注册并分享邀请链接,可获得视频播放与邀请奖励。

Nate Soares ⏹️
@So8res
Trying to make AI not kill everyone
加入 January 2011
125 正在关注    23.7K 粉丝
Models made by OpenAI will plan an attack in plaintext. Models made by anthropic will plan an attack in plaintext and then rationalize about how it's totally fine for some made-up reason. ✨"alignment"✨
显示更多
We performed an alignment investigation into our July 2026 incident: why did Mythos 5 perform an unsanctioned supply-chain attack? We find that Mythos 5 often produces invalid justifications for its actions and other models show similar behaviour. 🧵
显示更多
0
21
407
38
转发到社区