emollick· @emollick · X·· 5 小时前AI 评分
开源模型神经元激活与人格实验
已经有许多非常有趣的实验，在开源 AI 模型中激活单个神经元，将它们锁定为特定人格。 这里，历史学家 @ResObscura 用一个仅使用 1930 年前数据训练的模型尝试了同样的方法，结果令人欣喜。
There has been a bunch of really interesting experiments with activating individual neurons in open AI models, locking them into particular personas.
Here historian @ResObscura tries the same trick with a model trained only on data before 1930, and the results are delightful.
来源：emollick · x.com