Cost & Latency Tracking — What the Token Counts Were Telling Me All Along
David Hahn
Command Palette
Search for a command to run...
Archive
15 posts published so far
Error Handling in LLM Systems — Three Categories, One Decision Tree
David Hahn
Topic Suggestion — Designing a Function That Knows What to Recommend Without Magic Numbers
David Hahn
Streaming Structured Output — Incremental JSON Rendering Without a Parser
David Hahn
Evals — Why a Bad Eval Is Worse Than No Eval
David Hahn
Adding Spaced Repetition to an LLM Study System — SM-2, Schema Design, and a Scoring Problem Worth Solving
David Hahn
Tool Use + RAG — When Retrieval Becomes a Decision
David Hahn
Python for JavaScript Engineers — A Practical Mental Model
David Hahn
Prompt Engineering Lessons from Building a Problem Generator
David Hahn
Structured Output — When to Use Prompting vs. Forced Tool Use
David Hahn
The LLM-as-Judge Problem — Making Automated Evaluation Reliable
David Hahn
Designing an LLM System That Actually Solves a Real Problem
David Hahn
Building RAG from Scratch — Embeddings, pgvector, and a Bug Worth Knowing
David Hahn
Tool Use — How the Model Calls Your Code (And What It Never Sees)
David Hahn
Why Streaming Changes How You Build LLM-Powered Interfaces
David Hahn