Best-of-N Jailbreaking Introducing a black-box method that jailbreaks AI models across text, vision, and audio by applying simple prompt augmentations. BoN achieves high success rates, such as 89% on GPT-4o and 78% on Claude 3.5 Sonnet, with 10,000 augmented prompts, and also

→ View original post on X — @askalphaxiv