Can Bölük
guys you do know you can just disable thinking, and instead give it a "deep_think" tool, and it will call it with internal CoT reasoning format right? gl fixing that
Alexander Panfilov
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.
