157 - Tim Schulz

On Episode 157 of the Silver Bullet Security Podcast, BIML’s Gary McGraw hosts Tim Schulz.  Tim talks about whitebox control and observability in machine learning systems (and especially transformer architectures), the limits of red teaming for securing AI,  "neural surgery,"  Agentic AI and the confused deputy problem, and the economics of network "smallification."

• Starseer
• Whitebox machine learning and looking inside networks
• Anthropics circuits thread
• Agentic AI and intention