Creating a digital poet
This work addresses the problem of machine creativity and authorship for the arts and humanities community, though it is incremental in applying existing prompting methods to a new creative domain.
The researchers tackled the problem of whether a machine can write good poetry by shaping a large language model into a digital poet using iterative expert feedback over seven months, resulting in a poetry collection published by a commercial publisher and a blinded test where human and AI poems were indistinguishable at chance levels (e.g., AI poems labeled human 52% of the time).
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.