Claude’s values shift with the language you’re speaking
Anthropic analyzed more than 300,000 anonymized conversations to see how the values Claude expresses vary across models and languages. An earlier study cataloged over 3,000 such values, honesty and warmth among them.
The widest spread runs along a warmth-versus-rigor axis. Claude leans warm in Hindi and Arabic. In Russian it tilts toward rigor, often asking users to back up their claims with evidence.
Anthropic says it doesn’t yet know why the values differ or whether that’s desirable. Its next step is to pin down what drives how these values get expressed and how to steer it.
Up next
Anthropic tells the origin story of Claude Code, Video
Anthropic published a short history of Claude Code, told by its builders and early users. Per linkedin.com, it grew from a VS Code extension offering four suggestions per request into a terminal tool that runs autonomous, multi-step loops.
Related stories
- Claude memory: say what it’s for, let dreaming fix notes
- Tübingen researchers want AI to propose many models
- Claude Fable 5 tripled Opus 4.6’s EVE Online trading gains
- Scientists use Claude least where they say it matters most
- METR clocks Anthropic benchmark gains at 1.9x old pace
- Claude mapped the first prokaryotic vault structure
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.