UTC+7
TECHNOLOGY / IMAGINATION / UNIVERSE
VXNUS
STAY CURIOUS

VXNUS / Archive

AI safety and privacy

Article connected to ai safety and privacy.

01

VX-26-05

The Limits of Being Told Who They Are

This research examines whether AI companions can move beyond static, prompt-defined descriptions of a person toward evolving, evidence-based models of them, and finds the idea technically plausible, ethically fraught, and only partially novel.

human-AI relationshipsAI memory architecturesPersonal identity and continuityUser modeling and personalizationAI safety and privacy
14 min readRead article