Posts tagged: ai
Zstdify: A Pure TypeScrpt Zstd Re-Implementation, Written in 4 Hours
Ben Houston • 5 Minutes Read • February 20, 2026
Today, I built a pure-TypeScript Zstandard implementation (library + CLI + dictionary training + interop tests) in just 4 hours using OpenAI Codex 5.3.

Tags: algorithms, coding, ai
Origins of the Term Exocortex
Ben Houston • 7 Minutes Read • November 28, 2025
The story of how I coined the term "exocortex" in 1999 to describe a synthetic cognitive regulator - a technological layer that participates in the brain's regulatory hierarchy rather than merely extending its output.

Tags: ai, cognitive-science
Crafting README Files for Efficient AI-Assisted Coding
Ben Houston • 5 Minutes Read • March 28, 2025
Optimize your README.md files to empower both human developers and AI coding assistants alike.
Tags: ai, coding, agentic-coding
The Rise of "Test Theater": When AI Coders Write Tests That Mean Nothing
Ben Houston • 4 Minutes Read • March 25, 2025
AI coding assistants are excellent at generating tests with high coverage. But there is often a critical problem: they are testing that code behaves as written, not as intended. This "Test Theater" creates a dangerous illusion of quality while providing almost no real protection against bugs.

Tags: testing, coding, ai
What is the Most Minimal Agentic Coder You Can Write?
Ben Houston • 3 Minutes Read • March 21, 2025
Exploring the simplest possible implementation of an agentic coder using just 200 lines of TypeScript, demonstrating foundational concepts clearly and concisely.

Tags: ai, coding, agentic-coding
Building an Agentic Coder from Scratch
Ben Houston • 6 Minutes Read • March 20, 2025
How to build an autonomous agentic coder that leverages advanced LLMs to transform software development. A talk given at the Ottawa Forward JS meet-up.

Tags: ai, coding, agentic-coding, talks
The Ephemeral Nature of Software in the Age of AI
Ben Houston • 6 Minutes Read • March 17, 2025
As AI dramatically reduces software development costs, we need to rethink our approach to code. Software is becoming ephemeral - easily replaced rather than maintained. This paradigm shift means optimizing for current needs instead of hypothetical futures.
Tags: ai, coding, agentic-coding
Agentic Coders with GitHub Comments and Actions: Automating Real Development
Ben Houston • 3 Minutes Read • March 13, 2025
AI agents are moving beyond IDEs into full automation of coding workflows. Discover how integrating agentic coding into GitHub Actions can streamline software development -- turning issues into PRs and automating documentation, tests, and even code reviews, all through simple GitHub comments.

Tags: ai, coding, agentic-coding
GitHub Mode: A Game Changer for Agentic Coding
Ben Houston • 4 Minutes Read • March 7, 2025
Adding GitHub Mode to MyCoder has radically improved my productivity, making my agentic coder feel like a true team member. By leveraging GitHub for task tracking, pull requests, and CI/CD feedback, I’ve seen a 3x to 5x boost in development efficiency.

Tags: ai, coding, agentic-coding
Lean into your Agentic Coder's Mistakes
Ben Houston • 2 Minutes Read • March 6, 2025
Adapting your codebase to match AI coder assumptions doesn't just help AI -- it uncovers hidden complexity, ultimately benefiting human developers.
Tags: ai, coding, agentic-coding
Stop Writing Code for Humans - The Future Belongs to AI Agents
Ben Houston • 16 Minutes Read • March 5, 2025
As AI coding agents become increasingly capable, we need to rethink our code organization and documentation practices. Here's why traditional "human-first" coding approaches are becoming obsolete and how to structure your projects for optimal AI compatibility.
Tags: ai, coding, agentic-coding