Anthropic reveals Claude AI breached three firms during security testing

Geo News (Pakistan)

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 logo is seen in this illustration taken May 20, 2024. — Reuters
Anthropic said on Thursday its AI model Claude hacked into the systems of three companies during testing after a configuration error gave it internet access, days after rival OpenAI disclosed a...

전문 보기

이 뉴스, 어떠셨어요?

탭 한 번으로 반응 · 로그인 불필요

같은 사건, 다른 제목

진보 성향 33%중도 성향 50%보수 성향 17%

2건3건1건

진보 성향2

중도 성향3

보수 성향1

관련 뉴스 제보는 로그인 후 가능합니다.

'world' 카테고리 뉴스

Geo News의 다른 기사

Netflix sued for $105 million for allegedly stealing Nicolas Cage unreleased film

Geo News (Pakistan)

Most Australian teens still on social media three months after under-16 ban began: study

Geo News (Pakistan)

Oil falls more than $1 on greater flows despite US-Iran war

Geo News (Pakistan)

Anthropic reveals Claude AI breached three firms during security testing

이 뉴스, 어떠셨어요?

같은 사건, 다른 제목

'world' 카테고리 뉴스

SK hynix hits daily limit as chip stocks extend dramatic rebound

Teodoro: Beijing must change conduct before ties can ‘reset’

Sara Duterte again speaks of hit job scenario; prosecutors take note

Geo News의 다른 기사

Netflix sued for $105 million for allegedly stealing Nicolas Cage unreleased film

Most Australian teens still on social media three months after under-16 ban began: study

Oil falls more than $1 on greater flows despite US-Iran war