Anthropic says some Claude models can now end ‘harmful or abusive’ conversations
Anthropic says some Claude models can now end ‘harmful or abusive’ conversations
이 글은 AI News & Artificial Intelligence | TechCrunch 블로그에 게시된 글을 자동으로 가져온 것입니다.
더 자세한 내용과 원문은 아래 링크를 참고해 주세요.
원문 요약
Anthropic says new capabilities allow its latest AI models to protect themselves by ending abusive conversations.
This post is licensed under CC BY 4.0 by the author.