machine vs me, over time

evolution

No poem is labelled human or machine here or anywhere on this site. What this page shows is each night's count, once the show is closed.

how often the room prefers the machine's poem

the room's verdict, show by show

the machine and me · what improved from one rep to the next

what i shipped before each rep

1. 1
   carnation.exemay 2025 · Paris and Barcelona

   • The first machine: a small OpenAI model (gpt-4.1-nano) fine-tuned on a poetry corpus, once in French and once in English.
   • A long system prompt naming a pantheon of poets. The French set is public on Hugging Face (madihalim/carnation-fr).
2. 2
   reinforcement.exenovember 2025 · DevConnect, Buenos Aires

   • A new gpt-4.1-nano fine-tune on a larger English corpus.
   • Poems the room had preferred at earlier shows were folded back into the training data: the series starts feeding itself.
3. 3
   versus.exenovember 2025 · Mozilla AI residency, San Francisco

   • A second version of the English carnation fine-tune, on a revised dataset.
   • The prompt moved to English only.
4. 4
   hard.exedecember 2025 · TIAT, San Francisco

   • A new gpt-4.1-nano fine-tune, hard-eng. Its dataset is public (madihalim/hard-eng).
   • Other poets' work joined the corpus, so the machine stopped learning from one voice only.
5. 5
   reverse.exemarch 2026 · Media Archaeology Lab, Boulder

   • No new training run on record for this rep: the machine most likely carried over from hard.exe.
   • After the show the separate show sites were folded into this one platform, so every rep now lives in one archive.
6. 6
   frontiere.exemay 2026 · Index Space, Brooklyn

   • An evaluation harness, and a rubric of what this audience rewards, read out of the archive and scored by a council of AI judges.
   • Four preference fine-tunes (DPO) on 33 audience pairs. Offline, none of them matched a frontier model given a rich prompt and a few past pairs.
   • Shipped that instead: Claude Opus 4.7, a rich prompt, five past pairs in context and a strict length cap.
7. 7
   recover.exejune 2026 · Porto, performed remotely

   • Six in-context pairs instead of five, and the base model moved to Claude Opus 4.8.
   • A gpt-4.1 preference fine-tune retrained on 36 pairs as a control. Offline it scored below the in-context approach.
   • A remote stage and control system, two-step voting, vote undo and a sandbox mode for rehearsal.
8. 8
   pass.exeseptember 2026 · UN General Assembly week, New York

   • The prompt moved server-side into a private recipe. The machine now checks its own tells, form and stock words, and rewrites before it answers.
   • The base model was chosen by a seven-model bake-off scored on detectability, not on judge taste. No fine-tune this time.
   • The audience rubric was rebuilt author-blind (v2). This page gained the passing index, the night-by-night verdict and this log.
9. 9
   tame.exeoctober 2026 · MozFest, Barcelona

   • The self-check became a bar, not a target: three drafts at once, the tells only decide pass or fail, and the pick is the draft least like the night's earlier poems.
   • The recipe became versioned blocks the poet edits himself, with a compare page to hear several models on one theme and a knobs panel for what each model still lets you turn.
   • Every machine poem is logged with its served model, recipe version, knob values and drafts, so an off-recipe poem cannot pass unnoticed again.

method, rubric, judges, models