Catalyst with Shayle Kann cover image

Live from Transition-AI 2026: Inside Google’s massive AI CapEx

Catalyst with Shayle Kann

00:00

Latency sensitivity across training, serving, and edge

Amin contrasts batch vs. interactive inference, geographic locality, and when edge or on-device compute matters.

Play episode from 22:40
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app