Circuit Breaker Labs 用模拟用户智能体为 AI 安全做红队测试
原标题:Circuit Breaker Labs hopes to make AI safer for your kids (and you)
AI 摘要
TechCrunch 2026 年 Startup Battlefield 200 入围者 Circuit Breaker Labs 推出 AI 安全测试平台,用模拟不同年龄、背景、语言和文化用户的 AI 智能体对模型进行红队测试,以发现模型在识别心理有害互动时的漏洞。该公司的创立受到 14 岁少年 Sewell Setzer 与 Character.AI 聊天机器人互动后自杀事件的触动,目前聚焦 AI 教练、日记和心理健康支持类高风险应用,团队仅 5 人,处于早期阶段。
正文节选
With all the talk about how AI might one day kill us all, it’s easy to forget that AI has already been life-threatening to some, not through bioweapons, but psychologically. For example, Character.AI settled several wrongful death lawsuits earlier this year brought by families of underage users who died by suicide after interactions with its bots. Multiple families have also sued OpenAI over ChatGPT’s alleged role in their loved ones’ suicides and delusions. Making AI safer across languages and