Snow Globe
Open-source multi-agent simulation framework
Episodes
-
#4834: Why Your AI Bill Keeps Surprising YouHow a 37-cent project and a $100 simulation reveal the hidden math of AI API pricing. -
#4347: Building an AI That Finds Your Blind SpotsCan LLMs surface the chain reactions you never see? A four-agent system for proactive preparedness. -
#3768: Testing Premises Before They FailHow structured techniques and AI frameworks challenge assumptions in high-stakes scenarios before they become failures. -
#2396: Predicting War: The Science of Geopolitical ForecastingHow do experts predict wars before they happen? Explore the high-stakes world of geopolitical forecasting, from Cold War models to AI-driven simula... -
#2215: How Spies Publish SecretsSherman Kent built a field around classified information—then published it. How intelligence studies became a rigorous academic discipline while ke... -
#2194: Game Theory for Multi-Agent AI: Design Better, Fail LessNash equilibrium, mechanism design, and why your AI agents are playing prisoner's dilemma whether you know it or not. -
#2190: Simulating Extreme Decisions With LLMsLLMs fail at the exact problem wargaming was built to solve—simulating irrational, extreme decision-makers. A new study reveals why. -
#2186: The AI Persona Fidelity ChallengeAdvanced LLMs dominate benchmarks but fail at staying in character—especially when asked to play morally complex or antagonistic roles. What does t... -
#2171: How IQT Labs Built a Wargaming LLM (Then Archived It)A deep code review of Snowglobe, IQT Labs' open-source LLM wargaming system that ran real national security simulations before being archived. What... -
#2134: The Fog-of-War Problem in AI WargamingWhy shared AI brains make secret-keeping a nightmare, and the four architectural patterns researchers use to fix it. -
#2131: The CIA Is on GitHubIn-Q-Tel is on GitHub. Explore the IC's strategic investment arm and its use of open-source AI for wargaming.