> In a new class of attack on AI systems, troublemakers can carry out these environmental indirect prompt injection attacks to hijack decision-making processes.
I have a coworker who brags about intentionally cutting off Waymos and robocars when he sees them on the road. He is "anti-clanker" and views it as civil disobedience to rise up against "machines taking over." Some mornings he comes in all hyped up talking about how he cut one off at a stop sign. It's weird.
These drones have cameras, it's a matter of time before they "share" footage... basically becoming robo-cops, traffic edition - this might be of interest to your coworker.
Just tell him that Waymo is now sharing videos of this behavior with auto insurance companies.
I don't know if they are or not. But why wouldn't they...
This is a legitimate movement in my eyes. I don’t participate, but I see it as valid. This is reminiscent of the Luddite movement - a badly misunderstood movement of folks who were trying to secure labor rights guarantees in the face of automation and new tools threatening to kill large swaths of the workforce.