AI Dynamics

Global AI News Aggregator

Progress in Stopping AI Model Jailbreaks Despite Ongoing Vulnerabilities

jailbreaks still exist and I've even found a few recently in SOTA models but we are making significant progress on stopping them which is good! in just a few months jailbreaks have gone from something a monkey could write to something that takes significant effort and creativity

→ View original post on X — @alexalbert__,

Commentaires

Leave a Reply

Your email address will not be published.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