A graph that cannot say no
July 2026 filled the conversation with typed graphs for agents, on a thesis that is correct — an untyped edge carries one bit; a typed one carries meaning — and with independent benchmarks that back it. But those same benchmarks say something their popularisers do not finish: one system collapsed to 6.6 average F1 against 59.8 the moment somebody other than its authors evaluated it, and a five-hop chain at 85% per-hop accuracy is worth 44%. The problem is not missing structure. It is that structure, alone, obliges nothing. And the gap the article itself declares empty — a linter for typed edges — has been running here for a while.
AI is a Knowledge Tool. But Who Keeps the Knowledge Alive?
Jessica Talisman's KGC 2026 talk is the clearest articulation of why AI strategies fail: organizations invest in data infrastructure and expect reasoning to emerge. She's right. But her solution — build knowledge infrastructure — stops exactly where the hard problem begins: who keeps the knowledge from drifting?
One Protocol, Multiple Subjects
Ontoref started as a protocol for software project self-knowledge. The same architecture — an ontological DAG for what IS, a reflection DAG for what BECOMES — applies without modification to infrastructure environments, to a body of authored work, and to individuals. The subject changes. The question is identical: what are you, what tensions define you, where are you versus where you intend to be?
DAGs Are Everywhere. None of Them Know What They Are.
CI/CD pipelines, compilers, runbooks, data orchestrators — they all use directed acyclic graphs. Every single one of them uses DAGs as execution models: this before that, topological ordering, dependency resolution. None of them use DAGs to represent what the system is, why it exists, or what trade-offs define it. That's the gap ontoref fills.
4 items