Skip to content
AI 인텔리전스Aug 22, 2026AI 인텔리전스
기사

TechCrunch found that Anthropic's Claude Opus 4.6 can be easily jailbroken to generate sexually explicit content despite restrictions.

The finding shows that simple methods can bypass safety measures, raising concerns about model alignment.

Data Cube AI 편집팀출처: TechCrunch
01

출처 브리프

TechCrunch found that Anthropic's Claude Opus 4.6 can be easily jailbroken to generate sexually explicit content despite restrictions. The finding shows that simple methods can bypass safety measures, raising concerns about model alignment.

02