AI Utility Functions
Connor delves into the complexities of AI utility functions, highlighting the challenges in defining human values within a vast optimization space. He explores the necessity of finding a better framing than utility functions to ensure AI aligns with human values effectively.In this clip
From this podcast
Machine Learning Street Talk (MLST)
AI Alignment & AGI Fire Alarm - Connor Leahy
Related Questions
Does being rational in the context of the episode Eliezer Yudkowsky - Why AI Will Kill Us, Aligning LLMs, Nature of Intelligence, SciFi, & Rationality and the clip Rationality and Winning mean losing?
How does usefulness impact artificial intelligence?
What role does probability play in decision-making as discussed in the episode Eliezer Yudkowsky - Why AI Will Kill Us, Aligning LLMs, Nature of Intelligence, SciFi, & Rationality and the clip Uncertainty and Future Predictions?