Episode Details

AI attackers now move at machine speed, while most security teams still move at meeting speed. Former Robinhood CSO Caleb Sima has seen an AI attacker up close, and he argues the only way to keep up is to take humans out of the defense loop.

Caleb joins Guy Podjarny to unpack what changes when the attacker is an agent: one that hits every surface at once, reverses open-source code to find a 0-day, and once inside, burns your own AI tokens to keep going.

What we cover:
– Why AI attackers outran the red teamers' predictions, including 400 Linux 0-days found at 2.5 hours each
– Whether sandboxes can contain AI agents, and why external monitoring matters
– Who is accountable when your AI agent hacks someone else
– What actually changes when an AI attacker gets inside your company
– Deception, digital twins and forensic-grade detection
– Automating security: instant patching, one-way vs two-way doors, and security teams that ship the fix

Chapters:
00:00:00 - Introduction
00:02:58 - AI security goes mainstream
00:05:52 - Why AI attackers surprised the red teamers
00:12:50 - Can sandboxes contain AI agents?
00:18:03 - Security vs safety vs alignment
00:22:18 - Who's accountable when your AI agent hacks?
00:29:00 - What changes when an AI attacker hits you
00:36:47 - Detection, forensics and deception
00:44:10 - Machine speed vs meeting speed: automating defense
00:48:53 - Security teams that ship the fix

Build your software factory, one workflow at a time, with Tessl:
https://tessl.co/9ja

🔔 Subscribe for weekly episodes on AI-native development

Are your defenses ready for AI attackers, or still running at meeting speed? Tell us in the comments.