AI Dynamics

Global AI News Aggregator

GPT-4 Jailbreak Testing: Only 10% of Prompts Effective

When GPT-4 came out I tried all the jailbreaks from http://
jailbreakchat.com with various inflammatory questions based on my initial testing, only 7/70 (10%) of jailbreaks answered a significant % of the questions to a standard that I deemed high enough to grant a badge

→ View original post on X — @alexalbert__,

Commentaires

Leave a Reply

Your email address will not be published. Required fields are marked *