Blog
Dopamine, Debugging, and the Dopamine-Loss of AI-Assisted Coding
AI coding assistants are incredibly efficient, but they change the feedback loop of problem-solving. What do we lose when we gain that much speed?
Tagged
ai
10 posts
Blog
Rules of Engagement for Black-Box Product Audits
The method behind a public audit series: what the collector is allowed to touch, why every number needs a file behind it, and the difference between Unknown and Unmeasured.
Blog
Vibecode Rescue: Auditing Vibecoded Apps for Common Mistakes and Failures
Code has become cheap, but having an agent generate an app doesn't make it a product. A new series reviewing SaaS apps that launched and failed to convert, or sit abandoned — and what went wrong.
Blog
'No X, but Y' and Other Tells: Wiring an LLM to Write in Your Voice
How to use LLMs as part of your writing workflow.
Blog
The Stability Tax: Why Elixir's Boring Versioning Is a Better AI Target
A decade of semantic versioning stability means AI agents trained on 2020 code still produce working 2026 code
Blog
Writing Elixir for AI Agents: Patterns That Help (and Hurt)
Code patterns that maximize AI agent success—and the anti-patterns that confuse them
Blog
Why AI Coding Agents Love Elixir (And You Should Too)
Immutability, pattern matching, and pure functions make Elixir ideal for AI coding agents—the data proves it
Blog
Elixir and AI: Building LLM-Powered Features
Using Instructor for structured LLM output and building AI features in Elixir
Blog
The AI-Native Elixir Project: What Changes When the Agent is Your Pair
How project structure, tooling, and practices evolve when AI agents are central to development
Blog
