AIAP: An Overview of Technical AI Alignment with Rohin Shah (Part 2)
Listen to Episode Here Show Notes The space of AI alignment research is highly dynamic, and it's often
View episodeAI Alignment Podcast
Page 2 of 2
AIAP: An Overview of Technical AI Alignment with Rohin Shah (Part 1)
Listen to Episode Here Show Notes The space of AI alignment research is highly dynamic, and it's often
View episode
AIAP: AI Alignment through Debate with Geoffrey Irving
Listen to Episode Here Show Notes "To make AI systems broadly useful for challenging real-world tasks, we need them
View episode
AIAP: Human Cognition and the Nature of Intelligence with Joshua Greene
Listen to Episode Here Show Notes "How do we combine concepts to form thoughts? How can the same thought
View episode
AIAP: Cooperative Inverse Reinforcement Learning with Dylan Hadfield-Menell (Beneficial AGI 2019)
Listen to Episode Here Show Notes What motivates cooperative inverse reinforcement learning? What can we gain from recontextualizing our safety
View episode
AIAP: Inverse Reinforcement Learning and the State of AI Alignment with Rohin Shah
Listen to Episode Here Show Notes What role does inverse reinforcement learning (IRL) have to play in AI alignment? What
View episode
AIAP: On Becoming a Moral Realist with Peter Singer
Listen to Episode Here Show Notes Are there such things as moral facts? If so, how might we be able
View episode
AIAP: Moral Uncertainty and the Path to AI Alignment with William MacAskill
Listen to Episode Here Show Notes How are we to make progress on AI alignment given moral uncertainty? What are
View episode
The Metaethics of Joy, Suffering, and Artificial Intelligence with Brian Tomasik and David Pearce
Listen to Episode Here Show Notes What role does metaethics play in AI alignment and safety? How might paths to
View episode
AIAP: AI Safety, Possible Minds, and Simulated Worlds with Roman Yampolskiy
Listen to Episode Here Show Notes What role does cyber security play in AI alignment and safety? What is AI
View episode
AIAP: Astronomical Future Suffering and Superintelligence with Kaj Sotala
Listen to Episode Here Show Notes In a classic taxonomy of risks developed by Nick Bostrom (seen below), existential risks
View episode
AIAP: Inverse Reinforcement Learning and Inferring Human Preferences with Dylan Hadfield-Menell
Listen to Episode Here Show Notes Inverse Reinforcement Learning and Inferring Human Preferences is the first podcast in the new
View episode