Best Chain of Thought Episodes on AI Security
Attacking agents, defending them, and the part software cannot cover.
Charles Guillemet makes the case for hardware authorization when agents move money. Dan Lorenc unpacks vendor reports that the average time to exploit has gone negative. Kris Lovejoy discusses her forecast for autonomous attacks, Tyler Akidau examines agent governance, and Malte Ubl addresses prompt injection and tool constraints. These five conversations cover both attack scenarios and the controls guests propose to limit an agent’s reach.
- 5 episodes
- 5 guests
- 4 hours of listening
- 3 jump-to moments
- 1
You Can't Secure an AI Agent with Software | Charles Guillemet, Ledger 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. Jump to the moment · 9:24 · Hardware signature for authorization → - 2
Time to Exploit is Negative: AI Broke the Patch Cycle | Dan Lorenc, Chainguard Dan Lorenc, Chainguard Chainguard’s Dan Lorenc on vendor reports, from Mandiant and CrowdStrike among others, that the average time to exploit is now negative, and his theory of how cheap models squeezed the long tail of late exploits. Jump to the moment · 3:42 · How time to exploit went negative → - 3
The First Fully Autonomous AI Attack is Coming | Kris Lovejoy, Kyndryl Kris Lovejoy, Kyndryl In the episode published in June 2026, Kris Lovejoy predicts a fully autonomous attack within 18 months. She explains how attackers could chain low-risk vulnerabilities and what that would mean for patching priorities. - 4
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. Jump to the moment · 10:29 · Agent identity and accountability → - 5
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.
- Best Chain of Thought Episodes for AI Founders Building an AI company: defensibility, GTM, and where the market stands.
- Best Chain of Thought Episodes for Engineers Shipping with AI: the craft, the workflow, and where it falls short.
- Best Chain of Thought Episodes on AI Agents How agents work: architecture, memory, context, frameworks.
- Best Chain of Thought Episodes on AI Evaluation Measuring whether AI works: evals, reliability, trust.
- Best Chain of Thought Episodes on Agent Memory How agents remember: memory stores, context engineering, and what breaks without them.
- Best Chain of Thought Episodes on Multi-Agent Systems Many agents, one system: orchestration patterns, protocols, and the overhead they add.
- Best Chain of Thought Episodes on Open Source AI Open weights, open ecosystems, and what they cost in production.
- Best Chain of Thought Episodes on AI Coding Agents What changes downstream when agents write most of the code.
- Best Chain of Thought Episodes for Enterprise AI Leaders Getting AI past the pilot: ROI, rollout, and the data underneath it.
- Best Chain of Thought Episodes on RAG & Retrieval Getting the right context to the model: chunking, vectors, graphs, and what breaks at scale.
- Best Chain of Thought Episodes on AI Infrastructure & Hardware What AI runs on: power, GPUs, networks, kernels and small models.
- Best Chain of Thought Episodes on Building AI Products Deciding what to build, setting a quality bar and shipping fast.

