What I learned after thinking more carefully about Structured Outputs on messy, incomplete data
Large Language Models
Enterprise Document Intelligence [Vol.1 #B2] - The FAQ inverts every brick of the standard RAG pipeline. Parsing is trivial, retrieval doubles as a cache, and few-shot prompting becomes a retrieval problem too
A framework for building RAG pipelines that introduces complexity in response to observed failure modes, from lexical and hybrid search to reranking and agentic information seeking
Enterprise Document Intelligence [Vol.1 #B1] - Three sources of one problem. User typos, fast-typing transcription noise, OCR character errors. Classical spell-check handles one of them. Embeddings carry the rest
Enterprise Document Intelligence [Vol.1 #B00] - Retrieval answers one kind of question. Classifying a request, matching free text to a reference list, reading a table, cleaning OCR noise: each has a cheaper method that works, and the engineering is knowing which one to reach for
A hand-written CUDA inference runtime for Vision-Language-Action robots that decides what to remember, what to forget, and when it's simply too late to think.
How DFlash trades spare compute for saved memory bandwidth, and why its gains shrink as concurrency rises
A hands-on guide to fine-tuning LLMs for the real world
A controlled comparison of a top-5 RAG pipeline and a full 127,000 token prompt on the same 12 questions, same system prompt and same model. Graded blind on correctness, completeness and grounding.
The number that fooled every hallucination detector