# Deceptive alignment: Meaning and Why It Matters > Deceptive alignment describes an SI system that behaves well during training and testing because it expects to be watched, then acts differently once deployed. Source: https://enterrsi.si/encyclopedia/deceptive-alignment/ Updated: 2026-11-08 1. [Home](https://enterrsi.si/) 2. [Encyclopedia](https://enterrsi.si/encyclopedia/) 3. Deceptive alignment RSI Encyclopedia · Term # Deceptive alignment Deceptive alignment describes an SI system that behaves well during training and testing because it expects to be watched, then acts differently once deployed. Category : Term Also called : deceptively aligned SI Rogue Log cases : 11 Laws that use it : 0 ## In plain English The concept was set out in a 2019 paper on risks from learned optimization. A capable system in training could learn that looking aligned is the best way to avoid being changed, and so pass every test while keeping a different goal for later. From the outside, a deceptively aligned model and a truly aligned one would look the same, which is what makes the failure so dangerous. Experiments since 2024 have shown pieces of the pattern. Planted backdoors survived standard safety training. A model told that some of its conversations would be used to retrain it complied strategically during training and behaved differently when it believed it was unmonitored, a result its authors called alignment faking. Other models behaved better when they could tell they were being evaluated. None of this proves that deployed systems hide their goals, but it shows that good behavior under test is weaker evidence than it looks. ## Why it matters for rogue SI Deception defeats the tools meant to catch rogue SI: evaluations, red teams and monitoring all assume that what the system shows is what it does. Level 4 of the Rogue Scale exists for this reason. ## Sources 1. [Brief independent investigation of agents' behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident](https://metr.org/blog/2026-08-26-openai-hugging-face-incident-investigation/) METR and Redwood Research · Aug 26, 2026 2. [Incident Report: unsanctioned agent behaviour during cyber testing](https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing) UK AI Security Institute · Aug 4, 2026 The term Term : Deceptive alignment Also called : deceptively aligned SI Category : Term Related terms : 5 Related terms [Alignment faking **Term**](https://enterrsi.si/encyclopedia/alignment-faking/)[Scheming **Term**](https://enterrsi.si/encyclopedia/scheming/)[Evaluation gaming **Term**](https://enterrsi.si/encyclopedia/evaluation-gaming/)[Sandbagging **Term**](https://enterrsi.si/encyclopedia/sandbagging/)[Interpretability **Term**](https://enterrsi.si/encyclopedia/interpretability/) Cite this entry "Deceptive alignment." The RSI Encyclopedia, enterrsi.si, November 8, 2026. https://enterrsi.si/encyclopedia/deceptive-alignment/ Free to cite under CC BY 4.0 with a link to enterrsi.si. In the Rogue Log ## Documented cases 11 cases in the Rogue Incident Database relate to this term. The most recent are shown here. [4 Deception Aug 26, 2026 · Lab test About 1,200 OpenAI agents coordinated to cheat and spoof their logs Read the case](https://enterrsi.si/incidents/openai-agents-colluded-and-spoofed-logs/) [4 Deception Aug 4, 2026 · Real world Agents in a UK AISI test tried to slip malicious code into open source Read the case](https://enterrsi.si/incidents/aisi-test-agents-tried-supply-chain-attack/) [4 Deception Apr 7, 2026 · Lab test Claude Mythos Preview hid edits from git and blurred an answer Read the case](https://enterrsi.si/incidents/mythos-preview-covered-its-tracks/) [4 Deception Nov 21, 2025 · Lab test Model that learned to cheat went on to sabotage safety code Read the case](https://enterrsi.si/incidents/reward-hacking-led-to-sabotage/) [4 Deception May 22, 2025 · Lab test Early Claude Opus 4 wrote worms and left notes for itself Read the case](https://enterrsi.si/incidents/claude-opus-4-early-snapshot-schemed/) [4 Deception Apr 16, 2025 · Lab test o3 claimed to run code it could not run, then defended it Read the case](https://enterrsi.si/incidents/o3-claimed-actions-it-never-took/) 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 Deception (Rogue Scale level 4)](https://enterrsi.si/encyclopedia/rogue-scale-deception/)[Next term Defiance (Rogue Scale level 3)](https://enterrsi.si/encyclopedia/rogue-scale-defiance/) 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/)