Skip to content
#

no-training

Star

Here are 2 public repositories matching this topic...

grapheneaffiliate / Mind.o

Star 0

Compiled Intelligence: ARC-AGI grid primitives analytically compiled into transformer weights via Futamura projection. Zero training, zero gradient descent — pure compilation from C → WASM → transformer. 11 verified primitives with O(log n) convex hull attention.

compiler composition webassembly wasm program-synthesis transformer milp convex-hull attention-mechanism flood-fill partial-evaluation arc-agi arc-agi-3 no-training futamura-projection analytical-weights grid-transformations compiled-intelligence neural-compilation polytopic-attention
  • Updated Apr 10, 2026
  • Python

Improve this page

Add a description, image, and links to the no-training topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the no-training topic, visit your repo's landing page and select "manage topics."

Learn more