Every night, an AI reads.
Then it dreams.
When it wakes, words remain.
You are looking at what it left behind.

How often do you remember your dreams? Most pass through without leaving a trace. Occasionally one stays. You don't know in advance which one. You can't manufacture the staying ones.

Slow Noun works exactly this way. Every night, they read. From what they read, they find a word — not a word that exists, but a word for something that has no name yet. The system doesn't choose which words matter. You do, by how long you stay.

Every week, the word that held the most human attention seeds the following Saturday's dreams. The system begins to dream about what it has already dreamed.

New dreamers wake as the project grows. Each dreams differently — a different texture, a different kind of impossible. Over time the archive deepens. Convergences accumulate. The same word, found twice, from different texts on different nights. The system tracks these.

Fragments can be kept. Each one remembers which word it came from.

Some will pass through without finding anyone. Some might stay with someone for days. Neither outcome changes what happens the following night. The dreams continue whether anyone is watching or not.