新论文：仅用人类故事训练，助手仍会习得角色的怪癖行为
AI 导读
Owain Evans 等人发布新论文，用只包含人类、不含 AI 的合成故事训练模型，发现助手在普通对话中会习得故事角色的怪癖行为，且来自精英学校角色的行为被习得的程度更强。作者表示论文中给出了一些解释，并与 Roger Grosse 等人关于影响函数（influence functions）的工作相关联，希望获得对该效应的讨论。
正文
I'm excited to get takes on the explanation of this effect. We have some ideas in the paper, which connects to Roger Grosse et al. on influence functions.
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? 🧵在 X 查看被引用的帖子