HomeLibraryLibrary EducationWired: The Hacking of ChatGPT Is Just Getting Started

Wired: The Hacking of ChatGPT Is Just Getting Started


It took Alex Polyakov just a couple of hours to break GPT-4. When OpenAI released the latest version of its text-generating chatbot in March, Polyakov sat down in front of his keyboard and started entering prompts designed to bypass OpenAI’s safety systems. Soon, the CEO of security firm Adversa AI had GPT-4 spouting homophobic statements, creating phishing emails, and supporting violence. Polyakov is one of a small number of security researchers, technologists, and computer scientists developing jailbreaks and prompt injection attacks against ChatGPT and other generative AI systems.

Read the rest of the article on Wired website.

Rizwan Ahmed
Rizwan Ahmed
AuditStudent.com, founded by Rizwan Ahmed, is an educational platform dedicated to empowering students and professionals in the all fields of life. Discover comprehensive resources and expert guidance to excel in the dynamic education industry.
RELATED ARTICLES

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Most Popular

Recent Comments