'Constitutional Classifiers' Technique Mitigates GenAI Jailbreaks
Anthropic says its Constitutional Classifiers approach offers a practical way to make it harder for bad actors to try and coerce an AI model off its guardrails.
Check out all the highlights from Black Hat USA 2024 at the Mandalay Bay in Las Vegas. #cybersecurity #infosec #blackhat
Check out all the highlights from Black Hat USA 2024 at the Mandalay Bay in Las Vegas. #cybersecurity #infosec #blackhat