mostlylucid.net - Scott Galloway's Developer Blog

HTTP Over the Decades: A Story of Physics, Latency, and Grudging Adaptation

HTTP didn't evolve. It was forced to change by physics, latency, and misuse. Every version exists because the previous one hit a hard constraint. If you understand those constraints, you understand...

Sunday, 28 December 2025 18:00

//

23 minute read

No, Small Models Are Not the "Budget Option"

AI LLM Ollama ONNX Opinion

Small and local LLMs are often framed as the cheap alternative to frontier models. That framing is wrong. They are not a degraded version of the same thing. They are a different architectural choice,...

Sunday, 28 December 2025 16:00

//

7 minute read

GraphRAG Part 2: Minimum Viable GraphRAG (No Per-Chunk LLM Calls)

ASP.NET DuckDB GraphRAG Knowledge Graphs Machine Learning Vector Search

In Part 1, we explored why GraphRAG matters. Now let's build a minimum viable GraphRAG that works without per-chunk LLM calls - pragmatic, offline-first, and cheap enough to run on a laptop: DuckDB...

Saturday, 27 December 2025 14:00

//

11 minute read

GraphRAG: Why Vector Search Breaks Down at the Corpus Level

ASP.NET Machine Learning ONNX Qdrant RAG Semantic Search Vector Search

Your RAG system is great at "needle" questions: retrieve a few relevant chunks and synthesise an answer. It struggles with two common query types: Sensemaking: "What are the main themes across this...

Friday, 26 December 2025 12:00

//

21 minute read

Probability Is Not a System: The Ten Commandments of LLM Use

AI LLM Opinion

I keep seeing the same failure mode in "AI-powered" systems: LLMs are being asked to do jobs we already solved decades ago - badly, probabilistically, and without guarantees. This isn't cutting edge....

Thursday, 25 December 2025 12:40

//

15 minute read

DataSummarizer: Fast Local Data Profiling

C# Data Analysis DuckDB LLM

Most “chat with your data” systems make the same mistake: they treat an LLM as if it were a database. They shove rows into context, embed chunks, or pick “representative samples” and hope the model...

Monday, 22 December 2025 18:30

//

6 minute read

DocSummarizer Part 3 - Advanced Concepts: The "I Went Too Far 🤦" Deep Dive

.NET AI BERT C# Embeddings LLM ONNX RAG

This is Part 3 of the DocSummarizer series: Part 1: Building a Document Summarizer with RAG - The architecture and why the pipeline approach beats naive LLM calls Part 2: Using the Tool - Quick-start...

Sunday, 21 December 2025 12:00

//

30 minute read

DocSummarizer Part 2 - Using the Tool

AI C# Docling LLM Ollama Qdrant RAG Tools

GitHub release .NET Version This is Part 2 of the DocSummarizer series. See Part 1 for the architecture and patterns, or Part 3 for the deep technical dive into embeddings and retrieval. Turn...

Sunday, 21 December 2025 11:00

//

21 minute read

Stop Shoving Documents Into LLMs: Build a Local Summarizer with Docling + RAG

AI C# Docling LLM Ollama Qdrant RAG

Here's the mistake everyone makes with document summarization: they extract the text and send as much as fits to an LLM. The LLM does its best with whatever landed in context, structure gets...

Sunday, 21 December 2025 10:00

//

13 minute read

Fetching and Analysing Web Content with LLMs in C#

Agents AI C# LLM Systems Design

📌 Note: This article teaches the fundamentals of web content extraction with LLMs using the simplest possible approach. For production use cases (web summarization, document analysis, agent tools),...

Friday, 19 December 2025 10:00

//

16 minute read