ontological-induction

Attention, But Make It Type-Safe

Self-attention lets every token see every other token — and that's both its power and its failure mode. We constrain transformers with categorical reachability so attention edges that violate the type system can never form. A dev-preview write-up of work targeting a workshop submission.

Introducing: The Categorical Structure of Sequence Modeling

A series on Ontological Induction — and why LLM hallucination is