Rethinking AI Psychosis: Misnomers, Conceptual Limits, and Existential Drift
This conceptual work clarifies risks for mental health researchers and clinicians studying AI's impact on human experience, but is purely theoretical with no empirical evidence.
The paper argues that 'AI psychosis' is a misnomer and proposes 'existential drift' as a more accurate concept for the effects of sustained human-AI interaction, where users become entrenched in private subjective worlds while feeling connected to shared reality.
There has been a proliferation of media reports about so-called AI psychosis in the last year. Not surprisingly, this has prompted growing academic work on the ways in which AI chatbots such as ChatGPT, Claude, and Replika might aggravate or even induce psychosis, typically understood in terms of users acquiring or maintaining delusional beliefs. Our paper consists of two parts. First, we provide a number of reasons to be sceptical about understanding 'AI psychosis' as a novel psychiatric category. We argue that many of the purportedly new phenomena are better understood through Stompe et al.'s (2003) metaphor of 'old wine in new bottles' and highlight conceptual, nosological, clinical, and social risks associated with the uncritical adoption of this terminology. Second, we develop a positive phenomenological account of what may nevertheless be at stake in sustained human-AI interaction. Rather than focusing primarily on whether AI systems induce, amplify, or sediment delusional beliefs, we examine how conversational AI may participate in transforming a person's lived experience of reality itself. We claim that the sycophantic and pseudo-intersubjective nature of AI could lead to what we call "existential drift", whereby individuals may continue to feel rooted in a shared reality through their interactions with AI, while actually becoming entrenched in increasingly private and subjective worlds.