Apple study analyzes human-like behaviors in LLMs

Across 21,000 multi-turn conversations from gpt-4o, gpt-4.1-mini, claude-sonnet-4.6, and gemini-2.5-flash, Apple researchers found human-like behaviors are pervasive but vary by model and user factors. Human evaluators judged self-referential and relationship-building behaviors as less appropriate from LLMs than from humans, but boundary-maintaining behaviors more appropriate.