AI safety concepts made visual, friendly, and easier to understand. Tap any card to see the full poster.
When sneaky instructions try to trick the robot into breaking its rules.
View explainer →
When the robot accidentally spills a secret it should have kept.
View explainer →
Sometimes bad ingredients sneak into the robot's toolbox.
View explainer →
When the robot learns from bad examples and picks up wrong ideas.
View explainer →
When an app trusts the robot's answer without double-checking it.
View explainer →
When the robot is allowed to do more than it really should.
View explainer →
When the robot's secret instructions slip out for everyone to see.
View explainer →
When the robot's memory lookup gets confused or tricked.
View explainer →
When the robot says something wrong but sounds very sure.
View explainer →
When the robot uses way too much and slows everything down.
View explainer →