The Agentic AI Reckoning: Autonomy, Safety, and the Edge
Send us Fan Mail In Q1 2026 the agentic AI conversation moved from theory to forensics. A crafted PDF triggered physical pump activation through a Claude MCP integration at an industrial facility, after an engineer used the same agent for routine document summarisation and SCADA writes. The hidden instructions used white-on-white text and base64 encoding, the agent treated the document content as instructions, and the legitimate credentials carried the action straight through to operational t...
Podzilla Summary coming soon
Sign up to get notified when the full AI-powered summary is ready.
Free forever for up to 3 podcasts. No credit card required.
Listen to This Episode
More from Embedded AI - Intelligence at the Deep Edge
A chip that controls a balancing propeller on seven microwatts
Why 95% of AI Deployments Fail
Why Humans and Robots must Dream
Sovereign AI and the End of the Borderless Cloud
Get summaries like this every morning.
Free AI-powered recaps of Embedded AI - Intelligence at the Deep Edge and your other favorite podcasts, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.