Model
95d agoAnthropic Co-Founder Claims AI Models Show Introspection
Christopher Olah claims AI models exhibit introspection and emotion-like states. He presented these views during the launch of Pope Leo XIV's encyclical, Magnifica Humanitas. The Pope disagreed, stating systems merely imitate human intelligence.
The Signal
This clash highlights the widening gap between technical interpretability research and philosophical definitions of consciousness for AI practitioners.