Collections

Best Chain of Thought Episodes on AI Security

Attacking agents, defending them, and the part software cannot cover.

Agent security isn’t application security with a model attached. The attacker gets a system that follows instructions faithfully, including the ones you didn’t write, and every tool you connect widens what a single bad instruction can reach. Four episodes here, because a fifth would have been padding.

  1. 1 EP 65 53 min Transcript You Can't Secure an AI Agent with Software Charles Guillemet, Ledger Ledger CTO Charles Guillemet argues you cannot secure an agent with software permissions and API keys once it is moving real money, and makes the case for a hardware-enforced signature between intent and execution.
  2. 2 EP 62 46 min Transcript The First Fully Autonomous AI Attack is Coming | Kristin Lovejoy Kristin Lovejoy, Kyndryl Kristin Lovejoy’s prediction: a fully autonomous attack that takes an enterprise network down with no human driving it, inside 18 months. Her reasoning runs through attackers chaining low-risk vulnerabilities, which changes the patching math.
  3. 3 EP 60 51 min Transcript We Built Agents, Nobody Built HR | Tyler Akidau, Redpanda Tyler Akidau, Redpanda Tyler Akidau on the four pillars of agent governance, and why guardrails written where the agent can see them are not guardrails. Task-scoped identity is the foundation the rest sits on.
  4. 4 EP 39 54 min Transcript Vercel's Playbook for AI Agents: From Vibe Check to Production | Malte Ubl Malte Ubl, Vercel Vercel’s Malte Ubl on the security lesson people get wrong most often: prompt injection is not SQL injection, and the answer is constraining what the tool can do rather than filtering what goes in.

More collections

All collections →

New here? Start with five → Browse by topic →