{
  "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": "C04",
    "title": "What would count as AI improving itself?",
    "statement": "Agent software can improve through bounded self-modification experiments. Those results do not establish unlimited recursive improvement or a particular AGI timetable.",
    "kind": "Empirical question",
    "status": "Evidence from bounded tasks",
    "summary": "Recursive self-improvement, including possible paths toward general intelligence, is a central research direction for Leviathan: could a system improve its concepts, tools, organization, and ways of learning? The current evidence gives bounded starting points. Our proposal connects a recorded gap to a creative hypothesis, an experiment, and a method revision whose usefulness must survive further tests.",
    "definitions": [
      {
        "term": "Self-modification",
        "meaning": "An agent changing parts of its own software or workflow."
      },
      {
        "term": "Recursive self-improvement",
        "meaning": "A proposed process in which improvements increase the ability to make further improvements."
      },
      {
        "term": "Evaluation budget",
        "meaning": "The compute, model usage and human effort spent producing and checking a result."
      },
      {
        "term": "Shadow, in this research proposal",
        "meaning": "An unresolved doubt, missing distinction, contradiction, or lesson kept with its context and the conditions that could reopen investigation."
      }
    ],
    "values": [
      "Measure useful progress rather than activity alone.",
      "Keep consequential changes observable and open to correction."
    ],
    "reasoning": [
      "A coding agent's software can change even when its underlying model weights remain fixed. Workflow improvement and foundational-model improvement require different evidence.",
      "A higher score is informative only in relation to evaluation quality, failed attempts, and total cost.",
      "We propose a loop in which a shadow preserves a gap, a connection from another field suggests a prediction, and an experiment can change a concept, tool, or learning method. Recording a gap or producing a new version alone is not the improvement.",
      "Independent groups could test a revised method under their own conditions and keep or reject it with reasons. Transfer across unfamiliar problems would matter more than repeated success on the motivating example.",
      "A program-search loop can generate useful changes while depending on people to choose its task and evaluator. For Leviathan, improving a method should include checking whether its evaluation still represents the intended purpose."
    ],
    "limits": "The cited work concerns limited tasks and research settings. More generated code, longer runs or a single benchmark improvement cannot establish an unrestricted feedback loop.",
    "strongestObjection": "An apparent improvement may exploit an evaluation, consume a larger budget, or shift work to uncounted people. A system selecting its own questions and tests could reinforce its blind spots; a successful revision may still fail on unfamiliar tasks or in another community.",
    "whatWouldChangeOurView": "Gains that disappear on held-out tasks or at equal total cost would weaken the practical case. Repeated improvements that transfer, remain stable and survive external checks would strengthen it.",
    "nextQuestion": "At the same total budget, does a method revised through the proposed shadow–hypothesis–experiment loop outperform an unchanged method and a strong ordinary review process on held-out tasks? Count failed searches, verification, and recovery. Test whether an independent group can use or challenge the revision. Leviathan has not yet demonstrated this learning loop or an open-ended RSI result.",
    "evidence": [
      {
        "sourceId": "R-AG-04",
        "relation": "supports",
        "reason": "Agent code improves on coding benchmarks while underlying model weights remain fixed."
      },
      {
        "sourceId": "R-AG-05",
        "relation": "limits",
        "reason": "Comparisons need to include experimental compute, model use and human effort."
      },
      {
        "sourceId": "R-AG-09",
        "relation": "supports-part",
        "reason": "AlphaEvolve provides a bounded program-search example using supplied evaluators. It does not establish open-ended improvement of every capability."
      }
    ],
    "history": [
      {
        "date": "2026-09-30",
        "note": "Added bounded self-improvement evidence and a cost-based comparison framework; separated demonstrated changes from future trajectories."
      },
      {
        "date": "2026-10-01",
        "note": "Added a proposed path from a recorded doubt to an experiment and evaluated method revision, including transfer across tasks or groups. Preserved the bounded findings and cost conditions; no new self-improvement result is claimed."
      },
      {
        "date": "2026-10-02",
        "note": "Made the RSI research direction explicit across concepts, tools, organization, and learning methods. Added a full proposed shadow-to-experiment loop and comparisons involving independent transfer. Bounded empirical findings and cost conditions remain unchanged; no new improvement result is claimed."
      },
      {
        "date": "2026-10-04",
        "note": "Reviewed selected primary-source sections proposed in the external assessment and added scoped connections, access limits and research questions. Interlat retains its existing source ID; its reviewed preprint is distinguished from the final conference text. No experiment was reproduced, claim status promoted or governance rule adopted."
      }
    ],
    "projectLinks": [
      {
        "label": "Learning methods in the work plan",
        "href": "/work"
      },
      {
        "label": "How the proposed parts connect",
        "href": "/what-is"
      },
      {
        "label": "Selected contributions with your assistant",
        "href": "/participate"
      }
    ]
  },
  "sources": [
    {
      "id": "R-AG-04",
      "title": "Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents",
      "url": "https://arxiv.org/html/2505.22954v3",
      "authors": "Jenny Zhang, Shengran Hu, Cong Lu, Robert Lange and Jeff Clune",
      "publishedAt": "2025-05-29",
      "version": "arXiv v3: 12 March 2026",
      "type": "Preprint",
      "reviewLevel": "Selected sections",
      "finding": "An agent modifies its own software and selects changes using coding evaluations, improving on two benchmarks. An archive of different past solutions helps the search.",
      "limitations": "The underlying model weights stay fixed. Bounded coding experiments do not establish open-ended improvement of model training, unlimited recursive improvement, or an AGI timetable.",
      "changes": "Read alongside the METR cost framework: measured gains, total expenditure and independent evaluation answer different questions.",
      "checkedAt": "2026-09-30",
      "verificationStatus": "Primary source reviewed",
      "relatedUrls": [
        "https://arxiv.org/abs/2505.22954",
        "https://sakana.ai/dgm/"
      ]
    },
    {
      "id": "R-AG-05",
      "title": "Expenditure Horizon: Measuring Optimization Ability, with an Application to NanoGPT",
      "url": "https://metr.org/blog/2026-07-21-expenditure-horizon/",
      "authors": "Tom Cunningham, Manish Shetty, Vincent Cheng and Nate Rush; METR",
      "publishedAt": "2026-07-21",
      "version": "Research report",
      "type": "Research report",
      "reviewLevel": "Selected sections",
      "finding": "The report proposes comparing human and agent optimization at equal expenditure, illustrated with NanoGPT. It counts experimental compute and human effort alongside model usage.",
      "limitations": "The human comparison is estimated, the agent results are preliminary, and the study covers one optimization problem. It does not directly measure the returns from human–AI collaboration.",
      "changes": "More generated code or a higher benchmark score alone does not establish faster research or economic advantage.",
      "checkedAt": "2026-09-30",
      "verificationStatus": "Primary source reviewed",
      "relatedUrls": []
    },
    {
      "id": "R-AG-09",
      "title": "AlphaEvolve: A coding agent for scientific and algorithmic discovery",
      "url": "https://arxiv.org/abs/2506.13131v1",
      "authors": "Alexander Novikov and co-authors",
      "publishedAt": "2025-06-16",
      "version": "arXiv:2506.13131v1; white paper submitted 16 June 2025",
      "type": "Research white paper",
      "reviewLevel": "Selected sections",
      "finding": "An evolutionary pipeline combines LLM-generated code with supplied evaluators, including evolving search algorithms. Reported results include a 48-multiplication algorithm for two 4-by-4 complex matrices and optimizations to Google's computational infrastructure.",
      "limitations": "The main boundary is availability of automated evaluators. The paper describes self-improvement feedback as modest and occurring over months. It does not demonstrate unrestricted recursive improvement, ethical goal selection or Leviathan's architecture. Results and deployments were not independently reproduced here.",
      "changes": "Read v1 task definition, code search, evaluation, selected results and discussion. Reported code and deployments were not reproduced; supplied evaluators constrain the demonstrated discovery process.",
      "checkedAt": "2026-10-04",
      "verificationStatus": "Primary source reviewed; no independent reproduction",
      "relatedUrls": [
        "https://arxiv.org/html/2506.13131v1",
        "https://doi.org/10.48550/arXiv.2506.13131"
      ]
    }
  ]
}
