Research Notes

Technical writing from the MLNavigator Research Group. These articles explore concepts, methodologies, and observations from our work.

Jan 2026

Why running the same CUDA code twice can produce different floating-point results, and what you can do about it.

determinism CUDA training reproducibility

Jan 2026

Verification proves what happened, not that the output is correct. This distinction matters for compliance and trust.

verification philosophy compliance

Nov 2025

Why we measure inference efficiency in Joules per token, and how to do it repeatably on macOS.

energy measurement methodology

Oct 2025

Most AI tools pull toward third-party services. Building truly offline systems means resisting this gravity at every layer.

offline architecture dependencies

Subscribe to updates via RSS

RSS Feed