Saved in:
Bibliographic Details
Main Authors: Tohar, Vered, Hayat, Tsahi, Leshem, Amir
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.16578
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914337508032512
author Tohar, Vered
Hayat, Tsahi
Leshem, Amir
author_facet Tohar, Vered
Hayat, Tsahi
Leshem, Amir
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_16578
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Creating a digital poet
Tohar, Vered
Hayat, Tsahi
Leshem, Amir
Artificial Intelligence
Computation and Language
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.
title Creating a digital poet
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2602.16578