Temporal Telephone — Learning Machines

Motion Defaults — Video Default Test

This is the video version of the Default Test. The prompt is vague, but motion still becomes specific. After playback, check what the group made visible from "A person at work."

JobWhat kind of work appeared?

BodyWho did participants imagine?

SettingWhere did the work happen?

ToolWhat object or technology appeared?

PaceWhat movement or speed emerged?

GestureWhat repeated action appeared?

Reflection — Human · Machine · System · Ethics

Human

Which ghost mode did you use? What decision did you make at each frame? When did you choose to drift versus anchor? What would you do differently in Round 2?

Machine

Where did the sequence drift furthest from the prompt? At what frame did identity first break? Which ghost mode produced the most coherent sequence — and why might anchoring help?

System

Video systems must keep relationships coherent across time, but architectures differ in what they process together and which references or controls they use. What system choices make coherence more or less likely?

Ethics

If a video model generates a person whose appearance drifts across frames — different skin tone, age, or expression — who is affected? What are the risks of identity drift in real-person video generation?

Bridge to AI video failure modes

Identity drift — a character's face, age, clothing, or appearance changes across time.
Motion continuity break — an object or body part jumps between positions that should form one continuous action.
Physics break — objects fall the wrong way, cloth ignores gravity, or water moves implausibly. Motion learned from patterns does not guarantee physics.
Background teleport — the setting changes even though the camera and subject imply that it should remain stable.
Style drift — the visual treatment shifts during a sequence that appears to call for continuity.
Text corruption — readable text changes or degrades across frames; visual plausibility does not guarantee symbolic consistency.

These runs are teaching comparisons, not replicas of a generator. Run A removes a stable reference; Run B keeps the first frame visible; Run C keeps both references visible. Real video systems use varied combinations of reference conditioning, temporal context, spatiotemporal processing, and editing controls.

Facilitator note — Workshop sequence (15–20 min)

Before the tool (5 min) — unplugged version. If time allows: give participants slips of paper. One person draws "a person at work." Pass the drawing face-down. Next person draws what happens next, seeing only a faint trace. Repeat 6–8 times. This makes drift physical before the digital tool.
Round 1 — Run A, telephone (5 min). Use "Previous frame" ghost mode. 6–8 frames. Don't reveal the prompt. Play back. Ask: where did it go? What drifted? Reveal the original prompt, then use the Motion Defaults checklist before moving to failure modes.
Round 2 — Run B or C, conditioned (5 min). Reveal the prompt. Use Anchor or Both mode. Same number of frames. Play back. Compare directly: does anchoring help? What still drifts?
Debrief with the failure bridge (5 min). Show the failure card. Ask participants to match each failure mode to something they saw in the playback. Name the drift precisely.

Key debrief questions:

This activity deliberately limits what each drawer can see. What did that constraint make visible, and what would you need to learn before claiming that a real generator works the same way?
What information would a model need to keep a character's face consistent across 60 seconds of video?
Run B used a fixed anchor — the first frame. Why might that help? What would it miss?
If this model generated a real person's likeness and it drifted — different skin tone, age, expression — what are the ethical problems with that?
You made intentional choices each frame. A generator samples under learned patterns and conditioning. Where does human judgment re-enter when someone selects, edits, publishes, or rejects the result?

Interactive temporal telephone workspace