spb/localvm-research Public License
Running LLMs larger than memory on a consumer Mac — falsification-driven research: margin-gated deferred refinement, out-of-core verification on Apple Silicon. TR-01 published.
Python 63.2%
JavaScript 23.5%
CSS 11.8%
Shell 0.9%
Makefile 0.5%
1---2project: localvm-research3document: expC_semantic_locality/hypothesis4author: Simon-Pierre Boucher5contact: contact@spboucher.ai6created: 2026-08-117status: draft8---910# Hypothesis — expC_semantic_locality1112```text13Hypothesis14 <what we believe and why>1516Falsification criterion17 <the concrete measurable outcome that would prove this wrong>1819Method20 <exact procedure, model(s), data, seeds, measurement points>2122Baseline23 <what this is compared against — no straw men>2425Result26 <filled after the run: numbers, with mean/median/std and run count>2728Interpretation29 <what the numbers mean; alternative explanations considered>3031Next experiment32 <the most informative follow-up given this result>33```34