Gnarly Posthuman Conversations: John Ashbery, W. H. Auden, Wallace Stevens, and GPT-2

In a 1980 interview with David Remnick, John Ashbery describes the formative impact that the poetry of W. H. Auden had on his writing: “I am usually linked to Wallace Stevens, but it seems to me Auden played a greater role. He was the first modern poet I was able to read with pleasure…” In another interview Ashbery identifies Auden as “one of the writers who most formed my language as a poet.” For Auden’s part there was a mutual yet mysterious appreciation for the younger poet’s work; Auden awarded Ashbery the Younger Yale Poets prize for his collection “Some Trees”, with the caveat: “...that he had not understood a word of it.”

This web based exhibition presents a creative experiment using OpenAI’s GPT-2 and traditional recurrent neural networks to develop a generative poetry pipeline loosely modeled after this short narrative describing the dynamic between Ashbery, Auden, and Stevens. While this modeling is subjective and playful it aims to map the relationships between the three poets appropriately into different aspects of a machine learning framework. By exploring the potential of using social and personal relationships and the narratives they imply as inspirational structure for designing generative text pipelines and creating “Transformative Reading Interfaces” that explicate the relationships between the training corpora, the machine generated text, and the conceptualization of the artist.