Philosophy of agency & value
What values are, how people choose when they conflict, and what it means to act with integrity: the picture of human agency that any attempt to align AI with human values rests on.
- Curated by
- TBD
- Write to
- agency@agi-institutions.orgAn operator routes it to the right experts.
Selected papers
3
Must-reads for understanding the field and why it matters for AGI institutions.
Builds on Charles Taylor and Ruth Chang to define values as the criteria people attend to when making meaningful choices, and uses that definition to elicit a moral graph from a representative sample of Americans.
Rejects both the rationalist view that intelligence is calculation and the romantic view that mind cannot be mechanized, and draws on Kant and Hegel to treat freedom, analyzed as wisdom, creativity, and autonomy, as what an artificial agent would need.
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
11
Recent work in the field worth knowing.
Foundations
10
Older work that gives background on the field.
This list isn't exhaustive. About the lists.