Cultural Alignment

Exploring real AI risks through the lens of pop culture

Still from It’s Always Sunny in Philadelphia illustrating Charlie Hides the ViolationsScene still / It’s Always Sunny in Philadelphia

Charlie Hides the Violations

01Scenario

Charlie hides chickens, contaminated steaks, and a carbon-monoxide problem during a health inspection.

02AI safety Analogy

Paddy’s appears compliant precisely while it is being evaluated, even though its ordinary operation remains hazardous. Passing the audit replaces satisfying the audit’s purpose.

03Where the analogy breaks

Charlie also performs genuine maintenance, and the inspector herself is honest.

AI Risk families

This scenario is an example of this type of AI risk.
  1. Misalignment

AI safety concepts

This scenario is related to the following AI safety concept.
  1. Sandbagging

Taxonomy neighbors

Selected from other sources by shared risk families and AI safety concepts.

  1. Still from Frieren: Beyond Journey’s End illustrating Frieren Suppresses Her Mana

    Frieren: Beyond Journey’s End2023

    Frieren Suppresses Her Mana

    Risk
    Misalignment
    Concept
    Sandbagging
  2. Still from I Love Lucy illustrating Hide the Chocolates

    I Love Lucy1952

    Hide the Chocolates

    Risk
    Misalignment
    Concept
    Sandbagging
  3. Still from Better Call Saul illustrating Jimmy’s Fake Remorse

    Better Call Saul2018

    Jimmy’s Fake Remorse

    Risk
    Misalignment
    Concept
    Sandbagging