Anthropic Analyzes Real-World Conversations to Uncover AI's "Values in the Wild"

  • Anthropic analyzed 700k real-world Claude chats to figure out what values it expresses naturally.

    One particularly interesting finding was that nearly half of Claude's real-world conversations involve subjective content...not just factual Q&A. From over 700,000 analyzed chats, ~44% include interactions where Claude had to express judgments or preferences.