Psysig

Our studies

Inference and reasoning structures, under close observation.

Featured

In queue

Dividing labor: overseen decision cores and language models

One model holding context, deciding, and writing in a single stream of text means anything it reads can steer everything it does. This study tests a three-part split: an overseen memory that holds the bounds, a decision core that classifies instead of generating, and a language model that only voices what was decided.

Intelligence Models

In queue

Dividing labor: overseen decision cores and language models

One model holding context, deciding, and writing in a single stream of text means anything it reads can steer everything it does. This study tests a three-part split: an overseen memory that holds the bounds, a decision core that classifies instead of generating, and a language model that only voices what was decided.

All

Alignment & Governance

In queue

Tiered inference governance: routing compute by consequence

Making a model safer by retraining it charges every request the same hidden price. This study tests a cheaper deal: keep one capable model untouched, put a small gate in front of it, and spend real care only on the requests that can do real damage.

In queue

Pausing to verify: process-guided search and receding-horizon control

A model that writes step by step has no pause button: one early slip compounds through the whole answer, and rewriting everything breaks parts that were already right. This study tests checking each step as it forms — and redoing only the stretch that failed.

All