Creating a digital poet

2026-02-18

AI Summary

This study investigates whether large language models can generate artistically valuable and stylistically coherent poetry without fine-tuning, relying solely on prompt engineering—an approach that challenges conventional notions of human creativity and authorship. Over a seven-month period, the project employed an expert feedback–driven iterative prompting strategy to guide the model through in-context learning, enabling it to gradually develop a distinctive poetic voice and a consistent authorial persona. The resulting poetry collection underwent blind evaluation, with 52% of the AI-generated poems misattributed to human authors, and was subsequently published by a commercial press. This work demonstrates for the first time that prompt engineering alone can support sustained, coherent creative expression, thereby expanding the boundaries of AI’s role in artistic creation.

Technology Category

• Natural Language Processing: Prompt Engineering / Prompting
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Can a machine write good poetry? Any positive answer raises fundamental questions about the nature and value of art. We report a seven-month poetry workshop in which a large language model was shaped into a digital poet through iterative in-context expert feedback, without retraining. Across sessions, the model developed a distinctive style and a coherent corpus, supported by quantitative and qualitative analyses, and it produced a pen name and author image. In a blinded authorship test with 50 humanities students and graduates (three AI poems and three poems by well-known poets each), judgments were at chance: human poems were labeled human 54% of the time and AI poems 52%, with 95% confidence intervals including 50%. After the workshop, a commercial publisher released a poetry collection authored by the model. These results show that workshop-style prompting can support long-horizon creative shaping and renew debates on creativity and authorship.

Problem

• machine poetry
• creativity
• authorship
• artificial intelligence
• digital poet

Innovation

• in-context learning
• iterative prompting
• AI creativity
• authorship
• large language models