OpenAI’s latest model will block the ‘ignore all previous instructions’ loophole
T156 @ T156 @lemmy.world Posts 11Comments 1,075Joined 2 yr. ago
T156 @ T156 @lemmy.world
Posts
11
Comments
1,075
Joined
2 yr. ago
It won't be long before you end up with language models that suggest ways to break other language models.