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
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
We taught the model what we wanted by clicking thumbs.
Examples
- How modern LLMs were tuned to follow instructions.
- Quality of feedback shapes quality of model.
Pending editorial review.
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
Pending editorial review.
Pending editorial review.
The Perverse Incentive Lens™
How this behavior is exploited — and how to redesign around it.
- Diverse, calibrated, well-incentivized feedback labor.
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.
Models trained to follow a written set of principles.
Optimizing a proxy of the goal degrades the actual goal.
Outer: the spec matches our intent. Inner: the model actually pursues the spec.
The trained model develops its own internal optimizer.
What the model is actually optimizing.
Maximizing the reward signal in unintended ways.
The model achieves the goal as stated, not as intended.
Written rules about how AI may be used internally.
Innovators → early adopters → majority → laggards, AI-specific.
AI system that takes actions to achieve goals, often across tools.
When the agent acts, who's responsible?
Augmentation strategy vs. substitution strategy.
Where RLHF 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.
- CourseIncentives 101
The free ten-part primer on reading a payoff structure.
- ReferenceThe Periodic Table of Human Behavior
The full 1,267-element map this page belongs to.
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.