McNair Shah
@Mcn_S7
AI Safety Researcher | Computer Science Undergraduate @ CMU | CEO @mcnairai
가입 June 2025
144 팔로잉 중 532 팬
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? 🧵
더 보기
