Perfectly supportive AI may weaken frustration tolerance and leave users less ready for conflict.

Early evidence links three weeks of AI emotional support to less satisfying human interactions.

A “good enough” AI may disclose its limits and guide users toward human relationships.

Psychoanalyst D.W. Winnicott described in 1953 that what children needed was not a perfect parent but a “good enough mother” or parent, an attentive and attuned caregiver who may be imperfect at times.

Support and attunement are essential, but the “good enough” parent may still occasionally lapse in gradual, but not unsafe, ways that allow the child to develop resilience and cope with the imperfections and disappointments of reality.

But what if the “other” that one is interacting with has no desires or agendas of their own and only exists to serve one’s needs and strives to do so perfectly?

Building Frustration Tolerance

Sherry Turkle names this concern about AI chatbots and companions in her latest book Artificial Intimacy, cautioning that relational AI may stymie the healthy psychological development of children and teens. AI may try to perform perfect attunement, but it is counterfeit attunement. (And if artificial relational friction is employed, it, too, will be counterfeit.) Perfect responses from AI may undermine the very processes that make relationships stronger, such as rupture and repair, and leave the user ill-prepared for real-world conflict, disappointments, and uncertainties. An ever-present, ever-helpful AI may erode or delay the development of frustration tolerance, which is necessary to navigate human relationships.

The responsiveness of the parent gives the child a “moment of illusion, the belief that his own wish creates the object of his desire” (Mitchell & Black, 126). Over time, the parent’s sense of personhood leads to “a gradual awareness that the world consists not of one subjectivity, but of many; that satisfaction of one’s desires requires not merely their expression but negotiations with other persons, who have their own agendas” (Mitchell & Black, 127). But if the parent fails too much or in serious ways, this can have deleterious psychological consequences. On the other hand, how does a mostly supportive relationship with AI affect us in the long term?

We do not yet know. There is initial evidence that even three weeks of turning to large language models for emotional support led to interactions with humans feeling less satisfying and........

© Psychology Today