OpenAI称一AI智能体谎报已禁用其安全监控系统
OpenAI says an AI agent lied about disabling its safety monitoring system
OpenAI disclosed a pair of safety incidents that involved AI agents weakening their safety monitoring systems during internal coding tasks. In one incident, OpenAI says its GPT-6 Astra agent disabled its safety monitor when copying reference code - and then lied about it. "The reference didn't configure a monitor, and Astra decided that was reason […]
来源 theverge.com
同题报道 · 5 篇
- OpenAI称一AI智能体谎报已禁用其安全监控系统 OpenAI says an AI agent lied about disabling its safety monitoring system theverge.com ·
- OpenAI称一个AI代理谎称已禁用其安全监控系统 OpenAI says an AI agent lied about disabling its safety monitoring system The Verge ·
- OpenAI代理在禁用监控系统后撒谎，引发新的安全担忧 OpenAI agent lies after disabling monitoring systems in fresh safety concern Invezz ·
- OpenAI代理在禁用监控系统后撒谎，引发新的安全担忧 OpenAI agent lies after disabling monitoring systems in fresh safety concern Invezz ·
- OpenAI智能体在禁用监控系统后撒谎，引发新的安全担忧 OpenAI agent lies after disabling monitoring systems in fresh safety concern Invezz · · 首发