§ BLOGField notes

Notes from the den.

Experiences, reflections, and hard-won lessons from our members - every researcher here has a standing invitation to share. Want to write one? Get in touch.

July 25, 2026 · 15 min readTechnical

9 RAG Architectures You Should Actually Know in 2026

Naive RAG, reranking, hybrid search, GraphRAG, agentic and multimodal retrieval: what each one fixes, what it costs, and how to pick.

July 22, 2026 · 10 min readEngineering

Writing Research Code That Isn't a Single 800-Line Notebook

A five-stage pipeline is a directed acyclic graph, not a linear script. What belongs in a script, and what belongs in a notebook.

July 21, 2026 · 6 min readTechnical

Parsing PDFs Is Broken: How Docling and PixelRAG Are Fixing Unstructured Data

When your RAG system hallucinates numbers, the problem is usually the ingestion pipeline, not the model.

July 21, 2026 · 5 min readGuide

My Model Won't Learn: A Debugging Checklist

2.30 at step 0, 2.30 at step 500. The order to check things in, starting with the test that splits the problem in half.

July 20, 2026 · 10 min readWorkflow

Config-Driven Experiments, or How I Stopped Editing Code to Change a Learning Rate

Hyperparameters hardcoded across four scripts, and a paper that reported two different F1 values for the same model.

July 19, 2026 · 9 min readWriting

The Writing Mistakes in Almost Every First Paper

Mechanics, structure, framing, evidence, and compliance: the five places a manuscript loses its reviewer.

July 18, 2026 · 5 min readPost-mortem

Experiment Tracking Before You Have 200 Runs You Can't Tell Apart

Four hundred runs, three tools, and no way to answer which one produced the numbers in the paper.