AI Poetry Challenge
The Poetry Challenge invites participants to craft poems using generative AIs and reflect on the nature of AI-generated text and creativity.
The purpose
Reflect on the quality of AI generated poetry, AI’s algorithmic bias, and the ontology of creativity.
Discuss and share strategies for poetry generation prompts, in particular iterative or chain-of-thoughts prompting to get better results.
Compare different generative AIs’ capability on writing.
Recognise the impact of fine tuning and training on generative AI’s output capability.
What you need
Setting it up
Participants need access to generative AI tools, preferably at least 2 to compare differences in capability.
How long does it take?
For asynchronous online play, we suggest it will take individual participants 5-10 minutes. We suggest leaving the game open for a week to 10 days depending on the game host’s availability for engagement.
For synchronous in person play, we suggest 5-10 minutes of individual game play and discussion time.
How it works
Select a generative AI tool and direct it to compose a poem. E.g. “Write a limerick in praise of statistics for biological sciences.” Refine your prompt as appropriate.
Repeat the same prompt in a different generative AI tool.
Compare the outputs.
Suggested follow-up
Compose a short reflection on your experience with the image creation process, including any insights or challenges encountered.
Reflect on the nature of creativity. Is generative AI creative? Can outputs from generative AI truly demonstrate beauty, originality and creativity? Do you feel differently when the output is in a different format–image, audio, video?
Have generative AI generate a humorous or funny poem. How well does it fare?
For asynchronous online, we suggest participants share their screenshots and reflections in an online forum. The game host should plan on reviewing submissions, encouraging engagements, and assigning points on the leaderboard if there’s one.
Where it works well
If your participants are familiar with poetry in a language other than English, it can prove insightful on how well generative AI can imitate poetic structure in another language and when it becomes apparent that generative AI is merely translating.
What to watch out for
The challenge may pose challenges for participants unfamiliar with poetry writing or evaluating the quality of poems.
Authorship
This entry was written by Cecilia Lo.