Constitutional Classifiers: Defending against universal jailbreaks

Constitutional Classifiers: Defending against universal jailbreaks
Estimated read time 1 min read

Anthropic Safegaurds Research Team has developed a method ‘Constitutional Classifiers’ that protects LLMs against universal jailbreaks.

Continue reading on Medium »

 

​ Anthropic Safegaurds Research Team has developed a method ‘Constitutional Classifiers’ that protects LLMs against universal jailbreaks.Continue reading on Medium »   Read More AI on Medium 

#AI

Avatar for

You May Also Like

More From Author