Writing

Technical articles, insights, and lessons learned from building software systems. I write about architecture decisions, engineering practices, and the challenges of delivering reliable software at scale.

76 articles

ilo: A Programming Language for AI Agents, Not HumansMay 13, 2026 Loading ilo, Part 3: Harness Layer Two coding-agent forks (Warp, pi) that bake ilo in at the harness layer instead of loading it as a skill.

ilowarpclaude-codeai-agentstooling

ilo: A Programming Language for AI Agents, Not HumansMay 12, 2026 Loading ilo, Part 2: Agent Skill Second attempt at loading ilo into the agent loop. Package the spec as an agent skill so it loads only when ilo is relevant.

iloclaude-codeai-agentstooling

ilo: A Programming Language for AI Agents, Not HumansMay 11, 2026 Loading ilo, Part 1: System Message First attempt at loading ilo into a real agent loop. Paste the compact spec into the system message and see how far it gets.

iloclaude-codeai-agentstooling

May 10, 2026 pi vs Claude Code: The Philosophical Split Two TypeScript agents with opposite design choices. A half-million-line spaceship versus a four-tool kit.

llmagentsclaude-codepitooling

May 9, 2026 pi: The Minimal Coding Agent Mario Zechner built pi after souring on every existing coding agent. Two talks worth watching, and what he claims pi does differently.

llmagentspitooling

May 8, 2026 Coding Agents in May 2026: A Field Guide Claude Code, Codex CLI, opencode, kilocode, pi, plus the commercial tools. What each one is and where the philosophical lines fall.

llmagentsclaude-codecodexopencodetooling

May 7, 2026 The Claude Code Source Leak: What the Dump Shows A misconfigured package.json field shipped Claude Code's full source to npm. What the half-million lines say about how the tool is built, and what it gives competitors.

llmagentsclaude-codeanthropictooling

May 6, 2026 What's New in TypeScript 6.0 TypeScript 6.0 ships stricter defaults, modern compile targets, and clears the path for the Go-native 7.0 release later this year.

typescriptprogramming

May 5, 2026 DeepSeek V4 on Apple Silicon: Current Status What the V4-Pro and V4-Flash checkpoints weigh on disk and in memory, mapped to the unified-memory ceilings of current MacBook Pro and Mac Studio configurations.

llmaideepseekmlxapple-silicon

May 4, 2026 DeepSeek V4: Don't Look at What You Don't Need DeepSeek V4 reads a million tokens on roughly a quarter of V3.2's compute. It does this by selectively attending to the parts of context the prompt asks about, the same way humans skim a long book.

llmaiattentiondeepseek