The age of spiritual machines: Language quietus induces synthetic altered states of consciousness in artificial intelligence
This research provides a computational model for understanding the role of language categorization in altered states of consciousness, potentially offering insights for researchers studying human consciousness and mental health.
This paper investigates the relationship between language and consciousness in AI by simulating altered states in CLIP and FLAVA models. By reducing attention to language and vision, the models' semantic embedding spaces aligned more with disembodied, ego-less, spiritual, and unitive states, as well as minimal phenomenal experiences, compared to various other altered states. This manipulation also led to blurred semantic categories, where distinct concepts like 'giraffes' and 'bananas' became more similar.
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.