Initial Development and Evaluation of the Creative Artificial Intelligence through Recurring Developments and Determinations (CAIRDD) System

TL;DR

This paper introduces the CAIRDD system, an iterative approach to enhance the creativity of large language models by refining their outputs through concept injection, aiming to better emulate human-like creativity.

Contribution

It presents the initial development of the CAIRDD system and evaluates its key components to improve LLM creativity via iterative refinement.

Findings

System components show promising improvements in creative output.

Iterative concept injection enhances LLM-generated content.

Initial evaluation indicates potential for more human-like creativity.

Abstract

Computer system creativity is a key step on the pathway to artificial general intelligence (AGI). It is elusive, however, due to the fact that human creativity is not fully understood and, thus, it is difficult to develop this capability in software. Large language models (LLMs) provide a facsimile of creativity and the appearance of sentience, while not actually being either creative or sentient. While LLMs have created bona fide new content, in some cases - such as with harmful hallucinations - inadvertently, their deliberate creativity is seen by some to not match that of humans. In response to this challenge, this paper proposes a technique for enhancing LLM output creativity via an iterative process of concept injection and refinement. Initial work on the development of the Creative Artificial Intelligence through Recurring Developments and Determinations (CAIRDD) system is presented and the efficacy of key system components is evaluated.