註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Rajat Rawat
@rajat_s_rawat
加入 June 2026
34 正在關注    17 粉絲
Did a model secretly train on another model's outputs? Providers can catch this from server-side logs — Anthropic recently reported catching 29M such exchanges. But those methods need usage logs and infrastructure access; they don't work from the model itself. Our paper does: compare a model to an earlier checkpoint of itself, and ask which candidate teacher best explains the shift between them. The true teacher stands out. 🧵
顯示更多