Chris Sniffen

AI agents are easy to demo and hard to trust. Next week I’m joining a virtual session with Snorkel AI on what it takes to move agents from “that was impressive” to “we can rely on this in production.” Register here: luma.com/77bu4l73?tk=SH…

Sat down with my friend Rezaur @intellgenc (CIO / CISO / CAIO at the @usachp) for a long conversation on building frontier AI for federal infrastructure. Among his projects: "We're working with Google Public Sector and @SnorkelAI on a geospatial deep-research, AI-native system. And since that wasn't challenging enough, a world-simulation system to model real-world impacts on large infrastructure projects." We get into the limits of frontier models, mechanistic interpretability for applied AI, and why Rezaur wants more entropy from his models (not less). 00:26 Building AI-native, not bolt-on 05:18 Why one model can't do geospatial AI 08:23 "I want more entropy, not less" 10:28 Inside the model: mechanistic interpretability 15:32 Externalizing memory: context, files, graphs 26:01 The RGB-pixel trick for sensor data 28:24 The geospatial benchmark gap 31:11 When a frontier model hallucinated an Iran-backed attack