Prerequisites and Future Gains
Dwarkesh Patel explores the prerequisites for smart moral individuals and the potential for future gains in generality. The conversation delves into the complexity of aligning moral preferences and the possibility of a significant leap in progress, akin to the transition from chimps to humans.In this clip
From this podcast
Dwarkesh Podcast
Eliezer Yudkowsky - Why AI Will Kill Us, Aligning LLMs, Nature of Intelligence, SciFi, & Rationality
Related Questions
How do humans and GPTs compare?
Do you think GPT-4 is capable of understanding human emotions as discussed in the episode Peter Lee: Computing Theory and Practice, and GPT-4's Impact and the clip Emotional Intelligence Dilemma?
Can morality progress over time as discussed in the episode Jaron Lanier: Virtual Reality, Social Media & the Future of Humans and AI | Lex Fridman Podcast #218 and the clip Compassionate Systems?