Explainability in AI
The conversation delves into the complex relationship between explainability and performance in AI systems. While one perspective emphasizes the need for systems to articulate their reasoning, especially when errors occur, another highlights the intrinsic human desire for storytelling in understanding intelligence. This raises questions about whether neural networks can effectively engage in storytelling, regardless of their foundational mechanics.In this clip
From this podcast
Lex Fridman Podcast
Sergey Levine: Robotics and Machine Learning | Lex Fridman Podcast #108
Related Questions