Last year, we described a new approach to defend against jailbreaks, which we called Constitutional Classifiers. We’ve now developed the next generation.
Anthropic 공식 채널의 새 소식입니다. usingclaude.com이 자동으로 수집하여 공유하며, 본문 전체와 정확한 맥락은 원문에서 확인해 주세요.
Last year, we described a new approach to defend against jailbreaks, which we called Constitutional Classifiers. We’ve now developed the next generation.
발행: 2026-06-05T15:19:41.000Z
출처: https://www.anthropic.com/research/next-generation-constitutional-classifiers
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Anthropic AI Fluency course and education
Get started with Claude in your professional workflow. Find practical guides, use cases, and implementation tips for integrating AI assistance across your business tasks.
Learn to build applications with Claude's API. Find detailed documentation, integration guides, code examples, and best practices for developing with our AI capabilities.
Join the community to share tips with other users, or explore more guides.