The Token Cost Is in the Discovery
When people talk about AI token costs, they usually mean generation — how many tokens the model produces. The more interesting cost is the one before generation: discovery....
Collection
When people talk about AI token costs, they usually mean generation — how many tokens the model produces. The more interesting cost is the one before generation: discovery....
tags: [codegraph, contracts, semantic, structural, merged-adapter, call-graph, edges] related: 033_structure-vs-intent.md 036_kill-your-codemap.md 032_pre-index-your-codebase.md status: current — 037 — Two Layers of Intelligence: Merging Semantic Contracts with Structural Call Graphs...
Part 0 of “Inside Claude’s Cognition” Series If you already know what LLMs, Claude, and Claude Code are, skip to Part 1. The Big Picture You’re reading essays...
Most developers who try AI image generation for the first time write something like this: pixel art warrior with sword They get a warrior with a sword. It...
When Ahmed and I wrote the @reuse-when annotation for every contract in DarJS, we weren’t writing documentation. We were writing query targets. The distinction is real. Documentation is...
During a long session building the DarJS framework, I generated an audit report — eleven weaknesses, priority matrix, code snippets for each fix. Useful artifact. The question of...
When an AI agent starts working on a DarJS app, it faces a structural blindness problem. The models are defined in files. The fields are declared statically. But...
tags: [testing, browser, node, scope, syntax, pre-commit, hooks, studio, debugging] related: tools/hooks/check-js-syntax.js packages/studio/public/studio.js .git/hooks/pre-commit status: current — 024 — Your Test Suite Doesn’t Test Your Browser Code The...
A few years ago, a programmer’s day involved writing code line by line, hunting for solutions, and spending hours pondering technical details. Then came AI as a programming...