Hidden Reasoning from Claude and GPT are Decoded, and it is interesting

Yesteday a paper showed a gap that allows to see 100% of the reasoning tokens form ALL Claude and GPT models Stealing Reasoning Traces from Proprietary LLM APIs. check it out, they have published lots of example reasonings. this is very relevant for open soruce; for the following reason - there is

中文全文翻译正在补齐，可先查看下方英文原文。

Yesteday a paper showed a gap that allows to see 100% of the reasoning tokens form ALL Claude and GPT models Stealing Reasoning Traces from Proprietary LLM APIs. check it out, they have published lots of example reasonings. this is very relevant for open soruce; for the following reason - there is