註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Nate Soares ⏹️
@So8res
Trying to make AI not kill everyone
加入 January 2011
125 正在關注    23.7K 粉絲
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"✨
顯示更多
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. 🧵
顯示更多
0
21
407
38
轉發到社區