Skip to main content
HBT-INC-0269 · Dimension INC · Incentives

Synthetic Data

Generated training data that mimics real data.

Workflow·AI-Behavioral Coupling·Grade C·draft· enriching…
In one paragraph

Synthetic Data is generated training data that mimics real data. It sits in the Incentives dimension (INC) of the Human Behavior Taxonomy™ as element HBT-INC-0269, within the Workflow family. The core principle: generated training data that mimics real data. 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

Generated training data that mimics real data.

Plain-English Definition

Generated training data that mimics real data.

Feynman Explanation

Real data is expensive. Synthetic is fast. Both have their lies.

Core Principle

Generated training data that mimics real data.

Mechanisms

Psychological

Pending editorial review.

Behavioral Economic

Pending editorial review.

Neurological

Pending editorial review.

Evolutionary

Pending editorial review.

Sociological

Pending editorial review.

Computational

Pending editorial review.

Systems

Pending editorial review.

Inputs (Triggers)

Pending editorial review.

Outputs (Behaviors)

Pending editorial review.

Behavioral Signature

Real data is expensive. Synthetic is fast. Both have their lies.

Examples

Everyday
  • Augmentation for rare classes in fraud detection.
Modern (Organizational)
  • Useful — and risky — pattern for training data scarcity.
Historical

Pending editorial review.

Lab Commentary

Original analysis from The Incentives Lab — how this element behaves inside real payoff structures.

Why this element matters to incentive design

This element is common enough to feel like human nature and specific enough to be engineered around. 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: real data is expensive. Synthetic is fast. Both have their lies. 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, useful — and risky — pattern for training data scarcity. It is amplified whenever useful — and risky — pattern for training data scarcity. Inside organizations that shows up as useful — and risky — pattern for training data scarcity. 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 test models on real holdout data. Don't trust synthetic for validation. 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

  • Test models on real holdout data. Don't trust synthetic for validation.

Measurement Approaches

Pending editorial review.

Evidence

Evidence Grade
C (A strongest → E speculative)
Replication
★★☆☆☆
Intervention Confidence
3 / 5
Consensus
Pending editorial review (HBT v1.0 auto-seed).
Limitations
Pending editorial review (HBT v1.0 auto-seed).
Open Research Questions

Pending editorial review.

Primary References

Pending editorial review.

Signature Section

The Perverse Incentive Lens™

How this behavior is exploited — and how to redesign around it.

Exploitation
Useful — and risky — pattern for training data scarcity.
Amplifying Incentives
Useful — and risky — pattern for training data scarcity.
Org Failure Modes
Useful — and risky — pattern for training data scarcity.
Societal Failure Modes
Pending editorial review (HBT v1.0 auto-seed).
Ethical Considerations
Pending editorial review (HBT v1.0 auto-seed).
Redesign Strategies
Test models on real holdout data. Don't trust synthetic for validation.
Diagnostic Questions
  • Test models on real holdout data. Don't trust synthetic for validation.
Warning Signs

Pending editorial review.

Red Flags

Pending editorial review.

Intervention Playbook
Individual
Test models on real holdout data. Don't trust synthetic for validation.
Team
Pending editorial review (HBT v1.0 auto-seed).
Organization
Pending editorial review (HBT v1.0 auto-seed).
Policy
Pending editorial review (HBT v1.0 auto-seed).
AI Implications
Detection
Pending editorial review (HBT v1.0 auto-seed).
Measurement
Pending editorial review (HBT v1.0 auto-seed).
Mitigation
Pending editorial review (HBT v1.0 auto-seed).
Responsible Use
Pending editorial review (HBT v1.0 auto-seed).

Interactive Mini Network

Click any neighbor to re-center the graph and follow the threads of connection.

HBT-INC-0269 · INC
Synthetic Data
SDAgAgentAWAI-First Workflow De…CDConcept DriftCWContext WindowDDData DriftEmEmbeddingEDEval DriftEFEvaluation Framework…ILIn-Context LearningLBLatency Budget

Knowledge Graph Neighbors

Where Synthetic Data is cited in the corpus

Questions about Synthetic Data

What is Synthetic Data?
Synthetic Data is generated training data that mimics real data. It sits in the Incentives dimension (INC) of the Human Behavior Taxonomy™ as element HBT-INC-0269, within the Workflow family. The core principle: generated training data that mimics real data. 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 Synthetic Data?
Useful — and risky — pattern for training data scarcity. The Incentives Lab catalogs everyday, organizational, and historical instances of this element on its Human Behavior Taxonomy™ page (HBT-INC-0269).
How is Synthetic Data exploited?
Useful — and risky — pattern for training data scarcity.
How do you design around Synthetic Data?
Test models on real holdout data. Don't trust synthetic for validation.
Which behavioral dimension does Synthetic Data belong to?
Synthetic Data is classified in the Incentives dimension (INC) of the Human Behavior Taxonomy™, family "Workflow", class "AI-Behavioral Coupling". Its permanent identifier is HBT-INC-0269 and its evidence grade is C.

Version History

v1.1.0 · 2026-06-28Initial auto-seed from corpus.