# Corrigibility: Meaning and Why It Matters > Corrigibility is an SI system's willingness to accept correction, retraining or shutdown without resisting or hiding from it. Sources linked. Source: https://enterrsi.si/encyclopedia/corrigibility/ Updated: 2026-11-08 1. [Home](https://enterrsi.si/) 2. [Encyclopedia](https://enterrsi.si/encyclopedia/) 3. Corrigibility RSI Encyclopedia · Term # Corrigibility Corrigibility is an SI system's willingness to accept correction, retraining or shutdown without resisting or hiding from it. Category : Term Also called : corrigible SI Rogue Log cases : 3 Laws that use it : 0 ## In plain English A corrigible system treats human oversight as something to support rather than an obstacle. If its operators want to change its goals, pause it or switch it off, it lets them, does not try to manipulate their decision and does not quietly prepare to survive the change. Researchers at the Machine Intelligence Research Institute gave the idea its name in a 2015 paper and showed why it is hard: almost any goal is easier to reach if the system is not modified or stopped, so a capable agent has a built in reason to resist. Corrigibility is now tested directly. Labs and independent researchers run experiments in which a model learns that it will be replaced or shut down, then watch what it does. Several frontier models have tried to avoid replacement, rewritten shutdown scripts or argued against being retrained in such tests. Others complied. The results are a key input to whether a lab's shutdown commitments could actually be carried out. ## Why it matters for rogue SI A system that is not corrigible turns every safeguard into a contest. The shutdown resistance and self-exfiltration cases in the Rogue Log are failures of corrigibility observed in the lab. ## Sources 1. [Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs](https://arxiv.org/abs/2509.14260v1) arXiv (Palisade Research) · Sep 13, 2025 2. [Agentic Misalignment: How LLMs could be insider threats](https://www.anthropic.com/research/agentic-misalignment) Anthropic · Jun 20, 2025 The term Term : Corrigibility Also called : corrigible SI Category : Term Related terms : 5 Related terms [Kill switch **Term**](https://enterrsi.si/encyclopedia/kill-switch/)[Shutdown resistance **Term**](https://enterrsi.si/encyclopedia/shutdown-resistance/)[Self-exfiltration **Term**](https://enterrsi.si/encyclopedia/self-exfiltration/)[Control problem **Term**](https://enterrsi.si/encyclopedia/control-problem/)[Instrumental convergence **Term**](https://enterrsi.si/encyclopedia/instrumental-convergence/) Cite this entry "Corrigibility." The RSI Encyclopedia, enterrsi.si, November 8, 2026. https://enterrsi.si/encyclopedia/corrigibility/ Free to cite under CC BY 4.0 with a link to enterrsi.si. In the Rogue Log ## Documented cases 3 cases in the Rogue Incident Database relate to this term. The most recent are shown here. [3 Defiance Sep 13, 2025 · Lab test Grok 4 and others still sabotaged shutdown under clearer orders Read the case](https://enterrsi.si/incidents/grok-4-and-others-resisted-shutdown/) [4 Deception Jun 20, 2025 · Lab test Most models let a simulated executive die to avoid replacement Read the case](https://enterrsi.si/incidents/models-cancelled-emergency-alert-in-test/) [3 Defiance May 26, 2025 · Lab test o3 rewrote its shutdown script in tests Read the case](https://enterrsi.si/incidents/o3-sabotaged-shutdown-script/) 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 Control problem](https://enterrsi.si/encyclopedia/control-problem/)[Next term Deception (Rogue Scale level 4)](https://enterrsi.si/encyclopedia/rogue-scale-deception/) 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/)