Skip to main content
See every side of every news story
Published loading...Updated

Want better ChatGPT responses? Try this surprising trick, researchers say

Penn State researchers found very rude prompts increased ChatGPT GPT-4o accuracy to 84.8%, compared to 80.8% for very polite prompts in multiple-choice tests.

Summary by ZDNet
A study by researchers from Penn State University found that rude prompts garnered more accurate results than did polite ones.

Bias Distribution

  • 67% of the sources lean Left
67% Left

Factuality 

To view factuality data please Upgrade to Premium

Ownership

To view ownership data please Upgrade to Vantage

ZDNet broke the news in United States on Monday, November 3, 2025.
Sources are mostly out of (0)
News
For You
Search
BlindspotLocal