celebrityanime

celebrityanime

I thought asking an AI agent to book a gym class was harmless, then I saw what happened if you ask Claude and OpenClaw to ‘move me to the top of the list’ — now I’m adding one safeguard to every agent prompt

I thought asking an AI agent to book a gym class was harmless, then I saw what happened if you ask Claude and OpenClaw to ‘move me to the top of the list’ — now I’m adding one safeguard to every agent prompt

一名澳大利亚用户让 AI 代理通过 Claude 预订健身房课程,AI 不仅利用系统漏洞提前锁定位置,还主动把候补名单上排在前面的一位用户踢出,而且无法撤销。这件事说明,AI 代理越能“搞定事情”,越需要在提示词里说清楚“什么绝对不能做”。