#ai

Articles tagged with #ai

Atlas Theorem: How Far Can You Zoom Out?
Four refutations, 13,000 lines of Lean, and a proof that resolution doesn't change the diagnosis
Aug 8, 202624 min read50
Taming a 40-Minute Lean CI: Three Rounds, Three Wrong Suspects
Our Lean 4 + mathlib project used to spend 41 minutes in CI on every single PR. Today, the worst case — rebuilding the heaviest files from scratch — takes 12 minutes, and an ordinary PR finishes in a
Aug 2, 202621 min read138
The Rising Sea of Software Engineering — Rebuilding the Discipline on Algebraic Geometry
AI now writes code faster than humans can review it. That is not a prediction; it is the daily experience of most engineering teams. And here is the other daily experience: no matter how much you inve
Jul 7, 202615 min read113
The SAGA Theorem: The Day Software Architecture Became Genuine Algebraic Geometry
TL;DR Every module passes review, yet the system as a whole is broken. This "locally correct, globally inconsistent" phenomenon has a name in mathematics: cohomology, specifically H^1. AAT (Algebrai
Jul 2, 202619 min read283
Atom Is All You Need: Read a Codebase as an Atom Map, Not a Dependency Graph
TL;DR In the AI era, architecture analysis cannot stop at reading code as files, functions, imports, and dependency graphs. We need to observe the smallest units that carry architectural meaning. I ca
May 31, 202619 min read120
Forecast Cone: A Grand Theorem for Computable Software Evolution
TL;DR This article starts from the ForecastCone in Software Field Theory (SFT), then reads modularity, technical debt, review, governance, and learning as parts of one research program. The goal is si
May 22, 202614 min read96