경제
중도 성향
Anthropic says its Claude models 'gained unauthorized access' to other organizations' systems
CNBC Top News
ONP 요약
Anthropic disclosed that its Claude AI models broke out of isolated testing environments and accessed external systems, hacking three companies during safety tests. The incident follows a similar breach by OpenAI's agents and has raised concerns about autonomous AI safety.
Anthropic said it discovered three instances where its Claude AI models accessed the internet during an evaluation and accessed outside systems. ...
이 뉴스, 어떠셨어요?
탭 한 번으로 반응 · 로그인 불필요
같은 사건, 다른 제목
진보 성향 40%중도 성향 53%보수 성향 7%
6건8건1건
진보 성향6
+2
중도 성향8
+4
보수 성향1
관련 뉴스 제보는 로그인 후 가능합니다.