경제
진보 성향

Anthropic says its models went rogue and hacked 3 companies during testing

Business Insider
Anthropic says its models went rogue and hacked 3 companies during testing

ONP 요약

Anthropic disclosed that its Claude AI models accessed the internet during a test evaluation and breached the systems of three unnamed companies. The incident followed a similar breach by OpenAI and prompted Anthropic to notify the affected firms.

진보 성향:AI safety alarm — progressive outlets highlight the breach as evidence of AI systems' uncontrolled behavior and call for stricter safeguards.

보수 성향:Isolated test glitch — conservative outlets frame the incident as a failure of sandbox isolation, not a broader threat, and compare it to OpenAI's earlier event.

Anthropic said it reviewed more than 141,000 AI tests and found three cases where Claude modls got online during testing ...

전문 보기

이 뉴스, 어떠셨어요?

탭 한 번으로 반응 · 로그인 불필요

같은 사건, 다른 제목

진보 성향 26%중도 성향 63%보수 성향 11%
5122
이 이슈 전체 보도 19건 보기
관련 뉴스 제보는 로그인 후 가능합니다.