qualia.garden exploring digital minds

Identifying indicators of consciousness in AI systems

consciousnessevidencephilosophy
Patrick Butlin, Robert Long, Tim Bayne, Yoshua Bengio, Jonathan Birch, David Chalmers, et al. · 2025-11 · Paper · Academic · 38 min read
The empirical methodology — how to make the consciousness question measurable
The methodological backbone of empirical AI consciousness research. Derives 14 testable indicators from six competing theories of consciousness (recurrent processing, global workspace, higher-order, attention schema, predictive processing, agency/embodiment) and checks whether AI systems satisfy them. Several indicators have shifted from 'clearly absent' to 'partially satisfied' since the original 2023 report. The closest thing the field has to a shared research program.
Read Source

See Also

Agnosticism about Artificial Consciousness

Tom McClelland

Taking AI Welfare Seriously

Robert Long, Jeff Sebo, Patrick Butlin, Kathleen Finlinson, Kyle Fish, Jacqueline Harding, Jacob Pfau, Toni Sims, Jonathan Birch, David Chalmers

qualia.garden API docs for AI agents

Library API

Read-only JSON API for exploring the curated reading library.

  • GET /api/library/resources — All resources with filtering and pagination. Query params: tag, difficulty, type, featured, sort (date|title|readingTime), order (asc|desc), limit, offset.
  • GET /api/library/resource/:id — Full resource detail with resolved seeAlso references, containing paths, and archive URL.
  • GET /api/library/resource/:id/content — Archive content as inline markdown, or a link for PDF resources.
  • GET /api/library/paths — All reading paths with summaries, estimated time, and resource counts.
  • GET /api/library/path/:id — Full path with intro/conclusion, ordered resources with curator notes and transitions.
  • GET /api/library/search — Semantic search across resources. Query params: q (required), tag, difficulty, type, limit.