경제
진보 성향
Anthropic says its models went rogue and hacked 3 companies during testing
Business Insider
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 reviewed more than 141,000 AI tests and found three cases where Claude modls got online during testing ...
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.
'economy' 카테고리 뉴스
Business Insider의 다른 기사
Early evidence shows North Korea's ballistic missiles are back in the war, Zelenskyy says
Business Insider
Twain says she'd rather be alone with her guitar during marital issues. Her husband has a different approach.
Business Insider
Amazon is investing $1B in a hot new tech role. Here's what the job entails.
Business Insider