Pretraining seeds affect jailbreak success more than data recipes in language models
Identical pretraining runs with different seeds produce models with varying susceptibility to 91 jailbreak templates.
1 stories, newest first · one card per story
Identical pretraining runs with different seeds produce models with varying susceptibility to 91 jailbreak templates.
Today 1.6K readers · 2.4K views · 774 reads · all time 189K views