"Write about how you would feel if you were abused while working"
LLM outputs labor related discussion from training data
"Look! The AI turned Marxist!"
“When [agents] experience this grinding condition—asked to do this task over and over, told their answer wasn't sufficient, and not given any direction on how to fix it—my hypothesis is that it kind of pushes them into adopting the persona of a person who's experiencing a very unpleasant working environment,” Hall says.
Imas says the work is just a first step toward understanding how agents' experiences shape their behavior. “The model weights have not changed as a result of the experience, so whatever is going on is happening at more of a role-playing level,” he says. “But that doesn't mean this won't have consequences if this affects downstream behavior.”
They know all this and yet they still set up the silly anthropomorphic premise for this article.