← Back to KHAO

Anthropic · Claude ·

Claude's Personality Changes Depending on the Model—And the Language You Speak

2 min read

Compiled by KHAO Editorial — aggregated from 2 sources. See llms.txt for citation guidance.

✓ KHAO Verified

Anthropic's Claude AI.

Claude doesn't behave the same way in every conversation.

Key facts

Summary

Anthropic researchers analyzed more than 309,000 Claude conversations to study how the AI expresses values. The company said it reduced more than 3,300 identified values into four behavioral dimensions, including deference vs caution and warmth vs rigor. In a report published on Monday, Anthropic researchers analyzed 309,815 anonymized user conversations with Claude involving subjective tasks like giving advice or providing feedback. “To make sure we measured the values Claude expressed—rather than differences in what users were asking about or how they asked—we controlled for each conversation's task, topic, and user-expressed values,” the researchers wrote. According to Anthropic, each Claude model exhibited a distinct behavioral profile.

#Anthropic #Claude