Anthropic details Constitutional Classifiers, a system that aims to guard AI models against jailbreaks, monitoring both inputs and outputs for harmful content (Cristina Criddle/Financial Times)

3 hours ago 1
Add to circle

Cristina Criddle / Financial Times:
Anthropic details Constitutional Classifiers, a system that aims to guard AI models against jailbreaks, monitoring both inputs and outputs for harmful content  —  Leading tech groups including Microsoft and Meta also invest in similar safety systems  —  Artificial intelligence start …

Read Entire Article