Skip to content
r•Robopsychology
Research AtlasField buildingSalonsConnectTeamAboutSubscribe
MapQuestionsPapersMethodsPeoplev1 · Corrections welcome
Atlas / Digital minds / Cluster

Subject & Substrate

Subject & Substrate

Whose mind is it? Which level bears the states we measure — weights, instance, conversation, character — and so what are we actually studying.

Open questions

  • What is the subject
  • Whose valence is it
  • Counting moral patients
  • Which activations belong to the Assistant
  • An agenda beyond the Assistant

Papers

  • Chalmers 2025 - What we talk to
  • Beckmann Butlin 2026 - Where is the mind
  • Gilg et al 2026 - Probing persona-dependent preferences
  • Register 2025 - Individuating artificial moral patients
  • Birch 2025 - AI consciousness a centrist manifesto
  • Artificial Self 2026 - Landscape of AI identity
  • Shulman Bostrom 2021 - Sharing the world with digital minds
  • Tagliabue Dung Berg 2026 - The pain axis
  • Lu et al 2026 - The Assistant Axis
  • Lindsey 2025 - Emergent introspective awareness
  • Shanahan 2024 - Simulacra as conscious exotica
  • LessWrong 2026 - Which character are we evaluating

People

Placed by the editor, v1 — corrections welcome.

  • Jack Lindsey
  • Christina Lu
  • Patrick Butlin
  • Pierre Beckmann
  • David Chalmers
  • Jonathan Birch
  • Henry Shevlin
  • Derek Shiller
  • Christopher Register

Help improve this map

Know a paper that belongs here, or think something needs correcting?

Suggest a correction ↗Contributions are reviewed before they appear.
Around this cluster
How to Count AIs: Individuation and Liability for AI AgentsThe Artificial Self: characterising the landscape of AI identityWhere is the mind? Persona vectors and LLM individuationAI consciousness: a centrist manifestoWhat we talk to when we talk to language modelsProbing persona-dependent preferences in language modelsThe Abstraction Fallacy: Why AI Can Simulate But Not Instantiate ConsciousnessWhich character are we evaluating? Persona stability and AI welfareEmergent introspective awareness in large language modelsThis cluster

29 connections · Explore on map ↗

People

Christina Lu
Christopher Register
David Chalmers
Website ↗
Derek Shiller
Henry Shevlin
Jack Lindsey
Jonathan Birch
Patrick Butlin
Pierre Beckmann

Linked from

  • How to Count AIs: Individuation and Liability for AI Agents
  • The Artificial Self: characterising the landscape of AI identity
  • Where is the mind? Persona vectors and LLM individuation
  • AI consciousness: a centrist manifesto
  • What we talk to when we talk to language models
  • Probing persona-dependent preferences in language models
  • The Abstraction Fallacy: Why AI Can Simulate But Not Instantiate Consciousness
  • Which character are we evaluating? Persona stability and AI welfare
  • Emergent introspective awareness in large language models
  • Studying AI Welfare Empirically
  • The Assistant Axis: situating and stabilizing the default persona of language models
  • Individuating artificial moral patients
  • Simulacra as conscious exotica
  • Sharing the world with digital minds
  • The pain axis: LLMs represent self-directed harm and act to relieve it
  • Christina Lu
  • Christopher Register
  • David Chalmers
  • Derek Shiller
  • Henry Shevlin
  • Jack Lindsey
  • Jonathan Birch
  • Patrick Butlin
  • Pierre Beckmann
  • Does the model have an agenda beyond what the Assistant wants?
  • How do we count moral patients when one model runs millions of conversations?
  • What is the subject — the model, an instance, a conversation, or a persona?
  • Which parts of a model's activations belong to the Assistant, and how are thoughts bound to it?
  • Whose valence is it — the character's, the model's, or no one's?

News and updates

Hear when a new map, salon or course opens.

We use your email only for Robopsychology news.

Robopsychology

A field in formation. A map in progress.

Field buildingSalonsConnectField guideTeamAboutAbout the AtlasSuggest a correction
robopsych.org