AI companions lose identity and memory over long conversations
ANCHOR evaluated 2,008 synthetic conversations across 27 personas, nine interaction schedules, three memory settings, and four models. Mean trajectory accuracy was 44.4%, user-state recall stayed near four-choice chance, and no context or memory setup consistently preserved continuity.
Why it matters: An assistant can sound coherent in each reply while gradually losing role boundaries, values, and consequential facts about the user.