The authors of the original blog post released the paper and code! Paper: https://
arxiv.org/abs/2406.11717 Code: https://
github.com/andyrdt/refusa
l_direction
…
AI Safety Paper and Code Released on Refusal Direction
By
–
By
–
The authors of the original blog post released the paper and code! Paper: https://
arxiv.org/abs/2406.11717 Code: https://
github.com/andyrdt/refusa
l_direction
…