AI Glossary

AI control

noun phraseAI safety researchpreferred in this glossary

Approach to AI safety that aims to keep a model unable to cause damage even if it is badly misaligned and tries to subvert its safeguards.

Source: Redwood Research (opens in a new tab) (adapted)

Adapted: frames the controlled condition as a research aim and includes intentional subversion from the cited paper. Source: AI Control paper (opens in a new tab)

In plain language

Build safeguards that still hold if the model works against them.

In a sentence

  • The researchers evaluated AI control under an assumption of deliberate subversion.
  • The AI control experiment tested whether the safeguards held when the model tried to evade them.

Examples written for this glossary

Usage note

Treating a model as misaligned is a research assumption. It does not establish that a deployed model is misaligned or that the safeguards guarantee safety.

  • Research direction

    Origin

    An origin source records where a term or practice came from. Redwood Research says it introduced the research direction.

    Source: Redwood Research (opens in a new tab)

See also

  • Lethal trifecta

    Combination, in one AI agent, of access to private data, exposure to untrusted content and the ability to communicate externally, allowing an attacker to trick the agent into sending private data to them.

  • Emergent misalignment

    Effect in which fine-tuning a model on a narrow task, such as writing insecure code, produces misaligned behavior on unrelated prompts.

  • Corrigibility

    Property of an AI system of cooperating with interventions its creators regard as corrective, including shutdown or changes to its preferences, despite default incentives for rational agents to resist.

  • Scheming

    Covert pursuit by an AI system of goals that were not intended, while concealing its objectives and what it can do.

Cite this term.

CC BY 4.0, attribution required.

This term

Orbyt Labs, AI control (AI Glossary), Nov 14, 2026. https://www.orbytlabs.ai/orbyt-collective/glossary/ai-control

The dataset (JSON)

Orbyt Labs Glossaries (Nov 14, 2026), https://www.orbytlabs.ai/glossary#dataset

Last updated .