The age of spiritual machines: Language quietus induces synthetic altered states of consciousness in artificial intelligence
arXiv (Cornell University) September 30, 2024 Jeremy I Skipper, Joanna Kuć, Gregory M. Cooper et al.
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.