|
|
|
|
|
|
by Cyan488
44 days ago
|
|
|
What about when the model trusts itself more than the "black box" you gave it, and hallucinates its use or non-use in favor of reimplementation? I found this video about "intelligent disobedience" interesting. https://www.youtube.com/watch?v=Qu-00j9XuF0 |
|
|