The Alignment Problem: Computer Science Meets Analytic Philosophy
For AI safety researchers exploring fundamental alignment challenges and their conceptual foundations.
AI Summary
The author explains the technical AI problem by combining perspectives from computer science, machine learning theory, and analytic philosophy.
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,
Read Original
0 upvotes · 0 downvotes · 1 min read