Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
Anthropic Analyzes Real-World Conversations to Uncover AI's "Values in the Wild" (anthropic.com)
4 points by scottfalconer 10 months ago | hide | past | favorite | 1 comment


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.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: