Library

I don't collect papers. I collect ideas that change how I build systems.

Why it's in my library

This paper changed how I think about retrieval: the generator and the retriever are separate concerns, which means the corpus can be updated without retraining anything. It's the reason Compliance Agent and Graph-Augmented Agentic RAG both treat retrieval quality as a first-class problem, not a preprocessing step.

Applied in

Key ideas

RAGRetrievalGroundingContext Engineering

Read paper ↗arxiv.org

Why it's in my library

This is the paper that convinced me retrieval hit-rate isn't enough to evaluate a RAG system. A model can retrieve the right passage and still fail to use it, just because of where it landed in the context window. That's why eval suites need a faithfulness metric separate from retrieval accuracy.

Applied in

Key ideas

Long ContextEvaluationRAGFaithfulness

Read paper ↗arxiv.org

Why it's in my library

This paper is the clearest argument I've seen for writing rules down instead of hoping a model infers them from examples. The same instinct shows up in how I build deploy gates and validation layers: an explicit, auditable rule beats an implicit one, even when the implicit one technically works more often.

Applied in

Key ideas

Constitutional AISafetySelf-CritiqueAlignment

Read paper ↗arxiv.org

Why it's in my library

Everything else in this library assumes this paper. Self-attention is the reason retrieval, agents, and long-context evaluation are even the right things to be arguing about — it's the substrate, not a technique applied on top of one.

Key ideas

TransformersSelf-AttentionArchitecture

Read paper ↗arxiv.org

Why it's in my library

The chapters on consistency and replication are the reason DiffDDL exists in its current form: string-level schema diffing is the implicit-tradeoff version of a problem this book treats as a first-class design decision.

Applied in

Key ideas

Distributed SystemsConsistencySchema Design

Original publication ↗dataintensive.net