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
31 正在關注 19.6K 粉絲
Our evaluations show that frontier AI's cyber capabilities are advancing quickly. The length of cyber tasks frontier models can complete has been doubling every few months, and this rate has become faster over time, with recent models exceeding our previous trends. 🧵
顯示更多
