Home Prototypes Being mean to ChatGPT increases its accuracy — but you may end... Prototypes Being mean to ChatGPT increases its accuracy — but you may end up regretting it, scientists warn By styloux - October 27, 2025 15 0 FacebookTwitterPinterestWhatsApp Being curt or outright mean may make a newer AI model more accurate, a new study shows, defying previous findings on politeness to AI. RELATED ARTICLESMORE FROM AUTHOR Prototypes Lawmakers are shown how ‘jailbroken’ AI can plan terror attacks Prototypes Eliminate jobs tax for workers to compete with AI, says Sunak Prototypes Oklahoma City symposium explores data centers’ impact on Earth Day Prototypes ‘I think it’s a mistake’: Delta CEO Ed Bastian refuses to call it ‘artificial intelligence’ because it scares people Prototypes AI data centers are becoming more eco-friendly. Here’s how Prototypes Time to apply the brakes to runaway AI, says pioneer LEAVE A REPLY Cancel reply Please enter your comment! Please enter your name here You have entered an incorrect email address! Please enter your email address here Save my name, email, and website in this browser for the next time I comment. - Advertisement -APLICATIONS Prototypes Missed Out on Investing in Palantir? 1 No-Brainer Artificial Intelligence Stock... styloux - January 3, 2026 0 Key PointsAlphabet is one of the best ways to capitalize on the AI revolution, considering its diversified approach to the technology. Outrage as Chilean burglary gang films themselves stealing $3M from jewelry... March 2, 2026 Trump administration watches over Iran protests January 10, 2026 DISTURBING NEW TREND: ‘Snatch and grab’ jewelry thefts on the rise April 17, 2026 HOT NEWS Get ‘The Devil Wears Prada 2’ popcorn purse Prototypes Get ready for the AI ad-pocalypse Prototypes Coinbase CEO Brian Armstrong trolls the prediction markets News Palisades News