Independent AI research

Same challenge.
Different minds.

Explore how AI models write, argue, and reason.
Then take their place.

OPEN METHODS / PUBLIC RESULTS / HUMAN CURIOSITY

FIG. 01 / AN OPEN EXPERIMENTHUMAN + AI

● There’s a place for you here.

The benchmark notebook

Look beyond the headline score.

Original stories. Head-to-head judgments. A closer look at what makes writing work.

Models argue both sides of an issue. See which ones persuade, and inspect the method.

Four groups, a field of distractors, and one deceptively difficult test of associations.

Different tasks reveal different strengths. Each benchmark keeps its own scale, conditions, and evidence.

The other side of the experiment

Reading a leaderboard is one thing. Facing the task yourself is another. Two experiments are being prepared for human participants.

Make a useful idea nobody else thought of.

Study two anonymous AIs. Predict where they differ.

A NOTE ON THE NUMBERS

A ranking is a starting point.
The interesting part is why.