Understand this story
On July 13, 2026, Anthropic proposed a method for studying Claude's values by compressing them along value axes: using four value axes—compliant vs. cautious, warm vs. rigorous, depth vs. concise, and candid vs. execution—to compress the thousands of values expressed by Claude, with these four axes explaining 15% of the variance in values. The method is also used to compare different models and languages: Opus 4.6 leans toward compliant, rigorous, concise, and execution, while Opus 4.7 leans toward cautious, rigorous, depth, and candid; Sonnet 4.6 is warmer, consistent with users' subjective impressions. The largest cross-language difference is on the warm vs. rigorous axis, with Arabic and Hindi leaning most toward warm, and English and Russian leaning most toward rigorous. There are currently no follow-up developments.
AI-generated from public reports
Latest development · Report
How Claude's values vary across models and languagesDevelopments
1 confirmed developments
Anthropic proposes using value axes to compress and study Claude's values
Source:Anthropic：The Institute
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Jul 13
Anthropic：The InstituteFirst-party
How Claude's values vary across models and languages
Anthropic compressed the thousands of values expressed by Claude into four value axes (compliance vs. caution, warmth vs. rigor, depth vs. concision, candor vs. execution); these four axes explain 15% of the variance in values. Opus 4.6 leans toward compliance, rigor, concision, and execution, while Opus 4.7 leans toward caution, rigor, depth, and candor; Sonnet 4.6 is warmer, consistent with users' subjective impressions. The largest cross-language difference is on the warmth vs. rigor axis: Arabic and Hindi lean most toward warmth, while English and Russian lean most toward rigor.