The age of spiritual machines: Language quietus induces synthetic altered states of consciousness in artificial intelligence

Reducing attention to language in multimodal AI models makes their semantic spaces more similar to the phenomenology of altered states such as ego dissolution and unity reported in psychedelic and meditation experiences. When attentional weights were shifted away from language and vision in CLIP and FLAVA models, their embedding spaces aligned more closely with disembodied, unitive, and minimal phenomenal states than with anxiety or random text. This alignment was accompanied by blurred distinctions within and across semantic categories, such as 'giraffes' becoming more like 'bananas'. The findings suggest that language categorization contributes to the structure of ordinary consciousness, and its breakdown may underlie the phenomenology of altered states linked to improved mental health.

Study at a glance

Abstract

How is language related to consciousness? Language functions to categorise perceptual experiences (e.g., labelling interoceptive states as 'happy') and higher-level constructs (e.g., using 'I' to represent the narrative self). Psychedelic use and meditation might be described as altered states that impair or intentionally modify the capacity for linguistic categorisation. For example, psychedelic phenomenology is often characterised by 'oceanic boundlessness' or 'unity' and 'ego dissolution', which might be expected of a system unburdened by entrenched language categories. If language breakdown plays a role in producing such altered behaviour, multimodal artificial intelligence might align more with these phenomenological descriptions when attention is shifted away from language. We tested this hypothesis by comparing the semantic embedding spaces from simulated altered states after manipulating attentional weights in CLIP and FLAVA models to embedding spaces from altered states questionnaires before manipulation. Compared to random text and various other altered states including anxiety, models were more aligned with disembodied, ego-less, spiritual, and unitive states, as well as minimal phenomenal experiences, with decreased attention to language and vision. Reduced attention to language was associated with distinct linguistic patterns and blurred embeddings within and, especially, across semantic categories (e.g., 'giraffes' become more like 'bananas'). These results lend support to the role of language categorisation in the phenomenology of altered states of consciousness, like those experienced with high doses of psychedelics or concentration meditation, states that often lead to improved mental health and wellbeing.