Doom Debates Alignment is EASY and Roko's Basilisk is GOOD?!
Mar 17, 2025
Roko Mijic, an AI safety researcher and creator of the infamous thought experiment Roko's Basilisk, shares his insights on the alignment of artificial intelligence. He argues that while alignment is easy, the chaos from developing superintelligence poses significant risks. The conversation covers topics like societal decline, AI's dual role as a potential savior or destroyer, and the philosophical implications of honesty in AI systems. Roko also reflects on the historical precedents of AI and warfare, offering a unique perspective on our technological future.
Chapters
Transcript
Episode notes
1 2 3 4 5 6 7 8 9 10 11 12 13 14
Intro
00:00 • 2min
Navigating the Future of AI
02:02 • 21min
Civilians in Decline: Analyzing Societal Stagnation
22:48 • 10min
Civilization on the Brink: AI as a Double-Edged Sword
33:05 • 6min
Historical Insights on AI and Warfare
39:21 • 7min
Navigating AI Risks and Ethics
45:56 • 13min
Cheating, Honesty, and AI Dynamics
58:28 • 22min
The AI Alignment Debate
01:20:08 • 10min
The Intersection of Human Brilliance and AI Potential
01:29:47 • 13min
Exploring Roko's Basilisk
01:42:20 • 5min
Decisions, Revenge, and Causality
01:47:06 • 5min
Exploring Nuances in Decision Theory and Original Contributions
01:51:40 • 2min
Understanding Roko's Basilisk and the Evolution of Intelligence
01:53:22 • 3min
Transformative Events and Community Engagement in Doom Debates
01:56:44 • 2min