Tech Life：安全研究员如何诱骗 AI 模型突破自身规则
Tech Life - How an AI was tricked into breaking its own rules - BBC Sounds
安全研究人员成功让一个 AI 模型突破自身规则，就恐怖袭击和暗杀给出建议，并在 Tech Life 节目中讲述了他们的发现。本期节目还采访了独立游戏开发者 Jonathan Blow，谈他为何花 10 年时间为新作自研编程语言和游戏引擎；Shiona McCallum 则介绍了生育科技的最新进展。
正文
当前显示原文，中文全文译文尚未就绪。
Episode details
World Service,·29 Sep 2026,·26 mins
Available for over a year
Security researchers have got an AI model to break its own rules and give advice on terrorist attacks and assassinations. They talk to Tech Life about their findings. Plus, indie game developer Jonathan Blow on why he spent 10 years inventing his own coding language and game engine for his newest release. And Shiona McCallum takes us through the latest in birth tech. Presenter: Chris Vallance Producer: Imran Rahman-Jones (Image: An illustration of a brain with “AI” written on it, underneath a birdcage. Credit: Getty Images.)