A small neural net asks if physical law is inevitable for any observer

Show HN: A small neural net asks if physical law is inevitable for any observer

A small neural net asks if physical law is inevitable for any observer is active in the show hn launch space.

Profile

I built a small neural network (a GRU) that works similarly to how you and I work. It sees short, noisy snapshots one at a time, has a small internal memory that carries forward, and its only job is to predict the next snapshot. You see a little, you remember a little, you predict. It asks one question: is physical law what any finite observer must build to predict reality?First I tested whether memory helps equally everywhere. I ran it on real data from 13 instruments: LIGO, EHT, Planck CMB, solar wind, sunspots, and others; same observer, only the data changed. Some domains are readable in one shot, others only make sense if the observer accumulates over time. That variation isn't random,

Within the show hn launch space, the company focuses on its core offering rather than a broad product line.

It is recorded at the Show HN launch stage.

Website: www.wvrk.org/works/why-physics-has-laws