Study Finds Rude Prompts Outperform Polite Ones in ChatGPT Accuracy
The wording of natural language prompts has been shown to influence the performance of large language models (LLMs), yet the role of politeness and tone remains underexplored. In this study, we…
Read the full articleYou might also wanna read
Study finds large language models vulnerable to classic persuasion tactics for harmful requests
Are large language models (LLMs) susceptible to the same persuasive appeals as humans? We tested whether classic persuasion principles (auth
pnas.org·1mo agoShorter AI Prompts Often Outperform Longer Ones, Here Is Why
A technical analysis published on DEV Community argues that adding more words to an AI prompt typically degrades output quality rather than
The Cost of Kindness: Why Friendly AI Fails the Accuracy Test
Can AI be too kind? Oxford researchers found that prioritising chatbot empathy leads to a 30% increase in errors during critical, high-stake
Study finds nearly half of AI chatbot medical advice is inaccurate or fabricated
A new study found that nearly half of the medical advice generated by popular AI chatbots like ChatGPT and Grok is problematic. The chatbots
psypost.org·1mo ago
Study of 5 million queries reveals ChatGPT rewrites searches, injecting 'best,' 'reviews,' and current year
Peec AI's analysis of 5 million fanouts shows ChatGPT injects 'best,' 'reviews,' and '2026' into hidden searches, explaining why listicles d
ppc.land·1mo ago
Penn State study finds AI chatbots answer health questions accurately 75% of the time, experts urge caution
A new study reveals how AI is changing the game for online medical advice, but researchers urge caution before you self-diagnose.
fox7austin.com·21d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.