Tokenomics, or how to budget a single conversation. AI bills come in confusing units. The fix is to budget for the product the business sells: tokens. Cost per token is the only metric that compares two quotes. ai-economics ai-strategy ai-and-work If you have ever looked at an Artificial Intelligence (AI) bill and wondered whether the …
Tokenomics, or how to budget a single conversation · Hanh D. Brown Read More »
Building an agent that works in a notebook takes an afternoon. Getting that same agent to survive real traffic, recover from a crash at 3 am, and not leak someone else’s data while it runs large language model (LLM)-generated code is a different job entirely, and it’s the job most teams underestimate. Only a …
5 Tools for Building and Deploying AI Agents in Production Read More »
The transparent battlefield and the end of secrecy. A frozen front line in Ukraine teaches the future of warfare. Big, slow, heat-emitting platforms lose. The fix is procurement, not budget. ai-policy ai-hardware ai-markets The military hardware America spent seventy years buying may not survive its first real engagement. A frozen front line in Ukraine teaches …
The transparent battlefield and the end of secrecy · Hanh D. Brown Read More »
ContentsTL;DRThe Assumption I Went In WithWho This Is ForBuilding the ExperimentComponent 1: The Topology GeneratorComponent 2: The Agent PolicyComponent 3: The DiagnosticsWhat I DidWhat I GotLooking Underneath the Number That Didn’t MovePerformance CharacteristicsHonest Design Decisions1. The Deterministic Agent Policy2. Standard Library Keyword Matching3. Removing Circular Early Exits4. Budget Size and Ceiling Effects5. Dependency FootprintTrade-Offs and …
Graph Engineering Isn’t About More Connections — It’s About Which Ones Get Used Read More »
What revision is actually there to do for your thinking. Revision is the architect’s move. Five things it is for. One thing it is not. revision writing-craft working-method A draft that is not landing has two possible faults. The sentences are wrong, or the plan the sentences are serving is wrong. Almost nobody checks the …
What revision is actually there to do for your thinking · Hanh D. Brown Read More »
Contents# Introduction# 1. pyjanitor for Fluent, Chainable DataFrame Cleaning# 2. Great Expectations for Data Validation and Quality Checks# 3. ftfy for Fixing Broken Unicode and Text Encoding Problems# 4. ydata-profiling for Instant Dataset Audits# 5. Cerberus for Lightweight Schema Validation on Arbitrary Data Structures# Summary and Next Steps # Introduction Data cleaning is rarely interesting, but it does consume the majority of a …
5 Python Libraries That Make Data Cleaning More Enjoyable Read More »
A short defense of changing your mind out loud in public. Most writers write to appease readers. That is not expression. Changing your mind in public is what expression looks like when it has stopped appeasing. voice thinking-in-public identity creative-process Most writers write to appease readers. That is not expression. That is performance for someone …
A short defense of changing your mind out loud in public · Hanh D. Brown Read More »
, the good folks at DuckDB released a database communication protocol called Quack. Its main aim was to allow DuckDB databases held on different servers to communicate with each other over HTTP in a client/server arrangement and allow them to read and write each others data. In other words, using the Quack protocol, DuckDB sitting …
Running SQL Concurrently Across Three Remote DuckDB Servers with Quack Read More »
On reading the fifteen books I keep failing to finish. Fifteen books I have started multiple times. None of them is the book’s fault. The architect in me is still reading them. creative-process writing-craft working-method There are seven books on a shelf in the room where I write. Each one has a marker in it. …
On reading the fifteen books I keep failing to finish · Hanh D. Brown Read More »
Web scraping is the process of collecting information from websites automatically. A normal scraper usually extracts raw text, HTML elements, or the full page content. But when you are building AI agents or large language model (LLM) applications, sending the entire webpage to the model is not always the best approach. A better way …
How to Build a Simple AI Web Scraper with Python Read More »
