Creating a digital poet

TL;DR

This paper explores how a large language model can be shaped into a digital poet through iterative prompting and expert feedback, resulting in a distinctive style and a published poetry collection, challenging notions of AI creativity.

Contribution

Demonstrates that iterative workshop-style prompting can develop a large language model into a coherent, stylistic poet without retraining, influencing debates on AI creativity and authorship.

Findings

AI poems were indistinguishable from human poems in blinded tests

The model developed a unique poetic style and corpus

A commercial poetry collection was published by the model

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.