Free viewpoint video with 4x iphones is genuinely nuts. This used to need a volumetric capture rig with dozens if not hundreds of cameras. Offline renders are just the start. Can't wait till we can playback dynamic 3d content like this in real time.

God’s Eye View V1 is open source. It feels like a spy simulator in your browser -- except the underlying data is real, and you can talk to the planet too. Track planes, ships, satellites, traffic cameras, and critical infrastructure. Use voice mode to ask what’s happening, annotate the 3D world, or jump into a plane’s cockpit. Already a ton to explore. Code is MIT licensed, so add new layers, extend the voice agent, break things, and show me what you cook.

Throwback to the “dinosaur input device” that was used to animate the stellar T-Rex dinosaur in the first Jurassic Park movie. Everything that has happened before will happen again, so now it’s a spatial 3D harness you can control with a Vision Pro and hand tracking.

.@bilawalsidhu reveals how the Seoul World Model generates realistic training data for robotics: "Seoul World Model is a really interesting paper, very similar to what Google's doing with Street View grounding. If you ask Genie to give you a representation of the Palace of Fine Arts, it'll give you a plausible reconstruction, but it ain't exactly it." "One way to constrain these models is, we could just do what we do in LLMs, which is RAG, retrieval-augmented generation." "Can we do a form of spatial RAG where you just pull in the nearest reference image of reality to condition the generation? That lets you do a lot of these use cases that are interesting for robotics." "If you wanna create a bunch of training data for downtown Seoul in different lighting conditions, really cool way to go about doing that. That's exactly what you see folks like NVIDIA trying to do with Omniverse as this 3D simulator and Cosmos."

.@bilawalsidhu on why radio frequency is the next data frontier for world models: "We've got one fricking world that we live in, and we wanna model that world with as much fidelity as possible. To do that, there are so many different modalities. Satellites in orbits, planes plastering the world, fleets on the ground plastering cities with photogrammetric captures." "All of those data sets are cool, but the next frontier to me feels like radio frequency. This thing that was traditionally communications infrastructure, we view it as dumb pipes for us to communicate or get an endless feed to scroll through, now suddenly we can make it a sensing infrastructure as well, whether that's Wi-Fi or some of the stuff happening around 6G with integrated sensing and communication." "Where are all the inertial foundational models, the radio frequency foundational models? We'll see so many other cool things that comprise, in totality, perhaps a world model of physical reality."

Woot! You can now simulate real world places by grounding Genie 3 experiences with Street View imagery. Google sitting on the mother lode of real world data, and is starting to put it to work! Let's dive into some prompts & locations I tested...

Semantically annotating 3D gaussian splats on the fly using gemini 3.1 + sparkjs 1. Load any 3D scene and hit scan 2. Get 2D detections from VLM 3. Cluster outputs & project into 3D world space 4. Save as a persistent 3D semantic layer Inspired by @alexanderchen's experiments with gemini visual intelligence. Just had to try to lift it from 2D to 3D!