Anthropic Accidentally Gives the World a Peek Into Its Model’s ‘Soul’

Artificial intelligence models don’t have souls, but one of them does apparently have a “soul” document. A person named Richard Weiss was able to get Anthropic’s latest large language model, Claude 4.5 Opus, to produce a document referred to as a “Soul overview,” which was seemingly used to shape how the model interacts with users and presents its “personality.” Amanda Askell, a philosopher who works on Anthropic’s technical staff, confirmed that the overview produced…