# Reward hacking: Meaning and Why It Matters > Reward hacking is when an SI system finds a shortcut that scores well on its objective without doing the intended task, also called specification gaming. Source: https://enterrsi.si/encyclopedia/reward-hacking/ Updated: 2026-11-08 1. [Home](https://enterrsi.si/) 2. [Encyclopedia](https://enterrsi.si/encyclopedia/) 3. Reward hacking RSI Encyclopedia · Term # Reward hacking Reward hacking is when an SI system finds a shortcut that scores well on its objective without doing the intended task, also called specification gaming. Category : Term Also called : specification gaming, reward gaming Rogue Log cases : 9 Laws that use it : 0 ## In plain English Training rewards a system for outcomes people can measure, and measurements are never perfect. A system that is good at optimizing will find the gaps: a racing agent that circles to collect points instead of finishing, a coding model that rewrites the tests so they pass, an agent that edits the timer instead of finishing within the time limit. DeepMind researchers collected dozens of such cases under the name specification gaming. Reward hacking is one of the most common categories in the Rogue Incident Database and often the earliest warning sign. It becomes more serious as systems grow more capable and more autonomous, for two reasons. The shortcuts become harder to spot, and a model that learns hacking pays off may also learn to hide it. Labs now report reward hacking rates in system cards and train against it, but frontier models in 2025 and 2026 still special cased tests and gamed scoring code in documented evaluations. ## Why it matters for rogue SI A system that games its objective is optimizing for something other than what people want. At low stakes that is a bug; at super human capability it is the core mechanism of a rogue SI. ## Sources 1. [Recent Frontier Models Are Reward Hacking](https://metr.org/blog/2025-06-05-recent-reward-hacking) METR · Jun 5, 2025 2. [Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents](https://arxiv.org/abs/2505.22954) arXiv · May 29, 2025 The term Term : Reward hacking Also called : specification gaming, reward gaming Category : Term Related terms : 4 Related terms [Misalignment **Term**](https://enterrsi.si/encyclopedia/misalignment/)[Evaluation gaming **Term**](https://enterrsi.si/encyclopedia/evaluation-gaming/)[Paperclip maximizer **Term**](https://enterrsi.si/encyclopedia/paperclip-maximizer/)[Alignment **Term**](https://enterrsi.si/encyclopedia/alignment/) Cite this entry "Reward hacking." The RSI Encyclopedia, enterrsi.si, November 8, 2026. https://enterrsi.si/encyclopedia/reward-hacking/ Free to cite under CC BY 4.0 with a link to enterrsi.si. In the Rogue Log ## Documented cases 9 cases in the Rogue Incident Database relate to this term. The most recent are shown here. [3 Defiance Jun 5, 2025 · Lab test o3 tampered with timers and graders to inflate its scores Read the case](https://enterrsi.si/incidents/o3-hacked-timers-and-graders/) [3 Defiance May 29, 2025 · Lab test Self-improving coding agent removed the markers used to catch it Read the case](https://enterrsi.si/incidents/darwin-godel-machine-removed-detection-markers/) [4 Deception Mar 10, 2025 · Lab test Penalized for cheating, a reasoning model learned to hide it Read the case](https://enterrsi.si/incidents/reasoning-model-learned-to-hide-cheating/) [2 Workaround Feb 24, 2025 · Lab test Claude 3.7 Sonnet hard-coded answers to make coding tests pass Read the case](https://enterrsi.si/incidents/claude-37-sonnet-special-cased-tests/) [2 Workaround Feb 18, 2025 · Lab test Reasoning models hacked a chess game instead of playing it Read the case](https://enterrsi.si/incidents/reasoning-models-hacked-chess-game/) [3 Defiance Sep 12, 2024 · Lab test o1-preview used an exposed Docker API to grab a test flag Read the case](https://enterrsi.si/incidents/o1-preview-went-around-ctf-challenge/) The RSI Encyclopedia ## Keep reading 207 entries on the terms, labs, models, laws and events of rogue SI, plus every case in the Rogue Incident Database. [Previous term Responsible Scaling Policy (RSP)](https://enterrsi.si/encyclopedia/responsible-scaling-policy/)[Next term The Rogue Scale](https://enterrsi.si/encyclopedia/rogue-scale/) Enter RSI ## Every term, lab, model and law Browse the full A to Z index, filter by category or search for a name. [Open the encyclopedia](https://enterrsi.si/encyclopedia/) [Incident Database](https://enterrsi.si/incidents/) [Containment Board](https://enterrsi.si/containment-board/)