NotebookCHECK - Notebook Forum

English => News => Topic started by: Redaktion on November 25, 2025, 14:20:15

Title: Hacked by poetry – why AI models fail at poetic prompts
Post by: Redaktion on November 25, 2025, 14:20:15
Study results reveal that large language models are susceptible to input written in poetic form. In the study, hand-crafted poems successfully bypassed the AI's safety measures in 62% of cases.

https://www.notebookcheck.net/Hacked-by-poetry-why-AI-models-fail-at-poetic-prompts.1170524.0.html