THE PROBLEM OF (LACK OF) MEMORY IN NARRATIVES GENERATED BY ARTIFICIAL INTELLIGENCE

Authors

  • Fabio Cardoso Universidade Estadual Paulista (UNESP)

DOI:

https://doi.org/10.14244/2179-1465.RG.2023v14i3p44-53

Keywords:

Large Language Models, Memory, Audiovisual Screenplay

Abstract

The evolution of artificial intelligence text generation tools opens up the possibility of creatively using technology for the creation of audiovisual scripts. Language models like ChatGPT are capable of generating complex artistic content with user input. This enables the emergence of a new form of audiovisual content: continuous script generation. However, inherent technical difficulties in the current model of creating such software limit the effectiveness and scope of this form of creation. This article aims to investigate the most significant problem of this limitation, which is the lack of memory in LLM algorithms.

Downloads

Download data is not yet available.

Author Biography

Fabio Cardoso, Universidade Estadual Paulista (UNESP)

Doutor em Comunicação pela UNESP – Universidade Estadual Paulista.

References

DU, W.; HAN, Q. Research on Application of Artificial Intelligence in Movie Industry. 2021 International Conference on Image, Video Processing, and Artificial Intelligence. Shanghai: [s.n.]. 2021.

GREIMAS, A. J.; COURTÉS, J. Dicionário de Semiótica. São Paulo: Contexto, 2008.

KAPLAN, A.; HAENLEIN, M. Siri, Siri, in my hand: Who's the fairest in the land? On the interpretations, illustrations and implications of artificial intelligence. Business Horizons, 2019.

NOTHING, Forever. Direção: S. HARTLE e B. HABERSBERGER. [S.l.]: Mismatch Media. 2023.

WEIZENBAUM, J. ELIZA - a computer program for the study of natural language communication between man and machine. Communications of the ACM, jan. 1966.

RUSSEL, S.; NORVIG, P. Artificial Intelligence: A Modern Approach. 4. ed. [S.l.]: Pearson, 1995.

Downloads

Published

2024-05-06

How to Cite

CARDOSO, F. . THE PROBLEM OF (LACK OF) MEMORY IN NARRATIVES GENERATED BY ARTIFICIAL INTELLIGENCE. Revista GEMInIS, [S. l.], v. 15, n. 1, p. 44–53, 2024. DOI: 10.14244/2179-1465.RG.2023v14i3p44-53. Disponível em: https://revistageminis.ufscar.br/index.php/geminis/article/view/848. Acesso em: 30 jun. 2024.

Issue

Vol. 15 No. 1 (2024): AI narratives: trends in audiovisual production - Part 2

Section

Dossier - AI Narratives: Trends in Audiovisual Production

License

Copyright (c) 2024 Fabio Cardoso

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Authors who publish in this journal agree to the following terms:

a. Authors retain copyright and grant the journal the right of first publication, with the work simultaneously licensed under a Creative Commons Attribution License that allows sharing of the work with acknowledgment of authorship and initial publication in this journal.

b. Authors are authorized to assume additional contracts separately, for non-exclusive distribution of the version of the work published in this journal (eg, to publish in an institutional repository or as a book chapter), with acknowledgment of authorship and initial publication in this journal.