"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis cover image

Beyond Preference Alignment: Teaching AIs to Play Roles & Respect Norms, with Tan Zhi Xuan

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

CHAPTER

Navigating AI Alignment and Cooperation

This chapter explores self-other overlap in the context of AI alignment, emphasizing the importance of human cognitive mechanisms for empathy and collaboration. The speakers discuss the current disconnect in AI alignment strategies and propose modifying AI internal representations to enhance safety and reliability. Additionally, they examine the potential global implications of AI's development, advocating for a balanced approach to prevent an international arms race in AI technology.

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.
App store bannerPlay store banner