license: mit
tags:
- from-scratch
- opcode
- ternary
- trit
- execution-verified
- tiny
Binary-Trit Coder (Clay's opcode model)
A from-scratch, 3.17M-param causal transformer trained from random init on Issac's own opcode
substrate — a bijective ternary ("trit") op grammar: join (+), take (−), weave (×) over digit leaves,
prefix-notation, depth-2. No pretraining, no outside corpus.
Honest benchmark — its OWN domain, not Python
The metric is execution-verify rate: sample a program, run it for real, check the model's answer.
| Test | Score |
|---|---|
| in-distribution (depth-2, fresh) | 98.6% |
| OOD generalization (depth-3, never trained) | 47.0% |
This is NOT a Python code-gen model. It has an 18-token opcode vocab; it will score ~0 on LiveCodeBench/SciCode (wrong domain). Its "learn from doing" signal is the verify-rate above.
The chrysalis (capability layers, all execution-verified)
- variables/let-bindings (69.5% end-to-end; 100% with a calculator + show-work)
- ping-pong φ-lattice solver — recovers a hidden intermediate 100%
- calc-offload, dark-space inference, combustion candidate-spark
Files
scratch_coder.pt (weights + vocab), config.json. Architecture + inference in
github.com/issdandavis/loom scratch_coder.py.
Thesis: coding is finite + bijective + execution-verifiable, so a small model from random init can MASTER the mapping — proven here at 98.6%.