The Cringe Test: Why AI Can't Do Privacy Threat Modeling for You
Can AI do your privacy threat modeling for you? Dr. Kim Wuyts and Avi Douglen say no, and their answer comes down to something AI doesn't have: the cringe.
Listen to the episodeChris Romeo · Robert Hurlbut|317 episodes · 199 hours · since 2016
Latest episode
We Told the Agent No 11 Times. It Did It Anyway
Rock Lambros46 min
Jason Lemkin told the Replit agent eleven times not to touch anything, and it deleted his production database anyway. So who tells an agent no?
Start here
Start with our most-watched AI and LLM security episodes from the past year, or browse by topic instead.
More episodes
All 317AppSec Has Never Mattered More: The Time to Exploit Is Now Negative
When one AI model can find a vulnerability, another can write the exploit, and the gap between discovery and attack is collapsing.
Listen to the episodeYour Developers Are Letting AI Answer Your Security Findings
Are your developers still reading their security findings, or are their agents answering for them?
Listen to the episodeShadow MCP Servers: The AI Security Risk Hiding on Your Developers' Laptops
What happens when a protocol goes from idea to everywhere before security can catch up?
Listen to the episodeYour Opinion on AI Doesn't Matter. Learned Fragility Does
What happens when a tsunami of AI-written code meets a security industry that has spent decades chasing vulnerabilities? Brook S.E.
Listen to the episode