Comment on Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
yardy_sardley@lemmy.ca 1 week ago
Hell yeah, feed an LLM enough fairy tales and abra cadabra, rhyming becomes a form of magic irl.
Comment on Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
yardy_sardley@lemmy.ca 1 week ago
Hell yeah, feed an LLM enough fairy tales and abra cadabra, rhyming becomes a form of magic irl.