concept

The gap between the actual state of a codebase and the developer’s mental model, which rapidly accumulates when code is generated by AI rather than written by humans.

Context Hygiene is the disciplined practice of managing an LLM’s context window to maintain agent performance, accuracy, and efficiency. As context windows grow, the temptation is to “stuff” them, but practical experience shows that “context pollution” degrades reasoning capabilities. Core Principles 1. One Task Per Context Window Geoffrey Huntley emphasizes that developers should treat a context window like a small, precious resource (analagous to RAM in early computing). The rule is “one task per context window” (also formulated as Context is a Per-Feature Budget). ...

The fundamental shift in the software developer’s role — from an Executor who writes code line-by-line, to an Orchestrator who defines architecture, sets constraints, and manages a “factory of agents” to implement the details.

Treating text as an elastic medium by explicitly directing an AI to “zoom out” (summarize/condense) to reduce context noise, or “zoom in” to detail specific areas.

Low-cost, personal software built for a small, specific audience where usefulness and taste beat scale.

A development methodology where high-level technical specifications, rather than manual code entry, serve as the primary driver for implementation by AI agents.