In this episode of AI-Curious, we explore a side of AI that rarely gets the spotlight: Large Geospatial Models (LGMs). You’ve heard of LLMs — now meet their real-world counterpart. LGMs could power everything from autonomous vehicles and urban planning to smarter first-response systems and industrial logistics.

We speak with Bill Lakeland, CEO of Spexi, a company building a decentralized fleet of self-flying drones that are actively mapping the planet — one 25-acre hex at a time. We dig into how these drones collect fresh, high-res data; how that data is authenticated and standardized; and how it could enable a new generation of real-world AI applications.

Along the way, we discuss:

• (5:00) What LGMs are, and how they differ from LLMs

• (13:07) Why real-time geospatial data is crucial for first responders

• (20:33) How drones fit into the LGM landscape

• (25:12) How Spexi’s autonomous drone “specxagons” work

• (31:43) Why their aerial data is 900x more detailed than Google Earth

• (36:26) How they’re addressing privacy, regulation, and standardization

• (40:02) What happens after the footage is collected — and how it’s turned into insights

• (45:35) The future integration of LGMs and LLMs

• (48:00) Speculative futures: how LGMs could change everyday life

If you’re curious about AI in the physical world — not just on screens — this is a conversation you won’t want to miss.

Spexi:

https://www.spexi.com/

🎧 Subscribe to AI-Curious:

• Apple Podcasts
https://podcasts.apple.com/us/podcast/ai-curious-with-jeff-wilser/id1703130308

• Spotify
https://open.spotify.com/show/70a9Xbhu5XQ47YOgVTE44Q?si=c31e2c02d8b64f1b

• YouTube
https://www.youtube.com/@jeffwilser