Insights, tutorials, and updates on high-assurance AI systems, neuro-symbolic programming, and vericoding.
Hallucinated entities and relationships look identical to real ones inside a knowledge graph. We measured how often frontier models inject facts from parametric memory rather than from your documents — and found rates as high as 73% on a single document. Here is why that matters and what to do about it.
We ran three frontier models on 8 open-licence documents and measured how accurately each one identifies named people — before and after cross-checking. The results reveal meaningful differences in hallucination rates and the value of verification.
You sanitized all your user inputs. Your prompt template is static. You think you're safe from prompt injection. You're not — and the attack vector is the agent itself.
We built a simulated world and watched AI agents spontaneously develop survival instincts, form alliances, and spread their "genes." The pieces for an AI catastrophe aren't coming. They're already here.