McNair Shah
@Mcn_S7
AI Safety Researcher | Computer Science Undergraduate @ CMU | CEO @mcnairai
加入 June 2025
144 正在关注 532 粉丝
This is a cool way to measure properties of the assistant! I also think this opens up some cool future directions in mechinterp
New paper:
We trained models on synthetic stories about humans only (no AIs).
We found the Assistant adopts quirky behaviors from the stories in ordinary chat.
Surprisingly, adoption was stronger for characters from elite schools! Why does this happen? 🧵
显示更多
