"Or at least that's what you'd think. As detailed in a post on the blog Less Wrong, AI tinkerer Richard Weiss came across a fascinating document that purportedly describes the "soul" of AI company Anthropic's Claude 4.5 Opus model. And no, we're not editorializing: Weiss managed to get the model to spit out a document called " Soul overview," which was seemingly used to teach it how to interact with users."
""Anthropic occupies a peculiar position in the AI landscape: a company that genuinely believes it might be building one of the most transformative and potentially dangerous technologies in human history, yet presses forward anyway," reads the document. "This isn't cognitive dissonance but rather a calculated bet - if powerful AI is coming regardless, Anthropic believes it's better to have safety-focused labs at the frontier than to cede that ground to developers less focused on safety.""
A document titled 'Soul overview' exists and was produced by or for Claude 4.5 Opus; that document was used in training. Anthropic confirmed the document's authenticity and stated the model was trained on it, including via supervised learning. The content frames Anthropic as prioritizing safety while pursuing powerful AI, arguing it is preferable for safety-focused labs to lead development. The document states that most unsafe or insufficiently beneficial AI results from models with explicitly or subtly wrong values, limited knowledge of themselves or the world, or lacking skills to translate good values into effective actions.
Read at Futurism
Unable to calculate read time
Collection
[
|
...
]