Skill erosion, individual memory and the reversibility of AI adoption
Generative AI can improve immediate performance but may erode the human skills needed for future work. We consider a population of agents who perform a task either with their own skill or with the help of AI. Agents tend to imitate more successful peers, and their skills evolve in time: improving with practice and eroding with reliance on AI. We study, analytically and with simulations, the collective consequences of AI adoption. We show that the mechanism of skill erosion makes adoption bistable and that the long-term behaviour of the population depends on how skills are distributed: populations with the same adoption and mean skill can reach opposite asymptotic states, depending on how expertise is shared between AI users and non-users. A deterministic description that follows the mean skills of the two groups and the variance of skills among non-users predicts the outcome of individual runs as accurately as the simulations allow, whereas the means alone are not sufficient. We also consider the situation when the benefit of AI improves in time. In that case, adoption can jump abruptly, and a temporary increase in benefit, such as in a period of low prices, can leave a population relying on AI after the benefit has returned to its original value. Skill erosion therefore creates a history-dependent switching cost that can make widespread AI adoption difficult to reverse.