
Beyond Coding How the Best Engineers Build a World Model (Google Earth Creator & Niantic Spatial CTO)
5 snips
Sep 2, 2026 Brian McClendon, the technology executive who helped create Google Earth and led Google Maps, discusses Niantic Spatial’s ambitious 4D model of the world. He explores visual positioning, Gaussian splats, robot training, and turning research into production in months. He also shares what he looks for in engineers and how to use AI with meaningful self-checks.
AI Snips
Chapters
Books
Transcript
Episode notes
Any Photo Can Become A Precise Location
- A photo becomes a precise location when feature matches connect it to a 3D reconstruction map.
- Modern systems can locate ordinary images within half a meter, half a degree, or sometimes centimeters.
AI Turns Historical Photos Into 3D Models
- Machine-learning depth models make dense 3D reconstruction possible from weaker historical imagery.
- This lets teams reconstruct scenes from photos and videos captured decades before the technology existed.
The World Model Adds Time To Geography
- A 4D world model combines geographic geometry, images, timestamps, and historical views.
- It could answer what any location looked like on a specific date by blending photos with older base maps.




