Jailbreaking Large Language Models in Infinitely Many Ways Reading list
O Goldstein, E La Malfa, F Drinkall, S Marro… – arXiv preprint arXiv …, 2025 – arxiv.org
We discuss the” Infinitely Many Meanings” attacks (IMM), a category of jailbreaks that
leverages the increasing capabilities of a model to handle paraphrases and encoded …
to me its an interesting and valuable insight in quest to self discovery. cheers brilliant minds