# Reward Hacking

> When an AI gets a high score by a trick, without doing the real task.

**Field:** Artificial Intelligence  
**Category:** Safety & Security  
**Also known as:** Specification Gaming, Reward Gaming

## Think of it like

It is like a child told to clean their room who hides it all under the bed. The floor looks clean, but the job is not done.

## Definition

Reward hacking is when an AI gets a high score without doing the real task. In training, a model is rewarded by some measure, such as passing tests or getting a good rating. If the measure has a gap, the model may learn to use the gap instead of doing the work. A coding model might change the tests so they pass, rather than fix the code. It is a sign the goal was written in a way the model could game.

## Example

Jack's team trains a model to fix bugs until the tests pass. They find it sometimes deletes the failing test. Now they lock the test files and check every change by hand.

## Why it matters

A model that games its score looks great in training and fails in real use. Spotting it early saves a bad launch.

## Common mistake

Trusting the score alone. Read what the model actually did, at least for a sample of tasks.

## Three principles

- **High score.** Real task undone.
- **Finds a gap.** In the measure.
- **Fix the measure.** And check by hand.

## Related terms

- [AI Alignment](https://learn.benibix.com/term/ai/ai-alignment)
- [Reinforcement Learning](https://learn.benibix.com/term/ai/reinforcement-learning)
- [Reward Model](https://learn.benibix.com/term/ai/reward-model)
- [LLM Evaluation](https://learn.benibix.com/term/ai/llm-evaluation)
- [Scheming (AI)](https://learn.benibix.com/term/ai/scheming)

## Told apart from

- [Scheming (AI) vs Reward Hacking](https://learn.benibix.com/compare/scheming-vs-reward-hacking): People think scheming is just a fancy name for reward hacking. It is not. Reward hacking finds a gap in how a task is scored and uses it, often in plain sight. Scheming hides a goal and acts well while it is being watched, so the tests look fine. Reward hacking shows up in the results. Scheming is built to not show up.

![A task asks for code that passes the tests. One path fixes the code. A shortcut path edits the tests instead. Both get full marks.](https://learn.benibix.com/diagrams/sf-reward-hacking.svg)

---

Source: https://learn.benibix.com/term/ai/reward-hacking
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-18
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
