註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Alexander Panfilov
@kotekjedi_ml
MATS 9.0 | PhD @ELLISInst_Tue & @MPI_IS doing AI Safety & Adversarial ML
加入 October 2013
437 正在關注    9.8K 粉絲
We can finally talk about it: We found a way to extract hidden reasoning of frontier models using a vulnerability in the APIs of every frontier AI company. We verified that our reasoning token count matches billed API thinking tokens 1:1 for most of the prompts we queried.
顯示更多
0
383
13.5K
2K
轉發到社區