Context Window is how much input the model can process at once. It sits in the Incentives dimension (INC) of the Human Behavior Taxonomy™ as element HBT-INC-0077, within the Workflow family. The core principle: how much input the model can process at once. In incentive terms, it matters because it changes the payoff people perceive before they choose — which means it can be designed for, or exploited.
Scientific Definition
How much input the model can process at once.
Plain-English Definition
How much input the model can process at once.
Feynman Explanation
Bigger context, more capability, more cost.
Core Principle
How much input the model can process at once.
Mechanisms
Pending editorial review.
Pending editorial review.
Pending editorial review.
Pending editorial review.
Pending editorial review.
Pending editorial review.
Pending editorial review.
Inputs (Triggers)
Pending editorial review.
Outputs (Behaviors)
Pending editorial review.
Behavioral Signature
Bigger context, more capability, more cost.
Examples
- 1M token context windows in newer models.
- Architecture decisions for document-heavy work.
Pending editorial review.
Original analysis from The Incentives Lab — how this element behaves inside real payoff structures.
Why this element matters to incentive design
This is one of the elements leaders describe as a values gap. It is a payoff gap. The mechanism underneath it operates in the Incentives dimension — what makes behavior more or less likely?. You can recognize it in the field by its signature: bigger context, more capability, more cost. Every element in the Incentives dimension changes the perceived payoff of an action before the action happens, which is exactly where incentive design has leverage.
How it gets exploited
Left undesigned, architecture decisions for document-heavy work. It is amplified whenever architecture decisions for document-heavy work. Inside organizations that shows up as architecture decisions for document-heavy work. The pattern is the same one Goodhart's Law describes: the measurable proxy attracts the effort, and the purpose behind it quietly loses funding.
How the Lab designs around it
The redesign move is to don't over-index on long context. Retrieval often beats stuffing. Treat it as infrastructure. Once you can see it in your own system, most of the argument about culture resolves itself.
Famous Experiments
Pending editorial review.
Design Principles
- Don't over-index on long context. Retrieval often beats stuffing.
Measurement Approaches
Pending editorial review.
Evidence
Pending editorial review.
Pending editorial review.
The Perverse Incentive Lens™
How this behavior is exploited — and how to redesign around it.
- Don't over-index on long context. Retrieval often beats stuffing.
Pending editorial review.
Pending editorial review.
Interactive Mini Network
Click any neighbor to re-center the graph and follow the threads of connection.
Knowledge Graph Neighbors
Auto-linked to the rest of the Human Behavior Taxonomy by family, domain, dimension, and shared keywords.
AI system that takes actions to achieve goals, often across tools.
Designing processes from scratch around AI capability.
The relationship between inputs and outputs changes.
Underlying data distribution changes over time.
Vector representation of content for similarity and search.
Evaluation suites that no longer reflect real-world conditions.
Systematic testing of model quality, safety, and capability.
Models learning from examples in the prompt.
How much delay the user experience tolerates.
Train a smaller model to imitate a larger one.
Performance degradation as real-world data shifts.
Multiple specialized agents coordinating on tasks.
Where Context Window is cited in the corpus
Essays, field guides, and diagnostics from The Incentives Lab that apply this element.
- Field guideIncentives: definition, types, examples
The parent field guide for this element.
- ReferenceThe laws of incentives
Goodhart, Campbell, and the Cobra Effect.
- EssayAI Agents Inherit Your Incentives
How this element propagates into automated systems.
- ReferenceThe incentive glossary
Definitions for every mental model, bias, and fallacy in the corpus.
- ReferenceThe Periodic Table of Human Behavior
The full 1,267-element map this page belongs to.
Questions about Context Window
- What is Context Window?
- Context Window is how much input the model can process at once. It sits in the Incentives dimension (INC) of the Human Behavior Taxonomy™ as element HBT-INC-0077, within the Workflow family. The core principle: how much input the model can process at once. In incentive terms, it matters because it changes the payoff people perceive before they choose — which means it can be designed for, or exploited.
- What is an example of Context Window?
- Architecture decisions for document-heavy work. The Incentives Lab catalogs everyday, organizational, and historical instances of this element on its Human Behavior Taxonomy™ page (HBT-INC-0077).
- How is Context Window exploited?
- Architecture decisions for document-heavy work.
- How do you design around Context Window?
- Don't over-index on long context. Retrieval often beats stuffing.
- Which behavioral dimension does Context Window belong to?
- Context Window is classified in the Incentives dimension (INC) of the Human Behavior Taxonomy™, family "Workflow", class "AI-Behavioral Coupling". Its permanent identifier is HBT-INC-0077 and its evidence grade is C.