AI Incentives · Workflow

In-Context Learning

Models learning from examples in the prompt.

"Demonstration is faster than retraining."

Quick answer

What is In-Context Learning? Models learning from examples in the prompt. Often the right answer before reaching for fine-tuning.

In the wild

Few-shot prompting.

Why it matters in the room

Often the right answer before reaching for fine-tuning.

Counter-move

Master prompt engineering before investing in fine-tuning.

Visual · Reward gradient

In-Context Learning shows where an optimizer climbs vs where we want it to go.

Live example · Train around In-Context Learning

Pick what to reward the model for.

Models learning from examples in the prompt. In the wild: Few-shot prompting.

● Live

Pick a lever. There are no neutral ones — every incentive funds a behavior somewhere.

How does this land?

Pick a reaction to In-Context Learning

One tap. We'll point you at the most useful next surface based on how this hits.

Human Behavior Element™ · HBE Spec

The full taxonomy entry

Every concept in the Atlas uses the same structure — so In-Context Learning can be compared, recombined, and cited like an element on a periodic table.

About the standard →

HBT-A3820

Official name

In-Context Learning

AI Incentives · Workflow

Identity

HBT ID

HBT-A3820

Symbol

Official name

In-Context Learning

Synonyms

Workflow

Keywords

AI Incentives, Workflow, human behavior, incentive design

Version

v1.0

Last updated

Maintained by The Incentives Lab

Classification

Kingdom

Systems

Domain

Machine Behavior

Family

AI Alignment & Incentives

Class

Workflow

Element

In-Context Learning

Definition

Scientific

Models learning from examples in the prompt.

Plain-English

Models learning from examples in the prompt.

Feynman

Demonstration is faster than retraining.

Core principle

Models learning from examples in the prompt.

One-sentence summary

Often the right answer before reaching for fine-tuning.

Mechanisms

Psychological

Models learning from examples in the prompt.

Behavioral econ.

Often the right answer before reaching for fine-tuning.

Neurological

Reward, threat, and salience circuits bias attention toward the cue.

Evolutionary

Heuristics that paid off in ancestral environments now misfire in modern systems.

Sociological

Group norms and status incentives reinforce the pattern across a team.

Computational

Models trained on biased human signals will replicate and amplify the pattern.

Systems thinking

Feedback loops between metrics, incentives, and behavior lock the pattern in place.

Signals & signature

Inputs (activators)

Few-shot prompting.

Outputs (observable)

Often the right answer before reaching for fine-tuning.

Behavioral signature

You see In-Context Learning when the explanation for a decision sounds reasonable but the outcome keeps repeating.

Behavioral molecules

Often combines with related Atlas entries — see the rail below.

Pathways · before

A goal, metric, or contract clause makes the behavior rational locally.

Pathways · after

Locally rational choices accumulate into a systemic distortion.

Domains where it shows up

Business
Leadership
Government
Healthcare
Education
Sales
Marketing
AI
Negotiation
Media
Public Policy
Relationships

Examples

Everyday

Few-shot prompting.

Modern

Often the right answer before reaching for fine-tuning.

Historical

A pattern repeatedly documented since the foundational behavioral science literature on ai alignment & incentives.

Famous experiments

See the References block — primary papers in the Atlas link out to the original studies.

Design principles

How to leverage

Often the right answer before reaching for fine-tuning.

How to reduce

Master prompt engineering before investing in fine-tuning.

How to redesign

Master prompt engineering before investing in fine-tuning.

The Perverse Incentive Lens™

How it's exploited

Organizations weaponize in-context learning — sometimes deliberately, often by accident — when metrics reward the symptom rather than the outcome.

Common perverse incentives

Volume metrics, short review windows, bonus cliffs, and contracts that pay on activity rather than impact.

Failure modes

When In-Context Learning dominates, teams optimize for the dashboard while the real outcome quietly degrades.

Incentive redesign

Master prompt engineering before investing in fine-tuning.

Ethical considerations

Don't engineer in-context learning into customers, employees, or citizens as a manipulation tactic — design for informed choice instead.

Diagnostic questions

Where in our org would In-Context Learning most often show up unnoticed?
Which metric, ritual, or contract clause quietly rewards In-Context Learning?
If we removed every payoff for In-Context Learning, what behavior would replace it?
Who benefits when In-Context Learning persists — and who pays the cost?

Organizational warning signs

Metrics

A KPI is hit while the underlying outcome stalls or worsens.

Behaviors

People route around the rule rather than challenge it.

Language

'That's just how we do it here.' / 'The system requires it.'

Culture

Naming the pattern is treated as disloyalty.

Red flags

People defend the status quo using the language of in-context learning.
Decisions cluster around the easiest narrative rather than the strongest evidence.
New data changes the slide deck but not the decision.
Anyone naming the pattern is treated as the problem.

Intervention playbook

Immediate

Make the perverse payoff visible to the people creating it.

30-day

Run a small pilot that pays for the outcome, not the proxy.

Long-term

Rewrite the comp plan, contract, or ritual so the right behavior becomes the easy behavior.

AI considerations

Detect

Audit training data and reward signals for the same pattern this element describes.

Avoid amplifying

Don't optimize models on metrics that already encode the perverse incentive.

Counteract

Use the model to surface where the pattern is most active, then redesign the incentive — not the model.

Measurement

Metrics

Outcome-to-proxy ratio over time.

Assessment

The Incentives Lab III Diagnostic.

Survey

Calibrated pulse questions on rules vs. outcomes.

Behavioral signals

Where people work around the system.

Observational

Where the dashboard and the lived experience disagree.

Scientific evidence

Evidence grade

Synthesized from the behavioral science literature; see Atlas references.

Replication

Tracked in the Atlas as primary, replicated, or contested.

Intervention confidence

Moderate — patterns generalize, mechanisms vary by context.

Research consensus

Broad agreement on the pattern; ongoing debate on boundary conditions.

Known limitations

Local context, culture, and incentive structure all change the strength of the effect.

Open questions

How does In-Context Learning interact with AI-mediated decisions at scale?

References

Primary papers

See the Research Center →

Books

Curated in the Magazine →

Meta-analyses

Tracked in the Atlas registry.

Seminal authors

Kahneman, Tversky, Thaler, Ariely, Cialdini, Ostrom, Simon — and the field they built.

Cross references

Every Atlas entry is a node in a knowledge graph. See the related rail below to follow the connections.

Disciplinary layers

See In-Context Learning through 4 lenses

Each layer of the Incentives OS reframes this concept with its own thinkers, vocabulary, and diagnostic question.

Test yourself · 60 seconds

Do you actually know In-Context Learning?

Three quick questions. Result is saved into your review streak — come back when the term is due to lock it in.

Question 1 of 3Score: 0/3

Which best describes In-Context Learning?

Go deeper

Worked example, counter-example & concept map

On-demand AI analysis grounded in the Lab's research. Cached on your device after first run.

Diagnose

Find this pattern in your org →

15-minute III Assessment.

Learn

Master incentive intelligence →

12-week Executive Course.

Engage

Bring the Lab to your team →

Speaking, retainers, training.

How this lands in you

Your nervous system has a region for this.

Primary region

Prefrontal Cortex →

When you encounter In-Context Learning, your prefrontal cortex has to do extra work to override the automatic response — and that override budget is finite.

Executive control, planning, impulse override, working memory, System 2. First thing to go offline under stress, fatigue, or low blood sugar. Why your 4pm decisions are worse than your 9am ones.

See Prefrontal in the Brain Atlas →