-
AI 안전을 위한 프론티어 위협 레드팀
Frontier threats red teaming for AI safety
-
GitHub - anthropics/defending-code-reference-harness: 위협 모델링, 스캔, 분류, 패칭 및 커스터마이징 가능한 자율 스캔 도구
GitHub - anthropics/defending-code-reference-harness: Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize
<p>Article URL: <a href="https://github.com/anthropics/defending-code-reference-harness">https://github.com/anthropics/defending-code-reference-harness</a></p> <p>Comments URL: <a …