Why AI Needs JEPA World Models
Failed to add items
Add to basket failed.
Add to wishlist failed.
Remove from wishlist failed.
Adding to library failed
Follow podcast failed
Unfollow podcast failed
Why AI Needs JEPA World Models
-
Narrated by:
-
By:
About this listen
The Futurists starts 2026 with a stimulating conversation with serial entrepreneur Matt Miesnieks, a true pioneer of AR/XR and spatial computing. In his new startup venture, Primate AI, Matt is focused on a novel approach to artificial intelligence. He intends to construct spatial and dimensional concepts that replicate the way humans develop a mental model of the real world. Topics in this episode: how the limitations of LLMs create opportunities for new approaches, such as Yann LeCun’s JEPA (Joint Embedding Predictive Architecture); the distinction between trying to understand the real world and trying to generate new worlds; why it is so hard to get a robot to cross a busy street safely; why 3D world models are needed; what happens when the real world is machine-readable.