The Alignment Problem
Vahid discusses the challenges of defining objective functions for AI agents, using examples of robotic vacuum cleaners and self-driving cars. He highlights the difficulty of aligning objectives with desired outcomes and the need for verifiable alignment.In this clip
From this podcast
Data Skeptic
A Psychopathological Approach to Safety in AGI
Related Questions
Why is behavior important in artificial intelligence?
Can AI have complex goals as discussed in the episode Jeremie Harris: Realistic Alignment and AI Policy and the clip The Inner Alignment Problem?
Can AI motivations be shaped as discussed in the episode Jeremie Harris: Realistic Alignment and AI Policy and the clip The Challenge of AI Objectives?