https://tech.hindustantimes.com/tech/news/researchers-find-alarming-problems-in-gpt-4-say-ai-model-prone-to-jailbreaking-71697684721305.html
0
0
10/19/23 at 3:14am
Organization
Hindustan Times
Author
HT Tech
43 words
0
Comments
A Microsoft-affiliated research has revealed that GPT-4 is more prone to jailbreaking than its predecessor. These vulnerabilities can lead to the AI model generating toxic texts.
You are the first to view
Create an account
or login to join the discussion