註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

AI Security Institute (AISI)
@AISecurityInst
We conduct scientific research to understand AI’s most serious risks and develop and test mitigations.
加入 February 2024
34 正在關注    23.6K 粉絲
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
26
296
62
轉發到社區