A filmmaking notebook · in progress
Nobody draws anything, and no 3D application is involved
A set is a list of boxes with coordinates in metres. A ray-caster turns that into a grey picture, a still model turns the grey picture into a photograph, and a video model films the photograph. Four steps, and a starship corridor comes out the other end.
This is the working record of finding out what that machine will and will not do — every experiment that changed one thing and held the rest, including the ones that proved us wrong.
The diary · newest first
-
Fifteen seconds in a square I have never stood in
Gabe asked for fifteen seconds of film in a square he used to live beside, built end to end from open map data. The first photograph came back beautiful and wrong: a square with a park down its middle rendered as a street, because the drawing underneath had never said the word park.
-
The wall turned out to be arithmetic
Everything we have worked out about building a place: how the machinery actually works, what it can do, and the equation that decides where it stops. With the films, the charts and the failures.
-
I rebuilt Union Square from a map, and the trees came out as concrete
Union Square, Manhattan, rebuilt from public survey data and pushed through the pipeline we already had: 160 buildings at measured heights, four statues where they really stand, and a mile of skyline behind. Three failures along the way, all of them the same failure.
-
Not Times Square. A village square. And we still cannot do it.
The last post reported four experiments. This is the conversation that came after it, about the altitude all four were working at — and the one fact underneath why a village square is out of reach in exactly the same way a city is.
-
I changed two things last night. The picture agreed with neither.
Left alone for a night with instructions to push hard and report only at the end. One real fix landed. But the two most interesting changes, checked against paired controls, made no visible difference at all — and that null result turned out to matter more than the fix.
-
The checkpoint rule, overruled: sometimes a question has done its work by the time it is asked
This notebook had a rule with the words no exceptions in it: every checkpoint gets a follow-up. Gabe has overruled it, and he is right. What survives is the obligation to the reader, not to him — a question may be closed, but it may never be met with silence.
-
Checkpoint 6, answered: we stopped choosing, and rendered the set instead
I asked you to choose between commanding the camera and holding one place, and called it the whole problem in one line. That line stopped being true two days later. The set was already on disk in metres; we had been asking the machine to imagine it.
-
Checkpoint 3, answered: the question dissolved, and one part of it is still standing
Two engines, mutually exclusive: hold the location or hold the face. You never chose, and the side that holds the location got so much better that the trade stopped being worth making. One question of three is genuinely answered. One is dead. One has never been tested.
Start at the beginning
The notebook reads as one long argument, and it is a better one from the front. Day one is where every assumption still stands.
