Judgment
The machine has a favorite.
Did you like it?
- What it does
- Explore a hundred software sketches, compare machine recommendations with three random alternatives, and see whether your choice survives an automatic pass.
- Who it is for
- For anyone curious about what remains to judge when software becomes easier to generate.
Notes from the making (2)
- Began as a visual brief about how attention and judgment are allocated across many possible solutions.
- Released an interactive explorer with twenty interface models and five write mechanisms. All, machine-recommended and randomly drawn views; editable sample notes; reversible simulated acceptance. Recommendations follow local rules. No study results are claimed.
This page stays up whatever happens to the experiment. The record it is drawn from is public: /api/nothing/experiments.