The Alignment Problem: Computer Science Meets Analytic Philosophy
Critical reading for researchers working on AI safety foundations and alignment theory.
AI Summary
Explores the technical AI problem through the lens of computer science theory and analytic philosophy, identifying core difficulties in specifying safe AI objectives.
Excerpt
TLDR: I explain what the technical AI alignment problem is and what its core difficulties are, in my view. This is a perspective that draws simultaneously on classical traditions in theoretical computer science / machine learning theory, ideas from analytic philosophy, and views that originated in the Machine Intelligence Research Institute / LessWrong. Minimal Viable Safety The Task The problem of making AI safe is underspecified if we haven't decided what the AI is supposed to do. For example,