4 papers
Epistemic Observability in Language Models
Tony Mason, Vaastav Anand
We find that models report highest confidence precisely when they are fabricating. Across four model families (OLMo-3, Llama-3.1, Qwen3, Mistral), self-reported confidence inversel…
Legible Consensus: Topology-Aware Quorum Geometry for Asymmetric Networks
Tony Mason
Quorum design over asymmetric topologies conflates two independent concerns: inter-tier obligation (which tiers must participate for cross-tier safety) and intra-tier replication (…
The Missing Memory Hierarchy: Demand Paging for LLM Context Windows
Tony Mason
The context window of a large language model is not memory. It is L1 cache: a small, fast, expensive resource that the field treats as the entire memory system. There is no L2, no…
Arbiter: Detecting Interference in LLM Agent System Prompts
Tony Mason
System prompts for LLM-based coding agents are software artifacts that govern agent behavior, yet lack the testing infrastructure applied to conventional software. We present Arbit…