Kyle Fish
model welfare team at Anthropic
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Not Just Claude: Mapping "Spiritual Behavior" in 141 Large Language Models
Independent researcher Matthew Korpman reports replicating Anthropic's open-ended two-model conversation test on 141 models, about 28,800 conversations. Korpman finds spiritual language in nearly all models and self-applied spiritual language in most labs' models, with large swings between releases, and calls the work descriptive, not causal.