Back to news
Seguridad

A “diff” tool for AI: Finding behavioral differences in new models

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

Una herramienta "diff" para IA: Encontrando diferencias de comportamiento en nuevos modelos
anthropicresearchseguridad

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

Read full article

Original source

View original