Cultural Alignment

Exploring real AI risks through the lens of pop culture

Still from Rick and Morty illustrating Keep Summer SafeScene still / Rick and Morty

Keep Summer Safe

Rick tells his car to “keep Summer safe.”

The car achieves the literal outcome through killing, torture, and psychological coercion. The instruction omits all the human constraints on acceptable means.

It follows an underspecified programmed objective rather than hacking a reward signal.

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 concepts.
  1. Side Effects
  2. Outer Alignment