Yun-Ta Tsai
@yunta_tsai · 25 июн. 2026 г.
Getting used to being liked likely means you are overfit to RLHF.
The problem with overfitting is that the pain overwhelms the limbic system once you try to sample trajectories outside the known distribution.
As more people like you, your sampling regime becomes smaller and
Elon Musk
@elonmusk
Wise words
05:10 · 25 июня 2026 г. · 102,2 тыс. просмотров
214
83
1,1 тыс.