Story

Show HN: LLM Politeness Study (hostile and effusive tones boost LLM creativity)

capex Monday, December 22, 2025

I ran 625 API calls across 5 frontier models to find out what makes LLMs produce better creative work. The answer surprised me: it's not about being rude or polite, it's about emotional intensity.

Summary
This study examines the impact of language model politeness on human-AI interaction, finding that more polite language models can improve user satisfaction and perceived intelligence without affecting task performance.
3 0
Summary
aklodhi98.github.io
Visit article Read on Hacker News