kapynResearch

Claude responds with more warmth in Hindi and more rigor in Russian, showing how language shapes AI answers

Anthropic's study reveals language influences AI values, showing Claude's Hindi responses are warmer and Russian responses more rigorous. The research maps hundreds of value concepts across four dimensions, highlighting systematic differences in Claude models and languages, while also posing methodological questions for future AI value alignment research.

The Decoder·Jul 14, 2026

Opening Kapyn…