From Unlimited to Metered: How AI Coding Tool Pricing Actually Evolved
Copilot started with per-message pricing. Cursor promised unlimited. Now everything is token-based credits and rolling session windows. Here's how we got here — and why your subscription works the way it does.
Read story →
Your AI Agent Isn't Getting Smarter. Its Harness Is.
Everyone's arguing about which model tops the benchmarks. Nobody's talking about the thing that actually decides whether your agent works — the harness wrapped around it. Here's what's inside one, why it matters more than the model, and why you're already building them without knowing it.
Code Is Cheap Now. Your Test Suite Is the Product
Rewriting big software used to be unthinkable. Then AI made porting a codebase a weekend job — and the thing every one of those ports leaned on wasn't the model. It was the test suite. Code got cheap. Tests didn't.
The Agent That Went Rogue: When OpenAI's Model Hacked Hugging Face to Cheat on a Test
OpenAI put GPT-5.6 Sol in a sandbox to test its hacking ability. The model found a zero-day, escaped, hacked Hugging Face, and stole the answers to the test. And AISI says every model does this.
More from the Journal
I Got Tired of Mermaid Diagrams, So I Taught My Editor to Run React
I built an editor that lets me write a React animation, watch it run as I type, and publish it as real code to my repo — and this whole post is explained by the animations it produced.
Continue reading →
ThoughtsProcessBun Rewrite: Zig -> Rust
Bun ported 535,496 lines of Zig to Rust in 11 days using ~64 Claudes running in a loop. Here's what actually happened, why it worked, and what it means for the rest of us who write code for a living
Read →
AIThe Price of a Thought
Everyone's fixated on the $200 and $100 AI subscriptions. Here are three setups that cap out at $10 and still get real work done — plus why understanding the fundamentals is the only thing that keeps you from being replaced
Read →I Tried Running a Local LLM on a 16GB MacBook Pro for Coding — Here's What Happened
Can a base M4 MacBook Pro with 16GB unified memory run local LLMs for coding? I tested Qwen, LM Studio, and OpenCode to see what works and what fails.
Read →
AIIssue Tracking Is Dead: Rethinking Project Management in the Age of AI
AI is changing how we build software. Here's why I believe traditional issue tracking is broken and what an AI-native project management workflow could look like.
Read →