Beyond Weights — a Fixed Transmission Architecture for Learning Through Signal and Memory
Alexander Parnell · VektorGeist · 2026-08-14 · preprint, not peer reviewed
The architecture behind that learner, stated plainly: separate computation from knowledge. The pathway is fixed at construction and never changes; everything known lives in an append-only memory; learning is remembering rather than adjusting parameters. Includes the leg that does not close — composed responses drift across speakers — reported with the same weight as the parts that work.
Read the paper — 10.5281/zenodo.21850560
Open access under CC-BY-4.0. The DOI above is a concept DOI: it always resolves to the newest version.
Nothing here has been reproduced independently, outside the project that produced it. Every paper says so. Every page of the record says so. That is the ceiling on all of it, and it does not move until someone outside repeats the measurements.