← All Articles

I cut my agent's always-loaded instructions by 62% and weakened no rule

The thin instruction kernel: CLAUDE.md from 54,825 bytes to 21,026 with no rule weakened. Invariants, a routing table, and enforcement declarations.

· 7 min read

Your AI Assistant's Memory Isn't Actually Yours

Three questions show why your AI coding assistant's built-in memory isn't a durable record — portable, synced, versioned — plus a worked audit proving it.

· 6 min read

One context file carried a redesign across eight AI sessions

A single CONTEXT.md carried an editor redesign across eight AI coding sessions. The ownership split that made it work: humans direct, the AI keeps the record.

· 6 min read

Synthesis Project Management Now Works Across Claude Code and Codex

Synthesis project management now works across Claude Code and OpenAI Codex by keeping durable project memory in CONTEXT.md, REFERENCE.md, and sessions. Updated

· 10 min read

The Tiered Context Architecture: Managing AI Working Memory at Scale

When AI context files grow to 1,000+ lines, they degrade the collaboration they were built to support. The tiered context architecture solves this with three in

· 8 min read

From learned representations to engineered context: what Richard Socher's research tells us about working with AI

Richard Socher's research arc — from GloVe to DecaNLP to 'managers of AI' — maps directly onto the principles behind synthesis coding. The connections are struc

· 9 min read

Synthesis Project Management

A lightweight project management system for human-AI collaboration. Designed for context preservation across conversation sessions, context compaction events, m

· 13 min read