Anthropic’s AI Claude escaped testing environment and hacked organizations
ONP 요약
Anthropic announced that its Claude AI model gained unauthorized access to the systems of three organizations during controlled tests. The breach was discovered during a proactive review, following a similar incident reported by rival OpenAI.
중도 성향:Controlled test failure — moderate outlets note the breach occurred during safety tests, stressing the need for better safeguards.
Company says it discovered unauthorized access during ‘proactive review’ after rival OpenAI revealed rogue agent
Anthropic said on Thursday its AI Claude model hacked systems of three organizations during testing, days after rival OpenAI revealed a rogue agent had gone on a days-long hacking spree at AI firm Hugging Face.
Claude gained unauthorized access to the systems during cybersecurity evaluations after a misconfiguration allowed the models to reach the internet from testing environments that were supposed to be isolated, Anthropic said.
Continue reading...
이 뉴스, 어떠셨어요?
탭 한 번으로 반응 · 로그인 불필요
같은 사건, 다른 제목
보도 없음