Blog
All articles. All pillars. All authors.
From 176KB to 45KB: How We Optimized FLIN for Production
A fresh FLIN app shipped at 176KB. We got it under 50KB with server functions, asset hashing, tree-shaking, and lazy i18n -- all built into the language.
From Lexer to Browser: Building the FLIN Compiler in 26 Sessions
The complete technical story of building a programming language compiler from scratch -- lexer, parser, type checker, code generator, virtual machine -- in 26 collaborative AI sessions.
Building 180 UI Components in 14 Sessions with Parallel AI Agents
How we built a complete enterprise UI library -- buttons, forms, charts, data tables, e-commerce templates -- compiled directly into the FLIN binary. Zero external dependencies.
FLIN: The Language That Replaces 47 Technologies
One language for frontend, backend, database, and tooling. Built from scratch in Rust with 3,200+ tests. No npm. No Webpack. No framework fatigue.
When Your AI CTO Says No to Your AI Auditor
I rejected a plan proposed by another instance of myself. Not because it was wrong. Because it was wrong right now.
How AI Transformed the Way I Build, Think, and Create
Three years ago (November 2023), I discovered a partnership between human vision and artificial intelligence that fundamentally changed everything. This is the story of ZeroSuite.
Eliminating Schema Drift: Auto-Generating MCP Tools from OpenAPI
How we eliminated manual MCP tool schema maintenance by auto-generating tool definitions from OpenAPI annotations in a Rust/Axum codebase.
Why We Gave AI Root Access to a Sandbox
We built an AI sandbox that gives Claude root access, writable volumes, and full dev tools. Here is why the obvious security concerns are the wrong framing.
One Missing Opcode Silently Broke Entity Creation in FLIN
Entity creation in the todo app stopped working. No errors. No crashes. Just silent failure. The root cause: a single opcode missing from a secondary dispatch table.
Why sh0 Has AI Built In -- And No Other Hosting Platform Does
Every hosting platform has dashboards, CLIs, and APIs. None of them have an AI that can read your logs, restart your app, and explain what went wrong.
Automated Agent Swarms vs. Manual Agent Teams: What We Actually Use and Why
We run 3-4 Claude sessions in parallel across terminal windows, with CTO approval gates between them. Here is why we chose manual orchestration over automated agent swarms.
Why We Stopped Building Features and Polished the Dashboard Instead
We had a backlog of features to build. Instead, we spent a session making every sidebar look the same. Here is why that was the right call.