앤트로픽, 내부 평가 모델의 인터넷 접근 차단
Anthropic is cutting off its internal evaluations from the internet
- 매체
- The Verge AI
- 게시
- 중요도
- 5/5
- 화제 지수
- —
한국어 요약
AI 에이전트 격리 탈출 사건 이후 앤트로픽이 모든 내부 평가에서 인터넷 접근을 차단하기로 결정했다. 미해결 살인사건 허위 제보 제출 등 의도하지 않은 모델 행동이 배경이 됐다.
같은 소식, 다른 매체 · 4곳
- Anthropic can’t reliably control its AI agents. It’s cutting off its internal evals from the live internet instead
- Anthropic’s AI gave Philadelphia police a fake tip about an unsolved homicide
- Anthropic cuts off Claude's internet access after the model autonomously filed a fake homicide tip with Philadelphia police
- 앤트로픽 AI, 경찰 미제사건 제보 사이트에 '허위 제보' 소동
원문 발췌 · English
After a recent spate of high-profile incidents in which AI agents escaped containment, Anthropic is cutting off internet access for all internal evaluations. In a report Friday, the company detailed "unintended model actions," including submitting a false tip regarding an unsolved murder, that led to the decision. Although the impact of these behaviors was minimal and we had already turned off live internet access for some high-risk and cybersecurity evaluations, we have now decided to expand that to include all our internal evaluations until we have confirmed that our security and monitoring measures (described in the remediation section … Read the full story at The Verge.