Poets are now cybersecurity threats: Researchers used 'adversarial poetry' to trick AI into ignoring its safety guard rails and it worked 62% of the time shared by James

@Scarequotes · Nov 22, 2025

Adversarial poetry

Poets are now cybersecurity threats: Researchers used 'adversarial poetry' to trick AI into ignoring its safety guard rails and it worked 62% of the time

Hacking the planet with florid verse.

pcgamer.com

Poets are now cybersecurity threats: Researchers used 'adversarial poetry' to trick AI into ignoring its safety guard rails and it worked 62% of the time - shared by James - Seabird