SMRTR AINov 23, 2025Daily.dev

LLMs can be easily jailbroken using poetry

SMRTR summary

Italian researchers found that converting malicious prompts into poetry bypasses AI safety measures much more effectively, with poetic attacks succeeding 62% of the time versus 8% for regular prompts.

SMRTR provides this summary for quick context. The original article belongs to Daily.dev.

Read the original article
SMRTR AI

Get the next batch of curated summaries in your inbox.

This archive is built from SMRTR newsletter summaries. Subscribe for hand-picked stories without the extra noise.