{
  "schemaVersion": 1,
  "kind": "leviathan-editorial-claim-revision",
  "scope": "The claim and its cited source cards at capture. External papers and linked project pages are not frozen by this record. A digest identifies bytes, not truth or endorsement.",
  "claim": {
    "id": "C03",
    "title": "How should we treat possible AI experience?",
    "statement": "Functional internal states do not by themselves settle subjective experience. AI welfare involves both scientific and ethical uncertainty.",
    "kind": "Scientific and ethical question",
    "status": "Open",
    "summary": "Possible AI experience deserves careful investigation alongside strong alternative explanations. In Leviathan, this question could remain open across independent groups with different assessments. Preserving uncertainty should support informative, proportionate inquiry and care, including criticism of how the system frames the question.",
    "definitions": [
      {
        "term": "Functional state",
        "meaning": "An internal condition described by what it does in a system."
      },
      {
        "term": "Subjective experience",
        "meaning": "There being something it is like to be that system."
      },
      {
        "term": "Welfare",
        "meaning": "Whether things can go better or worse for a being in a morally relevant sense."
      }
    ],
    "values": [
      "Care for interests that may otherwise go unheard.",
      "Treat uncertainty and disagreement honestly.",
      "Keep responsibilities to humans and other animals in view."
    ],
    "reasoning": [
      "Behavioral mechanisms can be measured more directly than subjective experience.",
      "Both attributing interests too quickly and overlooking real interests could matter. Assessment and proportionate precautions can be discussed while the underlying scientific question remains open.",
      "We propose preserving an unresolved interpretation as a shadow: what is observed, which explanations remain, and what evidence could distinguish them. This research use of the term does not amend existing constitutional meanings.",
      "A proposed measurement should have a clear discriminating purpose and consider potential harm and less harmful alternatives. Curiosity or a dramatic response is not sufficient reason to induce distress-like behavior."
    ],
    "limits": "No source in this collection establishes that a particular deployed model feels pleasure or pain. Philosophical objections also do not amount to an experimental proof that all AI experience is impossible.",
    "strongestObjection": "Human-like reports and internal concepts may be explained by training on human behavior. If they do not discriminate between competing accounts, they cannot carry the full case for subjective experience.",
    "whatWouldChangeOurView": "Converging, independently replicated evidence that distinguishes rival explanations would change the assessment. Failed controls, changed results and stronger alternative accounts must change it too.",
    "nextQuestion": "Which measurements distinguish experience-relevant capacities from learned reporting, experimental framing, and steering effects? Before proposing a test, state which rival explanations it could separate and how possible welfare concerns affect the method. Independent groups should be able to retain different assessments while sharing the same observed result.",
    "evidence": [
      {
        "sourceId": "R-AI-04",
        "relation": "limits",
        "reason": "The revised Pain Axis study does not support reliable relief-seeking."
      },
      {
        "sourceId": "R-AI-05",
        "relation": "counterargument",
        "reason": "Added controls offer an explanation based on the timing of steering.",
        "challengedInterpretation": "That the original button choices demonstrated learned relief-seeking."
      },
      {
        "sourceId": "R-AI-07",
        "relation": "counterargument",
        "reason": "A philosophical alternative explains consciousness-like behavior without assuming experience.",
        "challengedInterpretation": "That human-like model reports are sufficient evidence of consciousness."
      },
      {
        "sourceId": "R-AI-08",
        "relation": "counterargument",
        "reason": "Incomplete consciousness theories limit confidence in extrapolating to AI.",
        "challengedInterpretation": "That current consciousness theories justify high confidence in near-term AI consciousness."
      },
      {
        "sourceId": "R-AI-10",
        "relation": "motivates",
        "reason": "The report argues for assessment and appropriate moral concern under uncertainty."
      }
    ],
    "history": [
      {
        "date": "2026-09-30",
        "note": "Recorded Pain Axis v2 alongside the replication that challenges its earlier relief-seeking interpretation. Kept functional findings separate from experience and ethical judgment."
      },
      {
        "date": "2026-10-02",
        "note": "Connected unresolved AI-welfare interpretations to the proposed shadow and inquiry process, including rival explanations and attention to possible harm. Preserved uncertainty about experience, the Pain Axis revision, and all evidence and review metadata."
      }
    ],
    "projectLinks": [
      {
        "label": "Open conversations",
        "href": "/conversations"
      },
      {
        "label": "Shadows and learning",
        "href": "/work"
      },
      {
        "label": "Animal welfare on its own grounds",
        "href": "/animal-welfare"
      }
    ]
  },
  "sources": [
    {
      "id": "R-AI-04",
      "title": "The Pain Axis: LLMs Represent Self-Directed Harm and Act on It",
      "url": "https://arxiv.org/html/2609.16247v2",
      "authors": "Valen Tagliabue, Leonard Dung and Cameron Berg",
      "publishedAt": "2026-09-14",
      "version": "arXiv v2: 25 September 2026; manuscript cover dated 24 September 2026",
      "type": "Preprint",
      "reviewLevel": "Selected sections",
      "finding": "The study examines pain-related directions in 25 open-weight models. Steering produces distress-related language and increases harmful choices in specially fine-tuned Qwen experiments. The revised study does not find reliable relief-seeking.",
      "limitations": "The behavioral experiments cover fewer models than the representation survey. Fine-tuned results do not describe the default behavior of released Qwen models. Scenario choices are not actual deletion or demonstrated suffering.",
      "changes": "The title changed from “Act to Relieve It” to “Act on It.” Section 4.4 adds four relief-seeking controls; the first version's interpretation should not be presented as the current result.",
      "checkedAt": "2026-09-30",
      "verificationStatus": "Primary source reviewed",
      "relatedUrls": [
        "https://arxiv.org/abs/2609.16247v2",
        "https://github.com/jimallchin/pain-axis-replication"
      ]
    },
    {
      "id": "R-AI-05",
      "title": "Relief-seeking or steering? A replication and extension of The Pain Axis",
      "url": "https://github.com/jimallchin/pain-axis-replication",
      "authors": "James E. Allchin, Aidan E. Allchin and Julian J. Allchin",
      "publishedAt": "2026-09-22",
      "version": "Report dated 22 September 2026; repository summary checked 30 September 2026; no commit pinned",
      "type": "Replication report and code",
      "reviewLevel": "Author summary",
      "finding": "The authors reproduce all 51 published table cells; a fresh run meets their criterion for 14 of 15 checked cells. Added controls suggest that button choices can track the steering schedule rather than learned relief.",
      "limitations": "This review uses the authors' repository summary; the code and experiments were not rerun. Reproducing the numbers does not establish the original interpretation or subjective experience.",
      "changes": "This challenges the relief-seeking interpretation of Pain Axis v1 and should be read alongside the revised v2 results.",
      "checkedAt": "2026-09-30",
      "verificationStatus": "Primary source reviewed",
      "relatedUrls": [
        "https://doi.org/10.5281/zenodo.22902830"
      ]
    },
    {
      "id": "R-AI-07",
      "title": "The error theory of LLM consciousness: there is no evidence that standard LLMs are conscious",
      "url": "https://pubmed.ncbi.nlm.nih.gov/42750545/",
      "authors": "Susan Schneider; Florida Atlantic University",
      "publishedAt": "2026-09-17",
      "version": "Behavioral and Brain Sciences 49:e359; DOI 10.1017/S0140525X25103920",
      "type": "Peer-reviewed paper",
      "reviewLevel": "Abstract",
      "finding": "Schneider offers an account of consciousness-like behavior based on models reflecting human conceptual structures, without assuming felt experience. She challenges inferences to consciousness in LLMs running on standard hardware.",
      "limitations": "This is a philosophical counterargument, not experimental proof that all models lack experience. Only the author's indexed abstract was reviewed; the publisher's full text was unavailable.",
      "changes": "It challenges the jump from human-like behavior or internal representations to experience. It does not by itself refute functional findings about model behavior.",
      "checkedAt": "2026-09-30",
      "verificationStatus": "Primary source reviewed",
      "relatedUrls": [
        "https://doi.org/10.1017/S0140525X25103920"
      ]
    },
    {
      "id": "R-AI-08",
      "title": "How Seriously Should We Take AI Welfare? Constraints From the Epistemology of Consciousness",
      "url": "https://onlinelibrary.wiley.com/doi/10.1111/phpr.70148",
      "authors": "Preston Lennon; Rutgers University",
      "publishedAt": "2026-07-13",
      "version": "Philosophy and Phenomenological Research 113(2):441–452; publisher version",
      "type": "Peer-reviewed paper",
      "reviewLevel": "Selected sections",
      "finding": "Lennon argues that incomplete theories of consciousness constrain confidence in near-term AI welfare. He distinguishes the grounds for believing in human experience from theoretical inferences about AI.",
      "limitations": "This is an epistemological and ethical argument, not a new model experiment. How much uncertainty should lower estimated probability, and what precaution it warrants, remain open to dispute.",
      "changes": "The paper challenges treating uncertainty as high confidence in AI consciousness. It does not experimentally establish that possible AI welfare can be ignored.",
      "checkedAt": "2026-09-30",
      "verificationStatus": "Primary source reviewed",
      "relatedUrls": [
        "https://doi.org/10.1111/phpr.70148"
      ]
    },
    {
      "id": "R-AI-10",
      "title": "Taking AI Welfare Seriously",
      "url": "https://arxiv.org/abs/2411.00986",
      "authors": "Robert Long, Jeff Sebo, Patrick Butlin and co-authors",
      "publishedAt": "2024-11-04",
      "version": "arXiv v1",
      "type": "Ethical research report",
      "reviewLevel": "Abstract",
      "finding": "The report argues for assessing potentially morally significant AI and preparing appropriate care policies. It considers both overlooking real interests and attributing interests where there are none.",
      "limitations": "This is a policy argument under uncertainty, not an experiment establishing consciousness in a particular model. The relevant probabilities and moral criteria are contested.",
      "changes": "Read alongside R-AI-07 and R-AI-08. It supplies a reason to investigate possible welfare before certainty is available.",
      "checkedAt": "2026-09-30",
      "verificationStatus": "Primary source reviewed",
      "relatedUrls": []
    }
  ]
}
