Mental Models

They are the cause; everything else is the effect. Read these first.

• Orthogonality — Model capability and harness engineering are two independent forces. Find the direction orthogonal to model capability, where every investment compounds instead of depreciates.
• Cybernetics — Harness engineering is cybernetics. Feedback loops, requisite variety, atypical state machines, second-order observation — understand these, and you see agentic systems differently.
• Entropy — Disorder accumulates in every running agent system. Context rots, errors cascade, intent drifts. Not a bug — the default direction. Understanding the thermodynamics of information is how you find engineering space within the constraint.
• Operating System — The five pillars OS engineers refined over fifty years — memory management, scheduling, trust boundaries, cooperation protocols — are being reinvented in agent harness. Each pillar unfolds, and each break point marks design space the OS paradigm does not cover.
• Fractal — Self-similarity is not a coincidental observation about agentic systems — it is a generative principle of complexity. The same structure repeats at the prompt, agent, and swarm scales. Understand the principle, and engineering intuition transfers across layers.
• Causality — LLMs learn from statistical co-occurrence; they live in an ocean of correlation. When your application demands the reliability of causation, the system needs causal discipline — staying honest about what it knows and how it knows it.