• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Creating a digital poet View PDF HTML (experimental)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.
Article Summaries:
- A seven‑month workshop used a large language model to create a “digital poet” through iterative in‑context expert feedback, without any model retraining. Over the course of the sessions, the model produced a distinctive poetic style, a coherent corpus, a pen name, and an author image. In a blind authorship test involving 50 humanities students and graduates, participants could not reliably distinguish the AI poems from those of well‑known poets, with identification rates near chance. Following the workshop, a commercial publisher released a poetry collection credited to the model, prompting renewed discussion about creativity, authorship, and the role of AI in artistic production.
Sources: