Can AI Achieve Greatness in Poetry? Examining LLMs' Artistic Limitations
By
networked
4mo ago· 19 min readenInsight
100/100
Golden Brown
Bagelometer↗
Toasted golden, schmeared with insight. Top of the rack.
Score100TypeanalysisSentimentneutral
Summary
The article examines whether large language models (LLMs) can produce truly great poetry, moving beyond technical proficiency to explore the philosophical question of what constitutes greatness in poetry. The author, who has studied LLM poetry for over five years, acknowledges that modern LLMs have impressive technical abilities in rhyme, meter, metaphor, and wit, but questions whether any LLM output can achieve genuine artistic greatness. The piece explores the nature of poetic greatness and whether AI-generated poetry can reach that level, referencing experiments by Gwern and Mercor.
Key quotes
· 5 pulledWith every new model, the technical abilities improve: pro models can produce lines and stanzas, handle rhyme and meter, and create surprising and witty turns of phrase, produce impressive metaphors.
Does any LLM output rise to the level of good poetry, or even great poetry? It's a different question than studies about favorable ratings ask.
I'm interested in greatness, what it is, and can LLMs get there.
Technique is not the problem.
My definition of 'great' poetry, which I've used over...
Experiments by Gwern and Mercor
