무슨 발표인가

• AI 모델 궤적의 잠재 국가안보 위험 평가
• 위험 평가 도전과 최적사례 논의

원문 (영어)

In this post, we are sharing what we have learned about the trajectory of potential national security risks from frontier AI models, along with some of our thoughts about challenges and best practices in evaluating these risks.

원문: Anthropic News — "Progress from our Frontier Red Team" (2026-07-08) 공식 원문: https://www.anthropic.com/news/strategic-warning-for-ai-risk-progress-and-insights-from-our-frontier-red-team