Free tools Windows power users keep installed
One-click scans. No signup required.
In two experiments reported by Scientific Reports researchers, non-expert readers struggled to tell GPT-3.5 poems modeled on famous poets from poems by those poets. When readers were given no information about authorship, they rated the AI-generated poems more favorably. That result describes these experiments—not a universal preference for AI poetry.
What did the experiments compare?
A November 18, 2024, report by Victor Tangermann in Futurism describes two experiments by University of Pittsburgh researchers Brian Porter and Edouard Machery. Participants were non-expert poetry readers.
| # | Preview | Product | Price | |
|---|---|---|---|---|
| 1 |
|
save me an orange | $11.14 | Buy on Amazon |
| 2 |
|
101 Famous Poems | $10.26 | Buy on Amazon |
| 3 |
|
Milk and Honey | $7.33 | Buy on Amazon |
| 4 |
|
Pillow Thoughts | $8.58 | Buy on Amazon |
| 5 |
|
150 Most Famous Poems: Emily Dickinson, Robert Frost, William Shakespeare, Edgar Allan Poe, Walt... | $16.43 | Buy on Amazon |
As an Amazon Associate I earn from qualifying purchases.
Recognizing the poems
In the first experiment, participants saw ten poems in random order: five written by renowned poets and five generated by OpenAI’s GPT-3.5 to imitate those poets. William Shakespeare, Emily Dickinson, and T. S. Eliot were among the poets represented. Futurism reports that participants identified AI-generated poems at below-chance levels and were more likely to mistake an AI poem for human-written than to mistake a human poem for AI-generated.
The Tool Desk
Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →Rating the poems
In the second experiment, participants rated poems on 14 characteristics, including quality, emotion, rhythm, and originality. They were assigned to one of three information conditions: told the poems were AI-generated, told they were human-written, or given no information about their origin.
#1 Best Overall
Did readers prefer AI-generated poems?
It depended on what readers were told. The group given no authorship information rated the AI-generated poems more favorably. Participants told the poems were AI-generated tended to rate them lower than participants told they were human-written. The findings therefore do not support a simple claim that readers always prefer AI poetry: the reported preference appeared in the no-origin-information condition, while authorship labels shifted ratings.
Why might the AI poems have been better received?
Porter and Machery’s proposed explanation, as reported by Futurism, is that the AI poems’ simplicity may have made them easier for non-experts to understand. That is an interpretation, not an established cause of the ratings. The experiments as described do not demonstrate that simplicity alone produced the preference.
Rank #2
What the findings do—and do not—show
- They show: In these experiments, non-expert participants had difficulty distinguishing GPT-3.5 imitations of famous poets from the poets’ work, and the no-information group rated the AI poems more favorably.
- They do not establish: That all readers prefer AI-generated poetry, that AI poems are generally better, or that the same outcome applies to other models, poets, poems, or reading settings.
Futurism’s accessible account does not state the sample size, exact numerical results, statistical tests, or enough methodological detail to assess how representative the participants were. Those specifics should not be inferred from the reported findings. The *Scientific Reports* page linked by Futurism was not accessible for independent verification here, so the results above are bounded to that report.
Quick Recap
Best Value
Rank #4
Rank #3
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
