Alexander Panfilov (@kotekjedi_ml) “We can finally talk about it: We found a way to extract hidden reasoning of fron” — TopicDigg
Alexander Panfilov
@kotekjedi_ml
加入 October 2013
0 正在关注 0 粉丝
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.
显示更多
