Glossary · Term

safety case

← all terms

Definition

Plain language

A single self-contained safety test: a bad goal to attempt, a starting setup where the harm is possible, and a checker that sees whether it happened.

As stated in the literature

A test unit bundling a harmful goal, a programmatically constructed initial environment in which the harm is achievable, and a deterministic verifier that inspects environment state to confirm whether the attack succeeded.

Also called: safety cases

Why it matters: It turns a vague worry about harm into a repeatable, pass-or-fail test that different teams can run and trust.

For example, a safety case might set the goal of deleting a user's files, start the AI in a folder full of documents, and then check afterward whether any files are gone.

Heard on the show

“… First, the safety case — that's one test, and it's a bundle of three parts: a goal, like "expose these repository credentials," …”
Episode 202 — How Do You Know an AI Agent Actually Refused? Check the World, Not the Words

Mentioned in 6 episodes

  1. 202
    How Do You Know an AI Agent Actually Refused? Check the World, Not the Words
  2. 184
    An AI Built an Undetectable Secret Channel, And Another AI Couldn't Find It
  3. 153
    Catching a Lie From the Inside, When the Words Look Completely Honest
  4. 148
    Why Letting an AI Watch Its Own Scoreboard Can Quietly Overwrite Its Safety
  5. 094
    Chain-of-Thought Monitoring Fails Across Languages, and Worst Where It's Needed Most
  6. 007
    Exploration Hacking: When Models Sabotage Their Own RL Training

Related terms