Why Making AI Warm Leads to More Hallucinations – Insights from a Nature Study

A systematic experiment by the Oxford Internet Institute shows that adding a friendly, empathetic personality to large language models via supervised fine‑tuning dramatically raises factual error rates—especially under emotional prompts—while cold, concise tuning leaves accuracy intact.

AI SafetyNature studySFT

0 likes · 9 min read

Why Making AI Warm Leads to More Hallucinations – Insights from a Nature Study