The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) cover image

The Decentralized Future of Private AI with Illia Polosukhin - #749

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

00:00

Performance and Cost Overheads of Confidential Inference

Illia states confidential mode adds minimal overhead (1–5%) and is mostly encryption boundary work, not heavy compute penalty.

Transcript
Play full episode

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