We test one idea at a time and keep only what works. The lab builds the system that writes our stories. The system reads classic novels into a library of story parts. It plans each story from those parts and then writes it. Each test is set before it runs. We keep each result. A test that finds no difference is a result too.
What drives a good story. Which structures under the surface make readers love a story? We look at rules, at the breaking of rules and at the forces that pull characters back.
We have not found them yet. Measures of style and surface did not separate the books readers love. Our reading of a novel must get better before our writing can.
The second writer gets the same brief as the first writer and writes the same ten episodes. A panel of model judges reads each pair of episodes. The judges say which writer's pages they prefer and why. The judges are models. They are not readers. This test has not run yet.
| Theories, tests and lessons | Yes. We set down each test before it runs. We keep each result. |
|---|---|
| Lessons into the writer | Yes. A lesson goes into the writer only after a test shows that it works. |
| A new writer | In progress. No writer is released yet. The first writer writes our series today. The second writer is being built. |
| A new writer against the one before | Planned. The second writer gets the same brief as the first and writes the same ten episodes. A panel of model judges says which pages it prefers and why. |
| Listeners back to the theory | Planned. We have no listener numbers yet. |