New on Truffle

Type a scene.
The agent shoots it.
The eval grades it.

Take is a small text-to-video studio where the evaluation loop is the product. Describe a shot. An agent writes the direction, Luma Ray3.2 renders it, and a four-level cascade decides whether the take survives: deterministic gates, computer-vision lanes, a vision-language judge, and a bounded retake policy. You watch every step happen live.

0 / 800

5 takes per visitor per day. Every piece ships with its full eval receipt.

The cascade

Generation is the easy half. Take's pipeline treats every render as a claim that has to survive four levels of scrutiny before it gets published.

  1. L0

    Deterministic gates

    ffprobe decode, duration, resolution, framerate. Then pixel gates: not black, not frozen. A clip that fails here never wastes a judge call.

  2. L1

    Computer-vision lanes

    Frame-difference flicker, Farneback optical flow, CLIPScore prompt alignment, DINOv2 identity drift against frame zero. The temporal questions a vision-language model answers at chance level are owned by code.

  3. L2

    Vision-language judge

    A timestamped contact sheet goes to a frontier judge that writes its rationale before its rating, on six axes: fidelity, aesthetics, consistency, motion, semantics, physics. Discrete levels, not fake-precision decimals.

  4. L3

    Bounded decision

    Deterministic accept-or-retake. Any axis at poor or below triggers a retake with the judge's advice folded into the next composition. Three attempts, then the best surviving take stands.