Four Pillars
Four Pillars. GSD is
the Fourth.
Each one changed what AI could make. GSD changes the complexity class.
Pillar One · Language
Attention
Θ(N²) per layer
Gave us language models.
01
Pillar Two · Clips
Diffusion Transformer Θ(L·M²·N²)
Gave us today’s video models.
02
Pillar Three · Streams
State Space Model
Θ(N)
Gave us long streams.
03
Pillar Four · Wishtales GSD
Topological Graph World Model
O(M log N + N)
The whole video, every layer, in one pass.
04
How GSD Works
Plan Once. Render Once.
GSD understands the whole story first, then executes it.
01
02
03
Symbolic Layer
Retrieve O(M log N)
Finds every character, voice and sound the story needs in the world graph.
Combinatorial Optimisation
Optimise O(1) amortised
Locks one quasi deterministic blueprint. Every sync decision, made once.
Combinatorial Optimisation
Render O(N)
Six layers from one shared state, in a single linear pass.
“Synchronisation is a property of the architecture, not a correction applied to the output.”
120s+
One shot, 154 s demonstrated
≈240 s
To render 120 s of six layer 4K
≈67x
Realised inference efficiency
Zero
Denoising steps
Measured on NVIDIA Blackwell B300.
Topological Identity
Shape, Not Coordinates.
One signature holds identity across every modality, every scene and every edit.
98.99%
Prompt to physics adherence
Prompt constraint adherence
98.89%
Across 10,000 outputs, measured on NVIDIA Blackwell B300.
Benchmarks
Five Numbers That Define the Gap.
Version 2026 evaluation against the commercial frontier.
29 of 39
Benchmark categories led
Safe by Construction
Harmful concepts are left out of the world graph, so they cannot be generated.
Governed for Enterprise
Brand rules and prohibited concepts are enforced inside the graph, as the video is made.