out ofdistribution

A model guesses your next move. Keep it guessing.

Your choices and the model’s guesses Your last twelve moves appear here, newest at the bottom. Solid dots mark your choice. Rings mark the guess. A red line joins them when the guess is wrong.

tap a side or use the ← → keys

The guess is made before you choose.

0 misses / 0 moves

longest run: 0

© 2026 Worth Building · An independent project

out of distribution

adjective, machine learning

  1. Of an input: unlike the data a model was trained on; outside its familiar range.
  2. Of a person: the same, said with admiration.

Engineers keep a phrase for the unfamiliar. It can show up in incident reports, said with a sigh, when the world stops resembling the examples. Little in the training data prepared the system for what just walked in.

A model trained on past examples can still meet something it does not know how to place. The phrase carries a small possibility: you were not implied by the past.

This page brought a small model. It has one job: to guess which button you will press, before you press it. It learns from every press. A rhythm, a repeated run, a habit you did not know you had. When it has too little to go on, it guesses.

The drawing keeps the evidence. A ring for its guess. A dot for your move. When the two part ways, a red line joins them. Your choices stay in this tab. Press “forget me” and its history is gone.

The score belongs to this small model and this sequence of choices. A person is a larger subject.

To be predicted is to be, in some small way, repeated. But the past is full of things someone did not see coming: a strange friendship, a sentence, a different way to spend a life. A model can meet something unfamiliar and return an error. We can meet the same thing and feel a beginning.

Same event, two readings. The machine files a failure report. We frame it.

May you always be slightly beyond the training data.