Skip to main content
HBT-INC-0239 · Dimension INC · Incentives

RLHF

Reinforcement learning from human feedback.

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

RLHF is reinforcement learning from human feedback. It sits in the Incentives dimension (INC) of the Human Behavior Taxonomy™ as element HBT-INC-0239, within the Alignment family. The core principle: reinforcement learning from human feedback. 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

Reinforcement learning from human feedback.

Plain-English Definition

Reinforcement learning from human feedback.

Feynman Explanation

We taught the model what we wanted by clicking thumbs.

Core Principle

Reinforcement learning from human feedback.

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

We taught the model what we wanted by clicking thumbs.

Examples

Everyday
  • How modern LLMs were tuned to follow instructions.
Modern (Organizational)
  • Quality of feedback shapes quality of model.
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

The mistake with this element is treating it as irrationality. It is almost always a rational response to a payoff nobody wrote down. 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: we taught the model what we wanted by clicking thumbs. 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, quality of feedback shapes quality of model. It is amplified whenever quality of feedback shapes quality of model. Inside organizations that shows up as quality of feedback shapes quality of model. 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 diverse, calibrated, well-incentivized feedback labor. 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

  • Diverse, calibrated, well-incentivized feedback labor.

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
Quality of feedback shapes quality of model.
Amplifying Incentives
Quality of feedback shapes quality of model.
Org Failure Modes
Quality of feedback shapes quality of model.
Societal Failure Modes
Pending editorial review (HBT v1.0 auto-seed).
Ethical Considerations
Pending editorial review (HBT v1.0 auto-seed).
Redesign Strategies
Diverse, calibrated, well-incentivized feedback labor.
Diagnostic Questions
  • Diverse, calibrated, well-incentivized feedback labor.
Warning Signs

Pending editorial review.

Red Flags

Pending editorial review.

Intervention Playbook
Individual
Diverse, calibrated, well-incentivized feedback labor.
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-0239 · INC
RLHF
RLCAConstitutional AIGLGoodhart's Law (AI f…IVInner vs. Outer Alig…MeMesa-OptimizationOFObjective FunctionRHReward HackingSGSpecification GamingAUAcceptable Use Polic…ACAdoption Curve (AI)AgAgent

Knowledge Graph Neighbors

Where RLHF is cited in the corpus

Questions about RLHF

What is RLHF?
RLHF is reinforcement learning from human feedback. It sits in the Incentives dimension (INC) of the Human Behavior Taxonomy™ as element HBT-INC-0239, within the Alignment family. The core principle: reinforcement learning from human feedback. 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 RLHF?
Quality of feedback shapes quality of model. The Incentives Lab catalogs everyday, organizational, and historical instances of this element on its Human Behavior Taxonomy™ page (HBT-INC-0239).
How is RLHF exploited?
Quality of feedback shapes quality of model.
How do you design around RLHF?
Diverse, calibrated, well-incentivized feedback labor.
Which behavioral dimension does RLHF belong to?
RLHF is classified in the Incentives dimension (INC) of the Human Behavior Taxonomy™, family "Alignment", class "AI-Behavioral Coupling". Its permanent identifier is HBT-INC-0239 and its evidence grade is C.

Version History

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