Definition◆Video · 1:11 — 2:09

Spatial intelligence is the next frontier of AI — the ability to generate, understand, reason with, and interact with spaces, whether physical or virtual.

Fei-Fei Li defines spatial intelligence as the next frontier of AI, centered on creating AI that can understand and interact with both physical and virtual spaces through large world models. ✦ AI generated

Fei-Fei Li · a16z Podcast · 2026-07-28 · original ↗

Share card ↓Export .md Export .txt

starts at this moment · 1:11

Elicited by

“Fei-Fei, for the listeners that may not have the background, maybe you can give an overview of what World Labs does.”

World Labs is a two-year-old startup. I think we should just recognize it's a frontier model lab. We are building the next frontier of AI which is what we call spatial intelligence. And spatial intelligence is about creating AI that has the ability to generate, understand, reason with, and interact with spaces, whether it's physical or virtual. And of course a means to an end towards spatial intelligence is building large world models.

verbatim transcript · starts at 1:11

Transcript · around this moment

1:14you can give an overview of what World Labs does. >> Yeah. Well, World Lab has is a two-year-old startup. I I I think we should just recognize it's a frontier model lab. It's uh we we are building the next frontier of AI which is what we call spatial intelligence. And uh spatial intelligence is about um creating AI that has the ability to generate uh understand reason with and interact with spaces

1:50whether it's physical or virtual. And of course uh a means to an end towards spatial intelligence is building large world models. And that's what uh World Labs is mostly focused on. >> Yeah. So you've been saying this since the very beginning which is um you know the machine's ability to perceive and reason about spaces and act on spaces but I always had the assumption that the acting on spaces was some like longist

2:17future thing but now you're acquiring a robotics company and so maybe talk a little bit about the timeliness of this and the intentions. >> Yeah. So first of all, it doesn't just take robotics to act within spaces or to interact, right? I mean, look at the creative field, whether it's VFX or gaming and or design. Many use cases, you can create and act within virtual spaces. World Warlab's thesis has always

▦ World Labs ✳ spatial intelligence ◉ Fei-Fei Li

Around this claim

This moment responds to

explains mechanism → The fundamental bottleneck in robotics is the lack of data for training and evaluation — unlike language models where data is abundant on the internet, robotics requires a real-to-sim-to-real pipeline to unlock scaling laws.Yunzhu Li · a16z Podcast explains mechanism → Simulation provides two specific benefits for robotics that real-world data alone cannot: systematic reliability through controlled coverage of all state-space variations, and efficiency through faster-than-human data generation.Yunzhu Li · a16z Podcast extends → Spatial intelligence is the next frontier of AI, and it requires building large world models—AI that can generate, understand, reason with, and interact with physical and virtual spaces.Fei-Fei Li · a16z Podcast explains mechanism → Simulation plays a critical role in robotic learning that real-world data cannot replace — it enables counterfactual reasoning, which is essential for robotics.Fei-Fei Li · a16z Podcast provides context → Scenix's platform is model-agnostic and embodiment-agnostic — it builds digital environments where any robot can learn and be evaluated, not the robots themselves.Yunzhu Li · a16z Podcast