Poems can hack ChatGPT? A new study reveals dangerous AI flaw | PCWorld
Researchers found that feeding dangerous prompts in the form of poems managed to evade " AI " safeguards—up to 90 percent of the time.
Read the original at PCWorld ↗
- Topics
- AI Safety & Existential Risk
- Mentions
- ChatGPTOpenAI
- Tracked via
- “dangerous AI”