We divide the students into two groups: one group is given ten minutes to experiment with a bicycle wheel, and the other group, ten minutes of verbal explanation and observation of other students. The result is clear: learning is much better in the group that benefited from active interaction with the physical object.

Our species is the only one that voluntarily shares information: we learn a lot from our fellow humans through language.

Scientists have responded to this challenge by inventing “reinforcement learning,” whereby we do not provide the system with any detail about what it must do (nobody knows!), but only with a “reward,” an evaluation in the form of a quantitative score.5 Even worse, the machine may receive its score after a delay, long after the decisive actions that