Independent research · Idaho Falls

Actual Science

Machine learning with the physics built in.

An independent lab working at the seam between physics and machine learning. Small specialist models, built so their answers can be checked.

Projects

Software · Alpha

Yates GR Studio

See the worked examples

An exact symbolic engine for general relativity. Curvature, horizons, quasinormal modes, junction conditions, and local geometry identity. Every result carries the proof obligations it discharged and exports as article-ready LaTeX. It is also the engine Eris computes through.

Operations
27 across 5 modules
Engine
exact symbolic
Toolkit suite
150 / 150 passing
Status
alpha, in use

Flagship · In development

Lyra

A physics specialist. Lyra is a language model fine-tuned to be the collaborator you want at the whiteboard. It reads the problem, checks the work, and explains the result. It runs on open-weight bases through QLoRA, trained on arXiv, mathematics, and the scientific literature.

Specialization buys a stricter standard. Lyra is judged the way physicists judge each other, on whether the answer survives checking. The metric is verified-correct rate. The failure it is built to kill is the confidently wrong answer.

Base
Qwen3-class open weights
Method
QLoRA fine-tune
Corpus
arXiv, mathematics, science
Judged on
verified-correct rate
Status
in development

Research · In build

Eris

A research assistant for general relativity, trained from scratch at the byte level and wired to a symbolic engine that performs the calculations. Eris reads the problem, selects the computation, and interprets what comes back. The numbers arrive from the engine, carrying provenance you can point at.

The channel delivering those results is provably inert. Carrying nothing, its effect on the output is exactly zero in IEEE-754 arithmetic, verified in two independent frameworks on the same checkpoint and enforced on every build. Switch it off and the injected values vanish while ordinary prose stays bit-for-bit identical. That is what makes the numerical output auditable.

The symbolic engine is our own, built here and validation-gated. The architecture is assembled, the training corpus is rebuilt and verified, and the second run is staged.

Domain
general relativity
Built
from scratch, byte-level
Parameters
210M
Channel
zero trainable parameters
Inertness
exactly 0.0, two frameworks
Status
run two staged

Principal researcher

Brandon Yates

Independent mathematical physicist, working in general relativity.

Approach

Frontier labs scale. This lab works at the algorithm layer, on open weights, in the open. Small and specialized, aimed at problems where being right is worth more than being large.

We build the models that solve the problem and show the proof.