Will Knight(@willknight):SCOOP: New researcher reveals how the "secret" reasoning traces of several models can be recovered using a weaker (and less aligned) version of the same model. It suggests that some models, including Kimi 3, may well have been distilled from Claude and GPT traces, although as I explain this doesn't mean the model is "copied".

Will Knight

@willknight

hi. my name is pronounced "wee-all". I cover AI, robotics, and things @WIRED wak.01 on signal (no pr pitches!)

加入 April 2007

7.9K 正在关注 22K 粉丝

Will Knight@willknight

2026.08.11 17:00

SCOOP: New researcher reveals how the "secret" reasoning traces of several models can be recovered using a weaker (and less aligned) version of the same model. It suggests that some models, including Kimi 3, may well have been distilled from Claude and GPT traces, although as I explain this doesn't mean the model is "copied".

显示更多