cd/entity/ChatGPT 4o· home entities ChatGPT 4o
grep -l @chatgpt 4o /news/*.json | wc -l → 2

ChatGPT 4o

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

07:43
2026-05-26
arxiv.org
large-language-models

Prompt Politeness Affects LLM Accuracy

A new study found that impolite prompts produce more accurate responses from large language models than polite ones, with accuracy rising from 80.8% for very polite prompts to 84.8% for very rude prom…

// co-occurs with top 7 entities