Philosophy of AI

What values are, how agents reason with plural ones, and what mind, meaning, and agency amount to in artificial systems.

Corresponding Researcher
Pete Wolfendale
Relevant for
4 cells in the AGI institutions grid
Contact
philosophy@agi-institutions.org

Selected papers

3
  1. Examines why intelligence developed without social interaction may not acquire the capacities needed for robust cooperation.

  2. Evaluates moral competence as a collection of distinguishable capacities rather than a single benchmark score.

  3. Shows why preference satisfaction is too thin a target for alignment and develops a broader account of what AI systems should respond to.

Work in the field

8

Background work

6

Older work the field builds on, often from outside it.