused on combining Gaea terrain masks with procedural logic for asset placement. See how he makes the procedural feel art-directed, driven by Quixel Megascans assets.

quixeltools's profile picture

Quixel

62,420 subscribers

15,917 Aufrufe • vor 11 Monaten •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Stuck in Roots by Lighting Artist Karim Yasser is an environment made using Unreal Engine 5.5.1 which takes us deep into the woods 🌳 The creation of this project is rooted in Quixel Megascans assets, unique meshes made with Unreal's modelling tools, Lumen and Nanite. Through these tools, Karim was able to approach the project like a canvas to create a more stylized look with higher quality lighting on.
0:36

Stuck in Roots by Lighting Artist Karim Yasser is an environment made using Unreal Engine 5.5.1 which takes us deep into the woods 🌳 The creation of this project is rooted in Quixel Megascans assets, unique meshes made with Unreal's modelling tools, Lumen and Nanite. Through these tools, Karim was able to approach the project like a canvas to create a more stylized look with higher quality lighting on.

Unreal Engine

20,208 Aufrufe • vor 1 Jahr

Jolan Huijskes explored the custom Blender and Unreal Engine 5 tools he developed for large-scale game environments, using them to build a fully playable world inspired by Saros. "This fan art project is an exploration of how environment art tools can be used to create large-scale levels for games with maximum control for Level Artists. I focused on tool development, composition, and art direction. In this article, I will explore how and why I developed these tools for my fan art project: Blender Fracture Generation (a tool to be released for free soon), Unreal Engine Array Tool, Unreal Engine Fracturing Tool, Unreal Engine PCG Scattering with Artist Control." Read the interview:
0:44

Jolan Huijskes explored the custom Blender and Unreal Engine 5 tools he developed for large-scale game environments, using them to build a fully playable world inspired by Saros. "This fan art project is an exploration of how environment art tools can be used to create large-scale levels for games with maximum control for Level Artists. I focused on tool development, composition, and art direction. In this article, I will explore how and why I developed these tools for my fan art project: Blender Fracture Generation (a tool to be released for free soon), Unreal Engine Array Tool, Unreal Engine Fracturing Tool, Unreal Engine PCG Scattering with Artist Control." Read the interview:

80 LEVEL

29,394 Aufrufe • vor 1 Monat

🏆 Best of Term – Environment | Interior (Fall 2025) Gnomon Certificate in Digital Production student Chiao Lu created this photorealistic, modular game environment. She was inspired by rural mountain towns and local general stores in her home, Taiwan. This project taught Chiao how to set dress an environment & tell a story with a limited number of props. She also learned how to generate procedural assets with Houdini and Unreal Blueprints, which helped make the piece feel more lived in and organic. Congratulations, Chiao! Gnomon Course: Demo Reel 1 Instructors: Anton Napierala, Gabriel Cervantes Software: Autodesk Maya, Unreal Engine, Adobe Substance 3D Designer/Painter, SideFX Houdini, SpeedTree Concept: Original
0:46

🏆 Best of Term – Environment | Interior (Fall 2025) Gnomon Certificate in Digital Production student Chiao Lu created this photorealistic, modular game environment. She was inspired by rural mountain towns and local general stores in her home, Taiwan. This project taught Chiao how to set dress an environment & tell a story with a limited number of props. She also learned how to generate procedural assets with Houdini and Unreal Blueprints, which helped make the piece feel more lived in and organic. Congratulations, Chiao! Gnomon Course: Demo Reel 1 Instructors: Anton Napierala, Gabriel Cervantes Software: Autodesk Maya, Unreal Engine, Adobe Substance 3D Designer/Painter, SideFX Houdini, SpeedTree Concept: Original

Gnomon

10,963 Aufrufe • vor 5 Monaten

Master Total War: PHARAOH with an AI Advisor powered by NVIDIA ACE. See how Creative Assembly’s R&D team is exploring new onboarding experiences by enhancing the in-game Advisor with NVIDIA ACE, helping guide players on their journey to becoming a powerful Bronze-Age ruler.
1:57

Master Total War: PHARAOH with an AI Advisor powered by NVIDIA ACE. See how Creative Assembly’s R&D team is exploring new onboarding experiences by enhancing the in-game Advisor with NVIDIA ACE, helping guide players on their journey to becoming a powerful Bronze-Age ruler.

NVIDIA GeForce

40,616 Aufrufe • vor 9 Monaten

How do you make a vibe-coded world feel truly alive instead of looking like a few assets randomly scattered across an empty map? I keep running into this problem. The AI can generate the terrain and each asset individually, but it struggles with placement, density and composition. A forest becomes ten isolated trees. A town becomes three buildings beside a road. The assets exist, but the environment never feels naturally constructed. It made me think about last year, when I opened X and discovered the insane project @levelsio was building: a multiplayer flight game running entirely in the browser, with a sponsorship system where brands could buy their own advertising blimps. The entire project was vibe-coded. Watching such an ambitious idea become a real multiplayer game was incredible, and it was exactly the kind of project that pushed me to go 100% into vibe coding. Now Astra is emerging as OpenAI’s next major model family (whether it eventually ships as GPT‑5.7, GPT‑6 or something else) and I’m ridiculously excited to discover what this new generation will let us build. So here’s a little nod to that inspiration with my own project where you can pilot a plane. And yes, I absolutely love Disney’s Planes 😂 How do you handle environmental placement in your projects? Better prompts, procedural generation, specialized tools, or manual level design afterward?
1:19

How do you make a vibe-coded world feel truly alive instead of looking like a few assets randomly scattered across an empty map? I keep running into this problem. The AI can generate the terrain and each asset individually, but it struggles with placement, density and composition. A forest becomes ten isolated trees. A town becomes three buildings beside a road. The assets exist, but the environment never feels naturally constructed. It made me think about last year, when I opened X and discovered the insane project @levelsio was building: a multiplayer flight game running entirely in the browser, with a sponsorship system where brands could buy their own advertising blimps. The entire project was vibe-coded. Watching such an ambitious idea become a real multiplayer game was incredible, and it was exactly the kind of project that pushed me to go 100% into vibe coding. Now Astra is emerging as OpenAI’s next major model family (whether it eventually ships as GPT‑5.7, GPT‑6 or something else) and I’m ridiculously excited to discover what this new generation will let us build. So here’s a little nod to that inspiration with my own project where you can pilot a plane. And yes, I absolutely love Disney’s Planes 😂 How do you handle environmental placement in your projects? Better prompts, procedural generation, specialized tools, or manual level design afterward?

Givros

17,204 Aufrufe • vor 1 Monat

🎮 SNEAK: Claynosaurz x Gameloft + Consoles Gameloft’s team surprised us with an Early Gameplay Prototype, demonstrating how our world can expand across platforms, including consoles. Leveraging the latest Unreal Engine tech, they’ve built a sandbox where our interoperable assets—the same ones you’ll recognize from our mobile game—seamlessly translate into a new, immersive console experience. Gameloft chose Claynosaurz for this R&D, highlighting the synergy we’re building together. While this prototype is separate from our mobile game, it hints at big possibilities for us in new digital playgrounds with a focus on spearheading interoperability. We're just getting started 🫡
0:44

🎮 SNEAK: Claynosaurz x Gameloft + Consoles Gameloft’s team surprised us with an Early Gameplay Prototype, demonstrating how our world can expand across platforms, including consoles. Leveraging the latest Unreal Engine tech, they’ve built a sandbox where our interoperable assets—the same ones you’ll recognize from our mobile game—seamlessly translate into a new, immersive console experience. Gameloft chose Claynosaurz for this R&D, highlighting the synergy we’re building together. While this prototype is separate from our mobile game, it hints at big possibilities for us in new digital playgrounds with a focus on spearheading interoperability. We're just getting started 🫡

Claynosaurz

104,600 Aufrufe • vor 1 Jahr

I built a Three.js rendering study inspired by Tiny Glade’s painterly aesthetic, and got it running at 120fps in the browser. Over the past few weeks, I’ve been studying how stylized games achieve that soft, handcrafted look in real time. Tiny Glade was a huge inspiration, and I wanted to use the browser as a constraint: no compute shaders, no native GPU access, and single-threaded JavaScript. As part of this study, I implemented: - GPU-driven instanced brick walls with procedural noise jitter and elastic build animations - Tree, bush, and flower rendering with billboard card expansion, wind sway, and grow animations - Procedural grass with terrain conformance and interactive push deformation - Animated water with layered noise, interactive ripples, and Fresnel-based reflections - Procedural terrain with slope-aware triplanar materials, dirt paths, and rocks - A 7-pass post-processing stack with TAA, bloom, depth of field, painterly filtering, ACES tonemapping, 3D LUT color grading, and film grain The hardest part wasn’t writing any single shader. It was making all of these systems work together at high frame rates inside WebGL, where every millisecond counts and performance problems compound quickly across animation, materials, post-processing, and scene management. Some techniques in this study were inspired by analyzing Tiny Glade’s rendering approach, while others were original implementations built from scratch from visual reference. That contrast taught me a lot: recreating an effect is one challenge, but designing your own shaders and systems to achieve a similar feel is a very different one. This is a private educational rendering study. Some temporary placeholder content is being used during the research phase, and any public or production version would use original or properly licensed assets. Huge credit to Pounce Light for the incredible art direction and rendering work in Tiny Glade: Three.js #gamedev #webgl #threejs #rendering #graphics #realtimerendering #shaderdev
7:21

I built a Three.js rendering study inspired by Tiny Glade’s painterly aesthetic, and got it running at 120fps in the browser. Over the past few weeks, I’ve been studying how stylized games achieve that soft, handcrafted look in real time. Tiny Glade was a huge inspiration, and I wanted to use the browser as a constraint: no compute shaders, no native GPU access, and single-threaded JavaScript. As part of this study, I implemented: - GPU-driven instanced brick walls with procedural noise jitter and elastic build animations - Tree, bush, and flower rendering with billboard card expansion, wind sway, and grow animations - Procedural grass with terrain conformance and interactive push deformation - Animated water with layered noise, interactive ripples, and Fresnel-based reflections - Procedural terrain with slope-aware triplanar materials, dirt paths, and rocks - A 7-pass post-processing stack with TAA, bloom, depth of field, painterly filtering, ACES tonemapping, 3D LUT color grading, and film grain The hardest part wasn’t writing any single shader. It was making all of these systems work together at high frame rates inside WebGL, where every millisecond counts and performance problems compound quickly across animation, materials, post-processing, and scene management. Some techniques in this study were inspired by analyzing Tiny Glade’s rendering approach, while others were original implementations built from scratch from visual reference. That contrast taught me a lot: recreating an effect is one challenge, but designing your own shaders and systems to achieve a similar feel is a very different one. This is a private educational rendering study. Some temporary placeholder content is being used during the research phase, and any public or production version would use original or properly licensed assets. Huge credit to Pounce Light for the incredible art direction and rendering work in Tiny Glade: Three.js #gamedev #webgl #threejs #rendering #graphics #realtimerendering #shaderdev

Ibrahim Boona

58,625 Aufrufe • vor 6 Monaten

At Avalon we are building "Real-time creating" - the ability to generate gameplay ready persistent worlds prompted from text. While others are building real-time video world models, Avalon is building real-time world generation inside a fully playable, persistent multiplayer engine. Internally running at 3840×2180 at 60 FPS. Built on Unreal Engine. Multiplayer by default. Persistent by default. Gameplay-ready by default. This is not a video latent replay. Not a simulation of interaction. It is a real 3D world with physics, logic, and authoritative multiplayer state. Avalon is trained on proprietary Avalon interaction data and powered by a hybrid system that combines language understanding, 3D model generation, procedural systems, and structured gameplay logic synthesis. Players can walk through a live world and generate environments, assets, mechanics, and entirely new gameplay modes using natural language. We accomplish this through a combination of 3D model generation, game logic generation based on our proprietary systems, and AI driven world creation. While other players are inside it. Changes persist instantly. State is synchronized in real time. Creation happens inside the world, not outside of it. Describe a biome. Spawn a civilization. Create a survival mode. Build a dungeon crawler. Launch a new game inside the world. Avalon interprets intent and integrates it directly into the live multiplayer environment. This is not a world model predicting video. This is a gameplay engine that understands language. If you can describe it, you can build it. And others can walk into it instantly.
1:09

At Avalon we are building "Real-time creating" - the ability to generate gameplay ready persistent worlds prompted from text. While others are building real-time video world models, Avalon is building real-time world generation inside a fully playable, persistent multiplayer engine. Internally running at 3840×2180 at 60 FPS. Built on Unreal Engine. Multiplayer by default. Persistent by default. Gameplay-ready by default. This is not a video latent replay. Not a simulation of interaction. It is a real 3D world with physics, logic, and authoritative multiplayer state. Avalon is trained on proprietary Avalon interaction data and powered by a hybrid system that combines language understanding, 3D model generation, procedural systems, and structured gameplay logic synthesis. Players can walk through a live world and generate environments, assets, mechanics, and entirely new gameplay modes using natural language. We accomplish this through a combination of 3D model generation, game logic generation based on our proprietary systems, and AI driven world creation. While other players are inside it. Changes persist instantly. State is synchronized in real time. Creation happens inside the world, not outside of it. Describe a biome. Spawn a civilization. Create a survival mode. Build a dungeon crawler. Launch a new game inside the world. Avalon interprets intent and integrates it directly into the live multiplayer environment. This is not a world model predicting video. This is a gameplay engine that understands language. If you can describe it, you can build it. And others can walk into it instantly.

AVALON

65,926 Aufrufe • vor 7 Monaten

🎬 It’s been almost 2 months now that I’ve been working as a VFX AI Prompt Artist / Photoshop Editor on Season 2 of #houseofdavid, a major international production for Prime Video & Amazon MGM Studios. And honestly? It’s absolutely wild. The show is crushing it (No. 2 on Prime US, over 22 million viewers worldwide), and I’m super proud to have been part of the team since February What truly makes this project stand out is that, for the first time on a production of this scale, AI Artists have been directly integrated into the VFX pipeline. A bold move led by Wonder Project, and a strong signal for what’s coming next: generative AI has clearly found its place in the film industry. Day to day? 🎥 Massive sets, ⏱️ Tight deadlines, 🧠 Challenging sequences, 💬 Meetings with the cast, 🙌 And above all, an amazing team that’s an absolute joy to work with (LudovicCreator , Genmakers , Heather Cooper ) In this video, Jon Erwin talks about how AI was used in episode 6 of season 1, and shares his vision of what generative AI can bring to the future of filmmaking. A clear, inspiring message — and totally aligned with what I’m experiencing on this project every day. One thing’s for sure: AI in cinema is no longer just R&D… it’s already happening. And the story is just getting started.
3:09

🎬 It’s been almost 2 months now that I’ve been working as a VFX AI Prompt Artist / Photoshop Editor on Season 2 of #houseofdavid, a major international production for Prime Video & Amazon MGM Studios. And honestly? It’s absolutely wild. The show is crushing it (No. 2 on Prime US, over 22 million viewers worldwide), and I’m super proud to have been part of the team since February What truly makes this project stand out is that, for the first time on a production of this scale, AI Artists have been directly integrated into the VFX pipeline. A bold move led by Wonder Project, and a strong signal for what’s coming next: generative AI has clearly found its place in the film industry. Day to day? 🎥 Massive sets, ⏱️ Tight deadlines, 🧠 Challenging sequences, 💬 Meetings with the cast, 🙌 And above all, an amazing team that’s an absolute joy to work with (LudovicCreator , Genmakers , Heather Cooper ) In this video, Jon Erwin talks about how AI was used in episode 6 of season 1, and shares his vision of what generative AI can bring to the future of filmmaking. A clear, inspiring message — and totally aligned with what I’m experiencing on this project every day. One thing’s for sure: AI in cinema is no longer just R&D… it’s already happening. And the story is just getting started.

Pierrick Chevallier | IA

479,588 Aufrufe • vor 1 Jahr

What makes a magical world feel truly alive? For USC Games director and #RocoKingdom narrative consultant Richard Lemarchand, it begins with connection. Jinies are companions, living expressions of magic, and an integral part of the kingdom’s daily life. In this interview, Richard shares how the new game breathes life into a beloved classic, expanding it into a vast open world with cinematic storytelling and adventures shaped by friendship, courage, and responsibility. Now come see #RocoKingdom for yourself! Pre-register here: Don't forget wishlist us on Steam! #QuackQuackTest #RocoKingdom #Roco #Interview
6:00

What makes a magical world feel truly alive? For USC Games director and #RocoKingdom narrative consultant Richard Lemarchand, it begins with connection. Jinies are companions, living expressions of magic, and an integral part of the kingdom’s daily life. In this interview, Richard shares how the new game breathes life into a beloved classic, expanding it into a vast open world with cinematic storytelling and adventures shaped by friendship, courage, and responsibility. Now come see #RocoKingdom for yourself! Pre-register here: Don't forget wishlist us on Steam! #QuackQuackTest #RocoKingdom #Roco #Interview

Roco Kingdom

14,124 Aufrufe • vor 24 Tagen

What if you could npm install 3D models? Introducing Vibe3D - the shadcn for threejs Starting with the scifi asset kit, over 180+ models, all free and oss (MIT licensed) and two reference terrain meshes. All models are installed directly into your codebase instead of pre-packaged as code imports or worse yet, FBX files 🤮 Docs: This means, a simple "bunx vibe3d add Artificial Intelligence Papers-kit/pressure-gauge" will install the fully procedural code Want to change something? just tell your ai to do it It uses some shared helper code to produce the topology and at least per kit all items reuse and share the same materials, so technically performance should be better than letting your ai run wild on its own. Also releasing with it two skills: - Vibe model skill to produce your own models and kits, just "bunx vibe-model --global" and tell your ai to vibe model some 3d assets with a reference photo, you'll see it works - Vibe terrain "bunx vibe-terrain" installs the terrain mesh modeler, yea just try it out, best results with opus 5 ngl Everything is MIT licensed, i was just joking, no hate for unreal or unity Threejs still the best tho 🖕🏻 If you just want to see all 3D models up close: Yea, you can also just vampire it and download all modes as .glb files, good luck fixing some of them then though Big thanks to ThreeJS Assets for contributing 50 assets to the scifi kit! Everyone who spends some tokens on it will be added to the contributor list Oh and before i forget fuck you kenney, we roll our own kits now
1:01

What if you could npm install 3D models? Introducing Vibe3D - the shadcn for threejs Starting with the scifi asset kit, over 180+ models, all free and oss (MIT licensed) and two reference terrain meshes. All models are installed directly into your codebase instead of pre-packaged as code imports or worse yet, FBX files 🤮 Docs: This means, a simple "bunx vibe3d add Artificial Intelligence Papers-kit/pressure-gauge" will install the fully procedural code Want to change something? just tell your ai to do it It uses some shared helper code to produce the topology and at least per kit all items reuse and share the same materials, so technically performance should be better than letting your ai run wild on its own. Also releasing with it two skills: - Vibe model skill to produce your own models and kits, just "bunx vibe-model --global" and tell your ai to vibe model some 3d assets with a reference photo, you'll see it works - Vibe terrain "bunx vibe-terrain" installs the terrain mesh modeler, yea just try it out, best results with opus 5 ngl Everything is MIT licensed, i was just joking, no hate for unreal or unity Threejs still the best tho 🖕🏻 If you just want to see all 3D models up close: Yea, you can also just vampire it and download all modes as .glb files, good luck fixing some of them then though Big thanks to ThreeJS Assets for contributing 50 assets to the scifi kit! Everyone who spends some tokens on it will be added to the contributor list Oh and before i forget fuck you kenney, we roll our own kits now

robot 2.0

59,231 Aufrufe • vor 1 Monat

I ditched Unreal for AI. Kaiju Engine is a completely AI written replacement. To prove it was ready for production, I tested it by recreating and porting my old game, Firefall, into Kaiju, purely from the Steam download, no source. And it worked. Real game code is messy, full of difficult details and compromises. If our engine could handle a commercially released game, it proves you can ship a game with it. We're developing 2 orders of magnitude faster (93x) by lines of code and features. We have fewer bugs, and iteration is super fast. Build times have gone from 30 mins (Unreal) to 36 seconds. Feature rate is through the roof, days instead of months. Our original engine for Firefall took 2-3 years and cost over 5M to build (adjusted). Our new engine was written in 5 months for a couple grand. We built only what we needed, with none of the Unreal bloat. And we added some features: - Modern meshlet based rendering with PBR. - Vis Buffer/Forward+ with clustered lighting. - Id Tech 5 style megatexture streaming. - Planetary sized renderer (entire solar systems possible). - Seamless flight from ground to orbit and space. - No loading screens. - Procedural planet generation with plate simulation. - Client/Server at all times. - Ozz for animation. Jolt for Physics. - Companion Blender plug-in for AI directed asset exports. - 140fps currently, 200-300 projected after optimizations. You can see Firefall's assets and levels ported over into our engine in the video. Texture resolution and pop-in are limitations of the original game (high rez CDN based textures were lost when game went offline, fog hid the original's pop-in). Our meshlet renderer will be able to do much better with LOD and already supports high rez textures. I used Grok/Codex/Claude to tag team the code. This is not just a boon for indie games, it's a real game changer for game preservation. The reaction to seeing this 10 year old discontinued game revived is very emotional for Firefall fans. But we're not just preserving Firefall, we're going beyond, creating an original game that is the spiritual successor, Em-8ER. Gliding, jumpjets... it's all coming back. Moving past Unreal let us move much faster, without the bloat, and with better performance. If you want to signup to follow news on the game, sign up is free at
2:45

I ditched Unreal for AI. Kaiju Engine is a completely AI written replacement. To prove it was ready for production, I tested it by recreating and porting my old game, Firefall, into Kaiju, purely from the Steam download, no source. And it worked. Real game code is messy, full of difficult details and compromises. If our engine could handle a commercially released game, it proves you can ship a game with it. We're developing 2 orders of magnitude faster (93x) by lines of code and features. We have fewer bugs, and iteration is super fast. Build times have gone from 30 mins (Unreal) to 36 seconds. Feature rate is through the roof, days instead of months. Our original engine for Firefall took 2-3 years and cost over 5M to build (adjusted). Our new engine was written in 5 months for a couple grand. We built only what we needed, with none of the Unreal bloat. And we added some features: - Modern meshlet based rendering with PBR. - Vis Buffer/Forward+ with clustered lighting. - Id Tech 5 style megatexture streaming. - Planetary sized renderer (entire solar systems possible). - Seamless flight from ground to orbit and space. - No loading screens. - Procedural planet generation with plate simulation. - Client/Server at all times. - Ozz for animation. Jolt for Physics. - Companion Blender plug-in for AI directed asset exports. - 140fps currently, 200-300 projected after optimizations. You can see Firefall's assets and levels ported over into our engine in the video. Texture resolution and pop-in are limitations of the original game (high rez CDN based textures were lost when game went offline, fog hid the original's pop-in). Our meshlet renderer will be able to do much better with LOD and already supports high rez textures. I used Grok/Codex/Claude to tag team the code. This is not just a boon for indie games, it's a real game changer for game preservation. The reaction to seeing this 10 year old discontinued game revived is very emotional for Firefall fans. But we're not just preserving Firefall, we're going beyond, creating an original game that is the spiritual successor, Em-8ER. Gliding, jumpjets... it's all coming back. Moving past Unreal let us move much faster, without the bloat, and with better performance. If you want to signup to follow news on the game, sign up is free at

Grummz

357,432 Aufrufe • vor 1 Monat

🚨🚨Can agents earn money, run a business, or even self-organize a society in the physical social world? 🤖🤖 Can agents learn continually to survive and thrive in embodied environments, like how human babies grow? 👶 Super excited to introduce SimWorld, an open-ended simulator of LLM agents in infinite, realistic embodied worlds. SimWorld features 3 key designs: 1⃣Open-ended realistic world simulation - built on Unreal Engine 5, with accurate physical social dynamics - 100+ built-in environments (city, island, wilderness ...) - language-controllable procedural generation - text-to-3D asset generation 2⃣Native interface for LLM/VLM agents - Gym-like agent-environment interaction APIs - plug in any LLMs/VLMs (GPTs, Gemini, Qwen ...) - rich multi-modal perception - open-vocabulary natural-language action outputs 3⃣Diverse physical and social reasoning scenarios - long-horizon embodied reasoning - multi-agent collaboration / competition - easily customizable for any reasoning tasks SimWorld is fully open-sourced, with a hope to become a foundational infrastructure for real-world agent research across disciplines: robotics, economy, public health, education, etc. Project website + more details in the thread👇 ...1/
1:10

🚨🚨Can agents earn money, run a business, or even self-organize a society in the physical social world? 🤖🤖 Can agents learn continually to survive and thrive in embodied environments, like how human babies grow? 👶 Super excited to introduce SimWorld, an open-ended simulator of LLM agents in infinite, realistic embodied worlds. SimWorld features 3 key designs: 1⃣Open-ended realistic world simulation - built on Unreal Engine 5, with accurate physical social dynamics - 100+ built-in environments (city, island, wilderness ...) - language-controllable procedural generation - text-to-3D asset generation 2⃣Native interface for LLM/VLM agents - Gym-like agent-environment interaction APIs - plug in any LLMs/VLMs (GPTs, Gemini, Qwen ...) - rich multi-modal perception - open-vocabulary natural-language action outputs 3⃣Diverse physical and social reasoning scenarios - long-horizon embodied reasoning - multi-agent collaboration / competition - easily customizable for any reasoning tasks SimWorld is fully open-sourced, with a hope to become a foundational infrastructure for real-world agent research across disciplines: robotics, economy, public health, education, etc. Project website + more details in the thread👇 ...1/

Lianhui Qin@COLM2026

65,310 Aufrufe • vor 10 Monaten

A case study from 2025 on Fauci's chosen method of prevarication. Scene: A appearance by Anthony Fauci at the New Orleans book festival, where he explains why "masks worked". In this clip, he starts by declaring: "masks worked". Applause follows. We should ask how applause is appropriate. Whether masks work is a scientific problem. It is not a moral or political position. Should a scientist be applauded for giving his or her scientific opinion? If they are, then it's not being treated as a scientific opinion anymore. The applause shows just how ideological the whole discussion on masking became--and remains. But what follows is remarkable. The interviewer pushes back and questions whether masks really worked, whether scientific evidence really supports that position. Fauci yields and pivots: "there's the rub, Walter, a proper mask, an N95 or KN95." In other words, the implication is that the cloth and surgical masks that he recommended during the pandemic didn't work, but N95s do. Which somehow still allows Fauci to say, "masks worked". Isn't this remarkable? Fauci started with "masks worked", i.e. the masks that were widely recommended and worn. And for this he was applauded. But now, without conceding the mistake of surgical and cloth recommendations, he maintains that "masks worked" but only "N95s or KN95s". It gets richer. Then Fauci digs in deeper: N95s and KN95s work, yes. But, but, but! Only if the N95 and KN95 is "properly worn, all the time". That is, the mask has to be properly fitted (and that requires professional assistance) with a proper seal, and worn all the time. Ergo, "masks worked". We've gone from cloth and surgical mask recommendations to properly fitted N95 and KN95 masks worn all the time. This is why "masks worked". Then Fauci digs in even deeper: but you cannot take the mask off to eat! People complain that they took the mask off to eat and got COVID. You can't do normal things and say masks don't work! The only way masks work if you live entirely abnormal lives. Therefore, according to Fauci, "masks worked". Here's the thing: Fauci has just enumerated all of the arguments against masks working in the real world, all the while affirming that "masks worked". He gets his cake and eats it too: On the one hand, clinical studies show that not only do surgical and cloth masks not work for respiratory pathogens in a variety of environments, N95s haven't been shown to work to reduce the risk of infection by a respiratory pathogen when worn over the course of the day in normal working conditions either. (This is probably, as other studies show, because the seal breaks within just a few hours--something Fauci alludes to--and because people take the mask off.) On the other hand, if you mask harder, if you do it absolutely perfectly, then they DO work. Ergo, "masks worked". Does anyone else see how twisted this logic is? I mean, masks don't work under most or all real-world conditions. BUT, they do in theory. Therefore "masks worked", and therefore (by implication) surgical and cloth mask mandates were not pseudoscientific or a mistake. And for that performance Anthony Fauci is applauded and lionized, and he goes on and on. And nobody in the tribe pushes back on the ridiculousness of it. They just turn off their brains. And clap. It boggles the mind.
0:40

A case study from 2025 on Fauci's chosen method of prevarication. Scene: A appearance by Anthony Fauci at the New Orleans book festival, where he explains why "masks worked". In this clip, he starts by declaring: "masks worked". Applause follows. We should ask how applause is appropriate. Whether masks work is a scientific problem. It is not a moral or political position. Should a scientist be applauded for giving his or her scientific opinion? If they are, then it's not being treated as a scientific opinion anymore. The applause shows just how ideological the whole discussion on masking became--and remains. But what follows is remarkable. The interviewer pushes back and questions whether masks really worked, whether scientific evidence really supports that position. Fauci yields and pivots: "there's the rub, Walter, a proper mask, an N95 or KN95." In other words, the implication is that the cloth and surgical masks that he recommended during the pandemic didn't work, but N95s do. Which somehow still allows Fauci to say, "masks worked". Isn't this remarkable? Fauci started with "masks worked", i.e. the masks that were widely recommended and worn. And for this he was applauded. But now, without conceding the mistake of surgical and cloth recommendations, he maintains that "masks worked" but only "N95s or KN95s". It gets richer. Then Fauci digs in deeper: N95s and KN95s work, yes. But, but, but! Only if the N95 and KN95 is "properly worn, all the time". That is, the mask has to be properly fitted (and that requires professional assistance) with a proper seal, and worn all the time. Ergo, "masks worked". We've gone from cloth and surgical mask recommendations to properly fitted N95 and KN95 masks worn all the time. This is why "masks worked". Then Fauci digs in even deeper: but you cannot take the mask off to eat! People complain that they took the mask off to eat and got COVID. You can't do normal things and say masks don't work! The only way masks work if you live entirely abnormal lives. Therefore, according to Fauci, "masks worked". Here's the thing: Fauci has just enumerated all of the arguments against masks working in the real world, all the while affirming that "masks worked". He gets his cake and eats it too: On the one hand, clinical studies show that not only do surgical and cloth masks not work for respiratory pathogens in a variety of environments, N95s haven't been shown to work to reduce the risk of infection by a respiratory pathogen when worn over the course of the day in normal working conditions either. (This is probably, as other studies show, because the seal breaks within just a few hours--something Fauci alludes to--and because people take the mask off.) On the other hand, if you mask harder, if you do it absolutely perfectly, then they DO work. Ergo, "masks worked". Does anyone else see how twisted this logic is? I mean, masks don't work under most or all real-world conditions. BUT, they do in theory. Therefore "masks worked", and therefore (by implication) surgical and cloth mask mandates were not pseudoscientific or a mistake. And for that performance Anthony Fauci is applauded and lionized, and he goes on and on. And nobody in the tribe pushes back on the ridiculousness of it. They just turn off their brains. And clap. It boggles the mind.

Kevin Bass

117,690 Aufrufe • vor 1 Monat

Introducing Lithic ( the intelligent execution language powering the Lithosphere Network. For years blockchain has focused on programmable value. With Lithic, we move toward programmable intelligence. Lithic is designed to connect smart contracts, identity, AI systems, and cross-chain infrastructure into a unified execution fabric for the next phase of the internet. This is a core step toward the Web4 infrastructure stack we’ve been building at Lithosphere. Core Lithic Components • Lithic Execution Engine – deterministic runtime powering intelligent smart contract execution • LEP100 Intelligent Asset Framework – programmable token standard for adaptive digital assets • Lithic Modules (LSCL) – composable modules for governance, identity, compliance, and AI logic • Cross-Chain Orchestration Layer – communication between EVM, Cosmos environments, and external networks • Identity & Policy Hooks – programmable identity-aware transaction and asset control • AI Integration Layer – enabling intelligent validation, automation, and decision systems Together these components form the foundation for adaptive decentralized systems. Why Lithic matters Static contracts belong to Web3. Lithic enables: • intelligent assets • identity-aware protocols • AI-driven automation • modular decentralized infrastructure This is how blockchain evolves into the intelligent layer of the internet. 📚Lithic Documentation & Resources Learn more Docs: Tools, Scripts, examples etc: Lithic Contract Wizard and Verifier. LEP100 Standard-suite Lithosphere Developer Resources More developer tools, SDKs, and modules will be released alongside the Makalu Testnet.
0:57

Introducing Lithic ( the intelligent execution language powering the Lithosphere Network. For years blockchain has focused on programmable value. With Lithic, we move toward programmable intelligence. Lithic is designed to connect smart contracts, identity, AI systems, and cross-chain infrastructure into a unified execution fabric for the next phase of the internet. This is a core step toward the Web4 infrastructure stack we’ve been building at Lithosphere. Core Lithic Components • Lithic Execution Engine – deterministic runtime powering intelligent smart contract execution • LEP100 Intelligent Asset Framework – programmable token standard for adaptive digital assets • Lithic Modules (LSCL) – composable modules for governance, identity, compliance, and AI logic • Cross-Chain Orchestration Layer – communication between EVM, Cosmos environments, and external networks • Identity & Policy Hooks – programmable identity-aware transaction and asset control • AI Integration Layer – enabling intelligent validation, automation, and decision systems Together these components form the foundation for adaptive decentralized systems. Why Lithic matters Static contracts belong to Web3. Lithic enables: • intelligent assets • identity-aware protocols • AI-driven automation • modular decentralized infrastructure This is how blockchain evolves into the intelligent layer of the internet. 📚Lithic Documentation & Resources Learn more Docs: Tools, Scripts, examples etc: Lithic Contract Wizard and Verifier. LEP100 Standard-suite Lithosphere Developer Resources More developer tools, SDKs, and modules will be released alongside the Makalu Testnet.

King

158,123 Aufrufe • vor 6 Monaten

While learning Unreal Engine 5, I decided to port over most of Hyperion to it to see if I could potentially move my workflows over to UE5. Although it worked decently well, it didn't work well enough to allow me to change over entirely. Hyperion is simply too complex of an asset for real-time workflows (or at least is limited due to my knowledge of said workflows). 131 4K-8K UDIMs at over 8 channels and a solid amount of shaders with layering being the biggest bottleneck. I couldn't even match the shading setup to what I have in RenderMan, UE gave me a warning that the material was too complex. I was using the new Substrate materials, which mimic RenderMan LAMA shaders. The render below is using the pathtracer. As you can see there are some random flickering parts which I couldn't fix during my tests. This render of course doesn't have any displacement either (which Hyperion heavily relies on). I think Unreal Engine has a very bright future, but it is still limited by todays hardware technology for high end VFX work. Maybe in a few years I will give it another try when hardware improves and the engine becomes a bit more versatile in feature-set.
0:20

While learning Unreal Engine 5, I decided to port over most of Hyperion to it to see if I could potentially move my workflows over to UE5. Although it worked decently well, it didn't work well enough to allow me to change over entirely. Hyperion is simply too complex of an asset for real-time workflows (or at least is limited due to my knowledge of said workflows). 131 4K-8K UDIMs at over 8 channels and a solid amount of shaders with layering being the biggest bottleneck. I couldn't even match the shading setup to what I have in RenderMan, UE gave me a warning that the material was too complex. I was using the new Substrate materials, which mimic RenderMan LAMA shaders. The render below is using the pathtracer. As you can see there are some random flickering parts which I couldn't fix during my tests. This render of course doesn't have any displacement either (which Hyperion heavily relies on). I think Unreal Engine has a very bright future, but it is still limited by todays hardware technology for high end VFX work. Maybe in a few years I will give it another try when hardware improves and the engine becomes a bit more versatile in feature-set.

Rassoul Edji

25,133 Aufrufe • vor 1 Jahr

Over the last few weeks I have travelled the globe spending quality time with the humans in our digital art community. One thing I noticed is that we all share the same struggles, worries, and concerns but we also feel the same passion, love and conviction. This new series we created shows the human side of our great ecosystem. Along with my friend and director of the series Dave, we want the world to see the storytellers building our community; not for the price of their art but for their spirit and essence. This pilot episode features Erick (Erick / Snowfro / 🦩 / LAO / #️⃣ / 🔴) Together we explore Erick’s love for art, his deep connection to Marfa and how he made it a home for his family and Art Blocks Joined by friends die with the most likes and glitch Thank you to Vladislav for helping produce this project. He is a true patron of the community and tremendous builder. And finally to our producer mrs goku to you 💍🎉, for being the glue that makes this magical thing possible. We hope you all enjoy and come back for more soon. The more interest we can show the more we can make, so please give this a share. This is How We Build
26:40

Over the last few weeks I have travelled the globe spending quality time with the humans in our digital art community. One thing I noticed is that we all share the same struggles, worries, and concerns but we also feel the same passion, love and conviction. This new series we created shows the human side of our great ecosystem. Along with my friend and director of the series Dave, we want the world to see the storytellers building our community; not for the price of their art but for their spirit and essence. This pilot episode features Erick (Erick / Snowfro / 🦩 / LAO / #️⃣ / 🔴) Together we explore Erick’s love for art, his deep connection to Marfa and how he made it a home for his family and Art Blocks Joined by friends die with the most likes and glitch Thank you to Vladislav for helping produce this project. He is a true patron of the community and tremendous builder. And finally to our producer mrs goku to you 💍🎉, for being the glue that makes this magical thing possible. We hope you all enjoy and come back for more soon. The more interest we can show the more we can make, so please give this a share. This is How We Build

El Barba Roja blue check

307,758 Aufrufe • vor 11 Monaten

Repulsion (1965) is a British psychological horror thriller directed by Roman Polanski and starring Catherine Deneuve. Written by Polanski and Gérard Brach, the film follows Carol, a withdrawn young woman whose fragile state begins to unravel when she is left alone in the London apartment she shares with her sister. Polanski and Brach reportedly wrote the screenplay in just 17 days. The film was partly conceived as a commercial project that would help finance Cul-de-Sac, but it eventually became one of the defining psychological horror films of the 1960s. Polanski wanted an actress who could project innocence while suggesting something darker underneath, describing his ideal as “an angel with a slightly soiled halo.” Deneuve, only 21 at the time, was perfect for that contrast, especially after The Umbrellas of Cherbourg. Deneuve later recalled feeling unusually close to Polanski and Brach during production, describing the three French-speaking filmmakers as “the Three Musketeers.” She also said of the film, “That’s the film I feel I helped make.” For Polanski, making his first English-language feature in Britain was also a cultural discovery. “Repulsion was my discovery of London,” he later said, explaining how the unfamiliar city inspired him. Deneuve remembered Polanski as a young director who knew how to command a British crew: “He was no pushover.” Polanski, meanwhile, acknowledged that Deneuve was nervous and tired during the demanding shoot, which required her to remain intensely focused on Carol’s increasingly disturbed state.
2:11

Repulsion (1965) is a British psychological horror thriller directed by Roman Polanski and starring Catherine Deneuve. Written by Polanski and Gérard Brach, the film follows Carol, a withdrawn young woman whose fragile state begins to unravel when she is left alone in the London apartment she shares with her sister. Polanski and Brach reportedly wrote the screenplay in just 17 days. The film was partly conceived as a commercial project that would help finance Cul-de-Sac, but it eventually became one of the defining psychological horror films of the 1960s. Polanski wanted an actress who could project innocence while suggesting something darker underneath, describing his ideal as “an angel with a slightly soiled halo.” Deneuve, only 21 at the time, was perfect for that contrast, especially after The Umbrellas of Cherbourg. Deneuve later recalled feeling unusually close to Polanski and Brach during production, describing the three French-speaking filmmakers as “the Three Musketeers.” She also said of the film, “That’s the film I feel I helped make.” For Polanski, making his first English-language feature in Britain was also a cultural discovery. “Repulsion was my discovery of London,” he later said, explaining how the unfamiliar city inspired him. Deneuve remembered Polanski as a young director who knew how to command a British crew: “He was no pushover.” Polanski, meanwhile, acknowledged that Deneuve was nervous and tired during the demanding shoot, which required her to remain intensely focused on Carol’s increasingly disturbed state.

Remnants of the Past

12,390 Aufrufe • vor 8 Tagen