SIMA 2: A Gemini-Powered AI Agent for 3D Virtual Worlds

Introducing SIMA 2, the next milestone in our research creating general and helpful AI agents. By integrating the advanced capabilities of our Gemini models, SIMA is evolving from an instruction-follower into an interactive gaming companion.

Google DeepMind
👨‍💻🌍 Oh, look! Another developer's fever dream on #GitHub thinks it's building the next Matrix with "infinite" 3D worlds, but can't even navigate past its own navigation menu. 🤯 Meanwhile, AI is still writing code that barely surpasses a toddler's finger painting! 🖌️💻
https://github.com/world-grow/WorldGrow #developerfail #AIartificialintelligence #3Dworlds #techhumor #HackerNews #ngated
GitHub - world-grow/WorldGrow: WorldGrow: Generating Infinite 3D World

WorldGrow: Generating Infinite 3D World. Contribute to world-grow/WorldGrow development by creating an account on GitHub.

GitHub
Google DeepMind has unveiled Genie 3, its latest general purpose word model capable of generating 3D environments in real time based on text prompts. It allows real-time navigation at 24 frames per second with 720p resolution. Its current availability is limited to small group of researchers only.
#DeepMind #Genie3 #AIInnovation #ArtificialIntelligence #MachineLearning #TechNews #FutureTech #AIRevolution #3DWorlds #VirtualReality

Ever sketched something so bad it hurt to look at?

Vibe Draw doesn’t care. It turns your chaotic scribbles into full-blown 3D vibes.
Like, actual worlds. From lines. Madness.

Open-source magic here: https://github.com/martin226/vibe-draw

#AIArt #3DWorlds #OpenSource #GenerativeAI #VibeDraw #IndieDev #SketchTo3D #CreativeCoding

New physics sim trains robots 430,000 times faster than reality

“Genesis” can compress training times from decades into hours using 3D worlds conjured from text.

Ars Technica

"DeepMind, Google’s AI research org, has unveiled a model that can generate an “endless” variety of playable 3D worlds.

Called Genie 2, the model — the successor to DeepMind’s Genie, which was released earlier this year — can generate an interactive, real-time scene from a single image and text description (e.g. “A cute humanoid robot in the woods”). In this way, it’s similar to models under development by Fei-Fei Li’s company, World Labs, and Israeli startup Decart.

DeepMind claims that Genie 2 can generate a “vast diversity of rich 3D worlds,” including worlds in which users can take actions like jumping and swimming by using a mouse or keyboard. Trained on videos, the model’s able to simulate object interactions, animations, lighting, physics, reflections, and the behavior of “NPCs.”"

https://techcrunch.com/2024/12/04/deepminds-genie-2-can-generate-interactive-worlds-that-look-like-video-games/

#AI #GenerativeAI #GeneratedImages #DeepMind #Google #VideoGames #3DWorlds

DeepMind's Genie 2 can generate interactive worlds that look like video games | TechCrunch

DeepMind, Google's AI research org, has unveiled a model that can generate an 'endless' variety of playable 3D worlds.

TechCrunch
I uploaded the VRML compilation that was shown by Vinny Vinesauce in this video: https://www.youtube.com/watch?v=8naR1EUSduo
To Archive.org and on my website as well, if you're interested in exploring and examining a variety of VRML worlds, objects, games and animations from the 90s to the early 2000s
https://archive.org/details/VRMLCompilation
#vrml #virtualreality #90s #2000s #internethistory #3d #animations #3dworlds #gaming #archives #technology #software
[Vinesauce] Vinny - VRML Worlds

YouTube