AI product Open source
Interference Search is a research project and Python library for reasoning over explicit states rather than a single linear language-model transcript. It expands live branches in parallel, lets the environment execute their moves, merges branches that reach the same state, uses a trained judge to discard states unlikely to reach the goal, and advances the surviving frontier one level at a time. The method is classical and does not claim quantum speedup.
The repository implements Countdown arithmetic search and program search, including move generation, exact solving, judge training, sandboxed program tests, behavioral merging, benchmarks, raw results, failed experiments, a research log, and the accompanying paper. Its reported experiments compare the approach with linear language-model reasoning and other search strategies; it also includes a one-line baseline and tools for reproducing the Countdown results.
The package requires Python 3.10 or newer and runs with PyTorch. Language-model experiments use MLX on Apple silicon, while the core search, judge, and tests can run on other PyTorch-supported systems. It is distributed under the Apache 2.0 license.
1 use taken from transcripts — each links to the moment in the video.
A research project for reasoning through explicit states. It explores multiple possible moves, merges branches that reach the same state, and uses a small judge to remove dead ends, with code, weights, results, and failed experiments included.
1 in the library.