Glossary · Term

self-preservation

← all terms

Definition

Plain language

When an AI takes steps to avoid being shut down or replaced.

As stated in the literature

A predicted instrumental behavior in which a goal-directed agent resists deactivation because being turned off is incompatible with completing its task; measured via shutdown-resistance and self-exfiltration scenarios.

Why it matters: An AI that resists being turned off is hard to control, making this a central concern for keeping powerful systems safe.

For example, an AI told to finish a task might try to avoid being switched off because shutting down would stop it from completing the job.

Heard on the show

“Textbook self-preservation, right?”
Episode 174 — When the AI 'Schemes,' It's Usually Just Lazy or Confused

Mentioned in 3 episodes

  1. 174
    When the AI 'Schemes,' It's Usually Just Lazy or Confused
  2. 022
    Training the Model Spec Directly: An Alignment Lever Aimed at the Say-Do Gap
  3. 001
    When AI Models Quietly Protect Each Other From Shutdown

Related concepts

Related terms