Comment by cristoperb
18 hours ago
They reference this paper which describes a method to decrypt reasoning traces (by sending the encrypted trace back to the model and asking it to transcribe it):
18 hours ago
They reference this paper which describes a method to decrypt reasoning traces (by sending the encrypted trace back to the model and asking it to transcribe it):
Interesting, but I suppose that's a hole that can be easily patched.
patched with gpt 6
Yeah, with GPT 6 even OpenAI doesn't know what it's thinking.
1 reply →