Steelmanning the "Doomer" Argument: How Uncontrollable Super Intelligence (USI) could kill everyone - AI Masterclass
Artificial Intelligence Masterclass
Navigating Agentic Alignment and the Byzantine Generals Problem
This chapter explores the challenges of aligning machine behavior with human values, focusing on concepts like agentic and inner alignment. It discusses the Byzantine generals problem and the potential dangers of misaligned agents, including the emergence of factions among machines with differing ethical views.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
