scorecompute
All demonstrationsMONTE CARLO / CPU + CUDA

Find π in a cloud of points.

Turn a seeded cloud of random points into an estimate of π, with a convergence curve and sampling uncertainty you can inspect.

simulate_piTry the real call
Concept artwork · not calculation evidence
01 / UNDERSTAND THE METHOD

See what the tool does.

ILLUSTRATION · NOT A CALCULATION
INTERACTIVE 3D / METHOD STUDYExplore the method in space.
011insideoutsideπ ≈ 4 ×inside / all

Preparing the 3D exhibit…

A teaching illustration. Run the tool below to obtain a native calculation.Drag to inspect · arrow keys move the camera · no MCP call

02 / ASK THE ACTUAL TOOL

Make it your experiment.

Complete tool arguments

Arrays, coordinates and nested contracts remain editable here. Units and limits are checked by the real tool.

Runs only when you press the button. Input edits discard the previous displayed result. Public compute limits apply.

KNOW WHAT THE RESULT MEANS

Useful evidence needs boundaries.

  • The default example runs on CPU. CUDA must be requested explicitly and requires available compatible hardware.
  • A confidence interval is not a guarantee that this individual run achieves a chosen accuracy.
  • This floating-point experiment differs from the contributor pilot’s pi_chunk_v1 integer grid. No speedup is implied by this illustration.
Choose another demonstrationCall the same tool from your AI