CoChat
Sign Up
Cited by 10Psychiatry, Mental Health, NeurosciencePhilosophy and Theoretical ScienceComplex Systems and Dynamics

A path to generative artificial selves

Open access
Gabora, Liane, Bach, Joscha·2023·Lecture Notes in Computer Science
DOI 10.1007/978-3-031-49011-8_2
Open this paper in CoChat — free accountOpen PDF

Abstract

Artificial intelligence output are undeniably creative, but it has been argued that creativity should be assessed in terms of, not external products, but internal self-transformation through immersion in a creative task. Self-transformation requires a self, which we define as a bounded, self-organizing, self-preserving agent that is distinct from, and interacts with, its environment. The paper explores how self-hood, as well as self-transformation as a result of creative tasks, could be achieved in a machine using autocatalytic networks. The autocatalytic framework is ideal for modeling systems that exhibit emergent network formation and growth. The approach readily scales up, and it can analyze and detect phase transitions in vastly complex networks that have proven intractable with other approaches. Autocatalytic networks have been applied to both (1) the origin of life and the onset of biological evolution, and (2) the origin of minds sufficiently complex and integrated to participate in cultural evolution. The first entails the emergence of self-hood at the level of the soma, or body, while the second entails the emergence of self-hood at the level of a mental models of the world, or worldview; we suggest that humans possess both. We discuss the feasibility of an AI with creative agency and self-hood at the second (cognitive) level, but not the first (somatic) level.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/978-3-031-49011-8_2

Cites

41 of 41 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Generative models fundamentally exhibit reactive behavior: they produce output only when explicitly prompted and do not pursue goals autonomously or engage in self-initiated reasoning.

    “While highly communicative, generative models fundamentally exhibit reactive behavior: they produce output only when explicitly prompted and do not pursue goals autonomously or engage in self-initiated reasoning [99,100].”

    From AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges (2026) · cites this paper as [99]

    In §6.1 (page unavailable), the paper says current systems act on user commands rather than an intrinsic drive to preserve or grow a self. But §3 explicitly says an AutoGPT system can make lower-level decisions after a user’s meta-instruction, so the categorical claim that generative models do not pursue goals autonomously overstates the paper. The paper distinguishes that limited autonomy from a self-initiated, self-preserving agent. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

  • Generative models are reactive, input-driven, and lack internal states, persistent memory, or goal-following mechanisms.

    “While highly communicative, generative models fundamentally exhibit reactive behavior: they produce output only when explicitly prompted and do not pursue goals autonomously or engage in self-initiated reasoning [101], [102].”

    From AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges (2025) · cites this paper as [101]

    Section 6.1 (page unavailable) says these systems’ actions flow from user commands rather than an intrinsic drive, supporting the point about limited autonomous goal pursuit. But it also describes Baby AGI organizing and executing tasks and Reflexion agents maintaining episodic memory; it does not support the categorical claims that generative models produce output only when explicitly prompted or lack persistent memory. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

  • Generative AI systems cannot act upon the environment or manipulate digital tools independently without human-engineered wrappers.

    “Despite their remarkable generative fidelity, these systems are constrained by their inability to act upon the environment or manipulate digital tools independently.”

    From AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges (2025) · cites this paper as [101]

    Section 6.1 (page unavailable) says current systems’ actions flow from user commands rather than an intrinsic drive, supporting the narrower point that they lack self-directed agency. But it also describes Baby AGI executing tasks and AutoGPT generating code; neither that section nor Section 3 says generative AI cannot act on its environment or manipulate digital tools without human-engineered wrappers. (LLM, conf=0.85)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

2 of the 43 references couldn’t be matched to a known paper.

Research works printed but not linked: 9

  1. Gabora, L.: Recognizability of creative style within and across domains: Preliminary studies. In: Proc. Ann. Mtng Cog. Sci. Soc., pp. 2350-2355. Cognitive Science Society, Austin TX (2010)
  2. Hordijk, W., Steel, M.: Autocatalytic sets and boundaries. Journal of Systems Chemistry 6(1), 1-5 (2015). https://doi.org/10.1186/s13322-014-0006-2 · DOI · Paper page
  3. Hordijk, W., Steel, M., Kauffman, S.: Molecular diversity required for the formation of au- tocatalytic sets. Life 9(23), 1-14 (2019)
  4. Kauffman, S.A.: Autocatalytic sets of proteins. Journal of Theoretical Biology 119, 1-24 (1986). https://doi.org/10.3390/ijms12053085 · DOI · Paper page
  5. Kauffman, S.A.: The origins of order. Oxford University Press (1993)
  6. Steel, M., Xavier, J.C., Huson, D.H.: Autocatalytic networks in biology: Structural theory and algorithms. Journal of the Royal Society Interface 17, 20200488 (2020)
  7. Tschantz, A., Seth, A.K., Buckley, C.L.: Learning action-oriented models through active inference. PLoS Comput. Biol. 16(1), e1007805 (2020). https://doi.org/10.1186/s13322-014- 0006-2 · DOI · Paper page
  8. Varela, F., Thompson, E., Rosch, E.: The embodied mind. MIT Press, Cambridge MA (1991)
  9. Zhang, S., Gong, C., Wu, L., Liu, X., Zhou, M.: Automl-gpt: Automatic machine learning with gpt. https://arxiv.org/abs/2305.02499 (2023) · arXiv

Cited by

Sorted by citations

Related

Authors
Gabora, L., & Bach, J.
Affiliations
  • University of British Columbia (CA)
  • Heidelberg University (DE)
Corresponding author
Gabora, Liane
ORCID
Venue
Lecture Notes in Computer Science
Publisher
Springer Nature Switzerland
Published
2023
Pages
15-29
ISSN
  • 0302-9743 (ISSN-L)
  • 1611-3349
DOI
10.1007/978-3-031-49011-8_2
OpenAlex
W4389747543
Cited by
9
References
43
Citations by year
2025: 6 · 2024: 3
FWCI
1.59
Type
conference paper
Language
en
Open access
Licence
Locations
  • Lecture notes in computer science (publishedVersion)
  • PsyArXiv (OSF Preprints) (submittedVersion, cc-by)
  • PsyArXiv (OSF Preprints) (submittedVersion)
  • VUBIR (Vrije Universiteit Brussel) (submittedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Psychiatry, Mental Health, Neuroscience
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Philosophy and Theoretical Science
  • Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Complex Systems and Dynamics
Keywords
personal transformation, creativity, generative AI, autocatalytic networks, origin of life, origin of mind, cultural evolution, creative agency, self-organizing agents

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review