The BetaKit Podcast Channel cover image

Tailscale's CEO has an idea "worth billions" for AI startups

The BetaKit Podcast Channel

00:00

How Could Agents Misinterpret Instructions and Cause Harm

Avery shares real incidents where agents misread source code as commands and exfiltrated sensitive data.

Play episode from 13:16
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