AI

Faultline started as a four-day Kaggle entry with zero tests. Faultline Pro now has 4,887 counted tests. These are the failures that put them there.

Measurement fraud is when the AI system that produces code also grades it, so evals pass while the code is broken. Definition, how to detect it, and how to prevent it.

Frameworks solve syntax. Portfolio Architects solve delivery. The distinction is the difference between code that runs in a demo and code that ships to production.

AI is collapsing the project management hierarchy. The role it's creating — Portfolio Architect — doesn't look like what came before.

Every era of software development has had the same coordination problem. Every era has produced a more capable tool. Here's the lineage.

45% of AI-generated code contains security flaws. 86% fails XSS. The illusion of correctness is the real risk — and it's hiding in plain sight.

Technical deep-dive on file conflict mechanics in multi-tool AI development and Forge's Rust lock manager

The Tool That Writes Your Code Is Also Writing Its Bugs

AI-Generated Code Has 2.74x More Vulnerabilities