ideasthesia

Sign in Subscribe

Ryan Collison

I write about cool science and share it here.

Multi-hop reasoning path through knowledge graph

Multi-Hop Reasoning: How Graphs Enable Complex Queries

Series: Graph RAG | Part: 5 of 10 The test of a knowledge system isn’t whether it can answer simple questions. It’s whether it can answer questions that require connecting information across multiple sources. “Who won the Nobel Prize in Physics?”—easy. Look it up. “Which Nobel Prize winners

Document extraction pipeline building knowledge graph

Building Knowledge Graphs from Documents: Extraction Pipelines

Series: Graph RAG | Part: 4 of 10 You have a thousand documents. Product specs. API documentation. Internal wikis. Support tickets. Research papers. A decade of accumulated knowledge locked in unstructured text. You need a knowledge graph. Which means you need to transform narrative text into structured triples: entities, relationships, and

Knowledge graph showing nodes and edges with semantic labels

Knowledge Graphs 101: Nodes, Edges, and Semantic Structure

Series: Graph RAG | Part: 3 of 10 A knowledge graph is a database that thinks in relationships. Instead of storing information in tables or documents, it stores meaning as a network: entities connected by labeled edges that specify how they relate. The structure isn’t metadata about your knowledge—it

Failed retrieval showing disconnected knowledge chunks

The Limits of Naive RAG: Why Your AI Agent Can't Reason

Series: Graph RAG | Part: 2 of 10 You built an AI agent. You connected it to your documentation, fed it embeddings, implemented vector search. The retrieval is fast. The responses cite sources. Everything should work. But ask it to compare two concepts across different documents and it fails. Ask it

Knowledge graph with semantic relationships for AI retrieval

Beyond Vector Search: Why Graph RAG Is the Future of AI Retrieval

Series: Graph RAG | Part: 1 of 10 The most expensive part of building an AI system isn’t the model. It’s what you feed it. Retrieval-Augmented Generation (RAG) systems power everything from customer service chatbots to enterprise knowledge bases to coding assistants. The architecture is deceptively simple: when

Synthesis of neuromorphic insights about biological computation

Synthesis: What Brain-Like Hardware Teaches About Brain-Like Computation

Synthesis: What Brain-Like Hardware Teaches About Brain-Like Computation Series: Neuromorphic Computing | Part: 9 of 9 We built chips that think like brains to make computers more efficient. What we learned instead was how brains actually work—and why coherence maintenance is computation's deepest constraint. This is

Wearable device with neuromorphic intelligence

Edge AGI: Intelligence on Your Wrist

Edge AGI: Intelligence on Your Wrist Series: Neuromorphic Computing | Part: 8 of 9 The computational future isn't in data centers. It's in the devices already pressed against your skin. Your smartwatch tracks heart rate, counts steps, measures sleep quality. But Intel's Loihi 2 chip,